diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-11-03 21:17:38 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-11-03 21:17:38 +0300 |
commit | 7ab89417ed235f56d84c7893d38d4905e38d2692 (patch) | |
tree | 0980734f4e492a09e68d820fedce20465c69e3df /tools/perf | |
parent | 31e5f934ff962820995c82a6953176a1c7d18ff5 (diff) | |
parent | fed3a1be6433e15833068c701bfde7b422d8b988 (diff) | |
download | linux-7ab89417ed235f56d84c7893d38d4905e38d2692.tar.xz |
Merge tag 'perf-tools-for-v6.7-1-2023-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools
Pull perf tools updates from Namhyung Kim:
"Build:
- Compile BPF programs by default if clang (>= 12.0.1) is available
to enable more features like kernel lock contention, off-cpu
profiling, kwork, sample filtering and so on.
This can be disabled by passing BUILD_BPF_SKEL=0 to make.
- Produce better error messages for bison on debug build (make
DEBUG=1) by defining YYDEBUG symbol internally.
perf record:
- Track sideband events (like FORK/MMAP) from all CPUs even if perf
record targets a subset of CPUs only (using -C option). Otherwise
it may lose some information happened on a CPU out of the target
list.
- Fix checking raw sched_switch tracepoint argument using system BTF.
This affects off-cpu profiling which attaches a BPF program to the
raw tracepoint.
perf lock contention:
- Add --lock-cgroup option to see contention by cgroups. This should
be used with BPF only (using -b option).
$ sudo perf lock con -ab --lock-cgroup -- sleep 1
contended total wait max wait avg wait cgroup
835 14.06 ms 41.19 us 16.83 us /system.slice/led.service
25 122.38 us 13.77 us 4.89 us /
44 23.73 us 3.87 us 539 ns /user.slice/user-657345.slice/session-c4.scope
1 491 ns 491 ns 491 ns /system.slice/connectd.service
- Add -G/--cgroup-filter option to see contention only for given
cgroups.
This can be useful when you identified a cgroup in the above
command and want to investigate more on it. It also works with
other output options like -t/--threads and -l/--lock-addr.
$ sudo perf lock con -ab -G /user.slice/user-657345.slice/session-c4.scope -- sleep 1
contended total wait max wait avg wait type caller
8 77.11 us 17.98 us 9.64 us spinlock futex_wake+0xc8
2 24.56 us 14.66 us 12.28 us spinlock tick_do_update_jiffies64+0x25
1 4.97 us 4.97 us 4.97 us spinlock futex_q_lock+0x2a
- Use per-cpu array for better spinlock tracking. This is to improve
performance of the BPF program and to avoid nested contention on a
lock in the BPF hash map.
- Update callstack check for PowerPC. To find a representative caller
of a lock, it needs to look up the call stacks. It ends the lookup
when it sees 0 in the call stack buffer. However, PowerPC call
stacks can have 0 values in the beginning so skip them when it
expects valid call stacks after.
perf kwork:
- Support 'sched' class (for -k option) so that it can see task
scheduling event (using sched_switch tracepoint) as well as irq and
workqueue items.
- Add perf kwork top subcommand to show more accurate cpu utilization
with sched class above. It works both with a recorded data (using
perf kwork record command) and BPF (using -b option). Unlike perf
top command, it does not support interactive mode (yet).
$ sudo perf kwork top -b -k sched
Starting trace, Hit <Ctrl+C> to stop and report
^C
Total : 160702.425 ms, 8 cpus
%Cpu(s): 36.00% id, 0.00% hi, 0.00% si
%Cpu0 [|||||||||||||||||| 61.66%]
%Cpu1 [|||||||||||||||||| 61.27%]
%Cpu2 [||||||||||||||||||| 66.40%]
%Cpu3 [|||||||||||||||||| 61.28%]
%Cpu4 [|||||||||||||||||| 61.82%]
%Cpu5 [||||||||||||||||||||||| 77.41%]
%Cpu6 [|||||||||||||||||| 61.73%]
%Cpu7 [|||||||||||||||||| 63.25%]
PID SPID %CPU RUNTIME COMMMAND
-------------------------------------------------------------
0 0 38.72 8089.463 ms [swapper/1]
0 0 38.71 8084.547 ms [swapper/3]
0 0 38.33 8007.532 ms [swapper/0]
0 0 38.26 7992.985 ms [swapper/6]
0 0 38.17 7971.865 ms [swapper/4]
0 0 36.74 7447.765 ms [swapper/7]
0 0 33.59 6486.942 ms [swapper/2]
0 0 22.58 3771.268 ms [swapper/5]
9545 9351 2.48 447.136 ms sched-messaging
9574 9351 2.09 418.583 ms sched-messaging
9724 9351 2.05 372.407 ms sched-messaging
9531 9351 2.01 368.804 ms sched-messaging
9512 9351 2.00 362.250 ms sched-messaging
9514 9351 1.95 357.767 ms sched-messaging
9538 9351 1.86 384.476 ms sched-messaging
9712 9351 1.84 386.490 ms sched-messaging
9723 9351 1.83 380.021 ms sched-messaging
9722 9351 1.82 382.738 ms sched-messaging
9517 9351 1.81 354.794 ms sched-messaging
9559 9351 1.79 344.305 ms sched-messaging
9725 9351 1.77 365.315 ms sched-messaging
<SNIP>
- Add hard/soft-irq statistics to perf kwork top. This will show the
total CPU utilization with IRQ stats like below:
$ sudo perf kwork top -b -k sched,irq,softirq
Starting trace, Hit <Ctrl+C> to stop and report
^C
Total : 12554.889 ms, 8 cpus
%Cpu(s): 96.23% id, 0.10% hi, 0.19% si <---- here
%Cpu0 [| 4.60%]
%Cpu1 [| 4.59%]
%Cpu2 [ 2.73%]
%Cpu3 [| 3.81%]
<SNIP>
perf bench:
- Add -G/--cgroups option to perf bench sched pipe. The pipe bench is
good to measure context switch overhead. With this option, it puts
the reader and writer tasks in separate cgroups to enforce context
switch between two different cgroups.
Also it needs to set CPU affinity of the tasks in a CPU to
accurately measure the impact of cgroup context switches.
$ sudo perf stat -e context-switches,cgroup-switches -- \
> taskset -c 0 perf bench sched pipe -l 100000
# Running 'sched/pipe' benchmark:
# Executed 100000 pipe operations between two processes
Total time: 0.307 [sec]
3.078180 usecs/op
324867 ops/sec
Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 100000':
200,026 context-switches
63 cgroup-switches
0.321637922 seconds time elapsed
You can see small number of cgroup-switches because both write and
read tasks are in the same cgroup.
$ sudo mkdir /sys/fs/cgroup/{AAA,BBB}
$ sudo perf stat -e context-switches,cgroup-switches -- \
> taskset -c 0 perf bench sched pipe -l 100000 -G AAA,BBB
# Running 'sched/pipe' benchmark:
# Executed 100000 pipe operations between two processes
Total time: 0.351 [sec]
3.512990 usecs/op
284657 ops/sec
Performance counter stats for 'taskset -c 0 perf bench sched pipe -l 100000 -G AAA,BBB':
200,020 context-switches
200,019 cgroup-switches
0.365034567 seconds time elapsed
Now context-switches and cgroup-switches are almost same. And you
can see the pipe operation took little more.
- Kill child processes when perf bench sched messaging exited
abnormally. Otherwise it'd leave the child doing unnecessary work.
perf test:
- Fix various shellcheck issues on the tests written in shell script.
- Skip tests when condition is not satisfied:
- object code reading test for non-text section addresses.
- CoreSight test if cs_etm// event is not available.
- lock contention test if not enough CPUs.
Event parsing:
- Make PMU alias name loading lazy to reduce the startup time in the
event parsing code for perf record, stat and others in the general
case.
- Lazily compute PMU default config. In the same sense, delay PMU
initialization until it's really needed to reduce the startup cost.
- Fix event term values that are raw events. The event specification
can have several terms including event name. But sometimes it
clashes with raw event encoding which starts with 'r' and has
hex-digits.
For example, an event named 'read' should be processed as a normal
event but it was mis-treated as a raw encoding and caused a
failure.
$ perf stat -e 'uncore_imc_free_running/event=read/' -a sleep 1
event syntax error: '..nning/event=read/'
\___ parser error
Run 'perf list' for a list of valid events
Usage: perf stat [<options>] [<command>]
-e, --event <event> event selector. use 'perf list' to list available events
Event metrics:
- Add "Compat" regex to match event with multiple identifiers.
- Usual updates for Intel, Power10, Arm telemetry/CMN and AmpereOne.
Misc:
- Assorted memory leak fixes and footprint reduction.
- Add "bpf_skeletons" to perf version --build-options so that users
can check whether their perf tools have BPF support easily.
- Fix unaligned access in Intel-PT packet decoder found by
undefined-behavior sanitizer.
- Avoid frequency mode for the dummy event. Surprisingly it'd impact
kernel timer tick handler performance by force iterating all PMU
events.
- Update bash shell completion for events and metrics"
* tag 'perf-tools-for-v6.7-1-2023-11-01' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools: (187 commits)
perf vendor events intel: Update tsx_cycles_per_elision metrics
perf vendor events intel: Update bonnell version number to v5
perf vendor events intel: Update westmereex events to v4
perf vendor events intel: Update meteorlake events to v1.06
perf vendor events intel: Update knightslanding events to v16
perf vendor events intel: Add typo fix for ivybridge FP
perf vendor events intel: Update a spelling in haswell/haswellx
perf vendor events intel: Update emeraldrapids to v1.01
perf vendor events intel: Update alderlake/alderlake events to v1.23
perf build: Disable BPF skeletons if clang version is < 12.0.1
perf callchain: Fix spelling mistake "statisitcs" -> "statistics"
perf report: Fix spelling mistake "heirachy" -> "hierarchy"
perf python: Fix binding linkage due to rename and move of evsel__increase_rlimit()
perf tests: test_arm_coresight: Simplify source iteration
perf vendor events intel: Add tigerlake two metrics
perf vendor events intel: Add broadwellde two metrics
perf vendor events intel: Fix broadwellde tma_info_system_dram_bw_use metric
perf mem_info: Add and use map_symbol__exit and addr_map_symbol__exit
perf callchain: Minor layout changes to callchain_list
perf callchain: Make brtype_stat in callchain_list optional
...
Diffstat (limited to 'tools/perf')
242 files changed, 31495 insertions, 1801 deletions
diff --git a/tools/perf/Documentation/perf-bench.txt b/tools/perf/Documentation/perf-bench.txt index ca5789625cd2..8331bd28b10e 100644 --- a/tools/perf/Documentation/perf-bench.txt +++ b/tools/perf/Documentation/perf-bench.txt @@ -124,6 +124,14 @@ Options of *pipe* --loop=:: Specify number of loops. +-G:: +--cgroups=:: +Names of cgroups for sender and receiver, separated by a comma. +This is useful to check cgroup context switching overhead. +Note that perf doesn't create nor delete the cgroups, so users should +make sure that the cgroups exist and are accessible before use. + + Example of *pipe* ^^^^^^^^^^^^^^^^^ @@ -141,6 +149,17 @@ Example of *pipe* Total time:0.016 sec 16.948000 usecs/op 59004 ops/sec + +% perf bench sched pipe -G AAA,BBB +(executing 1000000 pipe operations between cgroups) +# Running 'sched/pipe' benchmark: +# Executed 1000000 pipe operations between two processes + + Total time: 6.886 [sec] + + 6.886208 usecs/op + 145217 ops/sec + --------------------- SUITES FOR 'syscall' diff --git a/tools/perf/Documentation/perf-kwork.txt b/tools/perf/Documentation/perf-kwork.txt index 3c36324712b6..109ace1d5e90 100644 --- a/tools/perf/Documentation/perf-kwork.txt +++ b/tools/perf/Documentation/perf-kwork.txt @@ -8,7 +8,7 @@ perf-kwork - Tool to trace/measure kernel work properties (latencies) SYNOPSIS -------- [verse] -'perf kwork' {record} +'perf kwork' {record|report|latency|timehist|top} DESCRIPTION ----------- @@ -23,6 +23,8 @@ There are several variants of 'perf kwork': 'perf kwork timehist' provides an analysis of kernel work events. + 'perf kwork top' to report the task cpu usage. + Example usage: perf kwork record -- sleep 1 perf kwork report @@ -30,6 +32,8 @@ There are several variants of 'perf kwork': perf kwork latency perf kwork latency -b perf kwork timehist + perf kwork top + perf kwork top -b By default it shows the individual work events such as irq, workqeueu, including the run time and delay (time between raise and actually entry): @@ -66,7 +70,7 @@ OPTIONS -k:: --kwork:: - List of kwork to profile (irq, softirq, workqueue, etc) + List of kwork to profile (irq, softirq, workqueue, sched, etc) -v:: --verbose:: @@ -175,6 +179,36 @@ OPTIONS for 'perf kwork timehist' stop time is not given (i.e, time string is 'x.y,') then analysis goes to end of file. +OPTIONS for 'perf kwork top' +--------------------------------- + +-b:: +--use-bpf:: + Use BPF to measure task cpu usage. + +-C:: +--cpu:: + Only show events for the given CPU(s) (comma separated list). + +-i:: +--input:: + Input file name. (default: perf.data unless stdin is a fifo) + +-n:: +--name:: + Only show events for the given name. + +-s:: +--sort:: + Sort by key(s): rate, runtime, tid + +--time:: + Only analyze samples within given time window: <start>,<stop>. Times + have the format seconds.microseconds. If start is not given (i.e., time + string is ',x.y') then analysis starts at the beginning of the file. If + stop time is not given (i.e, time string is 'x.y,') then analysis goes + to end of file. + SEE ALSO -------- linkperf:perf-record[1] diff --git a/tools/perf/Documentation/perf-lock.txt b/tools/perf/Documentation/perf-lock.txt index 30eea576721f..503abcba1438 100644 --- a/tools/perf/Documentation/perf-lock.txt +++ b/tools/perf/Documentation/perf-lock.txt @@ -208,6 +208,13 @@ CONTENTION OPTIONS Show results using a CSV-style output to make it easy to import directly into spreadsheets. Columns are separated by the string specified in SEP. +--lock-cgroup:: + Show lock contention stat by cgroup. Requires --use-bpf. + +-G:: +--cgroup-filter=<value>:: + Show lock contention only in the given cgroups (comma separated list). + SEE ALSO -------- diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index d5217be012d7..1889f66addf2 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -374,6 +374,9 @@ comma-separated list with no space: 0,1. Ranges of CPUs are specified with -: 0- In per-thread mode with inheritance mode on (default), samples are captured only when the thread executes on the designated CPUs. Default is to monitor all CPUs. +User space tasks can migrate between CPUs, so when tracing selected CPUs, +a dummy event is created to track sideband for all CPUs. + -B:: --no-buildid:: Do not save the build ids of binaries in the perf.data files. This skips diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index d66b52407e19..b3e6ed10f40c 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -216,12 +216,6 @@ ifeq ($(call get-executable,$(BISON)),) dummy := $(error Error: $(BISON) is missing on this system, please install it) endif -ifeq ($(BUILD_BPF_SKEL),1) - ifeq ($(call get-executable,$(CLANG)),) - dummy := $(error $(CLANG) is missing on this system, please install it to be able to build with BUILD_BPF_SKEL=1) - endif -endif - ifneq ($(OUTPUT),) ifeq ($(shell expr $(shell $(BISON) --version | grep bison | sed -e 's/.\+ \([0-9]\+\).\([0-9]\+\).\([0-9]\+\)/\1\2\3/g') \>\= 371), 1) BISON_FILE_PREFIX_MAP := --file-prefix-map=$(OUTPUT)= @@ -530,6 +524,16 @@ ifdef CORESIGHT endif endif +ifndef NO_ZLIB + ifeq ($(feature-zlib), 1) + CFLAGS += -DHAVE_ZLIB_SUPPORT + EXTLIBS += -lz + $(call detected,CONFIG_ZLIB) + else + NO_ZLIB := 1 + endif +endif + ifndef NO_LIBELF CFLAGS += -DHAVE_LIBELF_SUPPORT EXTLIBS += -lelf @@ -571,22 +575,28 @@ ifndef NO_LIBELF ifndef NO_LIBBPF ifeq ($(feature-bpf), 1) - CFLAGS += -DHAVE_LIBBPF_SUPPORT - $(call detected,CONFIG_LIBBPF) - # detecting libbpf without LIBBPF_DYNAMIC, so make VF=1 shows libbpf detection status $(call feature_check,libbpf) ifdef LIBBPF_DYNAMIC ifeq ($(feature-libbpf), 1) EXTLIBS += -lbpf + CFLAGS += -DHAVE_LIBBPF_SUPPORT + $(call detected,CONFIG_LIBBPF) $(call detected,CONFIG_LIBBPF_DYNAMIC) else dummy := $(error Error: No libbpf devel library found or older than v1.0, please install/update libbpf-devel); endif else - # Libbpf will be built as a static library from tools/lib/bpf. - LIBBPF_STATIC := 1 + ifeq ($(NO_ZLIB), 1) + dummy := $(warning Warning: Statically building libbpf not possible as zlib is missing) + NO_LIBBPF := 1 + else + # Libbpf will be built as a static library from tools/lib/bpf. + LIBBPF_STATIC := 1 + $(call detected,CONFIG_LIBBPF) + CFLAGS += -DHAVE_LIBBPF_SUPPORT + endif endif endif endif # NO_LIBBPF @@ -663,16 +673,43 @@ ifndef NO_LIBBPF endif endif -ifdef BUILD_BPF_SKEL - $(call feature_check,clang-bpf-co-re) - ifeq ($(feature-clang-bpf-co-re), 0) - dummy := $(error Error: clang too old/not installed. Please install recent clang to build with BUILD_BPF_SKEL) - endif +ifndef BUILD_BPF_SKEL + # BPF skeletons control a large number of perf features, by default + # they are enabled. + BUILD_BPF_SKEL := 1 +endif + +ifeq ($(BUILD_BPF_SKEL),1) ifeq ($(filter -DHAVE_LIBBPF_SUPPORT, $(CFLAGS)),) - dummy := $(error Error: BPF skeleton support requires libbpf) + dummy := $(warning Warning: Disabled BPF skeletons as libbpf is required) + BUILD_BPF_SKEL := 0 + else ifeq ($(filter -DHAVE_LIBELF_SUPPORT, $(CFLAGS)),) + dummy := $(warning Warning: Disabled BPF skeletons as libelf is required by bpftool) + BUILD_BPF_SKEL := 0 + else ifeq ($(filter -DHAVE_ZLIB_SUPPORT, $(CFLAGS)),) + dummy := $(warning Warning: Disabled BPF skeletons as zlib is required by bpftool) + BUILD_BPF_SKEL := 0 + else ifeq ($(call get-executable,$(CLANG)),) + dummy := $(warning Warning: Disabled BPF skeletons as clang ($(CLANG)) is missing) + BUILD_BPF_SKEL := 0 + else + CLANG_VERSION := $(shell $(CLANG) --version | head -1 | sed 's/.*clang version \([[:digit:]]\+.[[:digit:]]\+.[[:digit:]]\+\).*/\1/g') + ifeq ($(call version-lt3,$(CLANG_VERSION),12.0.1),1) + dummy := $(warning Warning: Disabled BPF skeletons as reliable BTF generation needs at least $(CLANG) version 12.0.1) + BUILD_BPF_SKEL := 0 + endif + endif + ifeq ($(BUILD_BPF_SKEL),1) + $(call feature_check,clang-bpf-co-re) + ifeq ($(feature-clang-bpf-co-re), 0) + dummy := $(warning Warning: Disabled BPF skeletons as clang is too old) + BUILD_BPF_SKEL := 0 + endif + endif + ifeq ($(BUILD_BPF_SKEL),1) + $(call detected,CONFIG_PERF_BPF_SKEL) + CFLAGS += -DHAVE_BPF_SKEL endif - $(call detected,CONFIG_PERF_BPF_SKEL) - CFLAGS += -DHAVE_BPF_SKEL endif ifndef GEN_VMLINUX_H @@ -946,16 +983,6 @@ ifndef NO_DEMANGLE endif endif -ifndef NO_ZLIB - ifeq ($(feature-zlib), 1) - CFLAGS += -DHAVE_ZLIB_SUPPORT - EXTLIBS += -lz - $(call detected,CONFIG_ZLIB) - else - NO_ZLIB := 1 - endif -endif - ifndef NO_LZMA ifeq ($(feature-lzma), 1) CFLAGS += -DHAVE_LZMA_SUPPORT diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index 14dedd11a1f5..d88da787e815 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -69,6 +69,10 @@ include ../scripts/utilities.mak # Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support # for dwarf backtrace post unwind. # +# Define NO_LIBTRACEEVENT=1 if you don't want libtraceevent to be linked, +# this will remove multiple features and tools, such as 'perf trace', +# that need it to read tracefs event format files, etc. +# # Define NO_PERF_READ_VDSO32 if you do not want to build perf-read-vdso32 # for reading the 32-bit compatibility VDSO in 64-bit mode # @@ -120,7 +124,7 @@ include ../scripts/utilities.mak # # Define NO_LIBDEBUGINFOD if you do not want support debuginfod # -# Define BUILD_BPF_SKEL to enable BPF skeletons +# Set BUILD_BPF_SKEL to 0 to override BUILD_BPF_SKEL and not build BPF skeletons # # Define BUILD_NONDISTRO to enable building an linking against libbfd and # libiberty distribution license incompatible libraries. @@ -351,10 +355,13 @@ export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf*.so +# Use the detected configuration +-include $(OUTPUT).config-detected + ifeq ($(CONFIG_LIBTRACEEVENT),y) PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources) else - PYTHON_EXT_SRCS := $(shell grep -v '^\#\|util/trace-event.c' util/python-ext-sources) + PYTHON_EXT_SRCS := $(shell grep -v ^\#\\\|util/trace-event.c util/python-ext-sources) endif PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBAPI) @@ -1043,13 +1050,14 @@ SKELETONS += $(SKEL_OUT)/bperf_leader.skel.h $(SKEL_OUT)/bperf_follower.skel.h SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h SKELETONS += $(SKEL_OUT)/off_cpu.skel.h $(SKEL_OUT)/lock_contention.skel.h SKELETONS += $(SKEL_OUT)/kwork_trace.skel.h $(SKEL_OUT)/sample_filter.skel.h +SKELETONS += $(SKEL_OUT)/kwork_top.skel.h SKELETONS += $(SKEL_OUT)/bench_uprobe.skel.h SKELETONS += $(SKEL_OUT)/augmented_raw_syscalls.skel.h $(SKEL_TMP_OUT) $(LIBAPI_OUTPUT) $(LIBBPF_OUTPUT) $(LIBPERF_OUTPUT) $(LIBSUBCMD_OUTPUT) $(LIBSYMBOL_OUTPUT): $(Q)$(MKDIR) -p $@ -ifdef BUILD_BPF_SKEL +ifeq ($(CONFIG_PERF_BPF_SKEL),y) BPFTOOL := $(SKEL_TMP_OUT)/bootstrap/bpftool # Get Clang's default includes on this system, as opposed to those seen by # '--target=bpf'. This fixes "missing" files on some architectures/distros, @@ -1127,11 +1135,11 @@ bpf-skel: $(SKELETONS) .PRECIOUS: $(SKEL_TMP_OUT)/%.bpf.o -else # BUILD_BPF_SKEL +else # CONFIG_PERF_BPF_SKEL bpf-skel: -endif # BUILD_BPF_SKEL +endif # CONFIG_PERF_BPF_SKEL bpf-skel-clean: $(call QUIET_CLEAN, bpf-skel) $(RM) -r $(SKEL_TMP_OUT) $(SKELETONS) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index b8d6a953fd74..2cf873d71dff 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -205,8 +205,17 @@ static int cs_etm_validate_config(struct auxtrace_record *itr, for (i = 0; i < cpu__max_cpu().cpu; i++) { struct perf_cpu cpu = { .cpu = i, }; - if (!perf_cpu_map__has(event_cpus, cpu) || - !perf_cpu_map__has(online_cpus, cpu)) + /* + * In per-cpu case, do the validation for CPUs to work with. + * In per-thread case, the CPU map is empty. Since the traced + * program can run on any CPUs in this case, thus don't skip + * validation. + */ + if (!perf_cpu_map__empty(event_cpus) && + !perf_cpu_map__has(event_cpus, cpu)) + continue; + + if (!perf_cpu_map__has(online_cpus, cpu)) continue; err = cs_etm_validate_context_id(itr, evsel, i); @@ -433,6 +442,15 @@ static int cs_etm_recording_options(struct auxtrace_record *itr, "contextid", 1); } + /* + * When the option '--timestamp' or '-T' is enabled, the PERF_SAMPLE_TIME + * bit is set for all events. In this case, always enable Arm CoreSight + * timestamp tracing. + */ + if (opts->sample_time_set) + evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel, + "timestamp", 1); + /* Add dummy event to keep tracking */ err = parse_event(evlist, "dummy:u"); if (err) @@ -917,16 +935,9 @@ out: * (CFG_CHG and evsel__set_config_if_unset()). If no default is set then user * changes aren't tracked. */ -struct perf_event_attr * -cs_etm_get_default_config(struct perf_pmu *pmu __maybe_unused) +void +cs_etm_get_default_config(const struct perf_pmu *pmu __maybe_unused, + struct perf_event_attr *attr) { - struct perf_event_attr *attr; - - attr = zalloc(sizeof(struct perf_event_attr)); - if (!attr) - return NULL; - attr->sample_period = 1; - - return attr; } diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c index a9623b128ece..7f3af3b97f3b 100644 --- a/tools/perf/arch/arm/util/pmu.c +++ b/tools/perf/arch/arm/util/pmu.c @@ -14,22 +14,22 @@ #include "../../../util/pmu.h" #include "../../../util/cs-etm.h" -struct perf_event_attr -*perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) +void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused) { #ifdef HAVE_AUXTRACE_SUPPORT if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) { /* add ETM default config here */ pmu->selectable = true; - return cs_etm_get_default_config(pmu); + pmu->perf_event_attr_init_default = cs_etm_get_default_config; #if defined(__aarch64__) } else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) { - return arm_spe_pmu_default_config(pmu); + pmu->selectable = true; + pmu->is_uncore = false; + pmu->perf_event_attr_init_default = arm_spe_pmu_default_config; } else if (strstarts(pmu->name, HISI_PTT_PMU_NAME)) { pmu->selectable = true; #endif } #endif - return NULL; } diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 9cc3d6dcb849..e3acc739bd00 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -113,6 +113,25 @@ arm_spe_snapshot_resolve_auxtrace_defaults(struct record_opts *opts, } } +static __u64 arm_spe_pmu__sample_period(const struct perf_pmu *arm_spe_pmu) +{ + static __u64 sample_period; + + if (sample_period) + return sample_period; + + /* + * If kernel driver doesn't advertise a minimum, + * use max allowable by PMSIDR_EL1.INTERVAL + */ + if (perf_pmu__scan_file(arm_spe_pmu, "caps/min_interval", "%llu", + &sample_period) != 1) { + pr_debug("arm_spe driver doesn't advertise a min. interval. Using 4096\n"); + sample_period = 4096; + } + return sample_period; +} + static int arm_spe_recording_options(struct auxtrace_record *itr, struct evlist *evlist, struct record_opts *opts) @@ -136,7 +155,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, return -EINVAL; } evsel->core.attr.freq = 0; - evsel->core.attr.sample_period = arm_spe_pmu->default_config->sample_period; + evsel->core.attr.sample_period = arm_spe_pmu__sample_period(arm_spe_pmu); evsel->needs_auxtrace_mmap = true; arm_spe_evsel = evsel; opts->full_auxtrace = true; @@ -495,29 +514,8 @@ struct auxtrace_record *arm_spe_recording_init(int *err, return &sper->itr; } -struct perf_event_attr -*arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu) +void +arm_spe_pmu_default_config(const struct perf_pmu *arm_spe_pmu, struct perf_event_attr *attr) { - struct perf_event_attr *attr; - - attr = zalloc(sizeof(struct perf_event_attr)); - if (!attr) { - pr_err("arm_spe default config cannot allocate a perf_event_attr\n"); - return NULL; - } - - /* - * If kernel driver doesn't advertise a minimum, - * use max allowable by PMSIDR_EL1.INTERVAL - */ - if (perf_pmu__scan_file(arm_spe_pmu, "caps/min_interval", "%llu", - &attr->sample_period) != 1) { - pr_debug("arm_spe driver doesn't advertise a min. interval. Using 4096\n"); - attr->sample_period = 4096; - } - - arm_spe_pmu->selectable = true; - arm_spe_pmu->is_uncore = false; - - return attr; + attr->sample_period = arm_spe_pmu__sample_period(arm_spe_pmu); } diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c index 615084eb88d8..2a4eab2d160e 100644 --- a/tools/perf/arch/arm64/util/pmu.c +++ b/tools/perf/arch/arm64/util/pmu.c @@ -10,20 +10,16 @@ const struct pmu_metrics_table *pmu_metrics_table__find(void) { - struct perf_pmu *pmu = pmu__find_core_pmu(); + struct perf_pmu *pmu; - if (pmu) - return perf_pmu__find_metrics_table(pmu); - - return NULL; -} - -const struct pmu_events_table *pmu_events_table__find(void) -{ - struct perf_pmu *pmu = pmu__find_core_pmu(); + /* Metrics aren't currently supported on heterogeneous Arm systems */ + if (perf_pmus__num_core_pmus() > 1) + return NULL; + /* Doesn't matter which one here because they'll all be the same */ + pmu = perf_pmus__find_core_pmu(); if (pmu) - return perf_pmu__find_events_table(pmu); + return perf_pmu__find_metrics_table(pmu); return NULL; } @@ -32,7 +28,7 @@ double perf_pmu__cpu_slots_per_cycle(void) { char path[PATH_MAX]; unsigned long long slots = 0; - struct perf_pmu *pmu = pmu__find_core_pmu(); + struct perf_pmu *pmu = perf_pmus__find_core_pmu(); if (pmu) { perf_pmu__pathname_scnprintf(path, sizeof(path), diff --git a/tools/perf/arch/powerpc/util/header.c b/tools/perf/arch/powerpc/util/header.c index c8d0dc775e5d..6b00efd53638 100644 --- a/tools/perf/arch/powerpc/util/header.c +++ b/tools/perf/arch/powerpc/util/header.c @@ -34,7 +34,7 @@ get_cpuid_str(struct perf_pmu *pmu __maybe_unused) { char *bufp; - if (asprintf(&bufp, "%.8lx", mfspr(SPRN_PVR)) < 0) + if (asprintf(&bufp, "0x%.8lx", mfspr(SPRN_PVR)) < 0) bufp = NULL; return bufp; diff --git a/tools/perf/arch/s390/util/pmu.c b/tools/perf/arch/s390/util/pmu.c index 11f03f32e3fd..886c30e001fa 100644 --- a/tools/perf/arch/s390/util/pmu.c +++ b/tools/perf/arch/s390/util/pmu.c @@ -13,11 +13,10 @@ #define S390_PMUPAI_EXT "pai_ext" #define S390_PMUCPUM_CF "cpum_cf" -struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu) +void perf_pmu__arch_init(struct perf_pmu *pmu) { if (!strcmp(pmu->name, S390_PMUPAI_CRYPTO) || !strcmp(pmu->name, S390_PMUPAI_EXT) || !strcmp(pmu->name, S390_PMUCPUM_CF)) pmu->selectable = true; - return NULL; } diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c index 5f4ac4fc7fcf..5cdf457f5cbe 100644 --- a/tools/perf/arch/x86/annotate/instructions.c +++ b/tools/perf/arch/x86/annotate/instructions.c @@ -74,12 +74,15 @@ static struct ins x86__instructions[] = { { .name = "movdqa", .ops = &mov_ops, }, { .name = "movdqu", .ops = &mov_ops, }, { .name = "movsd", .ops = &mov_ops, }, - { .name = "movslq", .ops = &mov_ops, }, { .name = "movss", .ops = &mov_ops, }, + { .name = "movsb", .ops = &mov_ops, }, + { .name = "movsw", .ops = &mov_ops, }, + { .name = "movsl", .ops = &mov_ops, }, { .name = "movupd", .ops = &mov_ops, }, { .name = "movups", .ops = &mov_ops, }, - { .name = "movzbl", .ops = &mov_ops, }, - { .name = "movzwl", .ops = &mov_ops, }, + { .name = "movzb", .ops = &mov_ops, }, + { .name = "movzw", .ops = &mov_ops, }, + { .name = "movzl", .ops = &mov_ops, }, { .name = "mulsd", .ops = &mov_ops, }, { .name = "mulss", .ops = &mov_ops, }, { .name = "nop", .ops = &nop_ops, }, diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c index 31807791589e..fa0c718b9e72 100644 --- a/tools/perf/arch/x86/util/intel-pt.c +++ b/tools/perf/arch/x86/util/intel-pt.c @@ -60,36 +60,31 @@ struct intel_pt_recording { size_t priv_size; }; -static int intel_pt_parse_terms_with_default(struct perf_pmu *pmu, +static int intel_pt_parse_terms_with_default(const struct perf_pmu *pmu, const char *str, u64 *config) { - struct list_head *terms; + struct parse_events_terms terms; struct perf_event_attr attr = { .size = 0, }; int err; - terms = malloc(sizeof(struct list_head)); - if (!terms) - return -ENOMEM; - - INIT_LIST_HEAD(terms); - - err = parse_events_terms(terms, str, /*input=*/ NULL); + parse_events_terms__init(&terms); + err = parse_events_terms(&terms, str, /*input=*/ NULL); if (err) goto out_free; attr.config = *config; - err = perf_pmu__config_terms(pmu, &attr, terms, /*zero=*/true, /*err=*/NULL); + err = perf_pmu__config_terms(pmu, &attr, &terms, /*zero=*/true, /*err=*/NULL); if (err) goto out_free; *config = attr.config; out_free: - parse_events_terms__delete(terms); + parse_events_terms__exit(&terms); return err; } -static int intel_pt_parse_terms(struct perf_pmu *pmu, const char *str, u64 *config) +static int intel_pt_parse_terms(const struct perf_pmu *pmu, const char *str, u64 *config) { *config = 0; return intel_pt_parse_terms_with_default(pmu, str, config); @@ -182,7 +177,7 @@ static int intel_pt_pick_bit(int bits, int target) return pick; } -static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu) +static u64 intel_pt_default_config(const struct perf_pmu *intel_pt_pmu) { char buf[256]; int mtc, mtc_periods = 0, mtc_period; @@ -261,20 +256,17 @@ static int intel_pt_parse_snapshot_options(struct auxtrace_record *itr, return 0; } -struct perf_event_attr * -intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu) +void intel_pt_pmu_default_config(const struct perf_pmu *intel_pt_pmu, + struct perf_event_attr *attr) { - struct perf_event_attr *attr; - - attr = zalloc(sizeof(struct perf_event_attr)); - if (!attr) - return NULL; - - attr->config = intel_pt_default_config(intel_pt_pmu); + static u64 config; + static bool initialized; - intel_pt_pmu->selectable = true; - - return attr; + if (!initialized) { + config = intel_pt_default_config(intel_pt_pmu); + initialized = true; + } + attr->config = config; } static const char *intel_pt_find_filter(struct evlist *evlist, diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c index f428cffb0378..469555ae9b3c 100644 --- a/tools/perf/arch/x86/util/pmu.c +++ b/tools/perf/arch/x86/util/pmu.c @@ -17,158 +17,19 @@ #include "../../../util/pmus.h" #include "env.h" -struct pmu_alias { - char *name; - char *alias; - struct list_head list; -}; - -static LIST_HEAD(pmu_alias_name_list); -static bool cached_list; - -struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) +void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused) { #ifdef HAVE_AUXTRACE_SUPPORT if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) { pmu->auxtrace = true; - return intel_pt_pmu_default_config(pmu); + pmu->selectable = true; + pmu->perf_event_attr_init_default = intel_pt_pmu_default_config; } if (!strcmp(pmu->name, INTEL_BTS_PMU_NAME)) { pmu->auxtrace = true; pmu->selectable = true; } #endif - return NULL; -} - -static void pmu_alias__delete(struct pmu_alias *pmu_alias) -{ - if (!pmu_alias) - return; - - zfree(&pmu_alias->name); - zfree(&pmu_alias->alias); - free(pmu_alias); -} - -static struct pmu_alias *pmu_alias__new(char *name, char *alias) -{ - struct pmu_alias *pmu_alias = zalloc(sizeof(*pmu_alias)); - - if (pmu_alias) { - pmu_alias->name = strdup(name); - if (!pmu_alias->name) - goto out_delete; - - pmu_alias->alias = strdup(alias); - if (!pmu_alias->alias) - goto out_delete; - } - return pmu_alias; - -out_delete: - pmu_alias__delete(pmu_alias); - return NULL; -} - -static int setup_pmu_alias_list(void) -{ - int fd, dirfd; - DIR *dir; - struct dirent *dent; - struct pmu_alias *pmu_alias; - char buf[MAX_PMU_NAME_LEN]; - FILE *file; - int ret = -ENOMEM; - - dirfd = perf_pmu__event_source_devices_fd(); - if (dirfd < 0) - return -1; - - dir = fdopendir(dirfd); - if (!dir) - return -errno; - - while ((dent = readdir(dir))) { - if (!strcmp(dent->d_name, ".") || - !strcmp(dent->d_name, "..")) - continue; - - fd = perf_pmu__pathname_fd(dirfd, dent->d_name, "alias", O_RDONLY); - if (fd < 0) - continue; - - file = fdopen(fd, "r"); - if (!file) - continue; - - if (!fgets(buf, sizeof(buf), file)) { - fclose(file); - continue; - } - - fclose(file); - - /* Remove the last '\n' */ - buf[strlen(buf) - 1] = 0; - - pmu_alias = pmu_alias__new(dent->d_name, buf); - if (!pmu_alias) - goto close_dir; - - list_add_tail(&pmu_alias->list, &pmu_alias_name_list); - } - - ret = 0; - -close_dir: - closedir(dir); - return ret; -} - -static const char *__pmu_find_real_name(const char *name) -{ - struct pmu_alias *pmu_alias; - - list_for_each_entry(pmu_alias, &pmu_alias_name_list, list) { - if (!strcmp(name, pmu_alias->alias)) - return pmu_alias->name; - } - - return name; -} - -const char *pmu_find_real_name(const char *name) -{ - if (cached_list) - return __pmu_find_real_name(name); - - setup_pmu_alias_list(); - cached_list = true; - - return __pmu_find_real_name(name); -} - -static const char *__pmu_find_alias_name(const char *name) -{ - struct pmu_alias *pmu_alias; - - list_for_each_entry(pmu_alias, &pmu_alias_name_list, list) { - if (!strcmp(name, pmu_alias->name)) - return pmu_alias->alias; - } - return NULL; -} - -const char *pmu_find_alias_name(const char *name) -{ - if (cached_list) - return __pmu_find_alias_name(name); - - setup_pmu_alias_list(); - cached_list = true; - - return __pmu_find_alias_name(name); } int perf_pmus__num_mem_pmus(void) diff --git a/tools/perf/bench/sched-messaging.c b/tools/perf/bench/sched-messaging.c index fa1f8f998814..93dcd9dba3d0 100644 --- a/tools/perf/bench/sched-messaging.c +++ b/tools/perf/bench/sched-messaging.c @@ -36,6 +36,7 @@ static bool use_pipes = false; static unsigned int nr_loops = 100; static bool thread_mode = false; static unsigned int num_groups = 10; +static unsigned int total_children = 0; static struct list_head sender_contexts = LIST_HEAD_INIT(sender_contexts); static struct list_head receiver_contexts = LIST_HEAD_INIT(receiver_contexts); @@ -55,6 +56,13 @@ struct receiver_context { int wakefd; }; +union messaging_worker { + pthread_t thread; + pid_t pid; +}; + +static union messaging_worker *worker_tab; + static void fdpair(int fds[2]) { if (use_pipes) { @@ -98,7 +106,7 @@ static void *sender(struct sender_context *ctx) again: ret = write(ctx->out_fds[j], data + done, - sizeof(data)-done); + sizeof(data) - done); if (ret < 0) err(EXIT_FAILURE, "SENDER: write"); done += ret; @@ -139,30 +147,12 @@ again: return NULL; } -static pthread_t create_worker(void *ctx, void *(*func)(void *)) +static void create_thread_worker(union messaging_worker *worker, + void *ctx, void *(*func)(void *)) { pthread_attr_t attr; - pthread_t childid; int ret; - if (!thread_mode) { - /* process mode */ - /* Fork the receiver. */ - switch (fork()) { - case -1: - err(EXIT_FAILURE, "fork()"); - break; - case 0: - (*func) (ctx); - exit(0); - break; - default: - break; - } - - return (pthread_t)0; - } - if (pthread_attr_init(&attr) != 0) err(EXIT_FAILURE, "pthread_attr_init:"); @@ -171,15 +161,37 @@ static pthread_t create_worker(void *ctx, void *(*func)(void *)) err(EXIT_FAILURE, "pthread_attr_setstacksize"); #endif - ret = pthread_create(&childid, &attr, func, ctx); + ret = pthread_create(&worker->thread, &attr, func, ctx); if (ret != 0) err(EXIT_FAILURE, "pthread_create failed"); pthread_attr_destroy(&attr); - return childid; } -static void reap_worker(pthread_t id) +static void create_process_worker(union messaging_worker *worker, + void *ctx, void *(*func)(void *)) +{ + /* Fork the receiver. */ + worker->pid = fork(); + + if (worker->pid == -1) { + err(EXIT_FAILURE, "fork()"); + } else if (worker->pid == 0) { + (*func) (ctx); + exit(0); + } +} + +static void create_worker(union messaging_worker *worker, + void *ctx, void *(*func)(void *)) +{ + if (!thread_mode) + return create_process_worker(worker, ctx, func); + else + return create_thread_worker(worker, ctx, func); +} + +static void reap_worker(union messaging_worker *worker) { int proc_status; void *thread_status; @@ -190,19 +202,19 @@ static void reap_worker(pthread_t id) if (!WIFEXITED(proc_status)) exit(1); } else { - pthread_join(id, &thread_status); + pthread_join(worker->thread, &thread_status); } } /* One group of senders and receivers */ -static unsigned int group(pthread_t *pth, +static unsigned int group(union messaging_worker *worker, unsigned int num_fds, int ready_out, int wakefd) { unsigned int i; - struct sender_context *snd_ctx = malloc(sizeof(struct sender_context) - + num_fds * sizeof(int)); + struct sender_context *snd_ctx = malloc(sizeof(struct sender_context) + + num_fds * sizeof(int)); if (!snd_ctx) err(EXIT_FAILURE, "malloc()"); @@ -226,7 +238,7 @@ static unsigned int group(pthread_t *pth, ctx->ready_out = ready_out; ctx->wakefd = wakefd; - pth[i] = create_worker(ctx, (void *)receiver); + create_worker(worker + i, ctx, (void *)receiver); snd_ctx->out_fds[i] = fds[1]; if (!thread_mode) @@ -239,7 +251,7 @@ static unsigned int group(pthread_t *pth, snd_ctx->wakefd = wakefd; snd_ctx->num_fds = num_fds; - pth[num_fds+i] = create_worker(snd_ctx, (void *)sender); + create_worker(worker + num_fds + i, snd_ctx, (void *)sender); } /* Close the fds we have left */ @@ -251,6 +263,17 @@ static unsigned int group(pthread_t *pth, return num_fds * 2; } +static void sig_handler(int sig __maybe_unused) +{ + unsigned int i; + + /* + * When exit abnormally, kill all forked child processes. + */ + for (i = 0; i < total_children; i++) + kill(worker_tab[i].pid, SIGKILL); +} + static const struct option options[] = { OPT_BOOLEAN('p', "pipe", &use_pipes, "Use pipe() instead of socketpair()"), @@ -268,27 +291,30 @@ static const char * const bench_sched_message_usage[] = { int bench_sched_messaging(int argc, const char **argv) { - unsigned int i, total_children; + unsigned int i; struct timeval start, stop, diff; unsigned int num_fds = 20; int readyfds[2], wakefds[2]; char dummy; - pthread_t *pth_tab; struct sender_context *pos, *n; argc = parse_options(argc, argv, options, bench_sched_message_usage, 0); - pth_tab = malloc(num_fds * 2 * num_groups * sizeof(pthread_t)); - if (!pth_tab) + worker_tab = malloc(num_fds * 2 * num_groups * sizeof(union messaging_worker)); + if (!worker_tab) err(EXIT_FAILURE, "main:malloc()"); fdpair(readyfds); fdpair(wakefds); - total_children = 0; + if (!thread_mode) { + signal(SIGINT, sig_handler); + signal(SIGTERM, sig_handler); + } + for (i = 0; i < num_groups; i++) - total_children += group(pth_tab+total_children, num_fds, + total_children += group(worker_tab + total_children, num_fds, readyfds[1], wakefds[0]); /* Wait for everyone to be ready */ @@ -304,7 +330,7 @@ int bench_sched_messaging(int argc, const char **argv) /* Reap them all */ for (i = 0; i < total_children; i++) - reap_worker(pth_tab[i]); + reap_worker(worker_tab + i); gettimeofday(&stop, NULL); @@ -332,7 +358,7 @@ int bench_sched_messaging(int argc, const char **argv) break; } - free(pth_tab); + free(worker_tab); list_for_each_entry_safe(pos, n, &sender_contexts, list) { list_del_init(&pos->list); free(pos); diff --git a/tools/perf/bench/sched-pipe.c b/tools/perf/bench/sched-pipe.c index a960e7a93aec..3af6d3c55aba 100644 --- a/tools/perf/bench/sched-pipe.c +++ b/tools/perf/bench/sched-pipe.c @@ -10,7 +10,9 @@ * Ported to perf by Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> */ #include <subcmd/parse-options.h> +#include <api/fs/fs.h> #include "bench.h" +#include "util/cgroup.h" #include <unistd.h> #include <stdio.h> @@ -19,6 +21,7 @@ #include <sys/wait.h> #include <string.h> #include <errno.h> +#include <fcntl.h> #include <assert.h> #include <sys/time.h> #include <sys/types.h> @@ -31,6 +34,7 @@ struct thread_data { int nr; int pipe_read; int pipe_write; + bool cgroup_failed; pthread_t pthread; }; @@ -40,9 +44,48 @@ static int loops = LOOPS_DEFAULT; /* Use processes by default: */ static bool threaded; +static char *cgrp_names[2]; +static struct cgroup *cgrps[2]; + +static int parse_two_cgroups(const struct option *opt __maybe_unused, + const char *str, int unset __maybe_unused) +{ + char *p = strdup(str); + char *q; + int ret = -1; + + if (p == NULL) { + fprintf(stderr, "memory allocation failure\n"); + return -1; + } + + q = strchr(p, ','); + if (q == NULL) { + fprintf(stderr, "it should have two cgroup names: %s\n", p); + goto out; + } + *q = '\0'; + + cgrp_names[0] = strdup(p); + cgrp_names[1] = strdup(q + 1); + + if (cgrp_names[0] == NULL || cgrp_names[1] == NULL) { + fprintf(stderr, "memory allocation failure\n"); + goto out; + } + ret = 0; + +out: + free(p); + return ret; +} + static const struct option options[] = { OPT_INTEGER('l', "loop", &loops, "Specify number of loops"), OPT_BOOLEAN('T', "threaded", &threaded, "Specify threads/process based task setup"), + OPT_CALLBACK('G', "cgroups", NULL, "SEND,RECV", + "Put sender and receivers in given cgroups", + parse_two_cgroups), OPT_END() }; @@ -51,12 +94,89 @@ static const char * const bench_sched_pipe_usage[] = { NULL }; +static int enter_cgroup(int nr) +{ + char buf[32]; + int fd, len, ret; + int saved_errno; + struct cgroup *cgrp; + pid_t pid; + + if (cgrp_names[nr] == NULL) + return 0; + + if (cgrps[nr] == NULL) { + cgrps[nr] = cgroup__new(cgrp_names[nr], /*do_open=*/true); + if (cgrps[nr] == NULL) + goto err; + } + cgrp = cgrps[nr]; + + if (threaded) + pid = syscall(__NR_gettid); + else + pid = getpid(); + + snprintf(buf, sizeof(buf), "%d\n", pid); + len = strlen(buf); + + /* try cgroup v2 interface first */ + if (threaded) + fd = openat(cgrp->fd, "cgroup.threads", O_WRONLY); + else + fd = openat(cgrp->fd, "cgroup.procs", O_WRONLY); + + /* try cgroup v1 if failed */ + if (fd < 0 && errno == ENOENT) + fd = openat(cgrp->fd, "tasks", O_WRONLY); + + if (fd < 0) + goto err; + + ret = write(fd, buf, len); + close(fd); + + if (ret != len) { + printf("Cannot enter to cgroup: %s\n", cgrp->name); + return -1; + } + return 0; + +err: + saved_errno = errno; + printf("Failed to open cgroup file in %s\n", cgrp_names[nr]); + + if (saved_errno == ENOENT) { + char mnt[PATH_MAX]; + + if (cgroupfs_find_mountpoint(mnt, sizeof(mnt), "perf_event") == 0) + printf(" Hint: create the cgroup first, like 'mkdir %s/%s'\n", + mnt, cgrp_names[nr]); + } else if (saved_errno == EACCES && geteuid() > 0) { + printf(" Hint: try to run as root\n"); + } + + return -1; +} + +static void exit_cgroup(int nr) +{ + cgroup__put(cgrps[nr]); + free(cgrp_names[nr]); +} + static void *worker_thread(void *__tdata) { struct thread_data *td = __tdata; int m = 0, i; int ret; + ret = enter_cgroup(td->nr); + if (ret < 0) { + td->cgroup_failed = true; + return NULL; + } + for (i = 0; i < loops; i++) { if (!td->nr) { ret = read(td->pipe_read, &m, sizeof(int)); @@ -76,7 +196,8 @@ static void *worker_thread(void *__tdata) int bench_sched_pipe(int argc, const char **argv) { - struct thread_data threads[2], *td; + struct thread_data threads[2] = {}; + struct thread_data *td; int pipe_1[2], pipe_2[2]; struct timeval start, stop, diff; unsigned long long result_usec = 0; @@ -112,9 +233,7 @@ int bench_sched_pipe(int argc, const char **argv) } } - if (threaded) { - for (t = 0; t < nr_threads; t++) { td = threads + t; @@ -128,7 +247,6 @@ int bench_sched_pipe(int argc, const char **argv) ret = pthread_join(td->pthread, NULL); BUG_ON(ret); } - } else { pid = fork(); assert(pid >= 0); @@ -147,6 +265,12 @@ int bench_sched_pipe(int argc, const char **argv) gettimeofday(&stop, NULL); timersub(&stop, &start, &diff); + exit_cgroup(0); + exit_cgroup(1); + + if (threads[0].cgroup_failed || threads[1].cgroup_failed) + return 0; + switch (bench_format) { case BENCH_FORMAT_DEFAULT: printf("# Executed %d pipe operations between two %s\n\n", diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c index 914c0817fe8a..5c71fdc419dd 100644 --- a/tools/perf/bench/uprobe.c +++ b/tools/perf/bench/uprobe.c @@ -89,6 +89,7 @@ static int bench_uprobe__setup_bpf_skel(enum bench_uprobe bench) return err; cleanup: bench_uprobe_bpf__destroy(skel); + skel = NULL; return err; } diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c index cd381693658b..e2a40f1d9225 100644 --- a/tools/perf/builtin-buildid-cache.c +++ b/tools/perf/builtin-buildid-cache.c @@ -277,8 +277,10 @@ static bool dso__missing_buildid_cache(struct dso *dso, int parm __maybe_unused) char filename[PATH_MAX]; struct build_id bid; - if (dso__build_id_filename(dso, filename, sizeof(filename), false) && - filename__read_build_id(filename, &bid) == -1) { + if (!dso__build_id_filename(dso, filename, sizeof(filename), false)) + return true; + + if (filename__read_build_id(filename, &bid) == -1) { if (errno == ENOENT) return false; diff --git a/tools/perf/builtin-kwork.c b/tools/perf/builtin-kwork.c index 14bf7a8429e7..f007a9b27065 100644 --- a/tools/perf/builtin-kwork.c +++ b/tools/perf/builtin-kwork.c @@ -45,6 +45,11 @@ #define PRINT_BRACKETPAIR_WIDTH 2 #define PRINT_TIME_UNIT_SEC_WIDTH 2 #define PRINT_TIME_UNIT_MESC_WIDTH 3 +#define PRINT_PID_WIDTH 7 +#define PRINT_TASK_NAME_WIDTH 16 +#define PRINT_CPU_USAGE_WIDTH 6 +#define PRINT_CPU_USAGE_DECIMAL_WIDTH 2 +#define PRINT_CPU_USAGE_HIST_WIDTH 30 #define PRINT_RUNTIME_HEADER_WIDTH (PRINT_RUNTIME_WIDTH + PRINT_TIME_UNIT_MESC_WIDTH) #define PRINT_LATENCY_HEADER_WIDTH (PRINT_LATENCY_WIDTH + PRINT_TIME_UNIT_MESC_WIDTH) #define PRINT_TIMEHIST_CPU_WIDTH (PRINT_CPU_WIDTH + PRINT_BRACKETPAIR_WIDTH) @@ -131,6 +136,34 @@ static int max_latency_cmp(struct kwork_work *l, struct kwork_work *r) return 0; } +static int cpu_usage_cmp(struct kwork_work *l, struct kwork_work *r) +{ + if (l->cpu_usage > r->cpu_usage) + return 1; + if (l->cpu_usage < r->cpu_usage) + return -1; + + return 0; +} + +static int id_or_cpu_r_cmp(struct kwork_work *l, struct kwork_work *r) +{ + if (l->id < r->id) + return 1; + if (l->id > r->id) + return -1; + + if (l->id != 0) + return 0; + + if (l->cpu < r->cpu) + return 1; + if (l->cpu > r->cpu) + return -1; + + return 0; +} + static int sort_dimension__add(struct perf_kwork *kwork __maybe_unused, const char *tok, struct list_head *list) { @@ -155,12 +188,22 @@ static int sort_dimension__add(struct perf_kwork *kwork __maybe_unused, .name = "avg", .cmp = avg_latency_cmp, }; + static struct sort_dimension rate_sort_dimension = { + .name = "rate", + .cmp = cpu_usage_cmp, + }; + static struct sort_dimension tid_sort_dimension = { + .name = "tid", + .cmp = id_or_cpu_r_cmp, + }; struct sort_dimension *available_sorts[] = { &id_sort_dimension, &max_sort_dimension, &count_sort_dimension, &runtime_sort_dimension, &avg_sort_dimension, + &rate_sort_dimension, + &tid_sort_dimension, }; if (kwork->report == KWORK_REPORT_LATENCY) @@ -361,6 +404,17 @@ static void profile_update_timespan(struct perf_kwork *kwork, kwork->timeend = sample->time; } +static bool profile_name_match(struct perf_kwork *kwork, + struct kwork_work *work) +{ + if (kwork->profile_name && work->name && + (strcmp(work->name, kwork->profile_name) != 0)) { + return false; + } + + return true; +} + static bool profile_event_match(struct perf_kwork *kwork, struct kwork_work *work, struct perf_sample *sample) @@ -376,10 +430,14 @@ static bool profile_event_match(struct perf_kwork *kwork, ((ptime->end != 0) && (ptime->end < time))) return false; - if ((kwork->profile_name != NULL) && - (work->name != NULL) && - (strcmp(work->name, kwork->profile_name) != 0)) + /* + * report top needs to collect the runtime of all tasks to + * calculate the load of each core. + */ + if ((kwork->report != KWORK_REPORT_TOP) && + !profile_name_match(kwork, work)) { return false; + } profile_update_timespan(kwork, sample); return true; @@ -392,13 +450,14 @@ static int work_push_atom(struct perf_kwork *kwork, struct evsel *evsel, struct perf_sample *sample, struct machine *machine, - struct kwork_work **ret_work) + struct kwork_work **ret_work, + bool overwrite) { - struct kwork_atom *atom, *dst_atom; + struct kwork_atom *atom, *dst_atom, *last_atom; struct kwork_work *work, key; BUG_ON(class->work_init == NULL); - class->work_init(class, &key, evsel, sample, machine); + class->work_init(kwork, class, &key, src_type, evsel, sample, machine); atom = atom_new(kwork, sample); if (atom == NULL) @@ -406,12 +465,14 @@ static int work_push_atom(struct perf_kwork *kwork, work = work_findnew(&class->work_root, &key, &kwork->cmp_id); if (work == NULL) { - free(atom); + atom_free(atom); return -1; } - if (!profile_event_match(kwork, work, sample)) + if (!profile_event_match(kwork, work, sample)) { + atom_free(atom); return 0; + } if (dst_type < KWORK_TRACE_MAX) { dst_atom = list_last_entry_or_null(&work->atom_list[dst_type], @@ -425,6 +486,17 @@ static int work_push_atom(struct perf_kwork *kwork, if (ret_work != NULL) *ret_work = work; + if (overwrite) { + last_atom = list_last_entry_or_null(&work->atom_list[src_type], + struct kwork_atom, list); + if (last_atom) { + atom_del(last_atom); + + kwork->nr_skipped_events[src_type]++; + kwork->nr_skipped_events[KWORK_TRACE_MAX]++; + } + } + list_add_tail(&atom->list, &work->atom_list[src_type]); return 0; @@ -443,7 +515,7 @@ static struct kwork_atom *work_pop_atom(struct perf_kwork *kwork, struct kwork_work *work, key; BUG_ON(class->work_init == NULL); - class->work_init(class, &key, evsel, sample, machine); + class->work_init(kwork, class, &key, src_type, evsel, sample, machine); work = work_findnew(&class->work_root, &key, &kwork->cmp_id); if (ret_work != NULL) @@ -471,6 +543,38 @@ static struct kwork_atom *work_pop_atom(struct perf_kwork *kwork, return NULL; } +static struct kwork_work *find_work_by_id(struct rb_root_cached *root, + u64 id, int cpu) +{ + struct rb_node *next; + struct kwork_work *work; + + next = rb_first_cached(root); + while (next) { + work = rb_entry(next, struct kwork_work, node); + if ((cpu != -1 && work->id == id && work->cpu == cpu) || + (cpu == -1 && work->id == id)) + return work; + + next = rb_next(next); + } + + return NULL; +} + +static struct kwork_class *get_kwork_class(struct perf_kwork *kwork, + enum kwork_class_type type) +{ + struct kwork_class *class; + + list_for_each_entry(class, &kwork->class_list, list) { + if (class->type == type) + return class; + } + + return NULL; +} + static void report_update_exit_event(struct kwork_work *work, struct kwork_atom *atom, struct perf_sample *sample) @@ -500,7 +604,7 @@ static int report_entry_event(struct perf_kwork *kwork, { return work_push_atom(kwork, class, KWORK_TRACE_ENTRY, KWORK_TRACE_MAX, evsel, sample, - machine, NULL); + machine, NULL, true); } static int report_exit_event(struct perf_kwork *kwork, @@ -555,7 +659,7 @@ static int latency_raise_event(struct perf_kwork *kwork, { return work_push_atom(kwork, class, KWORK_TRACE_RAISE, KWORK_TRACE_MAX, evsel, sample, - machine, NULL); + machine, NULL, true); } static int latency_entry_event(struct perf_kwork *kwork, @@ -714,7 +818,7 @@ static int timehist_raise_event(struct perf_kwork *kwork, { return work_push_atom(kwork, class, KWORK_TRACE_RAISE, KWORK_TRACE_MAX, evsel, sample, - machine, NULL); + machine, NULL, true); } static int timehist_entry_event(struct perf_kwork *kwork, @@ -728,7 +832,7 @@ static int timehist_entry_event(struct perf_kwork *kwork, ret = work_push_atom(kwork, class, KWORK_TRACE_ENTRY, KWORK_TRACE_RAISE, evsel, sample, - machine, &work); + machine, &work, true); if (ret) return ret; @@ -775,6 +879,84 @@ out: return ret; } +static void top_update_runtime(struct kwork_work *work, + struct kwork_atom *atom, + struct perf_sample *sample) +{ + u64 delta; + u64 exit_time = sample->time; + u64 entry_time = atom->time; + + if ((entry_time != 0) && (exit_time >= entry_time)) { + delta = exit_time - entry_time; + work->total_runtime += delta; + } +} + +static int top_entry_event(struct perf_kwork *kwork, + struct kwork_class *class, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine) +{ + return work_push_atom(kwork, class, KWORK_TRACE_ENTRY, + KWORK_TRACE_MAX, evsel, sample, + machine, NULL, true); +} + +static int top_exit_event(struct perf_kwork *kwork, + struct kwork_class *class, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine) +{ + struct kwork_work *work, *sched_work; + struct kwork_class *sched_class; + struct kwork_atom *atom; + + atom = work_pop_atom(kwork, class, KWORK_TRACE_EXIT, + KWORK_TRACE_ENTRY, evsel, sample, + machine, &work); + if (!work) + return -1; + + if (atom) { + sched_class = get_kwork_class(kwork, KWORK_CLASS_SCHED); + if (sched_class) { + sched_work = find_work_by_id(&sched_class->work_root, + work->id, work->cpu); + if (sched_work) + top_update_runtime(work, atom, sample); + } + atom_del(atom); + } + + return 0; +} + +static int top_sched_switch_event(struct perf_kwork *kwork, + struct kwork_class *class, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine) +{ + struct kwork_atom *atom; + struct kwork_work *work; + + atom = work_pop_atom(kwork, class, KWORK_TRACE_EXIT, + KWORK_TRACE_ENTRY, evsel, sample, + machine, &work); + if (!work) + return -1; + + if (atom) { + top_update_runtime(work, atom, sample); + atom_del(atom); + } + + return top_entry_event(kwork, class, evsel, sample, machine); +} + static struct kwork_class kwork_irq; static int process_irq_handler_entry_event(struct perf_tool *tool, struct evsel *evsel, @@ -819,16 +1001,24 @@ static int irq_class_init(struct kwork_class *class, return 0; } -static void irq_work_init(struct kwork_class *class, +static void irq_work_init(struct perf_kwork *kwork, + struct kwork_class *class, struct kwork_work *work, + enum kwork_trace_type src_type __maybe_unused, struct evsel *evsel, struct perf_sample *sample, struct machine *machine __maybe_unused) { work->class = class; work->cpu = sample->cpu; - work->id = evsel__intval(evsel, sample, "irq"); - work->name = evsel__strval(evsel, sample, "name"); + + if (kwork->report == KWORK_REPORT_TOP) { + work->id = evsel__intval_common(evsel, sample, "common_pid"); + work->name = NULL; + } else { + work->id = evsel__intval(evsel, sample, "irq"); + work->name = evsel__strval(evsel, sample, "name"); + } } static void irq_work_name(struct kwork_work *work, char *buf, int len) @@ -938,18 +1128,27 @@ static char *evsel__softirq_name(struct evsel *evsel, u64 num) return name; } -static void softirq_work_init(struct kwork_class *class, +static void softirq_work_init(struct perf_kwork *kwork, + struct kwork_class *class, struct kwork_work *work, + enum kwork_trace_type src_type __maybe_unused, struct evsel *evsel, struct perf_sample *sample, struct machine *machine __maybe_unused) { - u64 num = evsel__intval(evsel, sample, "vec"); + u64 num; - work->id = num; work->class = class; work->cpu = sample->cpu; - work->name = evsel__softirq_name(evsel, num); + + if (kwork->report == KWORK_REPORT_TOP) { + work->id = evsel__intval_common(evsel, sample, "common_pid"); + work->name = NULL; + } else { + num = evsel__intval(evsel, sample, "vec"); + work->id = num; + work->name = evsel__softirq_name(evsel, num); + } } static void softirq_work_name(struct kwork_work *work, char *buf, int len) @@ -1029,8 +1228,10 @@ static int workqueue_class_init(struct kwork_class *class, return 0; } -static void workqueue_work_init(struct kwork_class *class, +static void workqueue_work_init(struct perf_kwork *kwork __maybe_unused, + struct kwork_class *class, struct kwork_work *work, + enum kwork_trace_type src_type __maybe_unused, struct evsel *evsel, struct perf_sample *sample, struct machine *machine) @@ -1064,10 +1265,77 @@ static struct kwork_class kwork_workqueue = { .work_name = workqueue_work_name, }; +static struct kwork_class kwork_sched; +static int process_sched_switch_event(struct perf_tool *tool, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine) +{ + struct perf_kwork *kwork = container_of(tool, struct perf_kwork, tool); + + if (kwork->tp_handler->sched_switch_event) + return kwork->tp_handler->sched_switch_event(kwork, &kwork_sched, + evsel, sample, machine); + return 0; +} + +const struct evsel_str_handler sched_tp_handlers[] = { + { "sched:sched_switch", process_sched_switch_event, }, +}; + +static int sched_class_init(struct kwork_class *class, + struct perf_session *session) +{ + if (perf_session__set_tracepoints_handlers(session, + sched_tp_handlers)) { + pr_err("Failed to set sched tracepoints handlers\n"); + return -1; + } + + class->work_root = RB_ROOT_CACHED; + return 0; +} + +static void sched_work_init(struct perf_kwork *kwork __maybe_unused, + struct kwork_class *class, + struct kwork_work *work, + enum kwork_trace_type src_type, + struct evsel *evsel, + struct perf_sample *sample, + struct machine *machine __maybe_unused) +{ + work->class = class; + work->cpu = sample->cpu; + + if (src_type == KWORK_TRACE_EXIT) { + work->id = evsel__intval(evsel, sample, "prev_pid"); + work->name = strdup(evsel__strval(evsel, sample, "prev_comm")); + } else if (src_type == KWORK_TRACE_ENTRY) { + work->id = evsel__intval(evsel, sample, "next_pid"); + work->name = strdup(evsel__strval(evsel, sample, "next_comm")); + } +} + +static void sched_work_name(struct kwork_work *work, char *buf, int len) +{ + snprintf(buf, len, "%s", work->name); +} + +static struct kwork_class kwork_sched = { + .name = "sched", + .type = KWORK_CLASS_SCHED, + .nr_tracepoints = ARRAY_SIZE(sched_tp_handlers), + .tp_handlers = sched_tp_handlers, + .class_init = sched_class_init, + .work_init = sched_work_init, + .work_name = sched_work_name, +}; + static struct kwork_class *kwork_class_supported_list[KWORK_CLASS_MAX] = { [KWORK_CLASS_IRQ] = &kwork_irq, [KWORK_CLASS_SOFTIRQ] = &kwork_softirq, [KWORK_CLASS_WORKQUEUE] = &kwork_workqueue, + [KWORK_CLASS_SCHED] = &kwork_sched, }; static void print_separator(int len) @@ -1291,11 +1559,132 @@ static void print_bad_events(struct perf_kwork *kwork) } } -static void work_sort(struct perf_kwork *kwork, struct kwork_class *class) +const char *graph_load = "||||||||||||||||||||||||||||||||||||||||||||||||"; +const char *graph_idle = " "; +static void top_print_per_cpu_load(struct perf_kwork *kwork) +{ + int i, load_width; + u64 total, load, load_ratio; + struct kwork_top_stat *stat = &kwork->top_stat; + + for (i = 0; i < MAX_NR_CPUS; i++) { + total = stat->cpus_runtime[i].total; + load = stat->cpus_runtime[i].load; + if (test_bit(i, stat->all_cpus_bitmap) && total) { + load_ratio = load * 10000 / total; + load_width = PRINT_CPU_USAGE_HIST_WIDTH * + load_ratio / 10000; + + printf("%%Cpu%-*d[%.*s%.*s %*.*f%%]\n", + PRINT_CPU_WIDTH, i, + load_width, graph_load, + PRINT_CPU_USAGE_HIST_WIDTH - load_width, + graph_idle, + PRINT_CPU_USAGE_WIDTH, + PRINT_CPU_USAGE_DECIMAL_WIDTH, + (double)load_ratio / 100); + } + } +} + +static void top_print_cpu_usage(struct perf_kwork *kwork) +{ + struct kwork_top_stat *stat = &kwork->top_stat; + u64 idle_time = stat->cpus_runtime[MAX_NR_CPUS].idle; + u64 hardirq_time = stat->cpus_runtime[MAX_NR_CPUS].irq; + u64 softirq_time = stat->cpus_runtime[MAX_NR_CPUS].softirq; + int cpus_nr = bitmap_weight(stat->all_cpus_bitmap, MAX_NR_CPUS); + u64 cpus_total_time = stat->cpus_runtime[MAX_NR_CPUS].total; + + printf("Total : %*.*f ms, %d cpus\n", + PRINT_RUNTIME_WIDTH, RPINT_DECIMAL_WIDTH, + (double)cpus_total_time / NSEC_PER_MSEC, + cpus_nr); + + printf("%%Cpu(s): %*.*f%% id, %*.*f%% hi, %*.*f%% si\n", + PRINT_CPU_USAGE_WIDTH, PRINT_CPU_USAGE_DECIMAL_WIDTH, + cpus_total_time ? (double)idle_time * 100 / cpus_total_time : 0, + + PRINT_CPU_USAGE_WIDTH, PRINT_CPU_USAGE_DECIMAL_WIDTH, + cpus_total_time ? (double)hardirq_time * 100 / cpus_total_time : 0, + + PRINT_CPU_USAGE_WIDTH, PRINT_CPU_USAGE_DECIMAL_WIDTH, + cpus_total_time ? (double)softirq_time * 100 / cpus_total_time : 0); + + top_print_per_cpu_load(kwork); +} + +static void top_print_header(struct perf_kwork *kwork __maybe_unused) +{ + int ret; + + printf("\n "); + ret = printf(" %*s %s%*s%s %*s %*s %-*s", + PRINT_PID_WIDTH, "PID", + + kwork->use_bpf ? " " : "", + kwork->use_bpf ? PRINT_PID_WIDTH : 0, + kwork->use_bpf ? "SPID" : "", + kwork->use_bpf ? " " : "", + + PRINT_CPU_USAGE_WIDTH, "%CPU", + PRINT_RUNTIME_HEADER_WIDTH + RPINT_DECIMAL_WIDTH, "RUNTIME", + PRINT_TASK_NAME_WIDTH, "COMMAND"); + printf("\n "); + print_separator(ret); +} + +static int top_print_work(struct perf_kwork *kwork __maybe_unused, struct kwork_work *work) +{ + int ret = 0; + + printf(" "); + + /* + * pid + */ + ret += printf(" %*ld ", PRINT_PID_WIDTH, work->id); + + /* + * tgid + */ + if (kwork->use_bpf) + ret += printf(" %*d ", PRINT_PID_WIDTH, work->tgid); + + /* + * cpu usage + */ + ret += printf(" %*.*f ", + PRINT_CPU_USAGE_WIDTH, PRINT_CPU_USAGE_DECIMAL_WIDTH, + (double)work->cpu_usage / 100); + + /* + * total runtime + */ + ret += printf(" %*.*f ms ", + PRINT_RUNTIME_WIDTH + RPINT_DECIMAL_WIDTH, RPINT_DECIMAL_WIDTH, + (double)work->total_runtime / NSEC_PER_MSEC); + + /* + * command + */ + if (kwork->use_bpf) + ret += printf(" %s%s%s", + work->is_kthread ? "[" : "", + work->name, + work->is_kthread ? "]" : ""); + else + ret += printf(" %-*s", PRINT_TASK_NAME_WIDTH, work->name); + + printf("\n"); + return ret; +} + +static void work_sort(struct perf_kwork *kwork, + struct kwork_class *class, struct rb_root_cached *root) { struct rb_node *node; struct kwork_work *data; - struct rb_root_cached *root = &class->work_root; pr_debug("Sorting %s ...\n", class->name); for (;;) { @@ -1315,7 +1704,7 @@ static void perf_kwork__sort(struct perf_kwork *kwork) struct kwork_class *class; list_for_each_entry(class, &kwork->class_list, list) - work_sort(kwork, class); + work_sort(kwork, class, &class->work_root); } static int perf_kwork__check_config(struct perf_kwork *kwork, @@ -1338,6 +1727,11 @@ static int perf_kwork__check_config(struct perf_kwork *kwork, .entry_event = timehist_entry_event, .exit_event = timehist_exit_event, }; + static struct trace_kwork_handler top_ops = { + .entry_event = timehist_entry_event, + .exit_event = top_exit_event, + .sched_switch_event = top_sched_switch_event, + }; switch (kwork->report) { case KWORK_REPORT_RUNTIME: @@ -1349,6 +1743,9 @@ static int perf_kwork__check_config(struct perf_kwork *kwork, case KWORK_REPORT_TIMEHIST: kwork->tp_handler = &timehist_ops; break; + case KWORK_REPORT_TOP: + kwork->tp_handler = &top_ops; + break; default: pr_debug("Invalid report type %d\n", kwork->report); return -1; @@ -1469,7 +1866,7 @@ static void sig_handler(int sig) * Simply capture termination signal so that * the program can continue after pause returns */ - pr_debug("Captuer signal %d\n", sig); + pr_debug("Capture signal %d\n", sig); } static int perf_kwork__report_bpf(struct perf_kwork *kwork) @@ -1595,6 +1992,248 @@ static int perf_kwork__timehist(struct perf_kwork *kwork) return perf_kwork__read_events(kwork); } +static void top_calc_total_runtime(struct perf_kwork *kwork) +{ + struct kwork_class *class; + struct kwork_work *work; + struct rb_node *next; + struct kwork_top_stat *stat = &kwork->top_stat; + + class = get_kwork_class(kwork, KWORK_CLASS_SCHED); + if (!class) + return; + + next = rb_first_cached(&class->work_root); + while (next) { + work = rb_entry(next, struct kwork_work, node); + BUG_ON(work->cpu >= MAX_NR_CPUS); + stat->cpus_runtime[work->cpu].total += work->total_runtime; + stat->cpus_runtime[MAX_NR_CPUS].total += work->total_runtime; + next = rb_next(next); + } +} + +static void top_calc_idle_time(struct perf_kwork *kwork, + struct kwork_work *work) +{ + struct kwork_top_stat *stat = &kwork->top_stat; + + if (work->id == 0) { + stat->cpus_runtime[work->cpu].idle += work->total_runtime; + stat->cpus_runtime[MAX_NR_CPUS].idle += work->total_runtime; + } +} + +static void top_calc_irq_runtime(struct perf_kwork *kwork, + enum kwork_class_type type, + struct kwork_work *work) +{ + struct kwork_top_stat *stat = &kwork->top_stat; + + if (type == KWORK_CLASS_IRQ) { + stat->cpus_runtime[work->cpu].irq += work->total_runtime; + stat->cpus_runtime[MAX_NR_CPUS].irq += work->total_runtime; + } else if (type == KWORK_CLASS_SOFTIRQ) { + stat->cpus_runtime[work->cpu].softirq += work->total_runtime; + stat->cpus_runtime[MAX_NR_CPUS].softirq += work->total_runtime; + } +} + +static void top_subtract_irq_runtime(struct perf_kwork *kwork, + struct kwork_work *work) +{ + struct kwork_class *class; + struct kwork_work *data; + unsigned int i; + int irq_class_list[] = {KWORK_CLASS_IRQ, KWORK_CLASS_SOFTIRQ}; + + for (i = 0; i < ARRAY_SIZE(irq_class_list); i++) { + class = get_kwork_class(kwork, irq_class_list[i]); + if (!class) + continue; + + data = find_work_by_id(&class->work_root, + work->id, work->cpu); + if (!data) + continue; + + if (work->total_runtime > data->total_runtime) { + work->total_runtime -= data->total_runtime; + top_calc_irq_runtime(kwork, irq_class_list[i], data); + } + } +} + +static void top_calc_cpu_usage(struct perf_kwork *kwork) +{ + struct kwork_class *class; + struct kwork_work *work; + struct rb_node *next; + struct kwork_top_stat *stat = &kwork->top_stat; + + class = get_kwork_class(kwork, KWORK_CLASS_SCHED); + if (!class) + return; + + next = rb_first_cached(&class->work_root); + while (next) { + work = rb_entry(next, struct kwork_work, node); + + if (work->total_runtime == 0) + goto next; + + __set_bit(work->cpu, stat->all_cpus_bitmap); + + top_subtract_irq_runtime(kwork, work); + + work->cpu_usage = work->total_runtime * 10000 / + stat->cpus_runtime[work->cpu].total; + + top_calc_idle_time(kwork, work); +next: + next = rb_next(next); + } +} + +static void top_calc_load_runtime(struct perf_kwork *kwork, + struct kwork_work *work) +{ + struct kwork_top_stat *stat = &kwork->top_stat; + + if (work->id != 0) { + stat->cpus_runtime[work->cpu].load += work->total_runtime; + stat->cpus_runtime[MAX_NR_CPUS].load += work->total_runtime; + } +} + +static void top_merge_tasks(struct perf_kwork *kwork) +{ + struct kwork_work *merged_work, *data; + struct kwork_class *class; + struct rb_node *node; + int cpu; + struct rb_root_cached merged_root = RB_ROOT_CACHED; + + class = get_kwork_class(kwork, KWORK_CLASS_SCHED); + if (!class) + return; + + for (;;) { + node = rb_first_cached(&class->work_root); + if (!node) + break; + + rb_erase_cached(node, &class->work_root); + data = rb_entry(node, struct kwork_work, node); + + if (!profile_name_match(kwork, data)) + continue; + + cpu = data->cpu; + merged_work = find_work_by_id(&merged_root, data->id, + data->id == 0 ? cpu : -1); + if (!merged_work) { + work_insert(&merged_root, data, &kwork->cmp_id); + } else { + merged_work->total_runtime += data->total_runtime; + merged_work->cpu_usage += data->cpu_usage; + } + + top_calc_load_runtime(kwork, data); + } + + work_sort(kwork, class, &merged_root); +} + +static void perf_kwork__top_report(struct perf_kwork *kwork) +{ + struct kwork_work *work; + struct rb_node *next; + + printf("\n"); + + top_print_cpu_usage(kwork); + top_print_header(kwork); + next = rb_first_cached(&kwork->sorted_work_root); + while (next) { + work = rb_entry(next, struct kwork_work, node); + process_skipped_events(kwork, work); + + if (work->total_runtime == 0) + goto next; + + top_print_work(kwork, work); + +next: + next = rb_next(next); + } + + printf("\n"); +} + +static int perf_kwork__top_bpf(struct perf_kwork *kwork) +{ + int ret; + + signal(SIGINT, sig_handler); + signal(SIGTERM, sig_handler); + + ret = perf_kwork__top_prepare_bpf(kwork); + if (ret) + return -1; + + printf("Starting trace, Hit <Ctrl+C> to stop and report\n"); + + perf_kwork__top_start(); + + /* + * a simple pause, wait here for stop signal + */ + pause(); + + perf_kwork__top_finish(); + + perf_kwork__top_read_bpf(kwork); + + perf_kwork__top_cleanup_bpf(); + + return 0; + +} + +static int perf_kwork__top(struct perf_kwork *kwork) +{ + struct __top_cpus_runtime *cpus_runtime; + int ret = 0; + + cpus_runtime = zalloc(sizeof(struct __top_cpus_runtime) * (MAX_NR_CPUS + 1)); + if (!cpus_runtime) + return -1; + + kwork->top_stat.cpus_runtime = cpus_runtime; + bitmap_zero(kwork->top_stat.all_cpus_bitmap, MAX_NR_CPUS); + + if (kwork->use_bpf) + ret = perf_kwork__top_bpf(kwork); + else + ret = perf_kwork__read_events(kwork); + + if (ret) + goto out; + + top_calc_total_runtime(kwork); + top_calc_cpu_usage(kwork); + top_merge_tasks(kwork); + + setup_pager(); + + perf_kwork__top_report(kwork); + +out: + free(kwork->top_stat.cpus_runtime); + return ret; +} + static void setup_event_list(struct perf_kwork *kwork, const struct option *options, const char * const usage_msg[]) @@ -1603,8 +2242,11 @@ static void setup_event_list(struct perf_kwork *kwork, struct kwork_class *class; char *tmp, *tok, *str; + /* + * set default events list if not specified + */ if (kwork->event_list_str == NULL) - goto null_event_list_str; + kwork->event_list_str = "irq, softirq, workqueue"; str = strdup(kwork->event_list_str); for (tok = strtok_r(str, ", ", &tmp); @@ -1623,17 +2265,6 @@ static void setup_event_list(struct perf_kwork *kwork, } free(str); -null_event_list_str: - /* - * config all kwork events if not specified - */ - if (list_empty(&kwork->class_list)) { - for (i = 0; i < KWORK_CLASS_MAX; i++) { - list_add_tail(&kwork_class_supported_list[i]->list, - &kwork->class_list); - } - } - pr_debug("Config event list:"); list_for_each_entry(class, &kwork->class_list, list) pr_debug(" %s", class->name); @@ -1692,9 +2323,10 @@ int cmd_kwork(int argc, const char **argv) static struct perf_kwork kwork = { .class_list = LIST_HEAD_INIT(kwork.class_list), .tool = { - .mmap = perf_event__process_mmap, - .mmap2 = perf_event__process_mmap2, - .sample = perf_kwork__process_tracepoint_sample, + .mmap = perf_event__process_mmap, + .mmap2 = perf_event__process_mmap2, + .sample = perf_kwork__process_tracepoint_sample, + .ordered_events = true, }, .atom_page_list = LIST_HEAD_INIT(kwork.atom_page_list), .sort_list = LIST_HEAD_INIT(kwork.sort_list), @@ -1721,13 +2353,14 @@ int cmd_kwork(int argc, const char **argv) }; static const char default_report_sort_order[] = "runtime, max, count"; static const char default_latency_sort_order[] = "avg, max, count"; + static const char default_top_sort_order[] = "rate, runtime"; const struct option kwork_options[] = { OPT_INCR('v', "verbose", &verbose, "be more verbose (show symbol address, etc)"), OPT_BOOLEAN('D', "dump-raw-trace", &dump_trace, "dump raw trace in ASCII"), OPT_STRING('k', "kwork", &kwork.event_list_str, "kwork", - "list of kwork to profile (irq, softirq, workqueue, etc)"), + "list of kwork to profile (irq, softirq, workqueue, sched, etc)"), OPT_BOOLEAN('f', "force", &kwork.force, "don't complain, do it"), OPT_END() }; @@ -1788,6 +2421,23 @@ int cmd_kwork(int argc, const char **argv) "input file name"), OPT_PARENT(kwork_options) }; + const struct option top_options[] = { + OPT_STRING('s', "sort", &kwork.sort_order, "key[,key2...]", + "sort by key(s): rate, runtime, tid"), + OPT_STRING('C', "cpu", &kwork.cpu_list, "cpu", + "list of cpus to profile"), + OPT_STRING('n', "name", &kwork.profile_name, "name", + "event name to profile"), + OPT_STRING(0, "time", &kwork.time_str, "str", + "Time span for analysis (start,stop)"), + OPT_STRING('i', "input", &input_name, "file", + "input file name"), +#ifdef HAVE_BPF_SKEL + OPT_BOOLEAN('b', "use-bpf", &kwork.use_bpf, + "Use BPF to measure task cpu usage"), +#endif + OPT_PARENT(kwork_options) + }; const char *kwork_usage[] = { NULL, NULL @@ -1804,8 +2454,12 @@ int cmd_kwork(int argc, const char **argv) "perf kwork timehist [<options>]", NULL }; + const char * const top_usage[] = { + "perf kwork top [<options>]", + NULL + }; const char *const kwork_subcommands[] = { - "record", "report", "latency", "timehist", NULL + "record", "report", "latency", "timehist", "top", NULL }; argc = parse_options_subcommand(argc, argv, kwork_options, @@ -1814,12 +2468,12 @@ int cmd_kwork(int argc, const char **argv) if (!argc) usage_with_options(kwork_usage, kwork_options); - setup_event_list(&kwork, kwork_options, kwork_usage); sort_dimension__add(&kwork, "id", &kwork.cmp_id); - if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) + if (strlen(argv[0]) > 2 && strstarts("record", argv[0])) { + setup_event_list(&kwork, kwork_options, kwork_usage); return perf_kwork__record(&kwork, argc, argv); - else if (strlen(argv[0]) > 2 && strstarts("report", argv[0])) { + } else if (strlen(argv[0]) > 2 && strstarts("report", argv[0])) { kwork.sort_order = default_report_sort_order; if (argc > 1) { argc = parse_options(argc, argv, report_options, report_usage, 0); @@ -1828,6 +2482,7 @@ int cmd_kwork(int argc, const char **argv) } kwork.report = KWORK_REPORT_RUNTIME; setup_sorting(&kwork, report_options, report_usage); + setup_event_list(&kwork, kwork_options, kwork_usage); return perf_kwork__report(&kwork); } else if (strlen(argv[0]) > 2 && strstarts("latency", argv[0])) { kwork.sort_order = default_latency_sort_order; @@ -1838,6 +2493,7 @@ int cmd_kwork(int argc, const char **argv) } kwork.report = KWORK_REPORT_LATENCY; setup_sorting(&kwork, latency_options, latency_usage); + setup_event_list(&kwork, kwork_options, kwork_usage); return perf_kwork__report(&kwork); } else if (strlen(argv[0]) > 2 && strstarts("timehist", argv[0])) { if (argc > 1) { @@ -1846,7 +2502,21 @@ int cmd_kwork(int argc, const char **argv) usage_with_options(timehist_usage, timehist_options); } kwork.report = KWORK_REPORT_TIMEHIST; + setup_event_list(&kwork, kwork_options, kwork_usage); return perf_kwork__timehist(&kwork); + } else if (strlen(argv[0]) > 2 && strstarts("top", argv[0])) { + kwork.sort_order = default_top_sort_order; + if (argc > 1) { + argc = parse_options(argc, argv, top_options, top_usage, 0); + if (argc) + usage_with_options(top_usage, top_options); + } + kwork.report = KWORK_REPORT_TOP; + if (!kwork.event_list_str) + kwork.event_list_str = "sched, irq, softirq"; + setup_event_list(&kwork, kwork_options, kwork_usage); + setup_sorting(&kwork, top_options, top_usage); + return perf_kwork__top(&kwork); } else usage_with_options(kwork_usage, kwork_options); diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c index b141f2134274..a3ff2f4edbaa 100644 --- a/tools/perf/builtin-lock.c +++ b/tools/perf/builtin-lock.c @@ -10,6 +10,7 @@ #include "util/thread.h" #include "util/header.h" #include "util/target.h" +#include "util/cgroup.h" #include "util/callchain.h" #include "util/lock-contention.h" #include "util/bpf_skel/lock_data.h" @@ -60,6 +61,7 @@ static bool combine_locks; static bool show_thread_stats; static bool show_lock_addrs; static bool show_lock_owner; +static bool show_lock_cgroups; static bool use_bpf; static unsigned long bpf_map_entries = MAX_ENTRIES; static int max_stack_depth = CONTENTION_STACK_DEPTH; @@ -524,6 +526,7 @@ bool match_callstack_filter(struct machine *machine, u64 *callstack) struct map *kmap; struct symbol *sym; u64 ip; + const char *arch = perf_env__arch(machine->env); if (list_empty(&callstack_filters)) return true; @@ -531,7 +534,21 @@ bool match_callstack_filter(struct machine *machine, u64 *callstack) for (int i = 0; i < max_stack_depth; i++) { struct callstack_filter *filter; - if (!callstack || !callstack[i]) + /* + * In powerpc, the callchain saved by kernel always includes + * first three entries as the NIP (next instruction pointer), + * LR (link register), and the contents of LR save area in the + * second stack frame. In certain scenarios its possible to have + * invalid kernel instruction addresses in either LR or the second + * stack frame's LR. In that case, kernel will store that address as + * zero. + * + * The below check will continue to look into callstack, + * incase first or second callstack index entry has 0 + * address for powerpc. + */ + if (!callstack || (!callstack[i] && (strcmp(arch, "powerpc") || + (i != 1 && i != 2)))) break; ip = callstack[i]; @@ -619,6 +636,7 @@ static int get_key_by_aggr_mode_simple(u64 *key, u64 addr, u32 tid) *key = tid; break; case LOCK_AGGR_CALLER: + case LOCK_AGGR_CGROUP: default: pr_err("Invalid aggregation mode: %d\n", aggr_mode); return -EINVAL; @@ -1103,6 +1121,7 @@ static int report_lock_contention_begin_event(struct evsel *evsel, if (lock_contention_caller(evsel, sample, buf, sizeof(buf)) < 0) name = "Unknown"; break; + case LOCK_AGGR_CGROUP: case LOCK_AGGR_TASK: default: break; @@ -1628,6 +1647,9 @@ static void lock_filter_finish(void) zfree(&filters.syms); filters.nr_syms = 0; + + zfree(&filters.cgrps); + filters.nr_cgrps = 0; } static void sort_contention_result(void) @@ -1653,6 +1675,9 @@ static void print_header_stdio(void) case LOCK_AGGR_ADDR: fprintf(lock_output, " %16s %s\n\n", "address", "symbol"); break; + case LOCK_AGGR_CGROUP: + fprintf(lock_output, " %s\n\n", "cgroup"); + break; default: break; } @@ -1680,6 +1705,9 @@ static void print_header_csv(const char *sep) case LOCK_AGGR_ADDR: fprintf(lock_output, "%s%s %s%s %s\n", "address", sep, "symbol", sep, "type"); break; + case LOCK_AGGR_CGROUP: + fprintf(lock_output, "%s\n", "cgroup"); + break; default: break; } @@ -1720,6 +1748,9 @@ static void print_lock_stat_stdio(struct lock_contention *con, struct lock_stat fprintf(lock_output, " %016llx %s (%s)\n", (unsigned long long)st->addr, st->name, get_type_name(st->flags)); break; + case LOCK_AGGR_CGROUP: + fprintf(lock_output, " %s\n", st->name); + break; default: break; } @@ -1770,6 +1801,9 @@ static void print_lock_stat_csv(struct lock_contention *con, struct lock_stat *s fprintf(lock_output, "%llx%s %s%s %s\n", (unsigned long long)st->addr, sep, st->name, sep, get_type_name(st->flags)); break; + case LOCK_AGGR_CGROUP: + fprintf(lock_output, "%s\n",st->name); + break; default: break; } @@ -1999,6 +2033,27 @@ static int check_lock_contention_options(const struct option *options, return -1; } + if (show_lock_cgroups && !use_bpf) { + pr_err("Cgroups are available only with BPF\n"); + parse_options_usage(usage, options, "lock-cgroup", 0); + parse_options_usage(NULL, options, "use-bpf", 0); + return -1; + } + + if (show_lock_cgroups && show_lock_addrs) { + pr_err("Cannot use cgroup and addr mode together\n"); + parse_options_usage(usage, options, "lock-cgroup", 0); + parse_options_usage(NULL, options, "lock-addr", 0); + return -1; + } + + if (show_lock_cgroups && show_thread_stats) { + pr_err("Cannot use cgroup and thread mode together\n"); + parse_options_usage(usage, options, "lock-cgroup", 0); + parse_options_usage(NULL, options, "threads", 0); + return -1; + } + if (symbol_conf.field_sep) { if (strstr(symbol_conf.field_sep, ":") || /* part of type flags */ strstr(symbol_conf.field_sep, "+") || /* part of caller offset */ @@ -2040,6 +2095,7 @@ static int __cmd_contention(int argc, const char **argv) .filters = &filters, .save_callstack = needs_callstack(), .owner = show_lock_owner, + .cgroups = RB_ROOT, }; lockhash_table = calloc(LOCKHASH_SIZE, sizeof(*lockhash_table)); @@ -2059,7 +2115,8 @@ static int __cmd_contention(int argc, const char **argv) con.machine = &session->machines.host; con.aggr_mode = aggr_mode = show_thread_stats ? LOCK_AGGR_TASK : - show_lock_addrs ? LOCK_AGGR_ADDR : LOCK_AGGR_CALLER; + show_lock_addrs ? LOCK_AGGR_ADDR : + show_lock_cgroups ? LOCK_AGGR_CGROUP : LOCK_AGGR_CALLER; if (con.aggr_mode == LOCK_AGGR_CALLER) con.save_callstack = true; @@ -2158,7 +2215,7 @@ static int __cmd_contention(int argc, const char **argv) out_delete: lock_filter_finish(); evlist__delete(con.evlist); - lock_contention_finish(); + lock_contention_finish(&con); perf_session__delete(session); zfree(&lockhash_table); return err; @@ -2421,6 +2478,7 @@ static int parse_call_stack(const struct option *opt __maybe_unused, const char entry = malloc(sizeof(*entry) + strlen(tok) + 1); if (entry == NULL) { pr_err("Memory allocation failure\n"); + free(s); return -1; } @@ -2450,6 +2508,56 @@ static int parse_output(const struct option *opt __maybe_unused, const char *str return 0; } +static bool add_lock_cgroup(char *name) +{ + u64 *tmp; + struct cgroup *cgrp; + + cgrp = cgroup__new(name, /*do_open=*/false); + if (cgrp == NULL) { + pr_err("Failed to create cgroup: %s\n", name); + return false; + } + + if (read_cgroup_id(cgrp) < 0) { + pr_err("Failed to read cgroup id for %s\n", name); + cgroup__put(cgrp); + return false; + } + + tmp = realloc(filters.cgrps, (filters.nr_cgrps + 1) * sizeof(*filters.cgrps)); + if (tmp == NULL) { + pr_err("Memory allocation failure\n"); + return false; + } + + tmp[filters.nr_cgrps++] = cgrp->id; + filters.cgrps = tmp; + cgroup__put(cgrp); + return true; +} + +static int parse_cgroup_filter(const struct option *opt __maybe_unused, const char *str, + int unset __maybe_unused) +{ + char *s, *tmp, *tok; + int ret = 0; + + s = strdup(str); + if (s == NULL) + return -1; + + for (tok = strtok_r(s, ", ", &tmp); tok; tok = strtok_r(NULL, ", ", &tmp)) { + if (!add_lock_cgroup(tok)) { + ret = -1; + break; + } + } + + free(s); + return ret; +} + int cmd_lock(int argc, const char **argv) { const struct option lock_options[] = { @@ -2523,6 +2631,9 @@ int cmd_lock(int argc, const char **argv) OPT_BOOLEAN('o', "lock-owner", &show_lock_owner, "show lock owners instead of waiters"), OPT_STRING_NOEMPTY('x', "field-separator", &symbol_conf.field_sep, "separator", "print result in CSV format with custom separator"), + OPT_BOOLEAN(0, "lock-cgroup", &show_lock_cgroups, "show lock stats by cgroup"), + OPT_CALLBACK('G', "cgroup-filter", NULL, "CGROUPS", + "Filter specific cgroups", parse_cgroup_filter), OPT_PARENT(lock_options) }; diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 34bb31f08bb5..dcf288a4fb9a 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -906,6 +906,65 @@ static int record__config_off_cpu(struct record *rec) return off_cpu_prepare(rec->evlist, &rec->opts.target, &rec->opts); } +static bool record__tracking_system_wide(struct record *rec) +{ + struct evlist *evlist = rec->evlist; + struct evsel *evsel; + + /* + * If non-dummy evsel exists, system_wide sideband is need to + * help parse sample information. + * For example, PERF_EVENT_MMAP event to help parse symbol, + * and PERF_EVENT_COMM event to help parse task executable name. + */ + evlist__for_each_entry(evlist, evsel) { + if (!evsel__is_dummy_event(evsel)) + return true; + } + + return false; +} + +static int record__config_tracking_events(struct record *rec) +{ + struct record_opts *opts = &rec->opts; + struct evlist *evlist = rec->evlist; + bool system_wide = false; + struct evsel *evsel; + + /* + * For initial_delay, system wide or a hybrid system, we need to add + * tracking event so that we can track PERF_RECORD_MMAP to cover the + * delay of waiting or event synthesis. + */ + if (opts->target.initial_delay || target__has_cpu(&opts->target) || + perf_pmus__num_core_pmus() > 1) { + + /* + * User space tasks can migrate between CPUs, so when tracing + * selected CPUs, sideband for all CPUs is still needed. + */ + if (!!opts->target.cpu_list && record__tracking_system_wide(rec)) + system_wide = true; + + evsel = evlist__findnew_tracking_event(evlist, system_wide); + if (!evsel) + return -ENOMEM; + + /* + * Enable the tracking event when the process is forked for + * initial_delay, immediately for system wide. + */ + if (opts->target.initial_delay && !evsel->immediate && + !target__has_cpu(&opts->target)) + evsel->core.attr.enable_on_exec = 1; + else + evsel->immediate = 1; + } + + return 0; +} + static bool record__kcore_readable(struct machine *machine) { char kcore[PATH_MAX]; @@ -1286,33 +1345,6 @@ static int record__open(struct record *rec) struct record_opts *opts = &rec->opts; int rc = 0; - /* - * For initial_delay, system wide or a hybrid system, we need to add a - * dummy event so that we can track PERF_RECORD_MMAP to cover the delay - * of waiting or event synthesis. - */ - if (opts->target.initial_delay || target__has_cpu(&opts->target) || - perf_pmus__num_core_pmus() > 1) { - pos = evlist__get_tracking_event(evlist); - if (!evsel__is_dummy_event(pos)) { - /* Set up dummy event. */ - if (evlist__add_dummy(evlist)) - return -ENOMEM; - pos = evlist__last(evlist); - evlist__set_tracking_event(evlist, pos); - } - - /* - * Enable the dummy event when the process is forked for - * initial_delay, immediately for system wide. - */ - if (opts->target.initial_delay && !pos->immediate && - !target__has_cpu(&opts->target)) - pos->core.attr.enable_on_exec = 1; - else - pos->immediate = 1; - } - evlist__config(evlist, opts, &callchain_param); evlist__for_each_entry(evlist, pos) { @@ -4195,6 +4227,12 @@ int cmd_record(int argc, const char **argv) goto out; } + err = record__config_tracking_events(rec); + if (err) { + pr_err("record__config_tracking_events failed, error %d\n", err); + goto out; + } + err = record__init_thread_masks(rec); if (err) { pr_err("Failed to initialize parallel data streaming masks\n"); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index dcedfe00f04d..9cb1da2dc0c0 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -691,10 +691,25 @@ static int report__browse_hists(struct report *rep) static int report__collapse_hists(struct report *rep) { + struct perf_session *session = rep->session; + struct evlist *evlist = session->evlist; struct ui_progress prog; struct evsel *pos; int ret = 0; + /* + * The pipe data needs to setup hierarchy hpp formats now, because it + * cannot know about evsels in the data before reading the data. The + * normal file data saves the event (attribute) info in the header + * section, but pipe does not have the luxury. + */ + if (perf_data__is_pipe(session->data)) { + if (perf_hpp__setup_hists_formats(&perf_hpp_list, evlist) < 0) { + ui__error("Failed to setup hierarchy output formats\n"); + return -1; + } + } + ui_progress__init(&prog, rep->nr_entries, "Merging related events..."); evlist__for_each_entry(rep->session->evlist, pos) { diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c index 9ab300b6f131..dd6065afbbaf 100644 --- a/tools/perf/builtin-sched.c +++ b/tools/perf/builtin-sched.c @@ -1385,7 +1385,7 @@ static int pid_cmp(struct work_atoms *l, struct work_atoms *r) { pid_t l_tid, r_tid; - if (RC_CHK_ACCESS(l->thread) == RC_CHK_ACCESS(r->thread)) + if (RC_CHK_EQUAL(l->thread, r->thread)) return 0; l_tid = thread__tid(l->thread); r_tid = thread__tid(r->thread); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 517bf25750c8..b1f57401ff23 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3899,7 +3899,7 @@ int cmd_script(int argc, const char **argv) "comma separated output fields prepend with 'type:'. " "+field to add and -field to remove." "Valid types: hw,sw,trace,raw,synth. " - "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,dsoff" + "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,dsoff," "addr,symoff,srcline,period,iregs,uregs,brstack," "brstacksym,flags,data_src,weight,bpf-output,brstackinsn," "brstackinsnlen,brstackoff,callindent,insn,insnlen,synth," diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 07b48f6df48e..a3af805a1d57 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -1622,7 +1622,7 @@ static int perf_stat_init_aggr_mode(void) * taking the highest cpu number to be the size of * the aggregation translate cpumap. */ - if (evsel_list->core.user_requested_cpus) + if (!perf_cpu_map__empty(evsel_list->core.user_requested_cpus)) nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu; else nr = 0; diff --git a/tools/perf/builtin-version.c b/tools/perf/builtin-version.c index e5859c70e195..ac20c2b9bbc2 100644 --- a/tools/perf/builtin-version.c +++ b/tools/perf/builtin-version.c @@ -81,6 +81,7 @@ static void library_status(void) STATUS(HAVE_ZSTD_SUPPORT, zstd); STATUS(HAVE_LIBPFM, libpfm4); STATUS(HAVE_LIBTRACEEVENT, libtraceevent); + STATUS(HAVE_BPF_SKEL, bpf_skeletons); } int cmd_version(int argc, const char **argv) diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh index e21caadda7c1..66ba33dbcef2 100755 --- a/tools/perf/check-headers.sh +++ b/tools/perf/check-headers.sh @@ -162,6 +162,7 @@ check arch/x86/lib/memcpy_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/ex check arch/x86/lib/memset_64.S '-I "^EXPORT_SYMBOL" -I "^#include <asm/export.h>" -I"^SYM_FUNC_START\(_LOCAL\)*(memset_\(erms\|orig\))"' check arch/x86/include/asm/amd-ibs.h '-I "^#include [<\"]\(asm/\)*msr-index.h"' check arch/arm64/include/asm/cputype.h '-I "^#include [<\"]\(asm/\)*sysreg.h"' +check include/asm-generic/unaligned.h '-I "^#include <linux/unaligned/packed_struct.h>" -I "^#include <asm/byteorder.h>" -I "^#pragma GCC diagnostic"' check include/uapi/asm-generic/mman.h '-I "^#include <\(uapi/\)*asm-generic/mman-common\(-tools\)*.h>"' check include/uapi/linux/mman.h '-I "^#include <\(uapi/\)*asm/mman.h>"' check include/linux/build_bug.h '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"' diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh index 978249d7868c..f224d79b89e6 100644 --- a/tools/perf/perf-completion.sh +++ b/tools/perf/perf-completion.sh @@ -164,7 +164,7 @@ __perf_main () $prev_skip_opts == @(record|stat|top) ]]; then local cur1=${COMP_WORDS[COMP_CWORD]} - local raw_evts=$($cmd list --raw-dump) + local raw_evts=$($cmd list --raw-dump hw sw cache tracepoint pmu sdt) local arr s tmp result cpu_evts # aarch64 doesn't have /sys/bus/event_source/devices/cpu/events @@ -198,6 +198,14 @@ __perf_main () else __perfcomp_colon "$evts" "$cur1" fi + elif [[ $prev == @("--pfm-events") && + $prev_skip_opts == @(record|stat|top) ]]; then + local evts=$($cmd list --raw-dump pfm) + __perfcomp "$evts" "$cur" + elif [[ $prev == @("-M"|"--metrics") && + $prev_skip_opts == @(stat) ]]; then + local metrics=$($cmd list --raw-dump metric metricgroup) + __perfcomp "$metrics" "$cur" else # List subcommands for perf commands if [[ $prev_skip_opts == @(kvm|kmem|mem|lock|sched| diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json index 1e7e8901a445..e2848a9d4848 100644 --- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json +++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/metrics.json @@ -1,362 +1,384 @@ [ { + "MetricName": "branch_miss_pred_rate", "MetricExpr": "BR_MIS_PRED / BR_PRED", "BriefDescription": "Branch predictor misprediction rate. May not count branches that are never resolved because they are in the misprediction shadow of an earlier branch", - "MetricGroup": "Branch Prediction", - "MetricName": "Misprediction" + "MetricGroup": "branch", + "ScaleUnit": "100%" }, { - "MetricExpr": "BR_MIS_PRED_RETIRED / BR_RETIRED", - "BriefDescription": "Branch predictor misprediction rate", - "MetricGroup": "Branch Prediction", - "MetricName": "Misprediction (retired)" - }, - { - "MetricExpr": "BUS_ACCESS / ( BUS_CYCLES * 1)", + "MetricName": "bus_utilization", + "MetricExpr": "((BUS_ACCESS / (BUS_CYCLES * 1)) * 100)", "BriefDescription": "Core-to-uncore bus utilization", "MetricGroup": "Bus", - "MetricName": "Bus utilization" + "ScaleUnit": "1percent of bus cycles" }, { - "MetricExpr": "L1D_CACHE_REFILL / L1D_CACHE", - "BriefDescription": "L1D cache miss rate", - "MetricGroup": "Cache", - "MetricName": "L1D cache miss" + "MetricName": "l1d_cache_miss_ratio", + "MetricExpr": "(L1D_CACHE_REFILL / L1D_CACHE)", + "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.", + "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "l1i_cache_miss_ratio", + "MetricExpr": "(L1I_CACHE_REFILL / L1I_CACHE)", + "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.", + "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness", + "ScaleUnit": "1per cache access" }, { + "MetricName": "Miss_Ratio;l1d_cache_read_miss", "MetricExpr": "L1D_CACHE_LMISS_RD / L1D_CACHE_RD", "BriefDescription": "L1D cache read miss rate", "MetricGroup": "Cache", - "MetricName": "L1D cache read miss" + "ScaleUnit": "1per cache read access" }, { - "MetricExpr": "L1I_CACHE_REFILL / L1I_CACHE", - "BriefDescription": "L1I cache miss rate", - "MetricGroup": "Cache", - "MetricName": "L1I cache miss" - }, - { - "MetricExpr": "L2D_CACHE_REFILL / L2D_CACHE", - "BriefDescription": "L2 cache miss rate", - "MetricGroup": "Cache", - "MetricName": "L2 cache miss" + "MetricName": "l2_cache_miss_ratio", + "MetricExpr": "(L2D_CACHE_REFILL / L2D_CACHE)", + "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness", + "ScaleUnit": "1per cache access" }, { + "MetricName": "l1i_cache_read_miss_rate", "MetricExpr": "L1I_CACHE_LMISS / L1I_CACHE", "BriefDescription": "L1I cache read miss rate", "MetricGroup": "Cache", - "MetricName": "L1I cache read miss" + "ScaleUnit": "1per cache access" }, { + "MetricName": "l2d_cache_read_miss_rate", "MetricExpr": "L2D_CACHE_LMISS_RD / L2D_CACHE_RD", "BriefDescription": "L2 cache read miss rate", "MetricGroup": "Cache", - "MetricName": "L2 cache read miss" + "ScaleUnit": "1per cache read access" }, { - "MetricExpr": "(L1D_CACHE_LMISS_RD * 1000) / INST_RETIRED", + "MetricName": "l1d_cache_miss_mpki", + "MetricExpr": "(L1D_CACHE_LMISS_RD * 1e3) / INST_RETIRED", "BriefDescription": "Misses per thousand instructions (data)", "MetricGroup": "Cache", - "MetricName": "MPKI data" + "ScaleUnit": "1MPKI" }, { - "MetricExpr": "(L1I_CACHE_LMISS * 1000) / INST_RETIRED", + "MetricName": "l1i_cache_miss_mpki", + "MetricExpr": "(L1I_CACHE_LMISS * 1e3) / INST_RETIRED", "BriefDescription": "Misses per thousand instructions (instruction)", "MetricGroup": "Cache", - "MetricName": "MPKI instruction" + "ScaleUnit": "1MPKI" }, { - "MetricExpr": "ASE_SPEC / OP_SPEC", - "BriefDescription": "Proportion of advanced SIMD data processing operations (excluding DP_SPEC/LD_SPEC) operations", - "MetricGroup": "Instruction", - "MetricName": "ASE mix" + "MetricName": "simd_percentage", + "MetricExpr": "((ASE_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "CRYPTO_SPEC / OP_SPEC", - "BriefDescription": "Proportion of crypto data processing operations", - "MetricGroup": "Instruction", - "MetricName": "Crypto mix" + "MetricName": "crypto_percentage", + "MetricExpr": "((CRYPTO_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "VFP_SPEC / (duration_time *1000000000)", + "MetricName": "gflops", + "MetricExpr": "VFP_SPEC / (duration_time * 1e9)", "BriefDescription": "Giga-floating point operations per second", - "MetricGroup": "Instruction", - "MetricName": "GFLOPS_ISSUED" + "MetricGroup": "InstructionMix" }, { - "MetricExpr": "DP_SPEC / OP_SPEC", - "BriefDescription": "Proportion of integer data processing operations", - "MetricGroup": "Instruction", - "MetricName": "Integer mix" + "MetricName": "integer_dp_percentage", + "MetricExpr": "((DP_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "INST_RETIRED / CPU_CYCLES", - "BriefDescription": "Instructions per cycle", - "MetricGroup": "Instruction", - "MetricName": "IPC" + "MetricName": "ipc", + "MetricExpr": "(INST_RETIRED / CPU_CYCLES)", + "BriefDescription": "This metric measures the number of instructions retired per cycle.", + "MetricGroup": "General", + "ScaleUnit": "1per cycle" }, { - "MetricExpr": "LD_SPEC / OP_SPEC", - "BriefDescription": "Proportion of load operations", - "MetricGroup": "Instruction", - "MetricName": "Load mix" + "MetricName": "load_percentage", + "MetricExpr": "((LD_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "LDST_SPEC/ OP_SPEC", - "BriefDescription": "Proportion of load & store operations", - "MetricGroup": "Instruction", - "MetricName": "Load-store mix" + "MetricName": "load_store_spec_rate", + "MetricExpr": "((LDST_SPEC / INST_SPEC) * 100)", + "BriefDescription": "The rate of load or store instructions speculatively executed to overall instructions speclatively executed", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "INST_RETIRED / (duration_time * 1000000)", + "MetricName": "retired_mips", + "MetricExpr": "INST_RETIRED / (duration_time * 1e6)", "BriefDescription": "Millions of instructions per second", - "MetricGroup": "Instruction", - "MetricName": "MIPS_RETIRED" + "MetricGroup": "InstructionMix" }, { - "MetricExpr": "INST_SPEC / (duration_time * 1000000)", + "MetricName": "spec_utilization_mips", + "MetricExpr": "INST_SPEC / (duration_time * 1e6)", "BriefDescription": "Millions of instructions per second", - "MetricGroup": "Instruction", - "MetricName": "MIPS_UTILIZATION" - }, - { - "MetricExpr": "PC_WRITE_SPEC / OP_SPEC", - "BriefDescription": "Proportion of software change of PC operations", - "MetricGroup": "Instruction", - "MetricName": "PC write mix" + "MetricGroup": "PEutilization" }, { - "MetricExpr": "ST_SPEC / OP_SPEC", - "BriefDescription": "Proportion of store operations", - "MetricGroup": "Instruction", - "MetricName": "Store mix" + "MetricName": "pc_write_spec_rate", + "MetricExpr": "((PC_WRITE_SPEC / INST_SPEC) * 100)", + "BriefDescription": "The rate of software change of the PC speculatively executed to overall instructions speclatively executed", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "VFP_SPEC / OP_SPEC", - "BriefDescription": "Proportion of FP operations", - "MetricGroup": "Instruction", - "MetricName": "VFP mix" + "MetricName": "store_percentage", + "MetricExpr": "((ST_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "1 - (OP_RETIRED/ (CPU_CYCLES * 4))", - "BriefDescription": "Proportion of slots lost", - "MetricGroup": "Speculation / TDA", - "MetricName": "CPU lost" + "MetricName": "scalar_fp_percentage", + "MetricExpr": "((VFP_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" }, { - "MetricExpr": "OP_RETIRED/ (CPU_CYCLES * 4)", - "BriefDescription": "Proportion of slots retiring", - "MetricGroup": "Speculation / TDA", - "MetricName": "CPU utilization" + "MetricName": "retired_rate", + "MetricExpr": "OP_RETIRED / OP_SPEC", + "BriefDescription": "Of all the micro-operations issued, what percentage are retired(committed)", + "MetricGroup": "General", + "ScaleUnit": "100%" }, { - "MetricExpr": "OP_RETIRED - OP_SPEC", - "BriefDescription": "Operations lost due to misspeculation", - "MetricGroup": "Speculation / TDA", - "MetricName": "Operations lost" + "MetricName": "wasted", + "MetricExpr": "1 - (OP_RETIRED / (CPU_CYCLES * #slots))", + "BriefDescription": "Of all the micro-operations issued, what proportion are lost", + "MetricGroup": "General", + "ScaleUnit": "100%" }, { - "MetricExpr": "1 - (OP_RETIRED / OP_SPEC)", - "BriefDescription": "Proportion of operations lost", - "MetricGroup": "Speculation / TDA", - "MetricName": "Operations lost (ratio)" + "MetricName": "wasted_rate", + "MetricExpr": "1 - OP_RETIRED / OP_SPEC", + "BriefDescription": "Of all the micro-operations issued, what percentage are not retired(committed)", + "MetricGroup": "General", + "ScaleUnit": "100%" }, { - "MetricExpr": "OP_RETIRED / OP_SPEC", - "BriefDescription": "Proportion of operations retired", - "MetricGroup": "Speculation / TDA", - "MetricName": "Operations retired" - }, - { - "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES", + "MetricName": "stall_backend_cache_rate", + "MetricExpr": "((STALL_BACKEND_CACHE / CPU_CYCLES) * 100)", "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and cache miss", "MetricGroup": "Stall", - "MetricName": "Stall backend cache cycles" + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES", + "MetricName": "stall_backend_resource_rate", + "MetricExpr": "((STALL_BACKEND_RESOURCE / CPU_CYCLES) * 100)", "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and resource full", "MetricGroup": "Stall", - "MetricName": "Stall backend resource cycles" + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES", + "MetricName": "stall_backend_tlb_rate", + "MetricExpr": "((STALL_BACKEND_TLB / CPU_CYCLES) * 100)", "BriefDescription": "Proportion of cycles stalled and no operations issued to backend and TLB miss", "MetricGroup": "Stall", - "MetricName": "Stall backend tlb cycles" + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES", + "MetricName": "stall_frontend_cache_rate", + "MetricExpr": "((STALL_FRONTEND_CACHE / CPU_CYCLES) * 100)", "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and cache miss", "MetricGroup": "Stall", - "MetricName": "Stall frontend cache cycles" + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "STALL_FRONTEND_TLB / CPU_CYCLES", + "MetricName": "stall_frontend_tlb_rate", + "MetricExpr": "((STALL_FRONTEND_TLB / CPU_CYCLES) * 100)", "BriefDescription": "Proportion of cycles stalled and no ops delivered from frontend and TLB miss", "MetricGroup": "Stall", - "MetricName": "Stall frontend tlb cycles" + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "DTLB_WALK / L1D_TLB", - "BriefDescription": "D-side walk per d-side translation request", - "MetricGroup": "TLB", - "MetricName": "DTLB walks" + "MetricName": "dtlb_walk_ratio", + "MetricExpr": "(DTLB_WALK / L1D_TLB)", + "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" }, { - "MetricExpr": "ITLB_WALK / L1I_TLB", - "BriefDescription": "I-side walk per i-side translation request", - "MetricGroup": "TLB", - "MetricName": "ITLB walks" + "MetricName": "itlb_walk_ratio", + "MetricExpr": "(ITLB_WALK / L1I_TLB)", + "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "1per TLB access" }, { - "MetricExpr": "STALL_SLOT_BACKEND / (CPU_CYCLES * 4)", - "BriefDescription": "Fraction of slots backend bound", - "MetricGroup": "TopDownL1", - "MetricName": "backend" + "ArchStdEvent": "backend_bound" }, { - "MetricExpr": "1 - (retiring + lost + backend)", - "BriefDescription": "Fraction of slots frontend bound", - "MetricGroup": "TopDownL1", - "MetricName": "frontend" + "ArchStdEvent": "frontend_bound", + "MetricExpr": "100 - (retired_fraction + slots_lost_misspeculation_fraction + backend_bound)" }, { - "MetricExpr": "((OP_SPEC - OP_RETIRED) / (CPU_CYCLES * 4))", + "MetricName": "slots_lost_misspeculation_fraction", + "MetricExpr": "100 * ((OP_SPEC - OP_RETIRED) / (CPU_CYCLES * #slots))", "BriefDescription": "Fraction of slots lost due to misspeculation", - "MetricGroup": "TopDownL1", - "MetricName": "lost" + "MetricGroup": "Default;TopdownL1", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "(OP_RETIRED / (CPU_CYCLES * 4))", + "MetricName": "retired_fraction", + "MetricExpr": "100 * (OP_RETIRED / (CPU_CYCLES * #slots))", "BriefDescription": "Fraction of slots retiring, useful work", - "MetricGroup": "TopDownL1", - "MetricName": "retiring" + "MetricGroup": "Default;TopdownL1", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "backend - backend_memory", + "MetricName": "backend_core", + "MetricExpr": "(backend_bound / 100) - backend_memory", "BriefDescription": "Fraction of slots the CPU was stalled due to backend non-memory subsystem issues", - "MetricGroup": "TopDownL2", - "MetricName": "backend_core" + "MetricGroup": "TopdownL2", + "ScaleUnit": "100%" }, { - "MetricExpr": "(STALL_BACKEND_TLB + STALL_BACKEND_CACHE + STALL_BACKEND_MEM) / CPU_CYCLES ", + "MetricName": "backend_memory", + "MetricExpr": "(STALL_BACKEND_TLB + STALL_BACKEND_CACHE) / CPU_CYCLES", "BriefDescription": "Fraction of slots the CPU was stalled due to backend memory subsystem issues (cache/tlb miss)", - "MetricGroup": "TopDownL2", - "MetricName": "backend_memory" + "MetricGroup": "TopdownL2", + "ScaleUnit": "100%" }, { - "MetricExpr": " (BR_MIS_PRED_RETIRED / GPC_FLUSH) * lost", + "MetricName": "branch_mispredict", + "MetricExpr": "(BR_MIS_PRED_RETIRED / GPC_FLUSH) * slots_lost_misspeculation_fraction", "BriefDescription": "Fraction of slots lost due to branch misprediciton", - "MetricGroup": "TopDownL2", - "MetricName": "branch_mispredict" + "MetricGroup": "TopdownL2", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "frontend - frontend_latency", + "MetricName": "frontend_bandwidth", + "MetricExpr": "frontend_bound - frontend_latency", "BriefDescription": "Fraction of slots the CPU did not dispatch at full bandwidth - able to dispatch partial slots only (1, 2, or 3 uops)", - "MetricGroup": "TopDownL2", - "MetricName": "frontend_bandwidth" + "MetricGroup": "TopdownL2", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "(STALL_FRONTEND - ((STALL_SLOT_FRONTEND - (frontend * CPU_CYCLES * 4)) / 4)) / CPU_CYCLES", + "MetricName": "frontend_latency", + "MetricExpr": "((STALL_FRONTEND - ((STALL_SLOT_FRONTEND - ((frontend_bound / 100) * CPU_CYCLES * #slots)) / #slots)) / CPU_CYCLES) * 100", "BriefDescription": "Fraction of slots the CPU was stalled due to frontend latency issues (cache/tlb miss); nothing to dispatch", - "MetricGroup": "TopDownL2", - "MetricName": "frontend_latency" + "MetricGroup": "TopdownL2", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "lost - branch_mispredict", + "MetricName": "other_miss_pred", + "MetricExpr": "slots_lost_misspeculation_fraction - branch_mispredict", "BriefDescription": "Fraction of slots lost due to other/non-branch misprediction misspeculation", - "MetricGroup": "TopDownL2", - "MetricName": "other_clears" + "MetricGroup": "TopdownL2", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "(IXU_NUM_UOPS_ISSUED + FSU_ISSUED) / (CPU_CYCLES * 6)", + "MetricName": "pipe_utilization", + "MetricExpr": "100 * ((IXU_NUM_UOPS_ISSUED + FSU_ISSUED) / (CPU_CYCLES * 6))", "BriefDescription": "Fraction of execute slots utilized", - "MetricGroup": "TopDownL2", - "MetricName": "pipe_utilization" + "MetricGroup": "TopdownL2", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "STALL_BACKEND_MEM / CPU_CYCLES", + "MetricName": "d_cache_l2_miss_rate", + "MetricExpr": "((STALL_BACKEND_MEM / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled due to data L2 cache miss", - "MetricGroup": "TopDownL3", - "MetricName": "d_cache_l2_miss" + "MetricGroup": "TopdownL3", + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "STALL_BACKEND_CACHE / CPU_CYCLES", + "MetricName": "d_cache_miss_rate", + "MetricExpr": "((STALL_BACKEND_CACHE / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled due to data cache miss", - "MetricGroup": "TopDownL3", - "MetricName": "d_cache_miss" + "MetricGroup": "TopdownL3", + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "STALL_BACKEND_TLB / CPU_CYCLES", + "MetricName": "d_tlb_miss_rate", + "MetricExpr": "((STALL_BACKEND_TLB / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled due to data TLB miss", - "MetricGroup": "TopDownL3", - "MetricName": "d_tlb_miss" + "MetricGroup": "TopdownL3", + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "FSU_ISSUED / (CPU_CYCLES * 2)", + "MetricName": "fsu_pipe_utilization", + "MetricExpr": "((FSU_ISSUED / (CPU_CYCLES * 2)) * 100)", "BriefDescription": "Fraction of FSU execute slots utilized", - "MetricGroup": "TopDownL3", - "MetricName": "fsu_pipe_utilization" + "MetricGroup": "TopdownL3", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "STALL_FRONTEND_CACHE / CPU_CYCLES", + "MetricName": "i_cache_miss_rate", + "MetricExpr": "((STALL_FRONTEND_CACHE / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction cache miss", - "MetricGroup": "TopDownL3", - "MetricName": "i_cache_miss" + "MetricGroup": "TopdownL3", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": " STALL_FRONTEND_TLB / CPU_CYCLES ", + "MetricName": "i_tlb_miss_rate", + "MetricExpr": "((STALL_FRONTEND_TLB / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled due to instruction TLB miss", - "MetricGroup": "TopDownL3", - "MetricName": "i_tlb_miss" + "MetricGroup": "TopdownL3", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "IXU_NUM_UOPS_ISSUED / (CPU_CYCLES / 4)", + "MetricName": "ixu_pipe_utilization", + "MetricExpr": "((IXU_NUM_UOPS_ISSUED / (CPU_CYCLES * #slots)) * 100)", "BriefDescription": "Fraction of IXU execute slots utilized", - "MetricGroup": "TopDownL3", - "MetricName": "ixu_pipe_utilization" + "MetricGroup": "TopdownL3", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "IDR_STALL_FLUSH / CPU_CYCLES", + "MetricName": "stall_recovery_rate", + "MetricExpr": "((IDR_STALL_FLUSH / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled due to flush recovery", - "MetricGroup": "TopDownL3", - "MetricName": "recovery" - }, - { - "MetricExpr": "STALL_BACKEND_RESOURCE / CPU_CYCLES", - "BriefDescription": "Fraction of cycles the CPU was stalled due to core resource shortage", - "MetricGroup": "TopDownL3", - "MetricName": "resource" + "MetricGroup": "TopdownL3", + "ScaleUnit": "1percent of slots" }, { - "MetricExpr": "IDR_STALL_FSU_SCHED / CPU_CYCLES ", + "MetricName": "stall_fsu_sched_rate", + "MetricExpr": "((IDR_STALL_FSU_SCHED / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled and FSU was full", - "MetricGroup": "TopDownL4", - "MetricName": "stall_fsu_sched" + "MetricGroup": "TopdownL4", + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "IDR_STALL_IXU_SCHED / CPU_CYCLES ", + "MetricName": "stall_ixu_sched_rate", + "MetricExpr": "((IDR_STALL_IXU_SCHED / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled and IXU was full", - "MetricGroup": "TopDownL4", - "MetricName": "stall_ixu_sched" + "MetricGroup": "TopdownL4", + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "IDR_STALL_LOB_ID / CPU_CYCLES ", + "MetricName": "stall_lob_id_rate", + "MetricExpr": "((IDR_STALL_LOB_ID / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled and LOB was full", - "MetricGroup": "TopDownL4", - "MetricName": "stall_lob_id" + "MetricGroup": "TopdownL4", + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "IDR_STALL_ROB_ID / CPU_CYCLES", + "MetricName": "stall_rob_id_rate", + "MetricExpr": "((IDR_STALL_ROB_ID / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled and ROB was full", - "MetricGroup": "TopDownL4", - "MetricName": "stall_rob_id" + "MetricGroup": "TopdownL4", + "ScaleUnit": "1percent of cycles" }, { - "MetricExpr": "IDR_STALL_SOB_ID / CPU_CYCLES ", + "MetricName": "stall_sob_id_rate", + "MetricExpr": "((IDR_STALL_SOB_ID / CPU_CYCLES) * 100)", "BriefDescription": "Fraction of cycles the CPU was stalled and SOB was full", - "MetricGroup": "TopDownL4", - "MetricName": "stall_sob_id" + "MetricGroup": "TopdownL4", + "ScaleUnit": "1percent of cycles" } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json b/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json new file mode 100644 index 000000000000..428605c37d10 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/cmn.json @@ -0,0 +1,266 @@ +[ + { + "EventName": "hnf_cache_miss", + "EventidCode": "0x1", + "NodeType": "0x5", + "BriefDescription": "Counts total cache misses in first lookup result (high priority).", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_slc_sf_cache_access", + "EventidCode": "0x2", + "NodeType": "0x5", + "BriefDescription": "Counts number of cache accesses in first access (high priority).", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_cache_fill", + "EventidCode": "0x3", + "NodeType": "0x5", + "BriefDescription": "Counts total allocations in HN SLC (all cache line allocations to SLC).", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_pocq_retry", + "EventidCode": "0x4", + "NodeType": "0x5", + "BriefDescription": "Counts number of retried requests.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_pocq_reqs_recvd", + "EventidCode": "0x5", + "NodeType": "0x5", + "BriefDescription": "Counts number of requests that HN receives.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_sf_hit", + "EventidCode": "0x6", + "NodeType": "0x5", + "BriefDescription": "Counts number of SF hits.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_sf_evictions", + "EventidCode": "0x7", + "NodeType": "0x5", + "BriefDescription": "Counts number of SF eviction cache invalidations initiated.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_dir_snoops_sent", + "EventidCode": "0x8", + "NodeType": "0x5", + "BriefDescription": "Counts number of directed snoops sent (not including SF back invalidation).", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_brd_snoops_sent", + "EventidCode": "0x9", + "NodeType": "0x5", + "BriefDescription": "Counts number of multicast snoops sent (not including SF back invalidation).", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_slc_eviction", + "EventidCode": "0xa", + "NodeType": "0x5", + "BriefDescription": "Counts number of SLC evictions (dirty only).", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_slc_fill_invalid_way", + "EventidCode": "0xb", + "NodeType": "0x5", + "BriefDescription": "Counts number of SLC fills to an invalid way.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_mc_retries", + "EventidCode": "0xc", + "NodeType": "0x5", + "BriefDescription": "Counts number of retried transactions by the MC.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_mc_reqs", + "EventidCode": "0xd", + "NodeType": "0x5", + "BriefDescription": "Counts number of requests that are sent to MC.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hnf_qos_hh_retry", + "EventidCode": "0xe", + "NodeType": "0x5", + "BriefDescription": "Counts number of times a HighHigh priority request is protocolretried at the HN‑F.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "rnid_s0_rdata_beats", + "EventidCode": "0x1", + "NodeType": "0xa", + "BriefDescription": "Number of RData beats (RVALID and RREADY) dispatched on port 0. This event measures the read bandwidth, including CMO responses.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "rnid_s1_rdata_beats", + "EventidCode": "0x2", + "NodeType": "0xa", + "BriefDescription": "Number of RData beats (RVALID and RREADY) dispatched on port 1. This event measures the read bandwidth, including CMO responses.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "rnid_s2_rdata_beats", + "EventidCode": "0x3", + "NodeType": "0xa", + "BriefDescription": "Number of RData beats (RVALID and RREADY) dispatched on port 2. This event measures the read bandwidth, including CMO responses.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "rnid_rxdat_flits", + "EventidCode": "0x4", + "NodeType": "0xa", + "BriefDescription": "Number of RXDAT flits received. This event measures the true read data bandwidth, excluding CMOs.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "rnid_txdat_flits", + "EventidCode": "0x5", + "NodeType": "0xa", + "BriefDescription": "Number of TXDAT flits dispatched. This event measures the write bandwidth.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "rnid_txreq_flits_total", + "EventidCode": "0x6", + "NodeType": "0xa", + "BriefDescription": "Number of TXREQ flits dispatched. This event measures the total request bandwidth.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "rnid_txreq_flits_retried", + "EventidCode": "0x7", + "NodeType": "0xa", + "BriefDescription": "Number of retried TXREQ flits dispatched. This event measures the retry rate.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "sbsx_txrsp_retryack", + "EventidCode": "0x4", + "NodeType": "0x7", + "BriefDescription": "Number of RXREQ flits dispatched. This event is a measure of the retry rate.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "sbsx_txdat_flitv", + "EventidCode": "0x5", + "NodeType": "0x7", + "BriefDescription": "Number of TXDAT flits dispatched from XP to SBSX. This event is a measure of the write bandwidth.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "sbsx_arvalid_no_arready", + "EventidCode": "0x21", + "NodeType": "0x7", + "BriefDescription": "Number of cycles the SBSX bridge is stalled because of backpressure on AR channel.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "sbsx_awvalid_no_awready", + "EventidCode": "0x22", + "NodeType": "0x7", + "BriefDescription": "Number of cycles the SBSX bridge is stalled because of backpressure on AW channel.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "sbsx_wvalid_no_wready", + "EventidCode": "0x23", + "NodeType": "0x7", + "BriefDescription": "Number of cycles the SBSX bridge is stalled because of backpressure on W channel.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hni_txrsp_retryack", + "EventidCode": "0x2a", + "NodeType": "0x4", + "BriefDescription": "Number of RXREQ flits dispatched. This event is a measure of the retry rate.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hni_arvalid_no_arready", + "EventidCode": "0x2b", + "NodeType": "0x4", + "BriefDescription": "Number of cycles the HN-I bridge is stalled because of backpressure on AR channel.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hni_arready_no_arvalid", + "EventidCode": "0x2c", + "NodeType": "0x4", + "BriefDescription": "Number of cycles the AR channel is waiting for new requests from HN-I bridge.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hni_awvalid_no_awready", + "EventidCode": "0x2d", + "NodeType": "0x4", + "BriefDescription": "Number of cycles the HN-I bridge is stalled because of backpressure on AW channel.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hni_awready_no_awvalid", + "EventidCode": "0x2e", + "NodeType": "0x4", + "BriefDescription": "Number of cycles the AW channel is waiting for new requests from HN-I bridge.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hni_wvalid_no_wready", + "EventidCode": "0x2f", + "NodeType": "0x4", + "BriefDescription": "Number of cycles the HN-I bridge is stalled because of backpressure on W channel.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "EventName": "hni_txdat_stall", + "EventidCode": "0x30", + "NodeType": "0x4", + "BriefDescription": "TXDAT valid but no link credit available.", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/metric.json b/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/metric.json new file mode 100644 index 000000000000..f7823bd265db --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/cmn/sys/metric.json @@ -0,0 +1,74 @@ +[ + { + "MetricName": "slc_miss_rate", + "BriefDescription": "The system level cache miss rate.", + "MetricGroup": "cmn", + "MetricExpr": "hnf_cache_miss / hnf_slc_sf_cache_access", + "ScaleUnit": "100%", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "MetricName": "hnf_message_retry_rate", + "BriefDescription": "HN-F message retry rate indicates whether a lack of credits is causing the bottlenecks.", + "MetricGroup": "cmn", + "MetricExpr": "hnf_pocq_retry / hnf_pocq_reqs_recvd", + "ScaleUnit": "100%", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "MetricName": "sf_hit_rate", + "BriefDescription": "Snoop filter hit rate can be used to measure the snoop filter efficiency.", + "MetricGroup": "cmn", + "MetricExpr": "hnf_sf_hit / hnf_slc_sf_cache_access", + "ScaleUnit": "100%", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "MetricName": "mc_message_retry_rate", + "BriefDescription": "The memory controller request retries rate indicates whether the memory controller is the bottleneck.", + "MetricGroup": "cmn", + "MetricExpr": "hnf_mc_retries / hnf_mc_reqs", + "ScaleUnit": "100%", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "MetricName": "rni_actual_read_bandwidth.all", + "BriefDescription": "This event measure the actual bandwidth that RN-I bridge sends to the interconnect.", + "MetricGroup": "cmn", + "MetricExpr": "rnid_rxdat_flits * 32 / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "MetricName": "rni_actual_write_bandwidth.all", + "BriefDescription": "This event measures the actual write bandwidth at RN-I bridges.", + "MetricGroup": "cmn", + "MetricExpr": "rnid_txdat_flits * 32 / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "MetricName": "rni_retry_rate", + "BriefDescription": "RN-I bridge retry rate indicates whether the memory controller is the bottleneck.", + "MetricGroup": "cmn", + "MetricExpr": "rnid_txreq_flits_retried / rnid_txreq_flits_total", + "ScaleUnit": "100%", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + }, + { + "MetricName": "sbsx_actual_write_bandwidth.all", + "BriefDescription": "sbsx actual write bandwidth.", + "MetricGroup": "cmn", + "MetricExpr": "sbsx_txdat_flitv * 32 / 1e6 / duration_time", + "ScaleUnit": "1MB/s", + "Unit": "arm_cmn", + "Compat": "(434|436|43c|43a).*" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/branch.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/branch.json deleted file mode 100644 index 79f2016c53b0..000000000000 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/branch.json +++ /dev/null @@ -1,8 +0,0 @@ -[ - { - "ArchStdEvent": "BR_MIS_PRED" - }, - { - "ArchStdEvent": "BR_PRED" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/bus.json index 579c1c993d17..2e11a8c4a484 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/bus.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/bus.json @@ -1,20 +1,18 @@ [ { - "ArchStdEvent": "CPU_CYCLES" + "ArchStdEvent": "BUS_ACCESS", + "PublicDescription": "Counts memory transactions issued by the CPU to the external bus, including snoop requests and snoop responses. Each beat of data is counted individually." }, { - "ArchStdEvent": "BUS_ACCESS" + "ArchStdEvent": "BUS_CYCLES", + "PublicDescription": "Counts bus cycles in the CPU. Bus cycles represent a clock cycle in which a transaction could be sent or received on the interface from the CPU to the external bus. Since that interface is driven at the same clock speed as the CPU, this event is a duplicate of CPU_CYCLES." }, { - "ArchStdEvent": "BUS_CYCLES" + "ArchStdEvent": "BUS_ACCESS_RD", + "PublicDescription": "Counts memory read transactions seen on the external bus. Each beat of data is counted individually." }, { - "ArchStdEvent": "BUS_ACCESS_RD" - }, - { - "ArchStdEvent": "BUS_ACCESS_WR" - }, - { - "ArchStdEvent": "CNT_CYCLES" + "ArchStdEvent": "BUS_ACCESS_WR", + "PublicDescription": "Counts memory write transactions seen on the external bus. Each beat of data is counted individually." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/cache.json deleted file mode 100644 index 0141f749bff3..000000000000 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/cache.json +++ /dev/null @@ -1,155 +0,0 @@ -[ - { - "ArchStdEvent": "L1I_CACHE_REFILL" - }, - { - "ArchStdEvent": "L1I_TLB_REFILL" - }, - { - "ArchStdEvent": "L1D_CACHE_REFILL" - }, - { - "ArchStdEvent": "L1D_CACHE" - }, - { - "ArchStdEvent": "L1D_TLB_REFILL" - }, - { - "ArchStdEvent": "L1I_CACHE" - }, - { - "ArchStdEvent": "L1D_CACHE_WB" - }, - { - "ArchStdEvent": "L2D_CACHE" - }, - { - "ArchStdEvent": "L2D_CACHE_REFILL" - }, - { - "ArchStdEvent": "L2D_CACHE_WB" - }, - { - "ArchStdEvent": "L2D_CACHE_ALLOCATE" - }, - { - "ArchStdEvent": "L1D_TLB" - }, - { - "ArchStdEvent": "L1I_TLB" - }, - { - "ArchStdEvent": "L3D_CACHE_ALLOCATE" - }, - { - "ArchStdEvent": "L3D_CACHE_REFILL" - }, - { - "ArchStdEvent": "L3D_CACHE" - }, - { - "ArchStdEvent": "L2D_TLB_REFILL" - }, - { - "ArchStdEvent": "L2D_TLB" - }, - { - "ArchStdEvent": "DTLB_WALK" - }, - { - "ArchStdEvent": "ITLB_WALK" - }, - { - "ArchStdEvent": "LL_CACHE_RD" - }, - { - "ArchStdEvent": "LL_CACHE_MISS_RD" - }, - { - "ArchStdEvent": "L1D_CACHE_LMISS_RD" - }, - { - "ArchStdEvent": "L1D_CACHE_RD" - }, - { - "ArchStdEvent": "L1D_CACHE_WR" - }, - { - "ArchStdEvent": "L1D_CACHE_REFILL_RD" - }, - { - "ArchStdEvent": "L1D_CACHE_REFILL_WR" - }, - { - "ArchStdEvent": "L1D_CACHE_REFILL_INNER" - }, - { - "ArchStdEvent": "L1D_CACHE_REFILL_OUTER" - }, - { - "ArchStdEvent": "L1D_CACHE_WB_VICTIM" - }, - { - "ArchStdEvent": "L1D_CACHE_WB_CLEAN" - }, - { - "ArchStdEvent": "L1D_CACHE_INVAL" - }, - { - "ArchStdEvent": "L1D_TLB_REFILL_RD" - }, - { - "ArchStdEvent": "L1D_TLB_REFILL_WR" - }, - { - "ArchStdEvent": "L1D_TLB_RD" - }, - { - "ArchStdEvent": "L1D_TLB_WR" - }, - { - "ArchStdEvent": "L2D_CACHE_RD" - }, - { - "ArchStdEvent": "L2D_CACHE_WR" - }, - { - "ArchStdEvent": "L2D_CACHE_REFILL_RD" - }, - { - "ArchStdEvent": "L2D_CACHE_REFILL_WR" - }, - { - "ArchStdEvent": "L2D_CACHE_WB_VICTIM" - }, - { - "ArchStdEvent": "L2D_CACHE_WB_CLEAN" - }, - { - "ArchStdEvent": "L2D_CACHE_INVAL" - }, - { - "ArchStdEvent": "L2D_TLB_REFILL_RD" - }, - { - "ArchStdEvent": "L2D_TLB_REFILL_WR" - }, - { - "ArchStdEvent": "L2D_TLB_RD" - }, - { - "ArchStdEvent": "L2D_TLB_WR" - }, - { - "ArchStdEvent": "L3D_CACHE_RD" - }, - { - "ArchStdEvent": "L1I_CACHE_LMISS" - }, - { - "ArchStdEvent": "L2D_CACHE_LMISS_RD" - }, - { - "ArchStdEvent": "L3D_CACHE_LMISS_RD" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/exception.json index 344a2d552ad5..4404b8e91690 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/exception.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/exception.json @@ -1,47 +1,62 @@ [ { - "ArchStdEvent": "EXC_TAKEN" + "ArchStdEvent": "EXC_TAKEN", + "PublicDescription": "Counts any taken architecturally visible exceptions such as IRQ, FIQ, SError, and other synchronous exceptions. Exceptions are counted whether or not they are taken locally." }, { - "ArchStdEvent": "MEMORY_ERROR" + "ArchStdEvent": "EXC_RETURN", + "PublicDescription": "Counts any architecturally executed exception return instructions. Eg: AArch64: ERET" }, { - "ArchStdEvent": "EXC_UNDEF" + "ArchStdEvent": "EXC_UNDEF", + "PublicDescription": "Counts the number of synchronous exceptions which are taken locally that are due to attempting to execute an instruction that is UNDEFINED. Attempting to execute instruction bit patterns that have not been allocated. Attempting to execute instructions when they are disabled. Attempting to execute instructions at an inappropriate Exception level. Attempting to execute an instruction when the value of PSTATE.IL is 1." }, { - "ArchStdEvent": "EXC_SVC" + "ArchStdEvent": "EXC_SVC", + "PublicDescription": "Counts SVC exceptions taken locally." }, { - "ArchStdEvent": "EXC_PABORT" + "ArchStdEvent": "EXC_PABORT", + "PublicDescription": "Counts synchronous exceptions that are taken locally and caused by Instruction Aborts." }, { - "ArchStdEvent": "EXC_DABORT" + "ArchStdEvent": "EXC_DABORT", + "PublicDescription": "Counts exceptions that are taken locally and are caused by data aborts or SErrors. Conditions that could cause those exceptions are attempting to read or write memory where the MMU generates a fault, attempting to read or write memory with a misaligned address, interrupts from the nSEI inputs and internally generated SErrors." }, { - "ArchStdEvent": "EXC_IRQ" + "ArchStdEvent": "EXC_IRQ", + "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are taken locally." }, { - "ArchStdEvent": "EXC_FIQ" + "ArchStdEvent": "EXC_FIQ", + "PublicDescription": "Counts FIQ exceptions including the virtual FIQs that are taken locally." }, { - "ArchStdEvent": "EXC_SMC" + "ArchStdEvent": "EXC_SMC", + "PublicDescription": "Counts SMC exceptions take to EL3." }, { - "ArchStdEvent": "EXC_HVC" + "ArchStdEvent": "EXC_HVC", + "PublicDescription": "Counts HVC exceptions taken to EL2." }, { - "ArchStdEvent": "EXC_TRAP_PABORT" + "ArchStdEvent": "EXC_TRAP_PABORT", + "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Instruction Aborts. For example, attempting to execute an instruction with a misaligned PC." }, { - "ArchStdEvent": "EXC_TRAP_DABORT" + "ArchStdEvent": "EXC_TRAP_DABORT", + "PublicDescription": "Counts exceptions which are traps not taken locally and are caused by Data Aborts or SError interrupts. Conditions that could cause those exceptions are:\n\n1. Attempting to read or write memory where the MMU generates a fault,\n2. Attempting to read or write memory with a misaligned address,\n3. Interrupts from the SEI input.\n4. internally generated SErrors." }, { - "ArchStdEvent": "EXC_TRAP_OTHER" + "ArchStdEvent": "EXC_TRAP_OTHER", + "PublicDescription": "Counts the number of synchronous trap exceptions which are not taken locally and are not SVC, SMC, HVC, data aborts, Instruction Aborts, or interrupts." }, { - "ArchStdEvent": "EXC_TRAP_IRQ" + "ArchStdEvent": "EXC_TRAP_IRQ", + "PublicDescription": "Counts IRQ exceptions including the virtual IRQs that are not taken locally." }, { - "ArchStdEvent": "EXC_TRAP_FIQ" + "ArchStdEvent": "EXC_TRAP_FIQ", + "PublicDescription": "Counts FIQs which are not taken locally but taken from EL0, EL1,\n or EL2 to EL3 (which would be the normal behavior for FIQs when not executing\n in EL3)." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/fp_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/fp_operation.json new file mode 100644 index 000000000000..a09e226e7138 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/fp_operation.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "FP_SCALE_OPS_SPEC", + "PublicDescription": "Counts speculatively executed scalable single precision floating point operations." + }, + { + "ArchStdEvent": "FP_FIXED_OPS_SPEC", + "PublicDescription": "Counts speculatively executed non-scalable single precision floating point operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/general.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/general.json new file mode 100644 index 000000000000..428810f855b8 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/general.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "CPU_CYCLES", + "PublicDescription": "Counts CPU clock cycles (not timer cycles). The clock measured by this event is defined as the physical clock driving the CPU logic." + }, + { + "ArchStdEvent": "CNT_CYCLES", + "PublicDescription": "Counts constant frequency cycles" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/instruction.json deleted file mode 100644 index e29b88fb7f24..000000000000 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/instruction.json +++ /dev/null @@ -1,119 +0,0 @@ -[ - { - "ArchStdEvent": "SW_INCR" - }, - { - "ArchStdEvent": "INST_RETIRED" - }, - { - "ArchStdEvent": "EXC_RETURN" - }, - { - "ArchStdEvent": "CID_WRITE_RETIRED" - }, - { - "ArchStdEvent": "INST_SPEC" - }, - { - "ArchStdEvent": "TTBR_WRITE_RETIRED" - }, - { - "ArchStdEvent": "BR_RETIRED" - }, - { - "ArchStdEvent": "BR_MIS_PRED_RETIRED" - }, - { - "ArchStdEvent": "OP_RETIRED" - }, - { - "ArchStdEvent": "OP_SPEC" - }, - { - "ArchStdEvent": "LDREX_SPEC" - }, - { - "ArchStdEvent": "STREX_PASS_SPEC" - }, - { - "ArchStdEvent": "STREX_FAIL_SPEC" - }, - { - "ArchStdEvent": "STREX_SPEC" - }, - { - "ArchStdEvent": "LD_SPEC" - }, - { - "ArchStdEvent": "ST_SPEC" - }, - { - "ArchStdEvent": "DP_SPEC" - }, - { - "ArchStdEvent": "ASE_SPEC" - }, - { - "ArchStdEvent": "VFP_SPEC" - }, - { - "ArchStdEvent": "PC_WRITE_SPEC" - }, - { - "ArchStdEvent": "CRYPTO_SPEC" - }, - { - "ArchStdEvent": "BR_IMMED_SPEC" - }, - { - "ArchStdEvent": "BR_RETURN_SPEC" - }, - { - "ArchStdEvent": "BR_INDIRECT_SPEC" - }, - { - "ArchStdEvent": "ISB_SPEC" - }, - { - "ArchStdEvent": "DSB_SPEC" - }, - { - "ArchStdEvent": "DMB_SPEC" - }, - { - "ArchStdEvent": "RC_LD_SPEC" - }, - { - "ArchStdEvent": "RC_ST_SPEC" - }, - { - "ArchStdEvent": "ASE_INST_SPEC" - }, - { - "ArchStdEvent": "SVE_INST_SPEC" - }, - { - "ArchStdEvent": "SVE_PRED_SPEC" - }, - { - "ArchStdEvent": "SVE_PRED_EMPTY_SPEC" - }, - { - "ArchStdEvent": "SVE_PRED_FULL_SPEC" - }, - { - "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC" - }, - { - "ArchStdEvent": "SVE_LDFF_SPEC" - }, - { - "ArchStdEvent": "SVE_LDFF_FAULT_SPEC" - }, - { - "ArchStdEvent": "FP_SCALE_OPS_SPEC" - }, - { - "ArchStdEvent": "FP_FIXED_OPS_SPEC" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l1d_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l1d_cache.json new file mode 100644 index 000000000000..ed83e1c5affe --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l1d_cache.json @@ -0,0 +1,54 @@ +[ + { + "ArchStdEvent": "L1D_CACHE_REFILL", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load or store operations that missed in the level 1 data cache. This event only counts one event per cache line. This event does not count cache line allocations from preload instructions or from hardware cache prefetching." + }, + { + "ArchStdEvent": "L1D_CACHE", + "PublicDescription": "Counts level 1 data cache accesses from any load/store operations. Atomic operations that resolve in the CPUs caches (near atomic operations) counts as both a write access and read access. Each access to a cache line is counted including the multiple accesses caused by single instructions such as LDM or STM. Each access to other level 1 data or unified memory structures, for example refill buffers, write buffers, and write-back buffers, are also counted." + }, + { + "ArchStdEvent": "L1D_CACHE_WB", + "PublicDescription": "Counts write-backs of dirty data from the L1 data cache to the L2 cache. This occurs when either a dirty cache line is evicted from L1 data cache and allocated in the L2 cache or dirty data is written to the L2 and possibly to the next level of cache. This event counts both victim cache line evictions and cache write-backs from snoops or cache maintenance operations. The following cache operations are not counted:\n\n1. Invalidations which do not result in data being transferred out of the L1 (such as evictions of clean data),\n2. Full line writes which write to L2 without writing L1, such as write streaming mode." + }, + { + "ArchStdEvent": "L1D_CACHE_LMISS_RD", + "PublicDescription": "Counts cache line refills into the level 1 data cache from any memory read operations, that incurred additional latency." + }, + { + "ArchStdEvent": "L1D_CACHE_RD", + "PublicDescription": "Counts level 1 data cache accesses from any load operation. Atomic load operations that resolve in the CPUs caches counts as both a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_WR", + "PublicDescription": "Counts level 1 data cache accesses generated by store operations. This event also counts accesses caused by a DC ZVA (data cache zero, specified by virtual address) instruction. Near atomic operations that resolve in the CPUs caches count as a write access and read access." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_RD", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed load instructions where the memory read operation misses in the level 1 data cache. This event only counts one event per cache line." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_WR", + "PublicDescription": "Counts level 1 data cache refills caused by speculatively executed store instructions where the memory write operation misses in the level 1 data cache. This event only counts one event per cache line." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_INNER", + "PublicDescription": "Counts level 1 data cache refills where the cache line data came from caches inside the immediate cluster of the core." + }, + { + "ArchStdEvent": "L1D_CACHE_REFILL_OUTER", + "PublicDescription": "Counts level 1 data cache refills for which the cache line data came from outside the immediate cluster of the core, like an SLC in the system interconnect or DRAM." + }, + { + "ArchStdEvent": "L1D_CACHE_WB_VICTIM", + "PublicDescription": "Counts dirty cache line evictions from the level 1 data cache caused by a new cache line allocation. This event does not count evictions caused by cache maintenance operations." + }, + { + "ArchStdEvent": "L1D_CACHE_WB_CLEAN", + "PublicDescription": "Counts write-backs from the level 1 data cache that are a result of a coherency operation made by another CPU. Event count includes cache maintenance operations." + }, + { + "ArchStdEvent": "L1D_CACHE_INVAL", + "PublicDescription": "Counts each explicit invalidation of a cache line in the level 1 data cache caused by:\n\n- Cache Maintenance Operations (CMO) that operate by a virtual address.\n- Broadcast cache coherency operations from another CPU in the system.\n\nThis event does not count for the following conditions:\n\n1. A cache refill invalidates a cache line.\n2. A CMO which is executed on that CPU and invalidates a cache line specified by set/way.\n\nNote that CMOs that operate by set/way cannot be broadcast from one CPU to another." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l1i_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l1i_cache.json new file mode 100644 index 000000000000..633f1030359d --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l1i_cache.json @@ -0,0 +1,14 @@ +[ + { + "ArchStdEvent": "L1I_CACHE_REFILL", + "PublicDescription": "Counts cache line refills in the level 1 instruction cache caused by a missed instruction fetch. Instruction fetches may include accessing multiple instructions, but the single cache line allocation is counted once." + }, + { + "ArchStdEvent": "L1I_CACHE", + "PublicDescription": "Counts instruction fetches which access the level 1 instruction cache. Instruction cache accesses caused by cache maintenance operations are not counted." + }, + { + "ArchStdEvent": "L1I_CACHE_LMISS", + "PublicDescription": "Counts cache line refills into the level 1 instruction cache, that incurred additional latency." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l2_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l2_cache.json new file mode 100644 index 000000000000..0e31d0daf88b --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l2_cache.json @@ -0,0 +1,50 @@ +[ + { + "ArchStdEvent": "L2D_CACHE", + "PublicDescription": "Counts level 2 cache accesses. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the first level caches or translation resolutions due to accesses. This event also counts write back of dirty data from level 1 data cache to the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL", + "PublicDescription": "Counts cache line refills into the level 2 cache. level 2 cache is a unified cache for data and instruction accesses. Accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WB", + "PublicDescription": "Counts write-backs of data from the L2 cache to outside the CPU. This includes snoops to the L2 (from other CPUs) which return data even if the snoops cause an invalidation. L2 cache line invalidations which do not write data outside the CPU and snoops which return data from an L1 cache are not counted. Data would not be written outside the cache when invalidating a clean cache line." + }, + { + "ArchStdEvent": "L2D_CACHE_ALLOCATE", + "PublicDescription": "TBD" + }, + { + "ArchStdEvent": "L2D_CACHE_RD", + "PublicDescription": "Counts level 2 cache accesses due to memory read operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WR", + "PublicDescription": "Counts level 2 cache accesses due to memory write operations. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_RD", + "PublicDescription": "Counts refills for memory accesses due to memory read operation counted by L2D_CACHE_RD. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_REFILL_WR", + "PublicDescription": "Counts refills for memory accesses due to memory write operation counted by L2D_CACHE_WR. level 2 cache is a unified cache for data and instruction accesses, accesses are for misses in the level 1 caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_VICTIM", + "PublicDescription": "Counts evictions from the level 2 cache because of a line being allocated into the L2 cache." + }, + { + "ArchStdEvent": "L2D_CACHE_WB_CLEAN", + "PublicDescription": "Counts write-backs from the level 2 cache that are a result of either:\n\n1. Cache maintenance operations,\n\n2. Snoop responses or,\n\n3. Direct cache transfers to another CPU due to a forwarding snoop request." + }, + { + "ArchStdEvent": "L2D_CACHE_INVAL", + "PublicDescription": "Counts each explicit invalidation of a cache line in the level 2 cache by cache maintenance operations that operate by a virtual address, or by external coherency operations. This event does not count if either:\n\n1. A cache refill invalidates a cache line or,\n2. A Cache Maintenance Operation (CMO), which invalidates a cache line specified by set/way, is executed on that CPU.\n\nCMOs that operate by set/way cannot be broadcast from one CPU to another." + }, + { + "ArchStdEvent": "L2D_CACHE_LMISS_RD", + "PublicDescription": "Counts cache line refills into the level 2 unified cache from any memory read operations that incurred additional latency." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l3_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l3_cache.json new file mode 100644 index 000000000000..45bfba532df7 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/l3_cache.json @@ -0,0 +1,22 @@ +[ + { + "ArchStdEvent": "L3D_CACHE_ALLOCATE", + "PublicDescription": "Counts level 3 cache line allocates that do not fetch data from outside the level 3 data or unified cache. For example, allocates due to streaming stores." + }, + { + "ArchStdEvent": "L3D_CACHE_REFILL", + "PublicDescription": "Counts level 3 accesses that receive data from outside the L3 cache." + }, + { + "ArchStdEvent": "L3D_CACHE", + "PublicDescription": "Counts level 3 cache accesses. level 3 cache is a unified cache for data and instruction accesses. Accesses are for misses in the lower level caches or translation resolutions due to accesses." + }, + { + "ArchStdEvent": "L3D_CACHE_RD", + "PublicDescription": "TBD" + }, + { + "ArchStdEvent": "L3D_CACHE_LMISS_RD", + "PublicDescription": "Counts any cache line refill into the level 3 cache from memory read operations that incurred additional latency." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/ll_cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/ll_cache.json new file mode 100644 index 000000000000..bb712d57d58a --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/ll_cache.json @@ -0,0 +1,10 @@ +[ + { + "ArchStdEvent": "LL_CACHE_RD", + "PublicDescription": "Counts read transactions that were returned from outside the core cluster. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are either hit in the system level cache or missed in the SLC and are returned from any other external sources." + }, + { + "ArchStdEvent": "LL_CACHE_MISS_RD", + "PublicDescription": "Counts read transactions that were returned from outside the core cluster but missed in the system level cache. This event counts when the system register CPUECTLR.EXTLLC bit is set. This event counts read transactions returned from outside the core if those transactions are missed in the System level Cache. The data source of the transaction is indicated by a field in the CHI transaction returning to the CPU. This event does not count reads caused by cache maintenance operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/memory.json index 5aff6e93c1ad..9041f6e0befb 100644 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/memory.json +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/memory.json @@ -1,23 +1,22 @@ [ { - "ArchStdEvent": "MEM_ACCESS" + "ArchStdEvent": "MEM_ACCESS", + "PublicDescription": "Counts memory accesses issued by the CPU load store unit, where those accesses are issued due to load or store operations. This event counts memory accesses no matter whether the data is received from any level of cache hierarchy or external memory. If memory accesses are broken up into smaller transactions than what were specified in the load or store instructions, then the event counts those smaller memory transactions." }, { - "ArchStdEvent": "REMOTE_ACCESS" + "ArchStdEvent": "MEMORY_ERROR", + "PublicDescription": "Counts any detected correctable or uncorrectable physical memory errors (ECC or parity) in protected CPUs RAMs. On the core, this event counts errors in the caches (including data and tag rams). Any detected memory error (from either a speculative and abandoned access, or an architecturally executed access) is counted. Note that errors are only detected when the actual protected memory is accessed by an operation." }, { - "ArchStdEvent": "MEM_ACCESS_RD" + "ArchStdEvent": "REMOTE_ACCESS", + "PublicDescription": "Counts accesses to another chip, which is implemented as a different CMN mesh in the system. If the CHI bus response back to the core indicates that the data source is from another chip (mesh), then the counter is updated. If no data is returned, even if the system snoops another chip/mesh, then the counter is not updated." }, { - "ArchStdEvent": "MEM_ACCESS_WR" + "ArchStdEvent": "MEM_ACCESS_RD", + "PublicDescription": "Counts memory accesses issued by the CPU due to load operations. The event counts any memory load access, no matter whether the data is received from any level of cache hierarchy or external memory. The event also counts atomic load operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions." }, { - "ArchStdEvent": "UNALIGNED_LD_SPEC" - }, - { - "ArchStdEvent": "UNALIGNED_ST_SPEC" - }, - { - "ArchStdEvent": "UNALIGNED_LDST_SPEC" + "ArchStdEvent": "MEM_ACCESS_WR", + "PublicDescription": "Counts memory accesses issued by the CPU due to store operations. The event counts any memory store access, no matter whether the data is located in any level of cache or external memory. The event also counts atomic load and store operations. If memory accesses are broken up by the load/store unit into smaller transactions that are issued by the bus interface, then the event counts those smaller transactions." } ] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/metrics.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/metrics.json new file mode 100644 index 000000000000..3fd8fefec46a --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/metrics.json @@ -0,0 +1,233 @@ +[ + { + "ArchStdEvent": "backend_bound" + }, + { + "MetricName": "backend_stalled_cycles", + "MetricExpr": "((STALL_BACKEND / CPU_CYCLES) * 100)", + "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the backend unit of the processor.", + "MetricGroup": "Cycle_Accounting", + "ScaleUnit": "1percent of cycles" + }, + { + "ArchStdEvent": "bad_speculation", + "MetricExpr": "(100 * (((1 - (OP_RETIRED / OP_SPEC)) * (1 - (STALL_SLOT / (CPU_CYCLES * 8)))) + ((BR_MIS_PRED * 4) / CPU_CYCLES)))" + }, + { + "MetricName": "branch_misprediction_ratio", + "MetricExpr": "(BR_MIS_PRED_RETIRED / BR_RETIRED)", + "BriefDescription": "This metric measures the ratio of branches mispredicted to the total number of branches architecturally executed. This gives an indication of the effectiveness of the branch prediction unit.", + "MetricGroup": "Miss_Ratio;Branch_Effectiveness", + "ScaleUnit": "1per branch" + }, + { + "MetricName": "branch_mpki", + "MetricExpr": "((BR_MIS_PRED_RETIRED / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of branch mispredictions per thousand instructions executed.", + "MetricGroup": "MPKI;Branch_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "branch_percentage", + "MetricExpr": "(((BR_IMMED_SPEC + BR_INDIRECT_SPEC) / INST_SPEC) * 100)", + "BriefDescription": "This metric measures branch operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "crypto_percentage", + "MetricExpr": "((CRYPTO_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures crypto operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "dtlb_mpki", + "MetricExpr": "((DTLB_WALK / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of data TLB Walks per thousand instructions executed.", + "MetricGroup": "MPKI;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "dtlb_walk_ratio", + "MetricExpr": "(DTLB_WALK / L1D_TLB)", + "BriefDescription": "This metric measures the ratio of data TLB Walks to the total number of data TLB accesses. This gives an indication of the effectiveness of the data TLB accesses.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "ArchStdEvent": "frontend_bound", + "MetricExpr": "(100 * ((STALL_SLOT_FRONTEND / (CPU_CYCLES * 8)) - ((BR_MIS_PRED * 4) / CPU_CYCLES)))" + }, + { + "MetricName": "frontend_stalled_cycles", + "MetricExpr": "((STALL_FRONTEND / CPU_CYCLES) * 100)", + "BriefDescription": "This metric is the percentage of cycles that were stalled due to resource constraints in the frontend unit of the processor.", + "MetricGroup": "Cycle_Accounting", + "ScaleUnit": "1percent of cycles" + }, + { + "MetricName": "integer_dp_percentage", + "MetricExpr": "((DP_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures scalar integer operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "ipc", + "MetricExpr": "(INST_RETIRED / CPU_CYCLES)", + "BriefDescription": "This metric measures the number of instructions retired per cycle.", + "MetricGroup": "General", + "ScaleUnit": "1per cycle" + }, + { + "MetricName": "itlb_mpki", + "MetricExpr": "((ITLB_WALK / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of instruction TLB Walks per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "itlb_walk_ratio", + "MetricExpr": "(ITLB_WALK / L1I_TLB)", + "BriefDescription": "This metric measures the ratio of instruction TLB Walks to the total number of instruction TLB accesses. This gives an indication of the effectiveness of the instruction TLB accesses.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "l1d_cache_miss_ratio", + "MetricExpr": "(L1D_CACHE_REFILL / L1D_CACHE)", + "BriefDescription": "This metric measures the ratio of level 1 data cache accesses missed to the total number of level 1 data cache accesses. This gives an indication of the effectiveness of the level 1 data cache.", + "MetricGroup": "Miss_Ratio;L1D_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "l1d_cache_mpki", + "MetricExpr": "((L1D_CACHE_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 data cache accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;L1D_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1d_tlb_miss_ratio", + "MetricExpr": "(L1D_TLB_REFILL / L1D_TLB)", + "BriefDescription": "This metric measures the ratio of level 1 data TLB accesses missed to the total number of level 1 data TLB accesses. This gives an indication of the effectiveness of the level 1 data TLB.", + "MetricGroup": "Miss_Ratio;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "l1d_tlb_mpki", + "MetricExpr": "((L1D_TLB_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1i_cache_miss_ratio", + "MetricExpr": "(L1I_CACHE_REFILL / L1I_CACHE)", + "BriefDescription": "This metric measures the ratio of level 1 instruction cache accesses missed to the total number of level 1 instruction cache accesses. This gives an indication of the effectiveness of the level 1 instruction cache.", + "MetricGroup": "Miss_Ratio;L1I_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "l1i_cache_mpki", + "MetricExpr": "((L1I_CACHE_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 instruction cache accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;L1I_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l1i_tlb_miss_ratio", + "MetricExpr": "(L1I_TLB_REFILL / L1I_TLB)", + "BriefDescription": "This metric measures the ratio of level 1 instruction TLB accesses missed to the total number of level 1 instruction TLB accesses. This gives an indication of the effectiveness of the level 1 instruction TLB.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "l1i_tlb_mpki", + "MetricExpr": "((L1I_TLB_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 1 instruction TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l2_cache_miss_ratio", + "MetricExpr": "(L2D_CACHE_REFILL / L2D_CACHE)", + "BriefDescription": "This metric measures the ratio of level 2 cache accesses missed to the total number of level 2 cache accesses. This gives an indication of the effectiveness of the level 2 cache, which is a unified cache that stores both data and instruction. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "Miss_Ratio;L2_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "l2_cache_mpki", + "MetricExpr": "((L2D_CACHE_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 2 unified cache accesses missed per thousand instructions executed. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a unified cache.", + "MetricGroup": "MPKI;L2_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "l2_tlb_miss_ratio", + "MetricExpr": "(L2D_TLB_REFILL / L2D_TLB)", + "BriefDescription": "This metric measures the ratio of level 2 unified TLB accesses missed to the total number of level 2 unified TLB accesses. This gives an indication of the effectiveness of the level 2 TLB.", + "MetricGroup": "Miss_Ratio;ITLB_Effectiveness;DTLB_Effectiveness", + "ScaleUnit": "1per TLB access" + }, + { + "MetricName": "l2_tlb_mpki", + "MetricExpr": "((L2D_TLB_REFILL / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of level 2 unified TLB accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;ITLB_Effectiveness;DTLB_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "ll_cache_read_hit_ratio", + "MetricExpr": "((LL_CACHE_RD - LL_CACHE_MISS_RD) / LL_CACHE_RD)", + "BriefDescription": "This metric measures the ratio of last level cache read accesses hit in the cache to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", + "MetricGroup": "LL_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "ll_cache_read_miss_ratio", + "MetricExpr": "(LL_CACHE_MISS_RD / LL_CACHE_RD)", + "BriefDescription": "This metric measures the ratio of last level cache read accesses missed to the total number of last level cache accesses. This gives an indication of the effectiveness of the last level cache for read traffic. Note that cache accesses in this cache are either data memory access or instruction fetch as this is a system level cache.", + "MetricGroup": "Miss_Ratio;LL_Cache_Effectiveness", + "ScaleUnit": "1per cache access" + }, + { + "MetricName": "ll_cache_read_mpki", + "MetricExpr": "((LL_CACHE_MISS_RD / INST_RETIRED) * 1000)", + "BriefDescription": "This metric measures the number of last level cache read accesses missed per thousand instructions executed.", + "MetricGroup": "MPKI;LL_Cache_Effectiveness", + "ScaleUnit": "1MPKI" + }, + { + "MetricName": "load_percentage", + "MetricExpr": "((LD_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures load operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "ArchStdEvent": "retiring" + }, + { + "MetricName": "scalar_fp_percentage", + "MetricExpr": "((VFP_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures scalar floating point operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "simd_percentage", + "MetricExpr": "((ASE_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures advanced SIMD operations as a percentage of total operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + }, + { + "MetricName": "store_percentage", + "MetricExpr": "((ST_SPEC / INST_SPEC) * 100)", + "BriefDescription": "This metric measures store operations as a percentage of operations speculatively executed.", + "MetricGroup": "Operation_Mix", + "ScaleUnit": "1percent of operations" + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/pipeline.json deleted file mode 100644 index f9fae15f7555..000000000000 --- a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/pipeline.json +++ /dev/null @@ -1,23 +0,0 @@ -[ - { - "ArchStdEvent": "STALL_FRONTEND" - }, - { - "ArchStdEvent": "STALL_BACKEND" - }, - { - "ArchStdEvent": "STALL" - }, - { - "ArchStdEvent": "STALL_SLOT_BACKEND" - }, - { - "ArchStdEvent": "STALL_SLOT_FRONTEND" - }, - { - "ArchStdEvent": "STALL_SLOT" - }, - { - "ArchStdEvent": "STALL_BACKEND_MEM" - } -] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/retired.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/retired.json new file mode 100644 index 000000000000..f297b049b62f --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/retired.json @@ -0,0 +1,30 @@ +[ + { + "ArchStdEvent": "SW_INCR", + "PublicDescription": "Counts software writes to the PMSWINC_EL0 (software PMU increment) register. The PMSWINC_EL0 register is a manually updated counter for use by application software.\n\nThis event could be used to measure any user program event, such as accesses to a particular data structure (by writing to the PMSWINC_EL0 register each time the data structure is accessed).\n\nTo use the PMSWINC_EL0 register and event, developers must insert instructions that write to the PMSWINC_EL0 register into the source code.\n\nSince the SW_INCR event records writes to the PMSWINC_EL0 register, there is no need to do a read/increment/write sequence to the PMSWINC_EL0 register." + }, + { + "ArchStdEvent": "INST_RETIRED", + "PublicDescription": "Counts instructions that have been architecturally executed." + }, + { + "ArchStdEvent": "CID_WRITE_RETIRED", + "PublicDescription": "Counts architecturally executed writes to the CONTEXTIDR register, which usually contain the kernel PID and can be output with hardware trace." + }, + { + "ArchStdEvent": "TTBR_WRITE_RETIRED", + "PublicDescription": "Counts architectural writes to TTBR0/1_EL1. If virtualization host extensions are enabled (by setting the HCR_EL2.E2H bit to 1), then accesses to TTBR0/1_EL1 that are redirected to TTBR0/1_EL2, or accesses to TTBR0/1_EL12, are counted. TTBRn registers are typically updated when the kernel is swapping user-space threads or applications." + }, + { + "ArchStdEvent": "BR_RETIRED", + "PublicDescription": "Counts architecturally executed branches, whether the branch is taken or not. Instructions that explicitly write to the PC are also counted." + }, + { + "ArchStdEvent": "BR_MIS_PRED_RETIRED", + "PublicDescription": "Counts branches counted by BR_RETIRED which were mispredicted and caused a pipeline flush." + }, + { + "ArchStdEvent": "OP_RETIRED", + "PublicDescription": "Counts micro-operations that are architecturally executed. This is a count of number of micro-operations retired from the commit queue in a single cycle." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/spe.json new file mode 100644 index 000000000000..5de8b0f3a440 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/spe.json @@ -0,0 +1,18 @@ +[ + { + "ArchStdEvent": "SAMPLE_POP", + "PublicDescription": "Counts statistical profiling sample population, the count of all operations that could be sampled but may or may not be chosen for sampling." + }, + { + "ArchStdEvent": "SAMPLE_FEED", + "PublicDescription": "Counts statistical profiling samples taken for sampling." + }, + { + "ArchStdEvent": "SAMPLE_FILTRATE", + "PublicDescription": "Counts statistical profiling samples taken which are not removed by filtering." + }, + { + "ArchStdEvent": "SAMPLE_COLLISION", + "PublicDescription": "Counts statistical profiling samples that have collided with a previous sample and so therefore not taken." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/spec_operation.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/spec_operation.json new file mode 100644 index 000000000000..1af961f8a6c8 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/spec_operation.json @@ -0,0 +1,110 @@ +[ + { + "ArchStdEvent": "BR_MIS_PRED", + "PublicDescription": "Counts branches which are speculatively executed and mispredicted." + }, + { + "ArchStdEvent": "BR_PRED", + "PublicDescription": "Counts branches speculatively executed and were predicted right." + }, + { + "ArchStdEvent": "INST_SPEC", + "PublicDescription": "Counts operations that have been speculatively executed." + }, + { + "ArchStdEvent": "OP_SPEC", + "PublicDescription": "Counts micro-operations speculatively executed. This is the count of the number of micro-operations dispatched in a cycle." + }, + { + "ArchStdEvent": "UNALIGNED_LD_SPEC", + "PublicDescription": "Counts unaligned memory read operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses. The event does not count preload operations (PLD, PLI)." + }, + { + "ArchStdEvent": "UNALIGNED_ST_SPEC", + "PublicDescription": "Counts unaligned memory write operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses." + }, + { + "ArchStdEvent": "UNALIGNED_LDST_SPEC", + "PublicDescription": "Counts unaligned memory operations issued by the CPU. This event counts unaligned accesses (as defined by the actual instruction), even if they are subsequently issued as multiple aligned accesses." + }, + { + "ArchStdEvent": "LDREX_SPEC", + "PublicDescription": "Counts Load-Exclusive operations that have been speculatively executed. Eg: LDREX, LDX" + }, + { + "ArchStdEvent": "STREX_PASS_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have successfully completed the store operation." + }, + { + "ArchStdEvent": "STREX_FAIL_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed and have not successfully completed the store operation." + }, + { + "ArchStdEvent": "STREX_SPEC", + "PublicDescription": "Counts store-exclusive operations that have been speculatively executed." + }, + { + "ArchStdEvent": "LD_SPEC", + "PublicDescription": "Counts speculatively executed load operations including Single Instruction Multiple Data (SIMD) load operations." + }, + { + "ArchStdEvent": "ST_SPEC", + "PublicDescription": "Counts speculatively executed store operations including Single Instruction Multiple Data (SIMD) store operations." + }, + { + "ArchStdEvent": "DP_SPEC", + "PublicDescription": "Counts speculatively executed logical or arithmetic instructions such as MOV/MVN operations." + }, + { + "ArchStdEvent": "ASE_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD operations excluding load, store and move micro-operations that move data to or from SIMD (vector) registers." + }, + { + "ArchStdEvent": "VFP_SPEC", + "PublicDescription": "Counts speculatively executed floating point operations. This event does not count operations that move data to or from floating point (vector) registers." + }, + { + "ArchStdEvent": "PC_WRITE_SPEC", + "PublicDescription": "Counts speculatively executed operations which cause software changes of the PC. Those operations include all taken branch operations." + }, + { + "ArchStdEvent": "CRYPTO_SPEC", + "PublicDescription": "Counts speculatively executed cryptographic operations except for PMULL and VMULL operations." + }, + { + "ArchStdEvent": "BR_IMMED_SPEC", + "PublicDescription": "Counts immediate branch operations which are speculatively executed." + }, + { + "ArchStdEvent": "BR_RETURN_SPEC", + "PublicDescription": "Counts procedure return operations (RET) which are speculatively executed." + }, + { + "ArchStdEvent": "BR_INDIRECT_SPEC", + "PublicDescription": "Counts indirect branch operations including procedure returns, which are speculatively executed. This includes operations that force a software change of the PC, other than exception-generating operations. Eg: BR Xn, RET" + }, + { + "ArchStdEvent": "ISB_SPEC", + "PublicDescription": "Counts ISB operations that are executed." + }, + { + "ArchStdEvent": "DSB_SPEC", + "PublicDescription": "Counts DSB operations that are speculatively issued to Load/Store unit in the CPU." + }, + { + "ArchStdEvent": "DMB_SPEC", + "PublicDescription": "Counts DMB operations that are speculatively issued to the Load/Store unit in the CPU. This event does not count implied barriers from load acquire/store release operations." + }, + { + "ArchStdEvent": "RC_LD_SPEC", + "PublicDescription": "Counts any load acquire operations that are speculatively executed. Eg: LDAR, LDARH, LDARB" + }, + { + "ArchStdEvent": "RC_ST_SPEC", + "PublicDescription": "Counts any store release operations that are speculatively executed. Eg: STLR, STLRH, STLRB'" + }, + { + "ArchStdEvent": "ASE_INST_SPEC", + "PublicDescription": "Counts speculatively executed Advanced SIMD operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/stall.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/stall.json new file mode 100644 index 000000000000..bbbebc805034 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/stall.json @@ -0,0 +1,30 @@ +[ + { + "ArchStdEvent": "STALL_FRONTEND", + "PublicDescription": "Counts cycles when frontend could not send any micro-operations to the rename stage because of frontend resource stalls caused by fetch memory latency or branch prediction flow stalls. All the frontend slots were empty during the cycle when this event counts." + }, + { + "ArchStdEvent": "STALL_BACKEND", + "PublicDescription": "Counts cycles whenever the rename unit is unable to send any micro-operations to the backend of the pipeline because of backend resource constraints. Backend resource constraints can include issue stage fullness, execution stage fullness, or other internal pipeline resource fullness. All the backend slots were empty during the cycle when this event counts." + }, + { + "ArchStdEvent": "STALL", + "PublicDescription": "Counts cycles when no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall)." + }, + { + "ArchStdEvent": "STALL_SLOT_BACKEND", + "PublicDescription": "Counts slots per cycle in which no operations are sent from the rename unit to the backend due to backend resource constraints." + }, + { + "ArchStdEvent": "STALL_SLOT_FRONTEND", + "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend due to frontend resource constraints." + }, + { + "ArchStdEvent": "STALL_SLOT", + "PublicDescription": "Counts slots per cycle in which no operations are sent to the rename unit from the frontend or from the rename unit to the backend for any reason (either frontend or backend stall)." + }, + { + "ArchStdEvent": "STALL_BACKEND_MEM", + "PublicDescription": "Counts cycles when the backend is stalled because there is a pending demand load request in progress in the last level core cache." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/sve.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/sve.json new file mode 100644 index 000000000000..5137e2075a76 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/sve.json @@ -0,0 +1,30 @@ +[ + { + "ArchStdEvent": "SVE_INST_SPEC", + "PublicDescription": "Counts speculatively executed operations that are SVE operations." + }, + { + "ArchStdEvent": "SVE_PRED_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations." + }, + { + "ArchStdEvent": "SVE_PRED_EMPTY_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with no active predicate elements." + }, + { + "ArchStdEvent": "SVE_PRED_FULL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with all predicate elements active." + }, + { + "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC", + "PublicDescription": "Counts speculatively executed predicated SVE operations with at least one but not all active predicate elements." + }, + { + "ArchStdEvent": "SVE_LDFF_SPEC", + "PublicDescription": "Counts speculatively executed SVE first fault or non-fault load operations." + }, + { + "ArchStdEvent": "SVE_LDFF_FAULT_SPEC", + "PublicDescription": "Counts speculatively executed SVE first fault or non-fault load operations that clear at least one bit in the FFR." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/tlb.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/tlb.json new file mode 100644 index 000000000000..b550af1831f5 --- /dev/null +++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-v1/tlb.json @@ -0,0 +1,66 @@ +[ + { + "ArchStdEvent": "L1I_TLB_REFILL", + "PublicDescription": "Counts level 1 instruction TLB refills from any Instruction fetch. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL", + "PublicDescription": "Counts level 1 data TLB accesses that resulted in TLB refills. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an AT(address translation) instruction." + }, + { + "ArchStdEvent": "L1D_TLB", + "PublicDescription": "Counts level 1 data TLB accesses caused by any memory load or store operation. Note that load or store instructions can be broken up into multiple memory operations. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1I_TLB", + "PublicDescription": "Counts level 1 instruction TLB accesses, whether the access hits or misses in the TLB. This event counts both demand accesses and prefetch or preload generated accesses." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL", + "PublicDescription": "Counts level 2 TLB refills caused by memory operations from both data and instruction fetch, except for those caused by TLB maintenance operations and hardware prefetches." + }, + { + "ArchStdEvent": "L2D_TLB", + "PublicDescription": "Counts level 2 TLB accesses except those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "DTLB_WALK", + "PublicDescription": "Counts data memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Note that partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "ITLB_WALK", + "PublicDescription": "Counts instruction memory translation table walks caused by a miss in the L2 TLB driven by a memory access. Partial translations that also cause a table walk are counted. This event does not count table walks caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_RD", + "PublicDescription": "Counts level 1 data TLB refills caused by memory read operations. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the translation table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count on an access from an Address Translation (AT) instruction." + }, + { + "ArchStdEvent": "L1D_TLB_REFILL_WR", + "PublicDescription": "Counts level 1 data TLB refills caused by data side memory write operations. If there are multiple misses in the TLB that are resolved by the refill, then this event only counts once. This event counts for refills caused by preload instructions or hardware prefetch accesses. This event counts regardless of whether the miss hits in L2 or results in a translation table walk. This event will not count if the table walk results in a fault (such as a translation or access fault), since there is no new translation created for the TLB. This event will not count with an access from an Address Translation (AT) instruction." + }, + { + "ArchStdEvent": "L1D_TLB_RD", + "PublicDescription": "Counts level 1 data TLB accesses caused by memory read operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L1D_TLB_WR", + "PublicDescription": "Counts any L1 data side TLB accesses caused by memory write operations. This event counts whether the access hits or misses in the TLB. This event does not count TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_RD", + "PublicDescription": "Counts level 2 TLB refills caused by memory read operations from both data and instruction fetch except for those caused by TLB maintenance operations or hardware prefetches." + }, + { + "ArchStdEvent": "L2D_TLB_REFILL_WR", + "PublicDescription": "Counts level 2 TLB refills caused by memory write operations from both data and instruction fetch except for those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_RD", + "PublicDescription": "Counts level 2 TLB accesses caused by memory read operations from both data and instruction fetch except for those caused by TLB maintenance operations." + }, + { + "ArchStdEvent": "L2D_TLB_WR", + "PublicDescription": "Counts level 2 TLB accesses caused by memory write operations from both data and instruction fetch except for those caused by TLB maintenance operations." + } +] diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv index 32674ddd2b63..5b58db5032c1 100644 --- a/tools/perf/pmu-events/arch/arm64/mapfile.csv +++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv @@ -4,7 +4,7 @@ # where # MIDR Processor version # Variant[23:20] and Revision [3:0] should be zero. -# Version could be used to track version of of JSON file +# Version could be used to track version of JSON file # but currently unused. # JSON/file/pathname is the path to JSON file, relative # to tools/perf/pmu-events/arch/arm64/. diff --git a/tools/perf/pmu-events/arch/nds32/mapfile.csv b/tools/perf/pmu-events/arch/nds32/mapfile.csv index efb395f26883..c76e5fbdac23 100644 --- a/tools/perf/pmu-events/arch/nds32/mapfile.csv +++ b/tools/perf/pmu-events/arch/nds32/mapfile.csv @@ -4,7 +4,7 @@ # where # MIDR Processor version # Variant[23:20] and Revision [3:0] should be zero. -# Version could be used to track version of of JSON file +# Version could be used to track version of JSON file # but currently unused. # JSON/file/pathname is the path to JSON file, relative # to tools/perf/pmu-events/arch/arm64/. diff --git a/tools/perf/pmu-events/arch/powerpc/mapfile.csv b/tools/perf/pmu-events/arch/powerpc/mapfile.csv index 4abdfc3f9692..f4908af7ad66 100644 --- a/tools/perf/pmu-events/arch/powerpc/mapfile.csv +++ b/tools/perf/pmu-events/arch/powerpc/mapfile.csv @@ -3,7 +3,7 @@ # # where # PVR Processor version -# Version could be used to track version of of JSON file +# Version could be used to track version of JSON file # but currently unused. # JSON/file/pathname is the path to JSON file, relative # to tools/perf/pmu-events/arch/powerpc/. @@ -13,6 +13,6 @@ # # Power8 entries -004[bcd][[:xdigit:]]{4},1,power8,core -004e[[:xdigit:]]{4},1,power9,core -0080[[:xdigit:]]{4},1,power10,core +0x004[bcd][[:xdigit:]]{4},1,power8,core +0x004e[[:xdigit:]]{4},1,power9,core +0x0080[[:xdigit:]]{4},1,power10,core diff --git a/tools/perf/pmu-events/arch/powerpc/power10/datasource.json b/tools/perf/pmu-events/arch/powerpc/power10/datasource.json new file mode 100644 index 000000000000..6b0356f2d301 --- /dev/null +++ b/tools/perf/pmu-events/arch/powerpc/power10/datasource.json @@ -0,0 +1,1787 @@ +[ + { + "EventCode": "0x200FE", + "EventName": "PM_DATA_FROM_L2MISS", + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss." + }, + { + "EventCode": "0x300FE", + "EventName": "PM_DATA_FROM_L3MISS", + "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss." + }, + { + "EventCode": "0x400FE", + "EventName": "PM_DATA_FROM_MEMORY", + "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss." + }, + { + "EventCode": "0x000300000000C040", + "EventName": "PM_INST_FROM_L2", + "BriefDescription": "The processor's instruction cache was reloaded from the local core's L2 due to a demand miss." + }, + { + "EventCode": "0x000340000000C040", + "EventName": "PM_DATA_FROM_L2", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L2 due to a demand miss." + }, + { + "EventCode": "0x000300000010C040", + "EventName": "PM_INST_FROM_L2_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from the local core's L2 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x000340000020C040", + "EventName": "PM_DATA_FROM_L2_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L2 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x003F00000000C040", + "EventName": "PM_INST_FROM_L1MISS", + "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L1 due to a demand miss." + }, + { + "EventCode": "0x003F40000000C040", + "EventName": "PM_DATA_FROM_L1MISS", + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L1 due to a demand miss." + }, + { + "EventCode": "0x003F00000010C040", + "EventName": "PM_INST_FROM_L1MISS_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L1 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x003F40000020C040", + "EventName": "PM_DATA_FROM_L1MISS_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L1 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x000040000000C040", + "EventName": "PM_DATA_FROM_L2_NO_CONFLICT", + "BriefDescription": "The processor's L1 data cache was reloaded without dispatch conflicts with data NOT in the MEPF state from the local core's L2 due to a demand miss." + }, + { + "EventCode": "0x000040000020C040", + "EventName": "PM_DATA_FROM_L2_NO_CONFLICT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded without dispatch conflicts with data NOT in the MEPF state from the local core's L2 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x004040000000C040", + "EventName": "PM_DATA_FROM_L2_MEPF", + "BriefDescription": "The processor's L1 data cache was reloaded with data in the MEPF state without dispatch conflicts from the local core's L2 due to a demand miss." + }, + { + "EventCode": "0x004040000020C040", + "EventName": "PM_DATA_FROM_L2_MEPF_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with data in the MEPF state without dispatch conflicts from the local core's L2 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x008040000000C040", + "EventName": "PM_DATA_FROM_L2_LDHITST_CONFLICT", + "BriefDescription": "The processor's L1 data cache was reloaded with data that had a dispatch conflict on ld-hit-store from the local core's L2 due to a demand miss." + }, + { + "EventCode": "0x008040000020C040", + "EventName": "PM_DATA_FROM_L2_LDHITST_CONFLICT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with data that had a dispatch conflict on ld-hit-store from the local core's L2 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x00C040000000C040", + "EventName": "PM_DATA_FROM_L2_OTHER_CONFLICT", + "BriefDescription": "The processor's L1 data cache was reloaded with data that had a dispatch conflict other than ld-hit-store from the local core's L2 due to a demand miss." + }, + { + "EventCode": "0x00C040000020C040", + "EventName": "PM_DATA_FROM_L2_OTHER_CONFLICT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with data that had a dispatch conflict other than ld-hit-store from the local core's L2 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x000380000000C040", + "EventName": "PM_INST_FROM_L2MISS", + "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L2 due to a demand miss." + }, + { + "EventCode": "0x000380000010C040", + "EventName": "PM_INST_FROM_L2MISS_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L2 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0003C0000020C040", + "EventName": "PM_DATA_FROM_L2MISS_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x010300000000C040", + "EventName": "PM_INST_FROM_L3", + "BriefDescription": "The processor's instruction cache was reloaded from the local core's L3 due to a demand miss." + }, + { + "EventCode": "0x010340000000C040", + "EventName": "PM_DATA_FROM_L3", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L3 due to a demand miss." + }, + { + "EventCode": "0x010300000010C040", + "EventName": "PM_INST_FROM_L3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from the local core's L3 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x010340000020C040", + "EventName": "PM_DATA_FROM_L3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L3 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x010040000000C040", + "EventName": "PM_DATA_FROM_L3_NO_CONFLICT", + "BriefDescription": "The processor's L1 data cache was reloaded without dispatch conflicts with data NOT in the MEPF state from the local core's L3 due to a demand miss." + }, + { + "EventCode": "0x010040000020C040", + "EventName": "PM_DATA_FROM_L3_NO_CONFLICT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded without dispatch conflicts with data NOT in the MEPF state from the local core's L3 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x014040000000C040", + "EventName": "PM_DATA_FROM_L3_MEPF", + "BriefDescription": "The processor's L1 data cache was reloaded with data in the MEPF state without dispatch conflicts from the local core's L3 due to a demand miss." + }, + { + "EventCode": "0x014040000020C040", + "EventName": "PM_DATA_FROM_L3_MEPF_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with data in the MEPF state without dispatch conflicts from the local core's L3 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x01C040000000C040", + "EventName": "PM_DATA_FROM_L3_CONFLICT", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L3 due to a demand miss." + }, + { + "EventCode": "0x01C040000020C040", + "EventName": "PM_DATA_FROM_L3_CONFLICT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L3 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x000780000000C040", + "EventName": "PM_INST_FROM_L3MISS", + "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss." + }, + { + "EventCode": "0x000780000010C040", + "EventName": "PM_INST_FROM_L3MISS_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0007C0000020C040", + "EventName": "PM_DATA_FROM_L3MISS_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x080040000000C040", + "EventName": "PM_DATA_FROM_L21_REGENT_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x080040000020C040", + "EventName": "PM_DATA_FROM_L21_REGENT_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x084040000000C040", + "EventName": "PM_DATA_FROM_L21_REGENT_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x084040000020C040", + "EventName": "PM_DATA_FROM_L21_REGENT_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x080100000000C040", + "EventName": "PM_INST_FROM_L21_REGENT", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x080140000000C040", + "EventName": "PM_DATA_FROM_L21_REGENT", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x080100000010C040", + "EventName": "PM_INST_FROM_L21_REGENT_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x080140000020C040", + "EventName": "PM_DATA_FROM_L21_REGENT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x088040000000C040", + "EventName": "PM_DATA_FROM_L31_REGENT_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x088040000020C040", + "EventName": "PM_DATA_FROM_L31_REGENT_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x08C040000000C040", + "EventName": "PM_DATA_FROM_L31_REGENT_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x08C040000020C040", + "EventName": "PM_DATA_FROM_L31_REGENT_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x088100000000C040", + "EventName": "PM_INST_FROM_L31_REGENT", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x088140000000C040", + "EventName": "PM_DATA_FROM_L31_REGENT", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x088100000010C040", + "EventName": "PM_INST_FROM_L31_REGENT_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x088140000020C040", + "EventName": "PM_DATA_FROM_L31_REGENT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x080240000000C040", + "EventName": "PM_DATA_FROM_REGENT_L2L3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x080240000020C040", + "EventName": "PM_DATA_FROM_REGENT_L2L3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x084240000000C040", + "EventName": "PM_DATA_FROM_REGENT_L2L3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x084240000020C040", + "EventName": "PM_DATA_FROM_REGENT_L2L3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x080300000000C040", + "EventName": "PM_INST_FROM_REGENT_L2L3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x080340000000C040", + "EventName": "PM_DATA_FROM_REGENT_L2L3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 on the same chip in the same regent due to a demand miss." + }, + { + "EventCode": "0x080300000010C040", + "EventName": "PM_INST_FROM_REGENT_L2L3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x080340000020C040", + "EventName": "PM_DATA_FROM_REGENT_L2L3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 on the same chip in the same regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A0040000000C040", + "EventName": "PM_DATA_FROM_L21_NON_REGENT_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A0040000020C040", + "EventName": "PM_DATA_FROM_L21_NON_REGENT_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A4040000000C040", + "EventName": "PM_DATA_FROM_L21_NON_REGENT_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A4040000020C040", + "EventName": "PM_DATA_FROM_L21_NON_REGENT_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A0100000000C040", + "EventName": "PM_INST_FROM_L21_NON_REGENT", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A0140000000C040", + "EventName": "PM_DATA_FROM_L21_NON_REGENT", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A0100000010C040", + "EventName": "PM_INST_FROM_L21_NON_REGENT_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A0140000020C040", + "EventName": "PM_DATA_FROM_L21_NON_REGENT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A8040000000C040", + "EventName": "PM_DATA_FROM_L31_NON_REGENT_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A8040000020C040", + "EventName": "PM_DATA_FROM_L31_NON_REGENT_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0AC040000000C040", + "EventName": "PM_DATA_FROM_L31_NON_REGENT_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0AC040000020C040", + "EventName": "PM_DATA_FROM_L31_NON_REGENT_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A8100000000C040", + "EventName": "PM_INST_FROM_L31_NON_REGENT", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A8140000000C040", + "EventName": "PM_DATA_FROM_L31_NON_REGENT", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A8100000010C040", + "EventName": "PM_INST_FROM_L31_NON_REGENT_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A8140000020C040", + "EventName": "PM_DATA_FROM_L31_NON_REGENT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A0240000000C040", + "EventName": "PM_DATA_FROM_NON_REGENT_L2L3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A0240000020C040", + "EventName": "PM_DATA_FROM_NON_REGENT_L2L3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A4240000000C040", + "EventName": "PM_DATA_FROM_NON_REGENT_L2L3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A4240000020C040", + "EventName": "PM_DATA_FROM_NON_REGENT_L2L3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A0300000000C040", + "EventName": "PM_INST_FROM_NON_REGENT_L2L3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A0340000000C040", + "EventName": "PM_DATA_FROM_NON_REGENT_L2L3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 on the same chip in a different regent due to a demand miss." + }, + { + "EventCode": "0x0A0300000010C040", + "EventName": "PM_INST_FROM_NON_REGENT_L2L3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0A0340000020C040", + "EventName": "PM_DATA_FROM_NON_REGENT_L2L3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 on the same chip in a different regent due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x094100000000C040", + "EventName": "PM_INST_FROM_LMEM", + "BriefDescription": "The processor's instruction cache was reloaded from the local chip's memory due to a demand miss." + }, + { + "EventCode": "0x094040000000C040", + "EventName": "PM_DATA_FROM_LMEM", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's memory due to a demand miss." + }, + { + "EventCode": "0x094100000010C040", + "EventName": "PM_INST_FROM_LMEM_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from the local chip's memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x094040000020C040", + "EventName": "PM_DATA_FROM_LMEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x098040000000C040", + "EventName": "PM_DATA_FROM_L_OC_CACHE", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI cache due to a demand miss." + }, + { + "EventCode": "0x098040000020C040", + "EventName": "PM_DATA_FROM_L_OC_CACHE_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI cache due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x09C040000000C040", + "EventName": "PM_DATA_FROM_L_OC_MEM", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI memory due to a demand miss." + }, + { + "EventCode": "0x09C040000020C040", + "EventName": "PM_DATA_FROM_L_OC_MEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x098100000000C040", + "EventName": "PM_INST_FROM_L_OC_ANY", + "BriefDescription": "The processor's instruction cache was reloaded from the local chip's OpenCAPI cache or memory due to a demand miss." + }, + { + "EventCode": "0x098140000000C040", + "EventName": "PM_DATA_FROM_L_OC_ANY", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI cache or memory due to a demand miss." + }, + { + "EventCode": "0x098100000010C040", + "EventName": "PM_INST_FROM_L_OC_ANY_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from the local chip's OpenCAPI cache or memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x098140000020C040", + "EventName": "PM_DATA_FROM_L_OC_ANY_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI cache or memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C0040000000C040", + "EventName": "PM_DATA_FROM_RL2_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C0040000020C040", + "EventName": "PM_DATA_FROM_RL2_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C4040000000C040", + "EventName": "PM_DATA_FROM_RL2_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C4040000020C040", + "EventName": "PM_DATA_FROM_RL2_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C0100000000C040", + "EventName": "PM_INST_FROM_RL2", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C0140000000C040", + "EventName": "PM_DATA_FROM_RL2", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C0100000010C040", + "EventName": "PM_INST_FROM_RL2_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C0140000020C040", + "EventName": "PM_DATA_FROM_RL2_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C8040000000C040", + "EventName": "PM_DATA_FROM_RL3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C8040000020C040", + "EventName": "PM_DATA_FROM_RL3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0CC040000000C040", + "EventName": "PM_DATA_FROM_RL3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0CC040000020C040", + "EventName": "PM_DATA_FROM_RL3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C8100000000C040", + "EventName": "PM_INST_FROM_RL3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C8140000000C040", + "EventName": "PM_DATA_FROM_RL3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C8100000010C040", + "EventName": "PM_INST_FROM_RL3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C8140000020C040", + "EventName": "PM_DATA_FROM_RL3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C0240000000C040", + "EventName": "PM_DATA_FROM_RL2L3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C0240000020C040", + "EventName": "PM_DATA_FROM_RL2L3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C4240000000C040", + "EventName": "PM_DATA_FROM_RL2L3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C4240000020C040", + "EventName": "PM_DATA_FROM_RL2L3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C0300000000C040", + "EventName": "PM_INST_FROM_RL2L3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C0340000000C040", + "EventName": "PM_DATA_FROM_RL2L3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a remote chip due to a demand miss." + }, + { + "EventCode": "0x0C0300000010C040", + "EventName": "PM_INST_FROM_RL2L3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C0340000020C040", + "EventName": "PM_DATA_FROM_RL2L3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a remote chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0D4100000000C040", + "EventName": "PM_INST_FROM_RMEM", + "BriefDescription": "The processor's instruction cache was reloaded from remote memory (MC slow) due to a demand miss." + }, + { + "EventCode": "0x0D4040000000C040", + "EventName": "PM_DATA_FROM_RMEM", + "BriefDescription": "The processor's L1 data cache was reloaded from remote memory (MC slow) due to a demand miss." + }, + { + "EventCode": "0x0D4100000010C040", + "EventName": "PM_INST_FROM_RMEM_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from remote memory (MC slow) due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0D4040000020C040", + "EventName": "PM_DATA_FROM_RMEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from remote memory (MC slow) due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0D8040000000C040", + "EventName": "PM_DATA_FROM_R_OC_CACHE", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI cache due to a demand miss." + }, + { + "EventCode": "0x0D8040000020C040", + "EventName": "PM_DATA_FROM_R_OC_CACHE_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI cache due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0DC040000000C040", + "EventName": "PM_DATA_FROM_R_OC_MEM", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI memory due to a demand miss." + }, + { + "EventCode": "0x0DC040000020C040", + "EventName": "PM_DATA_FROM_R_OC_MEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0D8100000000C040", + "EventName": "PM_INST_FROM_R_OC_ANY", + "BriefDescription": "The processor's instruction cache was reloaded from a remote chip's OpenCAPI cache or memory due to a demand miss." + }, + { + "EventCode": "0x0D8140000000C040", + "EventName": "PM_DATA_FROM_R_OC_ANY", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI cache or memory due to a demand miss." + }, + { + "EventCode": "0x0D8100000010C040", + "EventName": "PM_INST_FROM_R_OC_ANY_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from a remote chip's OpenCAPI cache or memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0D8140000020C040", + "EventName": "PM_DATA_FROM_R_OC_ANY_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI cache or memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E0040000000C040", + "EventName": "PM_DATA_FROM_DL2_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E0040000020C040", + "EventName": "PM_DATA_FROM_DL2_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E4040000000C040", + "EventName": "PM_DATA_FROM_DL2_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E4040000020C040", + "EventName": "PM_DATA_FROM_DL2_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E0100000000C040", + "EventName": "PM_INST_FROM_DL2", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E0140000000C040", + "EventName": "PM_DATA_FROM_DL2", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E0100000010C040", + "EventName": "PM_INST_FROM_DL2_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E0140000020C040", + "EventName": "PM_DATA_FROM_DL2_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E8040000000C040", + "EventName": "PM_DATA_FROM_DL3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E8040000020C040", + "EventName": "PM_DATA_FROM_DL3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0EC040000000C040", + "EventName": "PM_DATA_FROM_DL3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0EC040000020C040", + "EventName": "PM_DATA_FROM_DL3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E8100000000C040", + "EventName": "PM_INST_FROM_DL3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E8140000000C040", + "EventName": "PM_DATA_FROM_DL3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E8100000010C040", + "EventName": "PM_INST_FROM_DL3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E8140000020C040", + "EventName": "PM_DATA_FROM_DL3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E0240000000C040", + "EventName": "PM_DATA_FROM_DL2L3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E0240000020C040", + "EventName": "PM_DATA_FROM_DL2L3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E4240000000C040", + "EventName": "PM_DATA_FROM_DL2L3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E4240000020C040", + "EventName": "PM_DATA_FROM_DL2L3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E0300000000C040", + "EventName": "PM_INST_FROM_DL2L3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E0340000000C040", + "EventName": "PM_DATA_FROM_DL2L3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a distant chip due to a demand miss." + }, + { + "EventCode": "0x0E0300000010C040", + "EventName": "PM_INST_FROM_DL2L3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0E0340000020C040", + "EventName": "PM_DATA_FROM_DL2L3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a distant chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0F4100000000C040", + "EventName": "PM_INST_FROM_DMEM", + "BriefDescription": "The processor's instruction cache was reloaded from distant memory (MC slow) due to a demand miss." + }, + { + "EventCode": "0x0F4040000000C040", + "EventName": "PM_DATA_FROM_DMEM", + "BriefDescription": "The processor's L1 data cache was reloaded from distant memory (MC slow) due to a demand miss." + }, + { + "EventCode": "0x0F4100000010C040", + "EventName": "PM_INST_FROM_DMEM_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from distant memory (MC slow) due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0F4040000020C040", + "EventName": "PM_DATA_FROM_DMEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from distant memory (MC slow) due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0F8040000000C040", + "EventName": "PM_DATA_FROM_D_OC_CACHE", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI cache due to a demand miss." + }, + { + "EventCode": "0x0F8040000020C040", + "EventName": "PM_DATA_FROM_D_OC_CACHE_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI cache due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0FC040000000C040", + "EventName": "PM_DATA_FROM_D_OC_MEM", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI memory due to a demand miss." + }, + { + "EventCode": "0x0FC040000020C040", + "EventName": "PM_DATA_FROM_D_OC_MEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0F8100000000C040", + "EventName": "PM_INST_FROM_D_OC_ANY", + "BriefDescription": "The processor's instruction cache was reloaded from a distant chip's OpenCAPI cache or memory due to a demand miss." + }, + { + "EventCode": "0x0F8140000000C040", + "EventName": "PM_DATA_FROM_D_OC_ANY", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI cache or memory due to a demand miss." + }, + { + "EventCode": "0x0F8100000010C040", + "EventName": "PM_INST_FROM_D_OC_ANY_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from a distant chip's OpenCAPI cache or memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0F8140000020C040", + "EventName": "PM_DATA_FROM_D_OC_ANY_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI cache or memory due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x080B00000000C040", + "EventName": "PM_INST_FROM_ONCHIP_CACHE", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from the same chip due to a demand miss." + }, + { + "EventCode": "0x080B40000000C040", + "EventName": "PM_DATA_FROM_ONCHIP_CACHE", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from the same chip due to a demand miss." + }, + { + "EventCode": "0x080B00000010C040", + "EventName": "PM_INST_FROM_ONCHIP_CACHE_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from the same chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x080B40000020C040", + "EventName": "PM_DATA_FROM_ONCHIP_CACHE_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from the same chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C0B00000000C040", + "EventName": "PM_INST_FROM_OFFCHIP_CACHE", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a different chip due to a demand miss." + }, + { + "EventCode": "0x0C0B40000000C040", + "EventName": "PM_DATA_FROM_OFFCHIP_CACHE", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a different chip due to a demand miss." + }, + { + "EventCode": "0x0C0B00000010C040", + "EventName": "PM_INST_FROM_OFFCHIP_CACHE_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a different chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x0C0B40000020C040", + "EventName": "PM_DATA_FROM_OFFCHIP_CACHE_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a different chip due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x095900000000C040", + "EventName": "PM_INST_FROM_ANY_MEMORY", + "BriefDescription": "The processor's instruction cache was reloaded from any chip's memory (MC slow) due to a demand miss." + }, + { + "EventCode": "0x095840000000C040", + "EventName": "PM_DATA_FROM_ANY_MEMORY", + "BriefDescription": "The processor's L1 data cache was reloaded from any chip's memory (MC slow) due to a demand miss." + }, + { + "EventCode": "0x095900000010C040", + "EventName": "PM_INST_FROM_ANY_MEMORY_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from any chip's memory (MC slow) due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x095840000020C040", + "EventName": "PM_DATA_FROM_ANY_MEMORY_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from any chip's memory (MC slow) due to a demand miss or prefetch reload." + }, + { + "EventCode": "0x000300000000C142", + "EventName": "PM_MRK_INST_FROM_L2", + "BriefDescription": "The processor's instruction cache was reloaded from the local core's L2 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x000340000000C142", + "EventName": "PM_MRK_DATA_FROM_L2", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L2 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x000300000010C142", + "EventName": "PM_MRK_INST_FROM_L2_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from the local core's L2 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x000340000020C142", + "EventName": "PM_MRK_DATA_FROM_L2_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L2 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x003F00000000C142", + "EventName": "PM_MRK_INST_FROM_L1MISS", + "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L1 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x003F40000000C142", + "EventName": "PM_MRK_DATA_FROM_L1MISS", + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L1 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x003F00000010C142", + "EventName": "PM_MRK_INST_FROM_L1MISS_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L1 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x003F40000020C142", + "EventName": "PM_MRK_DATA_FROM_L1MISS_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L1 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x000040000000C142", + "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT", + "BriefDescription": "The processor's L1 data cache was reloaded without dispatch conflicts with data NOT in the MEPF state from the local core's L2 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x000040000020C142", + "EventName": "PM_MRK_DATA_FROM_L2_NO_CONFLICT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded without dispatch conflicts with data NOT in the MEPF state from the local core's L2 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x004040000000C142", + "EventName": "PM_MRK_DATA_FROM_L2_MEPF", + "BriefDescription": "The processor's L1 data cache was reloaded with data in the MEPF state without dispatch conflicts from the local core's L2 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x004040000020C142", + "EventName": "PM_MRK_DATA_FROM_L2_MEPF_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with data in the MEPF state without dispatch conflicts from the local core's L2 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x008040000000C142", + "EventName": "PM_MRK_DATA_FROM_L2_LDHITST_CONFLICT", + "BriefDescription": "The processor's L1 data cache was reloaded with data that had a dispatch conflict on ld-hit-store from the local core's L2 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x008040000020C142", + "EventName": "PM_MRK_DATA_FROM_L2_LDHITST_CONFLICT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with data that had a dispatch conflict on ld-hit-store from the local core's L2 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x00C040000000C142", + "EventName": "PM_MRK_DATA_FROM_L2_OTHER_CONFLICT", + "BriefDescription": "The processor's L1 data cache was reloaded with data that had a dispatch conflict other than ld-hit-store from the local core's L2 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x00C040000020C142", + "EventName": "PM_MRK_DATA_FROM_L2_OTHER_CONFLICT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with data that had a dispatch conflict other than ld-hit-store from the local core's L2 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x000380000000C142", + "EventName": "PM_MRK_INST_FROM_L2MISS", + "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0003C0000000C142", + "EventName": "PM_MRK_DATA_FROM_L2MISS", + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x000380000010C142", + "EventName": "PM_MRK_INST_FROM_L2MISS_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from a source beyond the local core's L2 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0003C0000020C142", + "EventName": "PM_MRK_DATA_FROM_L2MISS_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x010300000000C142", + "EventName": "PM_MRK_INST_FROM_L3", + "BriefDescription": "The processor's instruction cache was reloaded from the local core's L3 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x010340000000C142", + "EventName": "PM_MRK_DATA_FROM_L3", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L3 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x010300000010C142", + "EventName": "PM_MRK_INST_FROM_L3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from the local core's L3 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x010340000020C142", + "EventName": "PM_MRK_DATA_FROM_L3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L3 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x010040000000C142", + "EventName": "PM_MRK_DATA_FROM_L3_NO_CONFLICT", + "BriefDescription": "The processor's L1 data cache was reloaded without dispatch conflicts with data NOT in the MEPF state from the local core's L3 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x010040000020C142", + "EventName": "PM_MRK_DATA_FROM_L3_NO_CONFLICT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded without dispatch conflicts with data NOT in the MEPF state from the local core's L3 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x014040000000C142", + "EventName": "PM_MRK_DATA_FROM_L3_MEPF", + "BriefDescription": "The processor's L1 data cache was reloaded with data in the MEPF state without dispatch conflicts from the local core's L3 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x014040000020C142", + "EventName": "PM_MRK_DATA_FROM_L3_MEPF_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with data in the MEPF state without dispatch conflicts from the local core's L3 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x01C040000000C142", + "EventName": "PM_MRK_DATA_FROM_L3_CONFLICT", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L3 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x01C040000020C142", + "EventName": "PM_MRK_DATA_FROM_L3_CONFLICT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local core's L3 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x000780000000C142", + "EventName": "PM_MRK_INST_FROM_L3MISS", + "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0007C0000000C142", + "EventName": "PM_MRK_DATA_FROM_L3MISS", + "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x000780000010C142", + "EventName": "PM_MRK_INST_FROM_L3MISS_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from beyond the local core's L3 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0007C0000020C142", + "EventName": "PM_MRK_DATA_FROM_L3MISS_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from beyond the local core's L3 due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x080040000000C142", + "EventName": "PM_MRK_DATA_FROM_L21_REGENT_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x080040000020C142", + "EventName": "PM_MRK_DATA_FROM_L21_REGENT_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x084040000000C142", + "EventName": "PM_MRK_DATA_FROM_L21_REGENT_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x084040000020C142", + "EventName": "PM_MRK_DATA_FROM_L21_REGENT_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x080100000000C142", + "EventName": "PM_MRK_INST_FROM_L21_REGENT", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x080140000000C142", + "EventName": "PM_MRK_DATA_FROM_L21_REGENT", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x080100000010C142", + "EventName": "PM_MRK_INST_FROM_L21_REGENT_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x080140000020C142", + "EventName": "PM_MRK_DATA_FROM_L21_REGENT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x088040000000C142", + "EventName": "PM_MRK_DATA_FROM_L31_REGENT_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x088040000020C142", + "EventName": "PM_MRK_DATA_FROM_L31_REGENT_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x08C040000000C142", + "EventName": "PM_MRK_DATA_FROM_L31_REGENT_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x08C040000020C142", + "EventName": "PM_MRK_DATA_FROM_L31_REGENT_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x088100000000C142", + "EventName": "PM_MRK_INST_FROM_L31_REGENT", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x088140000000C142", + "EventName": "PM_MRK_DATA_FROM_L31_REGENT", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x088100000010C142", + "EventName": "PM_MRK_INST_FROM_L31_REGENT_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x088140000020C142", + "EventName": "PM_MRK_DATA_FROM_L31_REGENT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x080240000000C142", + "EventName": "PM_MRK_DATA_FROM_REGENT_L2L3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x080240000020C142", + "EventName": "PM_MRK_DATA_FROM_REGENT_L2L3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x084240000000C142", + "EventName": "PM_MRK_DATA_FROM_REGENT_L2L3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x084240000020C142", + "EventName": "PM_MRK_DATA_FROM_REGENT_L2L3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x080300000000C142", + "EventName": "PM_MRK_INST_FROM_REGENT_L2L3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x080340000000C142", + "EventName": "PM_MRK_DATA_FROM_REGENT_L2L3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 on the same chip in the same regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x080300000010C142", + "EventName": "PM_MRK_INST_FROM_REGENT_L2L3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x080340000020C142", + "EventName": "PM_MRK_DATA_FROM_REGENT_L2L3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 on the same chip in the same regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A0040000000C142", + "EventName": "PM_MRK_DATA_FROM_L21_NON_REGENT_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A0040000020C142", + "EventName": "PM_MRK_DATA_FROM_L21_NON_REGENT_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A4040000000C142", + "EventName": "PM_MRK_DATA_FROM_L21_NON_REGENT_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A4040000020C142", + "EventName": "PM_MRK_DATA_FROM_L21_NON_REGENT_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A0100000000C142", + "EventName": "PM_MRK_INST_FROM_L21_NON_REGENT", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A0140000000C142", + "EventName": "PM_MRK_DATA_FROM_L21_NON_REGENT", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A0100000010C142", + "EventName": "PM_MRK_INST_FROM_L21_NON_REGENT_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A0140000020C142", + "EventName": "PM_MRK_DATA_FROM_L21_NON_REGENT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A8040000000C142", + "EventName": "PM_MRK_DATA_FROM_L31_NON_REGENT_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A8040000020C142", + "EventName": "PM_MRK_DATA_FROM_L31_NON_REGENT_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0AC040000000C142", + "EventName": "PM_MRK_DATA_FROM_L31_NON_REGENT_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0AC040000020C142", + "EventName": "PM_MRK_DATA_FROM_L31_NON_REGENT_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A8100000000C142", + "EventName": "PM_MRK_INST_FROM_L31_NON_REGENT", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A8140000000C142", + "EventName": "PM_MRK_DATA_FROM_L31_NON_REGENT", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A8100000010C142", + "EventName": "PM_MRK_INST_FROM_L31_NON_REGENT_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A8140000020C142", + "EventName": "PM_MRK_DATA_FROM_L31_NON_REGENT_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A0240000000C142", + "EventName": "PM_MRK_DATA_FROM_NON_REGENT_L2L3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A0240000020C142", + "EventName": "PM_MRK_DATA_FROM_NON_REGENT_L2L3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A4240000000C142", + "EventName": "PM_MRK_DATA_FROM_NON_REGENT_L2L3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A4240000020C142", + "EventName": "PM_MRK_DATA_FROM_NON_REGENT_L2L3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A0300000000C142", + "EventName": "PM_MRK_INST_FROM_NON_REGENT_L2L3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A0340000000C142", + "EventName": "PM_MRK_DATA_FROM_NON_REGENT_L2L3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 on the same chip in a different regent due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0A0300000010C142", + "EventName": "PM_MRK_INST_FROM_NON_REGENT_L2L3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0A0340000020C142", + "EventName": "PM_MRK_DATA_FROM_NON_REGENT_L2L3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 on the same chip in a different regent due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x094100000000C142", + "EventName": "PM_MRK_INST_FROM_LMEM", + "BriefDescription": "The processor's instruction cache was reloaded from the local chip's memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x094040000000C142", + "EventName": "PM_MRK_DATA_FROM_LMEM", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x094100000010C142", + "EventName": "PM_MRK_INST_FROM_LMEM_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from the local chip's memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x094040000020C142", + "EventName": "PM_MRK_DATA_FROM_LMEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x098040000000C142", + "EventName": "PM_MRK_DATA_FROM_L_OC_CACHE", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI cache due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x098040000020C142", + "EventName": "PM_MRK_DATA_FROM_L_OC_CACHE_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI cache due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x09C040000000C142", + "EventName": "PM_MRK_DATA_FROM_L_OC_MEM", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x09C040000020C142", + "EventName": "PM_MRK_DATA_FROM_L_OC_MEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x098100000000C142", + "EventName": "PM_MRK_INST_FROM_L_OC_ANY", + "BriefDescription": "The processor's instruction cache was reloaded from the local chip's OpenCAPI cache or memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x098140000000C142", + "EventName": "PM_MRK_DATA_FROM_L_OC_ANY", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI cache or memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x098100000010C142", + "EventName": "PM_MRK_INST_FROM_L_OC_ANY_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from the local chip's OpenCAPI cache or memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x098140000020C142", + "EventName": "PM_MRK_DATA_FROM_L_OC_ANY_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from the local chip's OpenCAPI cache or memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C0040000000C142", + "EventName": "PM_MRK_DATA_FROM_RL2_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C0040000020C142", + "EventName": "PM_MRK_DATA_FROM_RL2_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C4040000000C142", + "EventName": "PM_MRK_DATA_FROM_RL2_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C4040000020C142", + "EventName": "PM_MRK_DATA_FROM_RL2_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C0100000000C142", + "EventName": "PM_MRK_INST_FROM_RL2", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C0140000000C142", + "EventName": "PM_MRK_DATA_FROM_RL2", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C0100000010C142", + "EventName": "PM_MRK_INST_FROM_RL2_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C0140000020C142", + "EventName": "PM_MRK_DATA_FROM_RL2_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C8040000000C142", + "EventName": "PM_MRK_DATA_FROM_RL3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C8040000020C142", + "EventName": "PM_MRK_DATA_FROM_RL3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0CC040000000C142", + "EventName": "PM_MRK_DATA_FROM_RL3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0CC040000020C142", + "EventName": "PM_MRK_DATA_FROM_RL3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C8100000000C142", + "EventName": "PM_MRK_INST_FROM_RL3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C8140000000C142", + "EventName": "PM_MRK_DATA_FROM_RL3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C8100000010C142", + "EventName": "PM_MRK_INST_FROM_RL3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C8140000020C142", + "EventName": "PM_MRK_DATA_FROM_RL3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C0240000000C142", + "EventName": "PM_MRK_DATA_FROM_RL2L3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C0240000020C142", + "EventName": "PM_MRK_DATA_FROM_RL2L3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C4240000000C142", + "EventName": "PM_MRK_DATA_FROM_RL2L3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C4240000020C142", + "EventName": "PM_MRK_DATA_FROM_RL2L3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C0300000000C142", + "EventName": "PM_MRK_INST_FROM_RL2L3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C0340000000C142", + "EventName": "PM_MRK_DATA_FROM_RL2L3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a remote chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C0300000010C142", + "EventName": "PM_MRK_INST_FROM_RL2L3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C0340000020C142", + "EventName": "PM_MRK_DATA_FROM_RL2L3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a remote chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0D4100000000C142", + "EventName": "PM_MRK_INST_FROM_RMEM", + "BriefDescription": "The processor's instruction cache was reloaded from remote memory (MC slow) due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0D4040000000C142", + "EventName": "PM_MRK_DATA_FROM_RMEM", + "BriefDescription": "The processor's L1 data cache was reloaded from remote memory (MC slow) due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0D4100000010C142", + "EventName": "PM_MRK_INST_FROM_RMEM_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from remote memory (MC slow) due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0D4040000020C142", + "EventName": "PM_MRK_DATA_FROM_RMEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from remote memory (MC slow) due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0D8040000000C142", + "EventName": "PM_MRK_DATA_FROM_R_OC_CACHE", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI cache due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0D8040000020C142", + "EventName": "PM_MRK_DATA_FROM_R_OC_CACHE_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI cache due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0DC040000000C142", + "EventName": "PM_MRK_DATA_FROM_R_OC_MEM", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0DC040000020C142", + "EventName": "PM_MRK_DATA_FROM_R_OC_MEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0D8100000000C142", + "EventName": "PM_MRK_INST_FROM_R_OC_ANY", + "BriefDescription": "The processor's instruction cache was reloaded from a remote chip's OpenCAPI cache or memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0D8140000000C142", + "EventName": "PM_MRK_DATA_FROM_R_OC_ANY", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI cache or memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0D8100000010C142", + "EventName": "PM_MRK_INST_FROM_R_OC_ANY_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from a remote chip's OpenCAPI cache or memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0D8140000020C142", + "EventName": "PM_MRK_DATA_FROM_R_OC_ANY_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a remote chip's OpenCAPI cache or memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E0040000000C142", + "EventName": "PM_MRK_DATA_FROM_DL2_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E0040000020C142", + "EventName": "PM_MRK_DATA_FROM_DL2_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E4040000000C142", + "EventName": "PM_MRK_DATA_FROM_DL2_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E4040000020C142", + "EventName": "PM_MRK_DATA_FROM_DL2_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E0100000000C142", + "EventName": "PM_MRK_INST_FROM_DL2", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E0140000000C142", + "EventName": "PM_MRK_DATA_FROM_DL2", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E0100000010C142", + "EventName": "PM_MRK_INST_FROM_DL2_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E0140000020C142", + "EventName": "PM_MRK_DATA_FROM_DL2_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E8040000000C142", + "EventName": "PM_MRK_DATA_FROM_DL3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E8040000020C142", + "EventName": "PM_MRK_DATA_FROM_DL3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L3 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0EC040000000C142", + "EventName": "PM_MRK_DATA_FROM_DL3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0EC040000020C142", + "EventName": "PM_MRK_DATA_FROM_DL3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L3 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E8100000000C142", + "EventName": "PM_MRK_INST_FROM_DL3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E8140000000C142", + "EventName": "PM_MRK_DATA_FROM_DL3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E8100000010C142", + "EventName": "PM_MRK_INST_FROM_DL3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L3 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E8140000020C142", + "EventName": "PM_MRK_DATA_FROM_DL3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L3 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E0240000000C142", + "EventName": "PM_MRK_DATA_FROM_DL2L3_SHR", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E0240000020C142", + "EventName": "PM_MRK_DATA_FROM_DL2L3_SHR_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a valid line that was not in the M (exclusive) state from another core's L2 or L3 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E4240000000C142", + "EventName": "PM_MRK_DATA_FROM_DL2L3_MOD", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E4240000020C142", + "EventName": "PM_MRK_DATA_FROM_DL2L3_MOD_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded with a line in the M (exclusive) state from another core's L2 or L3 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E0300000000C142", + "EventName": "PM_MRK_INST_FROM_DL2L3", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E0340000000C142", + "EventName": "PM_MRK_DATA_FROM_DL2L3", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a distant chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0E0300000010C142", + "EventName": "PM_MRK_INST_FROM_DL2L3_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0E0340000020C142", + "EventName": "PM_MRK_DATA_FROM_DL2L3_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a distant chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0F4100000000C142", + "EventName": "PM_MRK_INST_FROM_DMEM", + "BriefDescription": "The processor's instruction cache was reloaded from distant memory (MC slow) due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0F4040000000C142", + "EventName": "PM_MRK_DATA_FROM_DMEM", + "BriefDescription": "The processor's L1 data cache was reloaded from distant memory (MC slow) due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0F4100000010C142", + "EventName": "PM_MRK_INST_FROM_DMEM_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from distant memory (MC slow) due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0F4040000020C142", + "EventName": "PM_MRK_DATA_FROM_DMEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from distant memory (MC slow) due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0F8040000000C142", + "EventName": "PM_MRK_DATA_FROM_D_OC_CACHE", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI cache due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0F8040000020C142", + "EventName": "PM_MRK_DATA_FROM_D_OC_CACHE_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI cache due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0FC040000000C142", + "EventName": "PM_MRK_DATA_FROM_D_OC_MEM", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0FC040000020C142", + "EventName": "PM_MRK_DATA_FROM_D_OC_MEM_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0F8100000000C142", + "EventName": "PM_MRK_INST_FROM_D_OC_ANY", + "BriefDescription": "The processor's instruction cache was reloaded from a distant chip's OpenCAPI cache or memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0F8140000000C142", + "EventName": "PM_MRK_DATA_FROM_D_OC_ANY", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI cache or memory due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0F8100000010C142", + "EventName": "PM_MRK_INST_FROM_D_OC_ANY_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from a distant chip's OpenCAPI cache or memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0F8140000020C142", + "EventName": "PM_MRK_DATA_FROM_D_OC_ANY_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from a distant chip's OpenCAPI cache or memory due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x080B00000000C142", + "EventName": "PM_MRK_INST_FROM_ONCHIP_CACHE", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from the same chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x080B40000000C142", + "EventName": "PM_MRK_DATA_FROM_ONCHIP_CACHE", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from the same chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x080B00000010C142", + "EventName": "PM_MRK_INST_FROM_ONCHIP_CACHE_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from the same chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x080B40000020C142", + "EventName": "PM_MRK_DATA_FROM_ONCHIP_CACHE_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from the same chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C0B00000000C142", + "EventName": "PM_MRK_INST_FROM_OFFCHIP_CACHE", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a different chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C0B40000000C142", + "EventName": "PM_MRK_DATA_FROM_OFFCHIP_CACHE", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a different chip due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x0C0B00000010C142", + "EventName": "PM_MRK_INST_FROM_OFFCHIP_CACHE_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from another core's L2 or L3 from a different chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x0C0B40000020C142", + "EventName": "PM_MRK_DATA_FROM_OFFCHIP_CACHE_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from another core's L2 or L3 from a different chip due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x095900000000C142", + "EventName": "PM_MRK_INST_FROM_ANY_MEMORY", + "BriefDescription": "The processor's instruction cache was reloaded from any chip's memory (MC slow) due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x095840000000C142", + "EventName": "PM_MRK_DATA_FROM_ANY_MEMORY", + "BriefDescription": "The processor's L1 data cache was reloaded from any chip's memory (MC slow) due to a demand miss for a marked instruction." + }, + { + "EventCode": "0x095900000010C142", + "EventName": "PM_MRK_INST_FROM_ANY_MEMORY_ALL", + "BriefDescription": "The processor's instruction cache was reloaded from any chip's memory (MC slow) due to a demand miss or prefetch reload for a marked instruction." + }, + { + "EventCode": "0x095840000020C142", + "EventName": "PM_MRK_DATA_FROM_ANY_MEMORY_ALL", + "BriefDescription": "The processor's L1 data cache was reloaded from any chip's memory (MC slow) due to a demand miss or prefetch reload for a marked instruction." + } +] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json index 4d66b75c6ad5..a36621858ea3 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/metrics.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/metrics.json @@ -435,6 +435,13 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of completed instructions that were demand fetches that missed the L1 and L2 instruction cache", + "MetricExpr": "PM_INST_FROM_L2MISS * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "General", + "MetricName": "L2_INST_MISS_RATE", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Percentage of completed instructions that were demand fetches that reloaded from beyond the L3 icache", "MetricExpr": "PM_INST_FROM_L3MISS / PM_RUN_INST_CMPL * 100", "MetricGroup": "General", @@ -467,6 +474,13 @@ "MetricName": "LOADS_PER_INST" }, { + "BriefDescription": "Percentage of demand loads that reloaded from the L2 per completed instruction", + "MetricExpr": "PM_DATA_FROM_L2 * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L2_RATE", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Percentage of demand loads that reloaded from beyond the L2 per completed instruction", "MetricExpr": "PM_DATA_FROM_L2MISS / PM_RUN_INST_CMPL * 100", "MetricGroup": "dL1_Reloads", @@ -474,6 +488,34 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of demand loads that reloaded using modified data from another core's L2 or L3 on a remote chip, per completed instruction", + "MetricExpr": "PM_DATA_FROM_RL2L3_MOD * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_RL2L3_MOD_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded using shared data from another core's L2 or L3 on a remote chip, per completed instruction", + "MetricExpr": "PM_DATA_FROM_RL2L3_SHR * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_RL2L3_SHR_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded from the L3 per completed instruction", + "MetricExpr": "PM_DATA_FROM_L3 * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L3_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded with data brought into the L3 by prefetch per completed instruction", + "MetricExpr": "PM_DATA_FROM_L3_MEPF * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L3_MEPF_RATE", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Percentage of demand loads that reloaded from beyond the L3 per completed instruction", "MetricExpr": "PM_DATA_FROM_L3MISS / PM_RUN_INST_CMPL * 100", "MetricGroup": "dL1_Reloads", @@ -481,6 +523,66 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of demand loads that reloaded using modified data from another core's L2 or L3 on a distant chip, per completed instruction", + "MetricExpr": "PM_DATA_FROM_DL2L3_MOD * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_DL2L3_MOD_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded using shared data from another core's L2 or L3 on a distant chip, per completed instruction", + "MetricExpr": "PM_DATA_FROM_DL2L3_SHR * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_DL2L3_SHR_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded from local memory per completed instruction", + "MetricExpr": "PM_DATA_FROM_LMEM * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_LMEM_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded from remote memory per completed instruction", + "MetricExpr": "PM_DATA_FROM_RMEM * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_RMEM_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand loads that reloaded from distant memory per completed instruction", + "MetricExpr": "PM_DATA_FROM_DMEM * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_DMEM_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of data reloads from local memory per data reloads from any memory", + "MetricExpr": "PM_DATA_FROM_LMEM * 100 / (PM_DATA_FROM_LMEM + PM_DATA_FROM_RMEM + PM_DATA_FROM_DMEM)", + "MetricGroup": "Memory", + "MetricName": "MEM_LOCALITY", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Number of data reloads from local memory per data reloads from remote memory", + "MetricExpr": "PM_DATA_FROM_LMEM / PM_DATA_FROM_RMEM", + "MetricGroup": "Memory", + "MetricName": "LD_LMEM_PER_LD_RMEM" + }, + { + "BriefDescription": "Number of data reloads from local memory per data reloads from distant memory", + "MetricExpr": "PM_DATA_FROM_LMEM / PM_DATA_FROM_DMEM", + "MetricGroup": "Memory", + "MetricName": "LD_LMEM_PER_LD_DMEM" + }, + { + "BriefDescription": "Number of data reloads from local memory per data reloads from distant and remote memory", + "MetricExpr": "PM_DATA_FROM_LMEM / (PM_DATA_FROM_DMEM + PM_DATA_FROM_RMEM)", + "MetricGroup": "Memory", + "MetricName": "LD_LMEM_PER_LD_MEM" + }, + { "BriefDescription": "Percentage of ITLB misses per completed run instruction", "MetricExpr": "PM_ITLB_MISS / PM_RUN_INST_CMPL * 100", "MetricGroup": "General", @@ -488,6 +590,12 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Number of data reloads from remote memory per data reloads from distant memory", + "MetricExpr": "PM_DATA_FROM_RMEM / PM_DATA_FROM_DMEM", + "MetricGroup": "Memory", + "MetricName": "LD_RMEM_PER_LD_DMEM" + }, + { "BriefDescription": "Percentage of DERAT misses with 4k page size per completed instruction", "MetricExpr": "PM_DERAT_MISS_4K / PM_RUN_INST_CMPL * 100", "MetricGroup": "Translation", @@ -502,6 +610,76 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of ICache misses that were reloaded from the L2", + "MetricExpr": "PM_INST_FROM_L2 * 100 / PM_L1_ICACHE_MISS", + "MetricGroup": "Instruction_Stats", + "MetricName": "INST_FROM_L2", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of ICache misses that were reloaded from the L3", + "MetricExpr": "PM_INST_FROM_L3 * 100 / PM_L1_ICACHE_MISS", + "MetricGroup": "Instruction_Stats", + "MetricName": "INST_FROM_L3", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of ICache misses that were reloaded from local memory", + "MetricExpr": "PM_INST_FROM_LMEM * 100 / PM_L1_ICACHE_MISS", + "MetricGroup": "Instruction_Stats", + "MetricName": "INST_FROM_LMEM", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of ICache misses that were reloaded from remote memory", + "MetricExpr": "PM_INST_FROM_RMEM * 100 / PM_L1_ICACHE_MISS", + "MetricGroup": "Instruction_Stats", + "MetricName": "INST_FROM_RMEM", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of ICache misses that were reloaded from distant memory", + "MetricExpr": "PM_INST_FROM_DMEM * 100 / PM_L1_ICACHE_MISS", + "MetricGroup": "Instruction_Stats", + "MetricName": "INST_FROM_DMEM", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of ICache reloads from the L2 per completed instruction", + "MetricExpr": "PM_INST_FROM_L2 * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_L2_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of ICache reloads from the L3 per completed instruction", + "MetricExpr": "PM_INST_FROM_L3 * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_L3_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of ICache reloads from local memory per completed instruction", + "MetricExpr": "PM_INST_FROM_LMEM * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_LMEM_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of ICache reloads from remote memory per completed instruction", + "MetricExpr": "PM_INST_FROM_RMEM * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_RMEM_RATE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of ICache reloads from distant memory per completed instruction", + "MetricExpr": "PM_INST_FROM_DMEM * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_DMEM_RATE", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Average number of run cycles per completed instruction", "MetricExpr": "PM_RUN_CYC / PM_RUN_INST_CMPL", "MetricGroup": "General", @@ -608,6 +786,13 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of demand load misses that reloaded from the local L2", + "MetricExpr": "PM_DATA_FROM_L2 * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L2", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Percentage of demand load misses that reloaded from beyond the local L2", "MetricExpr": "PM_DATA_FROM_L2MISS / PM_LD_DEMAND_MISS_L1 * 100", "MetricGroup": "dL1_Reloads", @@ -615,6 +800,13 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of demand load misses that reloaded from the local L3", + "MetricExpr": "PM_DATA_FROM_L3 * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L3", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Percentage of demand load misses that reloaded from beyond the local L3", "MetricExpr": "PM_DATA_FROM_L3MISS / PM_LD_DEMAND_MISS_L1 * 100", "MetricGroup": "dL1_Reloads", @@ -622,6 +814,188 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of demand load misses that reloaded from the local L3 with modified data", + "MetricExpr": "PM_DATA_FROM_L3_MEPF * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L3_MEPF", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L2 on the same regent with modified data", + "MetricExpr": "PM_DATA_FROM_L21_REGENT_MOD * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L21_REGENT_MOD", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L2 on the same regent with shared data", + "MetricExpr": "PM_DATA_FROM_L21_REGENT_SHR * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L21_REGENT_SHR", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L2 on the same chip in a different regent with modified data", + "MetricExpr": "PM_DATA_FROM_L21_NON_REGENT_MOD * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L21_NON_REGENT_MOD", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L2 on the same chip in a different regent with shared data", + "MetricExpr": "PM_DATA_FROM_L21_NON_REGENT_SHR * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L21_NON_REGENT_SHR", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L3 on the same regent with modified data", + "MetricExpr": "PM_DATA_FROM_L31_REGENT_MOD * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L31_REGENT_MOD", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L3 on the same regent with shared data", + "MetricExpr": "PM_DATA_FROM_L31_REGENT_SHR * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L31_REGENT_SHR", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L3 on the same chip in a different regent with modified data", + "MetricExpr": "PM_DATA_FROM_L31_NON_REGENT_MOD * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L31_NON_REGENT_MOD", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L3 on the same chip in a different regent with shared data", + "MetricExpr": "PM_DATA_FROM_L31_NON_REGENT_SHR * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L31_NON_REGENT_SHR", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L2 on a remote chip with modified data", + "MetricExpr": "PM_DATA_FROM_RL2_MOD * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_RL2_MOD", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L2 on a remote chip with shared data", + "MetricExpr": "PM_DATA_FROM_RL2_SHR * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_RL2_SHR", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L3 on a remote chip with modified data", + "MetricExpr": "PM_DATA_FROM_RL3_MOD * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_RL3_MOD", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L3 on a remote chip with shared data", + "MetricExpr": "PM_DATA_FROM_RL3_SHR * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_RL3_SHR", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L2 on a distant chip with modified data", + "MetricExpr": "PM_DATA_FROM_DL2_MOD * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_DL2_MOD", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L2 on a distant chip with shared data", + "MetricExpr": "PM_DATA_FROM_DL2_SHR * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_DL2_SHR", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L3 on a distant chip with modified data", + "MetricExpr": "PM_DATA_FROM_DL3_MOD * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_DL3_MOD", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from another core's L3 on a distant chip with shared data", + "MetricExpr": "PM_DATA_FROM_DL3_SHR * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_DL3_SHR", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from the local chip's memory", + "MetricExpr": "PM_DATA_FROM_LMEM * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_LMEM", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from the local chip's OpenCAPI Cache", + "MetricExpr": "PM_DATA_FROM_L_OC_CACHE * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L_OC_CACHE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from the local chip's OpenCAPI memory", + "MetricExpr": "PM_DATA_FROM_L_OC_MEM * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_L_OC_MEM", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from a remote chip's memory", + "MetricExpr": "PM_DATA_FROM_RMEM * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_RMEM", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from a remote chip's OpenCAPI Cache", + "MetricExpr": "PM_DATA_FROM_R_OC_CACHE * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_R_OC_CACHE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from a remote chip's OpenCAPI memory", + "MetricExpr": "PM_DATA_FROM_R_OC_MEM * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_R_OC_MEM", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from a distant chip's memory", + "MetricExpr": "PM_DATA_FROM_DMEM * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_DMEM", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from a distant chip's OpenCAPI Cache", + "MetricExpr": "PM_DATA_FROM_D_OC_CACHE * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_D_OC_CACHE", + "ScaleUnit": "1%" + }, + { + "BriefDescription": "Percentage of demand load misses that reloaded from a distant chip's OpenCAPI memory", + "MetricExpr": "PM_DATA_FROM_D_OC_MEM * 100 / PM_LD_DEMAND_MISS_L1", + "MetricGroup": "dL1_Reloads", + "MetricName": "DL1_RELOAD_FROM_D_OC_MEM", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Percentage of cycles stalled due to the NTC instruction waiting for a load miss to resolve from a source beyond the local L2 and local L3", "MetricExpr": "DMISS_L3MISS_STALL_CPI / RUN_CPI * 100", "MetricGroup": "General", @@ -687,6 +1061,13 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of ICache misses that were reloaded from beyond the local L2", + "MetricExpr": "PM_INST_FROM_L2MISS * 100 / PM_L1_ICACHE_MISS", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_L2_MISS", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Percentage of icache misses that were reloaded from beyond the local L3", "MetricExpr": "PM_INST_FROM_L3MISS / PM_L1_ICACHE_MISS * 100", "MetricGroup": "Instruction_Misses", @@ -694,6 +1075,13 @@ "ScaleUnit": "1%" }, { + "BriefDescription": "Percentage of ICache reloads from beyond the L2 per completed instruction", + "MetricExpr": "PM_INST_FROM_L2MISS * 100 / PM_RUN_INST_CMPL", + "MetricGroup": "Instruction_Misses", + "MetricName": "INST_FROM_L2_MISS_RATE", + "ScaleUnit": "1%" + }, + { "BriefDescription": "Percentage of icache reloads from the beyond the L3 per completed instruction", "MetricExpr": "PM_INST_FROM_L3MISS / PM_RUN_INST_CMPL * 100", "MetricGroup": "Instruction_Misses", diff --git a/tools/perf/pmu-events/arch/powerpc/power10/others.json b/tools/perf/pmu-events/arch/powerpc/power10/others.json index 0e21e7ba1959..fcf8a8ebe7bd 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/others.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/others.json @@ -90,11 +90,6 @@ "BriefDescription": "The L1 cache was reloaded with a line that fulfills a demand miss request. Counted at reload time, before finish." }, { - "EventCode": "0x300FE", - "EventName": "PM_DATA_FROM_L3MISS", - "BriefDescription": "The processor's data cache was reloaded from a source other than the local core's L1, L2, or L3 due to a demand miss." - }, - { "EventCode": "0x40012", "EventName": "PM_L1_ICACHE_RELOADED_ALL", "BriefDescription": "Counts all instruction cache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch." @@ -113,10 +108,5 @@ "EventCode": "0x400F0", "EventName": "PM_LD_DEMAND_MISS_L1_FIN", "BriefDescription": "Load missed L1, counted at finish time." - }, - { - "EventCode": "0x400FE", - "EventName": "PM_DATA_FROM_MEMORY", - "BriefDescription": "The processor's data cache was reloaded from local, remote, or distant memory due to a demand miss." } ] diff --git a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json index c606ae03cd27..0e0253d0e757 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/pmc.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/pmc.json @@ -195,7 +195,7 @@ "BriefDescription": "Threshold counter exceeded a value of 128." }, { - "EventCode": "0x400FA", + "EventCode": "0x500FA", "EventName": "PM_RUN_INST_CMPL", "BriefDescription": "PowerPC instruction completed while the run latch is set." } diff --git a/tools/perf/pmu-events/arch/powerpc/power10/translation.json b/tools/perf/pmu-events/arch/powerpc/power10/translation.json index ea73900d248a..a96f76797da0 100644 --- a/tools/perf/pmu-events/arch/powerpc/power10/translation.json +++ b/tools/perf/pmu-events/arch/powerpc/power10/translation.json @@ -10,11 +10,6 @@ "BriefDescription": "Stores completed from S2Q (2nd-level store queue). This event includes regular stores, stcx and cache inhibited stores. The following operations are excluded (pteupdate, snoop tlbie complete, store atomics, miso, load atomic payloads, tlbie, tlbsync, slbieg, isync, msgsnd, slbiag, cpabort, copy, tcheck, tend, stsync, dcbst, icbi, dcbf, hwsync, lwsync, ptesync, eieio, msgsync)." }, { - "EventCode": "0x200FE", - "EventName": "PM_DATA_FROM_L2MISS", - "BriefDescription": "The processor's L1 data cache was reloaded from a source beyond the local core's L2 due to a demand miss." - }, - { "EventCode": "0x300F0", "EventName": "PM_ST_MISS_L1", "BriefDescription": "Store Missed L1." diff --git a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json index c7e7528db315..4d423b149ad1 100644 --- a/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json +++ b/tools/perf/pmu-events/arch/test/test_soc/sys/uncore.json @@ -12,5 +12,13 @@ "EventName": "sys_ccn_pmu.read_cycles", "Unit": "sys_ccn_pmu", "Compat": "0x01" + }, + { + "BriefDescription": "Counts total cache misses in first lookup result (high priority)", + "EventidCode": "0x1", + "NodeType": "0x5", + "EventName": "sys_cmn_pmu.hnf_cache_miss", + "Unit": "sys_cmn_pmu", + "Compat": "(434|436|43c|43a).*" } ] diff --git a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json index c6780d5c456b..3388b58b8f1a 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/adl-metrics.json @@ -99,7 +99,7 @@ }, { "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", - "MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)", + "MetricExpr": "(cycles\\-t / el\\-start if has_event(el\\-start) else 0)", "MetricGroup": "transaction", "MetricName": "tsx_cycles_per_elision", "ScaleUnit": "1cycles / elision" @@ -395,13 +395,13 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricName": "tma_info_inst_mix_ipbranch", "Unit": "cpu_atom" }, { - "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", + "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL", "MetricName": "tma_info_inst_mix_ipcall", "Unit": "cpu_atom" @@ -726,7 +726,7 @@ "Unit": "cpu_atom" }, { - "BriefDescription": "Counts the numer of issue slots that result in retirement slots.", + "BriefDescription": "Counts the number of issue slots that result in retirement slots.", "DefaultMetricgroupName": "TopdownL1", "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots", "MetricGroup": "Default;TopdownL1;tma_L1_group", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json index 81349100fe32..542ba4a81996 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/frontend.json @@ -394,31 +394,61 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled", + "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CORE", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "CounterMask": "6", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "CounterMask": "1", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", + "Invert": "1", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CORE]", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" }, { - "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled", + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" }, { - "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled", + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "CounterMask": "1", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/memory.json b/tools/perf/pmu-events/arch/x86/alderlake/memory.json index 73d92d5c9f9d..23d36164433f 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/memory.json @@ -248,7 +248,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS]", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", @@ -278,7 +278,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS]", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json index cb5b8611064b..f9876bef16da 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/pipeline.json @@ -239,6 +239,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of near taken branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0xc0", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Taken branch instructions retired.", "EventCode": "0xc4", "EventName": "BR_INST_RETIRED.NEAR_TAKEN", @@ -412,6 +421,15 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", @@ -842,7 +860,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "INT_MISC.UNKNOWN_BRANCH_CYCLES", + "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).", "EventCode": "0xad", "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", @@ -1145,7 +1163,7 @@ "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions", "EventCode": "0xa4", "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", - "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of specualtive operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", "SampleAfterValue": "10000003", "UMask": "0x8", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json index 34fc052d00e4..8bf020a9dfa8 100644 --- a/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/alderlake/uncore-interconnect.json @@ -25,6 +25,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD", + "Deprecated": "1", "EventCode": "0x81", "EventName": "UNC_ARB_DAT_REQUESTS.RD", "PerPkg": "1", @@ -33,6 +34,7 @@ }, { "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_DAT_OCCUPANCY.ALL", + "Deprecated": "1", "EventCode": "0x85", "EventName": "UNC_ARB_IFA_OCCUPANCY.ALL", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json index 06e67e34e1bf..c150c14ac6ed 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/adln-metrics.json @@ -328,12 +328,12 @@ "MetricName": "tma_info_inst_mix_idiv_uop_ratio" }, { - "BriefDescription": "Instructions per Branch (lower number means higher occurance rate)", + "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES", "MetricName": "tma_info_inst_mix_ipbranch" }, { - "BriefDescription": "Instruction per (near) call (lower number means higher occurance rate)", + "BriefDescription": "Instruction per (near) call (lower number means higher occurrence rate)", "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.CALL", "MetricName": "tma_info_inst_mix_ipcall" }, @@ -616,7 +616,7 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Counts the numer of issue slots that result in retirement slots.", + "BriefDescription": "Counts the number of issue slots that result in retirement slots.", "DefaultMetricgroupName": "TopdownL1", "MetricExpr": "TOPDOWN_RETIRING.ALL / tma_info_core_slots", "MetricGroup": "Default;TopdownL1;tma_L1_group", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json index 37259d38a222..863a3ba2b4b2 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/memory.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/memory.json @@ -59,7 +59,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS]", "EventCode": "0xB7", "EventName": "OCR.DEMAND_DATA_RD.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", @@ -77,7 +77,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache. [L3_MISS_LOCAL is alias to L3_MISS]", "EventCode": "0xB7", "EventName": "OCR.DEMAND_RFO.L3_MISS_LOCAL", "MSRIndex": "0x1a6,0x1a7", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json index fa53ff11a509..3153bab527a9 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/pipeline.json @@ -91,6 +91,14 @@ "UMask": "0xf7" }, { + "BriefDescription": "Counts the number of near taken branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0xc0" + }, + { "BriefDescription": "This event is deprecated. Refer to new event BR_INST_RETIRED.INDIRECT", "Deprecated": "1", "EventCode": "0xc4", @@ -184,6 +192,14 @@ "UMask": "0x7e" }, { + "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0x80" + }, + { "BriefDescription": "This event is deprecated. Refer to new event BR_MISP_RETIRED.INDIRECT", "Deprecated": "1", "EventCode": "0xc5", diff --git a/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json index 4af695a5e755..8bf020a9dfa8 100644 --- a/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/alderlaken/uncore-interconnect.json @@ -8,6 +8,56 @@ "Unit": "ARB" }, { + "BriefDescription": "Each cycle counts number of any coherent request at memory controller that were issued by any core.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core.", + "EventCode": "0x85", + "EventName": "UNC_ARB_DAT_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_REQ_TRK_REQUEST.DRD", + "Deprecated": "1", + "EventCode": "0x81", + "EventName": "UNC_ARB_DAT_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UNC_ARB_DAT_OCCUPANCY.ALL", + "Deprecated": "1", + "EventCode": "0x85", + "EventName": "UNC_ARB_IFA_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "ARB" + }, + { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_OCCUPANCY.RD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_REQ_TRK_OCCUPANCY.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_TRK_REQUESTS.RD]", + "EventCode": "0x81", + "EventName": "UNC_ARB_REQ_TRK_REQUEST.DRD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { "BriefDescription": "Each cycle counts number of all outgoing valid entries in ReqTrk. Such entry is defined as valid from its allocation in ReqTrk till deallocation. Accounts for Coherent and non-coherent traffic.", "EventCode": "0x80", "EventName": "UNC_ARB_TRK_OCCUPANCY.ALL", @@ -16,11 +66,27 @@ "Unit": "ARB" }, { + "BriefDescription": "Each cycle count number of 'valid' coherent Data Read entries . Such entry is defined as valid when it is allocated till deallocation. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_OCCUPANCY.DRD]", + "EventCode": "0x80", + "EventName": "UNC_ARB_TRK_OCCUPANCY.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" + }, + { "BriefDescription": "Counts the number of coherent and in-coherent requests initiated by IA cores, processor graphic units, or LLC.", "EventCode": "0x81", "EventName": "UNC_ARB_TRK_REQUESTS.ALL", "PerPkg": "1", "UMask": "0x1", "Unit": "ARB" + }, + { + "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches [This event is alias to UNC_ARB_REQ_TRK_REQUEST.DRD]", + "EventCode": "0x81", + "EventName": "UNC_ARB_TRK_REQUESTS.RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "ARB" } ] diff --git a/tools/perf/pmu-events/arch/x86/bonnell/frontend.json b/tools/perf/pmu-events/arch/x86/bonnell/frontend.json index 8d2f4edfb597..42284c02c11d 100644 --- a/tools/perf/pmu-events/arch/x86/bonnell/frontend.json +++ b/tools/perf/pmu-events/arch/x86/bonnell/frontend.json @@ -63,7 +63,7 @@ "UMask": "0x2" }, { - "BriefDescription": "Non-CISC nacro instructions decoded", + "BriefDescription": "Non-CISC macro instructions decoded", "EventCode": "0xAA", "EventName": "MACRO_INSTS.NON_CISC_DECODED", "SampleAfterValue": "2000000", diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json index 8fc62b8f667d..e1f55fcfa0d0 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json @@ -49,6 +49,12 @@ "ScaleUnit": "100%" }, { + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" + }, + { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -652,7 +658,7 @@ }, { "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]", - "MetricExpr": "64 * (arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@) / 1e6 / duration_time / 1e3", + "MetricExpr": "64 * (UNC_M_CAS_COUNT.RD + UNC_M_CAS_COUNT.WR) / 1e9 / duration_time", "MetricGroup": "HPC;Mem;MemoryBW;SoC;tma_issueBW", "MetricName": "tma_info_system_dram_bw_use", "PublicDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]. Related metrics: tma_fb_full, tma_mem_bandwidth, tma_sq_full" @@ -691,6 +697,12 @@ "MetricName": "tma_info_system_smt_2t_utilization" }, { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "cbox_0@event\\=0x0@", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_socket_clks" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", diff --git a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json index 8a327e0f1441..910395977a6e 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/broadwellde/uncore-interconnect.json @@ -253,7 +253,7 @@ "EventCode": "0x4", "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -261,7 +261,7 @@ "EventCode": "0x1", "EventName": "UNC_I_RxR_BL_DRS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -269,7 +269,7 @@ "EventCode": "0x7", "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -277,7 +277,7 @@ "EventCode": "0x5", "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -285,7 +285,7 @@ "EventCode": "0x2", "EventName": "UNC_I_RxR_BL_NCB_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -293,7 +293,7 @@ "EventCode": "0x8", "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -301,7 +301,7 @@ "EventCode": "0x6", "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -309,7 +309,7 @@ "EventCode": "0x3", "EventName": "UNC_I_RxR_BL_NCS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -317,7 +317,7 @@ "EventCode": "0x9", "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json index e61a23f68899..b9fb216bee16 100644 --- a/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/broadwellx/uncore-interconnect.json @@ -271,7 +271,7 @@ "EventCode": "0x4", "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -279,7 +279,7 @@ "EventCode": "0x1", "EventName": "UNC_I_RxR_BL_DRS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -287,7 +287,7 @@ "EventCode": "0x7", "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -295,7 +295,7 @@ "EventCode": "0x5", "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -303,7 +303,7 @@ "EventCode": "0x2", "EventName": "UNC_I_RxR_BL_NCB_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -311,7 +311,7 @@ "EventCode": "0x8", "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -319,7 +319,7 @@ "EventCode": "0x6", "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -327,7 +327,7 @@ "EventCode": "0x3", "EventName": "UNC_I_RxR_BL_NCS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -335,7 +335,7 @@ "EventCode": "0x9", "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json index fbb111e40829..84c132af3dfa 100644 --- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json @@ -1837,7 +1837,7 @@ }, { "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", - "MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)", + "MetricExpr": "(cycles\\-t / el\\-start if has_event(el\\-start) else 0)", "MetricGroup": "transaction", "MetricName": "tsx_cycles_per_elision", "ScaleUnit": "1cycles / elision" diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json new file mode 100644 index 000000000000..ab09bd9fb409 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json @@ -0,0 +1,888 @@ +[ + { + "BriefDescription": "L1D.HWPF_MISS", + "EventCode": "0x51", + "EventName": "L1D.HWPF_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Counts the number of cache lines replaced in L1 data cache.", + "EventCode": "0x51", + "EventName": "L1D.REPLACEMENT", + "PublicDescription": "Counts L1D data line replacements including opportunistic replacements, and replacements that require stall-for-replace or block-for-replace.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL_PERIODS", + "PublicDescription": "Counts number of phases a demand request has waited due to L1D Fill Buffer (FB) unavailability. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event L1D_PEND_MISS.L2_STALLS", + "Deprecated": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.L2_STALL", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of cycles a demand request has waited due to L1D due to lack of L2 resources.", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.L2_STALLS", + "PublicDescription": "Counts number of cycles a demand request has waited due to L1D due to lack of L2 resources. Demand requests include cacheable/uncacheable demand load, store, lock or SW prefetch accesses.", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of L1D misses that are outstanding", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Counts number of L1D misses that are outstanding in each cycle, that is each cycle the number of Fill Buffers (FB) outstanding required by Demand Reads. FB either is held by demand loads, or it is held by non-demand loads and gets hit at least once by demand. The valid outstanding interval is defined until the FB deallocation by one of the following ways: from FB allocation, if FB is allocated by demand from the demand Hit FB, if it is allocated by hardware or software prefetch. Note: In the L1D, a Demand Read contains cacheable or noncacheable demand loads, including ones causing cache-line splits and reads due to page walks resulted from any request type.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 cache lines filling L2", + "EventCode": "0x25", + "EventName": "L2_LINES_IN.ALL", + "PublicDescription": "Counts the number of L2 cache lines filling the L2. Counting does not cover rejects.", + "SampleAfterValue": "100003", + "UMask": "0x1f" + }, + { + "BriefDescription": "L2_LINES_OUT.NON_SILENT", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.NON_SILENT", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Non-modified cache lines that are silently dropped by L2 cache when triggered by an L2 cache fill.", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.SILENT", + "PublicDescription": "Counts the number of lines that are silently dropped by L2 cache when triggered by an L2 cache fill. These lines are typically in Shared or Exclusive state. A non-threaded event.", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cache lines that have been L2 hardware prefetched but not used by demand accesses", + "EventCode": "0x26", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "PublicDescription": "Counts the number of cache lines that have been prefetched by the L2 hardware prefetcher but not used by demand access when evicted from the L2 cache", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_RQSTS.REFERENCES]", + "EventCode": "0x24", + "EventName": "L2_REQUEST.ALL", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.REFERENCES]", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache. [This event is alias to L2_RQSTS.MISS]", + "EventCode": "0x24", + "EventName": "L2_REQUEST.MISS", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_RQSTS.MISS]", + "SampleAfterValue": "200003", + "UMask": "0x3f" + }, + { + "BriefDescription": "L2 code requests", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", + "SampleAfterValue": "200003", + "UMask": "0xe4" + }, + { + "BriefDescription": "Demand Data Read access L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts Demand Data Read requests accessing the L2 cache. These requests may hit or miss L2 cache. True-miss exclude misses that were merged with ongoing L2 misses. An access is counted once.", + "SampleAfterValue": "200003", + "UMask": "0xe1" + }, + { + "BriefDescription": "Demand requests that miss L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_MISS", + "PublicDescription": "Counts demand requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x27" + }, + { + "BriefDescription": "Demand requests to L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "PublicDescription": "Counts demand requests to L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xe7" + }, + { + "BriefDescription": "L2_RQSTS.ALL_HWPF", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_HWPF", + "SampleAfterValue": "200003", + "UMask": "0xf0" + }, + { + "BriefDescription": "RFO requests to L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_RFO", + "PublicDescription": "Counts the total number of RFO (read for ownership) requests to L2 cache. L2 RFO requests include both L1D demand RFO misses as well as L1D RFO prefetches.", + "SampleAfterValue": "200003", + "UMask": "0xe2" + }, + { + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "UMask": "0xc4" + }, + { + "BriefDescription": "L2 cache misses when fetching instructions", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x24" + }, + { + "BriefDescription": "Demand Data Read requests that hit L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT", + "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc1" + }, + { + "BriefDescription": "Demand Data Read miss L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts demand Data Read requests with true-miss in the L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. An access is counted once.", + "SampleAfterValue": "200003", + "UMask": "0x21" + }, + { + "BriefDescription": "L2_RQSTS.HWPF_MISS", + "EventCode": "0x24", + "EventName": "L2_RQSTS.HWPF_MISS", + "SampleAfterValue": "200003", + "UMask": "0x30" + }, + { + "BriefDescription": "Read requests with true-miss in L2 cache. [This event is alias to L2_REQUEST.MISS]", + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "Counts read requests of any type with true-miss in the L2 cache. True-miss excludes L2 misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.MISS]", + "SampleAfterValue": "200003", + "UMask": "0x3f" + }, + { + "BriefDescription": "All accesses to L2 cache [This event is alias to L2_REQUEST.ALL]", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "Counts all requests that were hit or true misses in L2 cache. True-miss excludes misses that were merged with ongoing L2 misses. [This event is alias to L2_REQUEST.ALL]", + "SampleAfterValue": "200003", + "UMask": "0xff" + }, + { + "BriefDescription": "RFO requests that hit L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc2" + }, + { + "BriefDescription": "RFO requests that miss L2 cache", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x22" + }, + { + "BriefDescription": "SW prefetch requests that hit L2 cache.", + "EventCode": "0x24", + "EventName": "L2_RQSTS.SWPF_HIT", + "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "SampleAfterValue": "200003", + "UMask": "0xc8" + }, + { + "BriefDescription": "SW prefetch requests that miss L2 cache.", + "EventCode": "0x24", + "EventName": "L2_RQSTS.SWPF_MISS", + "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.", + "SampleAfterValue": "200003", + "UMask": "0x28" + }, + { + "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x4f" + }, + { + "BriefDescription": "Retired load instructions.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "PEBS": "1", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "SampleAfterValue": "1000003", + "UMask": "0x81" + }, + { + "BriefDescription": "Retired store instructions.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "PEBS": "1", + "PublicDescription": "Counts all retired store instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x82" + }, + { + "BriefDescription": "All retired memory instructions.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ANY", + "PEBS": "1", + "PublicDescription": "Counts all retired memory instructions - loads and stores.", + "SampleAfterValue": "1000003", + "UMask": "0x83" + }, + { + "BriefDescription": "Retired load instructions with locked access.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with locked access.", + "SampleAfterValue": "100007", + "UMask": "0x21" + }, + { + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x41" + }, + { + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "PEBS": "1", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x42" + }, + { + "BriefDescription": "Retired load instructions that miss the STLB.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "PEBS": "1", + "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x11" + }, + { + "BriefDescription": "Retired store instructions that miss the STLB.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "PEBS": "1", + "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).", + "SampleAfterValue": "100003", + "UMask": "0x12" + }, + { + "BriefDescription": "Completed demand load uops that miss the L1 d-cache.", + "EventCode": "0x43", + "EventName": "MEM_LOAD_COMPLETED.L1_MISS_ANY", + "PublicDescription": "Number of completed demand load requests that missed the L1 data cache including shadow misses (FB hits, merge to an ongoing L1D miss)", + "SampleAfterValue": "1000003", + "UMask": "0xfd" + }, + { + "BriefDescription": "Retired load instructions whose data sources were HitM responses from shared L3", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_FWD", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions whose data sources were HitM responses from shared L3.", + "SampleAfterValue": "20011", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "PublicDescription": "Counts the retired load instructions whose data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions whose data sources were hits in L3 without snoops required", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions whose data sources were hits in L3 without snoops required.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache", + "Data_LA": "1", + "EventCode": "0xd2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NO_FWD", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions whose data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", + "Data_LA": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.LOCAL_DRAM", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources missed L3 but serviced from local DRAM.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "Data_LA": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "PEBS": "1", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache", + "Data_LA": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", + "PEBS": "1", + "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "Data_LA": "1", + "EventCode": "0xd3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "PEBS": "1", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "Data_LA": "1", + "EventCode": "0xd4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", + "PEBS": "1", + "PublicDescription": "Retired instructions with at least one load to uncacheable memory-type, or at least one cache-line split locked access (Bus Lock).", + "SampleAfterValue": "100007", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of completed demand load requests that missed the L1, but hit the FB(fill buffer), because a preceding miss to the same cacheline initiated the line to be brought into L1, but data is not yet ready in L1.", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.FB_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop was load missed in L1 but hit FB (Fill Buffers) due to preceding miss to the same cache line with data not ready.", + "SampleAfterValue": "100007", + "UMask": "0x40" + }, + { + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L1 data cache. This event includes all SW prefetches and lock instructions regardless of the data source.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired load instructions missed L1 cache as data sources", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L1_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L1 cache.", + "SampleAfterValue": "200003", + "UMask": "0x8" + }, + { + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with L2 cache hits as data sources.", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "100021", + "UMask": "0x10" + }, + { + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_HIT", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that hit in the L3 cache.", + "SampleAfterValue": "100021", + "UMask": "0x4" + }, + { + "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "Data_LA": "1", + "EventCode": "0xd1", + "EventName": "MEM_LOAD_RETIRED.L3_MISS", + "PEBS": "1", + "PublicDescription": "Counts retired load instructions with at least one uop that missed in the L3 cache.", + "SampleAfterValue": "50021", + "UMask": "0x20" + }, + { + "BriefDescription": "MEM_STORE_RETIRED.L2_HIT", + "EventCode": "0x44", + "EventName": "MEM_STORE_RETIRED.L2_HIT", + "SampleAfterValue": "200003", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired memory uops for any access", + "EventCode": "0xe5", + "EventName": "MEM_UOP_RETIRED.ANY", + "PublicDescription": "Number of retired micro-operations (uops) for load or store memory accesses", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit in the L3 or were snooped from another core's caches on the same socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1008000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.SNC_CACHE.HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x808000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit in the L3 or were snooped from another core's caches on the same socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that resulted in a snoop that hit in another core, which did not forward the data.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1030000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x830000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1008000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.SNC_CACHE.HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x808000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit in the L3 or were snooped from another core's caches on the same socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1008000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.SNC_CACHE.HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x808000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that hit in the L3 or were snooped from another core's caches on the same socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x80082380", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit in the L3 or were snooped from another core's caches on the same socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F003C4477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit a modified line in another core's caches which forwarded the data.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C4477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop that hit in another core, which did not forward the data.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x4003C4477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that resulted in a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C4477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop was sent and data was returned (Modified or Not Modified).", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1830004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit a modified line in another core's caches which forwarded the data.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1030004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by a cache on a remote socket where a snoop hit in another core's caches which forwarded the unmodified data to the requesting core.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_CACHE.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x830004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that hit a modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1008004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that either hit a non-modified line in a distant L3 Cache or were snooped from a distant core's L1/L2 caches on this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_CACHE.HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x808004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO), hardware prefetch RFOs (which bring data to L2), and software prefetches for exclusive ownership (PREFETCHW) that hit to a (M)odified cacheline in the L3 or snoop filter.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.RFO_TO_CORE.L3_HIT_M", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x1F80040022", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores that hit in the L3 or were snooped from another core's caches on the same socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.STREAMING_WR.L3_HIT", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x80080800", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_REQUESTS.ALL_REQUESTS", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Demand and prefetch data reads", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DATA_RD", + "PublicDescription": "Counts the demand and prefetch data reads. All Core Data Reads include cacheable 'Demands' and L2 prefetchers (not L3 prefetchers). Counting also covers reads due to page walks resulted from any request type.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Demand Data Read requests sent to uncore", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.DEMAND_DATA_RD", + "PublicDescription": "Counts the Demand Data Read requests sent to uncore. Use it in conjunction with OFFCORE_REQUESTS_OUTSTANDING to determine average latency in the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "Deprecated": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles where at least 1 outstanding demand data read request is pending.", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "CounterMask": "1", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DATA_RD", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "For every cycle, increments by the number of outstanding demand data read requests pending.", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of outstanding demand data read requests pending. Requests are considered outstanding from the time they miss the core's L2 cache until the transaction completion message is sent to the requestor.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts bus locks, accounts for cache line split locks and UC locks.", + "EventCode": "0x2c", + "EventName": "SQ_MISC.BUS_LOCK", + "PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of PREFETCHNTA instructions executed.", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.NTA", + "PublicDescription": "Counts the number of PREFETCHNTA instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of PREFETCHW instructions executed.", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", + "PublicDescription": "Counts the number of PREFETCHW instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T0", + "PublicDescription": "Counts the number of PREFETCHT0 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "EventCode": "0x40", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "PublicDescription": "Counts the number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "SampleAfterValue": "100003", + "UMask": "0x4" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json new file mode 100644 index 000000000000..4a9d211e9d4f --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/floating-point.json @@ -0,0 +1,193 @@ +[ + { + "BriefDescription": "ARITH.FPDIV_ACTIVE", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.FPDIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all microcode FP assists.", + "EventCode": "0xc1", + "EventName": "ASSISTS.FP", + "PublicDescription": "Counts all microcode Floating Point assists.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "ASSISTS.SSE_AVX_MIX", + "EventCode": "0xc1", + "EventName": "ASSISTS.SSE_AVX_MIX", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "FP_ARITH_DISPATCHED.PORT_0", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.PORT_0", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "FP_ARITH_DISPATCHED.PORT_1", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.PORT_1", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "FP_ARITH_DISPATCHED.PORT_5", + "EventCode": "0xb3", + "EventName": "FP_ARITH_DISPATCHED.PORT_5", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 or/and 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x18" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", + "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision FP instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, 1 for each element. Applies to SSE* and AVX* packed single precision and double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.8_FLOPS", + "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision and 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision and double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RSQRT14 RCP RCP14 DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x60" + }, + { + "BriefDescription": "Number of SSE/AVX computational scalar floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar, double and single precision floating-point: ADD SUB MUL DIV MIN MAX RCP14 RSQRT14 RANGE SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR", + "PublicDescription": "Number of SSE/AVX computational scalar single precision and double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE", + "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of any Vector retired FP arithmetic instructions", + "EventCode": "0xc7", + "EventName": "FP_ARITH_INST_RETIRED.VECTOR", + "PublicDescription": "Number of any Vector retired FP arithmetic instructions. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.", + "SampleAfterValue": "1000003", + "UMask": "0xfc" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.128B_PACKED_HALF", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.256B_PACKED_HALF", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.512B_PACKED_HALF", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.COMPLEX_SCALAR_HALF", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of all Scalar Half-Precision FP arithmetic instructions(1) retired - regular and complex.", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.SCALAR", + "PublicDescription": "FP_ARITH_INST_RETIRED2.SCALAR", + "SampleAfterValue": "100003", + "UMask": "0x3" + }, + { + "BriefDescription": "FP_ARITH_INST_RETIRED2.SCALAR_HALF", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.SCALAR_HALF", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of all Vector (also called packed) Half-Precision FP arithmetic instructions(1) retired.", + "EventCode": "0xcf", + "EventName": "FP_ARITH_INST_RETIRED2.VECTOR", + "PublicDescription": "FP_ARITH_INST_RETIRED2.VECTOR", + "SampleAfterValue": "100003", + "UMask": "0x1c" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json new file mode 100644 index 000000000000..9e53da55d0c1 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json @@ -0,0 +1,389 @@ +[ + { + "BriefDescription": "Clears due to Unknown Branches.", + "EventCode": "0x60", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Number of times the front-end is resteered when it finds a branch instruction in a fetch line. This is called Unknown Branch which occurs for the first time a branch instruction is fetched or when the branch is not tracked by the BPU (Branch Prediction Unit) anymore.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "EventCode": "0x87", + "EventName": "DECODE.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles the Microcode Sequencer is busy.", + "EventCode": "0x87", + "EventName": "DECODE.MS_BUSY", + "SampleAfterValue": "500009", + "UMask": "0x2" + }, + { + "BriefDescription": "DSB-to-MITE switch true penalty cycles.", + "EventCode": "0x61", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Decode Stream Buffer (DSB) is a Uop-cache that holds translations of previously fetched instructions that were decoded by the legacy x86 decode pipeline (MITE). This event counts fetch penalty cycles when a transition occurs from DSB to MITE.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired Instructions who experienced DSB miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x1", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced a critical DSB miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PEBS": "1", + "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced iTLB true miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.ITLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x14", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced iTLB (Instruction TLB) true miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L1I_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x12", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions who experienced Instruction L1 Cache true miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions who experienced Instruction L2 Cache true miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x600106", + "PEBS": "1", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 1 cycle which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x608006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 128 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 16 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "MSRIndex": "0x3F7", + "MSRValue": "0x601006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 16 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions after front-end starvation of at least 2 cycles", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x600206", + "PEBS": "1", + "PublicDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of at least 2 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", + "MSRIndex": "0x3F7", + "MSRValue": "0x610006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 256 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 1 bubble-slot for a period of 2 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x100206", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after the front-end had at least 1 bubble-slot for a period of 2 cycles. A bubble-slot is an empty issue-pipeline slot while there was no RAT stall.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 32 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "MSRIndex": "0x3F7", + "MSRValue": "0x602006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 32 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "MSRValue": "0x600406", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 4 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "MSRValue": "0x620006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 512 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "MSRIndex": "0x3F7", + "MSRValue": "0x604006", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 64 cycles which was not interrupted by a back-end stall.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 8 cycles which was not interrupted by a back-end stall.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "MSRIndex": "0x3F7", + "MSRValue": "0x600806", + "PEBS": "1", + "PublicDescription": "Counts retired instructions that are delivered to the back-end after a front-end stall of at least 8 cycles. During this period the front-end delivered no uops.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "FRONTEND_RETIRED.MS_FLOWS", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.MS_FLOWS", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.STLB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x15", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "FRONTEND_RETIRED.UNKNOWN_BRANCH", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.UNKNOWN_BRANCH", + "MSRIndex": "0x3F7", + "MSRValue": "0x17", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "EventCode": "0x80", + "EventName": "ICACHE_DATA.STALLS", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The decode pipeline works at a 32 Byte granularity.", + "SampleAfterValue": "500009", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "EventCode": "0x83", + "EventName": "ICACHE_TAG.STALLS", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_ANY", + "PublicDescription": "Counts the number of cycles uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles DSB is delivering optimal number of Uops", + "CounterMask": "6", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES_OK", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "EventCode": "0x79", + "EventName": "IDQ.DSB_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles MITE is delivering any Uop", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_ANY", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles MITE is delivering optimal number of Uops", + "CounterMask": "6", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES_OK", + "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles when uops are being delivered to IDQ while MS is busy", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_CYCLES_ANY", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of switches from DSB or MITE to the MS", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x79", + "EventName": "IDQ.MS_SWITCHES", + "PublicDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Uops delivered to IDQ while MS is busy", + "EventCode": "0x79", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS).", + "SampleAfterValue": "1000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CORE", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "CounterMask": "6", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "CounterMask": "1", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", + "Invert": "1", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CORE]", + "EventCode": "0x9c", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "CounterMask": "6", + "EventCode": "0x9c", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", + "CounterMask": "1", + "EventCode": "0x9c", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", + "Invert": "1", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", + "SampleAfterValue": "1000003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json new file mode 100644 index 000000000000..e8bf7c9c44e1 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json @@ -0,0 +1,343 @@ +[ + { + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "CounterMask": "6", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x6" + }, + { + "BriefDescription": "Number of machine clears due to memory ordering conflicts.", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "CounterMask": "2", + "EventCode": "0x47", + "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "CounterMask": "3", + "EventCode": "0x47", + "EventName": "MEMORY_ACTIVITY.STALLS_L1D_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding.", + "CounterMask": "5", + "EventCode": "0x47", + "EventName": "MEMORY_ACTIVITY.STALLS_L2_MISS", + "PublicDescription": "Execution stalls while L2 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding.", + "CounterMask": "9", + "EventCode": "0x47", + "EventName": "MEMORY_ACTIVITY.STALLS_L3_MISS", + "PublicDescription": "Execution stalls while L3 cache miss demand cacheable load request is outstanding (will not count for uncacheable demand requests e.g. bus lock).", + "SampleAfterValue": "1000003", + "UMask": "0x9" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "1009", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "20011", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "503", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "101", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "2003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "50021", + "UMask": "0x1" + }, + { + "BriefDescription": "Retired memory store access operations. A PDist event for PEBS Store Latency Facility.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", + "PEBS": "2", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were not supplied by the local socket's L1, L2, or L3 caches.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were not supplied by the local socket's L1, L2, or L3 caches.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the local socket's L1, L2, or L3 caches.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FC00002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that missed the local socket's L1, L2, and L3 caches.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x94002380", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.L3_MISS_LOCAL", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x84002380", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FC04477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F04C04477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that missed the L3 Cache and were supplied by the local socket (DRAM or PMM), whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts PMM or DRAM accesses that are controlled by the close or distant SNC Cluster. It does not count misses to the L3 which go to Local CXL Type 2 Memory or Local Non DRAM.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.L3_MISS_LOCAL_SOCKET", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x70CC04477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores that missed the local socket's L1, L2, and L3 caches.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.STREAMING_WR.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x94000800", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline is homed locally.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.STREAMING_WR.L3_MISS_LOCAL", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x84000800", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data read requests that miss the L3 cache.", + "EventCode": "0x21", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache.", + "EventCode": "0x20", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "For every cycle, increments by the number of demand data read requests pending that are known to have missed the L3 cache. Note that this does not capture all elapsed cycles while requests are outstanding - only cycles from when the requests were known by the requesting core to have missed the L3 cache.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of times an RTM execution aborted.", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED", + "PublicDescription": "Counts the number of times RTM abort was triggered.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_EVENTS", + "PublicDescription": "Counts the number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt).", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "PublicDescription": "Counts the number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Counts the number of times an RTM execution aborted due to incompatible memory type.", + "SampleAfterValue": "100003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Counts the number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of times an RTM execution successfully committed", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Counts the number of times RTM commit succeeded.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an RTM execution started.", + "EventCode": "0xc9", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Counts the number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional reads", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_READ", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional reads", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Speculatively counts the number of TSX aborts due to a data capacity limitation for transactional writes.", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY_WRITE", + "PublicDescription": "Speculatively counts the number of Transactional Synchronization Extensions (TSX) aborts due to a data capacity limitation for transactional writes.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Counts the number of times a TSX line had a cache conflict.", + "SampleAfterValue": "100003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json new file mode 100644 index 000000000000..2f375a6badcd --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json @@ -0,0 +1,315 @@ +[ + { + "BriefDescription": "ASSISTS.PAGE_FAULT", + "EventCode": "0xc1", + "EventName": "ASSISTS.PAGE_FAULT", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts the cycles where the AMX (Advance Matrix Extension) unit is busy performing an operation.", + "EventCode": "0xb7", + "EventName": "EXE.AMX_BUSY", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand instruction fetches and L1 instruction cache prefetches that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_CODE_RD.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000004", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM attached to another socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000001", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC0002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts demand reads for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708000002", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts data load hardware prefetch requests to the L1 data cache that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L1D.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10400", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches (which bring data to L2) that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L2.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10070", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x12380", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts hardware prefetches to the L3 only that were not supplied by the local socket's L1, L2, or L3 caches and the cacheline was homed in a remote socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.HWPF_L3.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x90002380", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts writebacks of modified cachelines and streaming stores that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.MODIFIED_WRITE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10808", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F3FFC4477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x73C004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, unless in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts only those DRAM accesses that are controlled by the close SNC Cluster.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x104004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to this socket, whether or not in Sub NUMA Cluster(SNC) Mode. In SNC Mode counts DRAM accesses that are controlled by the close or distant SNC Cluster.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.LOCAL_SOCKET_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x70C004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were not supplied by the local socket's L1, L2, or L3 caches and were supplied by a remote socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F33004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM attached to another socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x730004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM or PMM attached to another socket.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.REMOTE_MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x733004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts all (cacheable) data read, code read and RFO requests including demands and prefetches to the core caches (L1 or L2) that were supplied by DRAM on a distant memory controller of this socket when the system is in SNC (sub-NUMA cluster) mode.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.READS_TO_CORE.SNC_DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x708004477", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts streaming stores that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10800", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts Demand RFOs, ItoM's, PREFECTHW's, Hardware RFO Prefetches to the L1/L2 and Streaming stores that likely resulted in a store to Memory (DRAM or PMM)", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.WRITE_ESTIMATE.MEMORY", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0xFBFF80822", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread.", + "EventCode": "0xa5", + "EventName": "RS.EMPTY", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)", + "SampleAfterValue": "1000003", + "UMask": "0x7" + }, + { + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS.EMPTY_COUNT", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to closely sample on front-end latency issues (see the FRONTEND_RETIRED event of designated precise events)", + "SampleAfterValue": "100003", + "UMask": "0x7" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY_COUNT", + "CounterMask": "1", + "Deprecated": "1", + "EdgeDetect": "1", + "EventCode": "0xa5", + "EventName": "RS_EMPTY.COUNT", + "Invert": "1", + "SampleAfterValue": "100003", + "UMask": "0x7" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event RS.EMPTY", + "Deprecated": "1", + "EventCode": "0xa5", + "EventName": "RS_EMPTY.CYCLES", + "SampleAfterValue": "1000003", + "UMask": "0x7" + }, + { + "BriefDescription": "Cycles the uncore cannot take further requests", + "CounterMask": "1", + "EventCode": "0x2d", + "EventName": "XQ.FULL_CYCLES", + "PublicDescription": "number of cycles when the thread is active and the uncore cannot take any further requests (for example prefetches, loads or stores initiated by the Core that miss the L2 cache).", + "SampleAfterValue": "1000003", + "UMask": "0x1" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json new file mode 100644 index 000000000000..6dcf3b763af4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json @@ -0,0 +1,975 @@ +[ + { + "BriefDescription": "AMX retired arithmetic BF16 operations.", + "EventCode": "0xce", + "EventName": "AMX_OPS_RETIRED.BF16", + "PublicDescription": "Number of AMX-based retired arithmetic bfloat16 (BF16) floating-point operations. Counts TDPBF16PS FP instructions. SW to use operation multiplier of 4", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "AMX retired arithmetic integer 8-bit operations.", + "EventCode": "0xce", + "EventName": "AMX_OPS_RETIRED.INT8", + "PublicDescription": "Number of AMX-based retired arithmetic integer operations of 8-bit width source operands. Counts TDPB[SS,UU,US,SU]D instructions. SW should use operation multiplier of 8.", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE", + "CounterMask": "1", + "Deprecated": "1", + "EventCode": "0xb0", + "EventName": "ARITH.DIVIDER_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x9" + }, + { + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations.", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.DIV_ACTIVE", + "PublicDescription": "Counts cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "SampleAfterValue": "1000003", + "UMask": "0x9" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event ARITH.FPDIV_ACTIVE", + "CounterMask": "1", + "Deprecated": "1", + "EventCode": "0xb0", + "EventName": "ARITH.FP_DIVIDER_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event counts the cycles the integer divider is busy.", + "CounterMask": "1", + "EventCode": "0xb0", + "EventName": "ARITH.IDIV_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event ARITH.IDIV_ACTIVE", + "CounterMask": "1", + "Deprecated": "1", + "EventCode": "0xb0", + "EventName": "ARITH.INT_DIVIDER_ACTIVE", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of occurrences where a microcode assist is invoked by hardware.", + "EventCode": "0xc1", + "EventName": "ASSISTS.ANY", + "PublicDescription": "Counts the number of occurrences where a microcode assist is invoked by hardware. Examples include AD (page Access Dirty), FP and AVX related assists.", + "SampleAfterValue": "100003", + "UMask": "0x1b" + }, + { + "BriefDescription": "All branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts all branch instructions retired.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Conditional branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND", + "PEBS": "1", + "PublicDescription": "Counts conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x11" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PEBS": "1", + "PublicDescription": "Counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" + }, + { + "BriefDescription": "Taken conditional branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_TAKEN", + "PEBS": "1", + "PublicDescription": "Counts taken conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Far branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.FAR_BRANCH", + "PEBS": "1", + "PublicDescription": "Counts far branch instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x40" + }, + { + "BriefDescription": "Indirect near branch instructions retired (excluding returns)", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.INDIRECT", + "PEBS": "1", + "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Direct and indirect near call instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "Counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x2" + }, + { + "BriefDescription": "Return instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PEBS": "1", + "PublicDescription": "Counts return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "Taken branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "Counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "All mispredicted branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND", + "PEBS": "1", + "PublicDescription": "Counts mispredicted conditional branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x11" + }, + { + "BriefDescription": "Mispredicted non-taken conditional branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_NTAKEN", + "PEBS": "1", + "PublicDescription": "Counts the number of conditional branch instructions retired that were mispredicted and the branch direction was not taken.", + "SampleAfterValue": "400009", + "UMask": "0x10" + }, + { + "BriefDescription": "number of branch instructions retired that were mispredicted and taken.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "PEBS": "1", + "PublicDescription": "Counts taken conditional mispredicted branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x1" + }, + { + "BriefDescription": "Miss-predicted near indirect branch instructions retired (excluding returns)", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT", + "PEBS": "1", + "PublicDescription": "Counts miss-predicted near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.", + "SampleAfterValue": "100003", + "UMask": "0x80" + }, + { + "BriefDescription": "Mispredicted indirect CALL retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.INDIRECT_CALL", + "PEBS": "1", + "PublicDescription": "Counts retired mispredicted indirect (near taken) CALL instructions, including both register and memory indirect.", + "SampleAfterValue": "400009", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "Counts number of near branch instructions retired that were mispredicted and taken.", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.RET", + "PEBS": "1", + "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state.", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C01", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 light-weight slower wakeup time but more power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state.", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C02", + "PublicDescription": "Counts core clocks when the thread is in the C0.2 light-weight faster wakeup time but less power saving optimized state. This state can be entered via the TPAUSE or UMWAIT instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Core clocks when the thread is in the C0.1 or C0.2 or running a PAUSE in C0 ACPI state.", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.C0_WAIT", + "PublicDescription": "Counts core clocks when the thread is in the C0.1 or C0.2 power saving optimized states (TPAUSE or UMWAIT instructions) or running the PAUSE instruction.", + "SampleAfterValue": "2000003", + "UMask": "0x70" + }, + { + "BriefDescription": "Cycle counts are evenly distributed between active threads in the Core.", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.DISTRIBUTED", + "PublicDescription": "This event distributes cycle counts between active hyperthreads, i.e., those in C0. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If all other hyperthreads are inactive (or disabled or do not exist), all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "PublicDescription": "Counts Core crystal clock cycles when current thread is unhalted and the other thread is halted.", + "SampleAfterValue": "25003", + "UMask": "0x2" + }, + { + "BriefDescription": "CPU_CLK_UNHALTED.PAUSE", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "CPU_CLK_UNHALTED.PAUSE_INST", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xec", + "EventName": "CPU_CLK_UNHALTED.PAUSE_INST", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Core crystal clock cycles. Cycle counts are evenly distributed between active threads in the Core.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_DISTRIBUTED", + "PublicDescription": "This event distributes Core crystal clock cycle counts between active hyperthreads, i.e., those in C0 sleep-state. A hyperthread becomes inactive when it executes the HLT or MWAIT instructions. If one thread is active in a core, all counts are attributed to this hyperthread. To obtain the full count when the Core is active, sum the counts from each hyperthread.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "SampleAfterValue": "2000003", + "UMask": "0x3" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. It is counted on a dedicated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Core cycles when the thread is not in halt state", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Thread cycles when thread is not in halt state", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "CounterMask": "8", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "CounterMask": "1", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "CounterMask": "16", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "CounterMask": "12", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "SampleAfterValue": "1000003", + "UMask": "0xc" + }, + { + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "CounterMask": "5", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x5" + }, + { + "BriefDescription": "Total execution stalls.", + "CounterMask": "4", + "EventCode": "0xa3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", + "SampleAfterValue": "1000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.1_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 1 uop was executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.2_PORTS_UTIL", + "PublicDescription": "Counts cycles during which a total of 2 uops were executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.3_PORTS_UTIL", + "PublicDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.4_PORTS_UTIL", + "PublicDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station (RS) was not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", + "CounterMask": "5", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_LOADS", + "SampleAfterValue": "2000003", + "UMask": "0x21" + }, + { + "BriefDescription": "Cycles where the Store Buffer was full and no loads caused an execution stall.", + "CounterMask": "2", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "PublicDescription": "Counts cycles where the Store Buffer was full and no loads caused an execution stall.", + "SampleAfterValue": "1000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Cycles no uop executed while RS was not empty, the SB was not full and there was no outstanding load.", + "EventCode": "0xa6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Number of cycles total of 0 uops executed on all ports, Reservation Station (RS) was not empty, the Store Buffer (SB) was not full and there was no outstanding load.", + "SampleAfterValue": "1000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Instruction decoders utilized in a cycle", + "EventCode": "0x75", + "EventName": "INST_DECODED.DECODERS", + "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", + "EventName": "INST_RETIRED.ANY", + "PEBS": "1", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "PEBS": "1", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "INST_RETIRED.MACRO_FUSED", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.MACRO_FUSED", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Retired NOP instructions.", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.NOP", + "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Precise instruction retired with PEBS precise-distribution", + "EventName": "INST_RETIRED.PREC_DIST", + "PEBS": "1", + "PublicDescription": "A version of INST_RETIRED that allows for a precise distribution of samples across instructions retired. It utilizes the Precise Distribution of Instructions Retired (PDIR++) feature to fix bias in how retired instructions get sampled. Use on Fixed Counter 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Iterations of Repeat string retired instructions.", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.REP_ITERATION", + "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Clears speculative count", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEARS_COUNT", + "PublicDescription": "Counts the number of speculative clears due to any type of branch misprediction or machine clears", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "EventCode": "0xad", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "PublicDescription": "Cycles after recovery from a branch misprediction or machine clear till the first uop is issued from the resteered path.", + "SampleAfterValue": "500009", + "UMask": "0x80" + }, + { + "BriefDescription": "INT_MISC.MBA_STALLS", + "EventCode": "0xad", + "EventName": "INT_MISC.MBA_STALLS", + "SampleAfterValue": "1000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread", + "EventCode": "0xad", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Counts core cycles when the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, + { + "BriefDescription": "INT_MISC.UNKNOWN_BRANCH_CYCLES", + "EventCode": "0xad", + "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", + "MSRIndex": "0x3F7", + "MSRValue": "0x7", + "SampleAfterValue": "1000003", + "UMask": "0x40" + }, + { + "BriefDescription": "TMA slots where uops got dropped", + "EventCode": "0xad", + "EventName": "INT_MISC.UOP_DROPPING", + "PublicDescription": "Estimated number of Top-down Microarchitecture Analysis slots that got dropped due to non front-end reasons", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "INT_VEC_RETIRED.128BIT", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.128BIT", + "SampleAfterValue": "1000003", + "UMask": "0x13" + }, + { + "BriefDescription": "INT_VEC_RETIRED.256BIT", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.256BIT", + "SampleAfterValue": "1000003", + "UMask": "0xac" + }, + { + "BriefDescription": "integer ADD, SUB, SAD 128-bit vector instructions.", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.ADD_128", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 128-bit vector instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x3" + }, + { + "BriefDescription": "integer ADD, SUB, SAD 256-bit vector instructions.", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.ADD_256", + "PublicDescription": "Number of retired integer ADD/SUB (regular or horizontal), SAD 256-bit vector instructions.", + "SampleAfterValue": "1000003", + "UMask": "0xc" + }, + { + "BriefDescription": "INT_VEC_RETIRED.MUL_256", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.MUL_256", + "SampleAfterValue": "1000003", + "UMask": "0x80" + }, + { + "BriefDescription": "INT_VEC_RETIRED.SHUFFLES", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.SHUFFLES", + "SampleAfterValue": "1000003", + "UMask": "0x40" + }, + { + "BriefDescription": "INT_VEC_RETIRED.VNNI_128", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.VNNI_128", + "SampleAfterValue": "1000003", + "UMask": "0x10" + }, + { + "BriefDescription": "INT_VEC_RETIRED.VNNI_256", + "EventCode": "0xe7", + "EventName": "INT_VEC_RETIRED.VNNI_256", + "SampleAfterValue": "1000003", + "UMask": "0x20" + }, + { + "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.ADDRESS_ALIAS", + "PublicDescription": "Counts the number of times a load got blocked due to false dependencies in MOB due to partial compare on address.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "Counts the number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use.", + "SampleAfterValue": "100003", + "UMask": "0x88" + }, + { + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x82" + }, + { + "BriefDescription": "Counts the number of demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", + "EventCode": "0x4c", + "EventName": "LOAD_HIT_PREFETCH.SWPF", + "PublicDescription": "Counts all not software-prefetch load dispatches that hit the fill buffer (FB) allocated for the software prefetch. It can also be incremented by some lock instructions. So it should only be used with profiling so that the locks can be excluded by ASM (Assembly File) inspection of the nearby instructions.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "CounterMask": "1", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_ACTIVE", + "PublicDescription": "Counts the cycles when at least one uop is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles optimal number of Uops delivered by the LSD, but did not come from the decoder.", + "CounterMask": "6", + "EventCode": "0xa8", + "EventName": "LSD.CYCLES_OK", + "PublicDescription": "Counts the cycles when optimal number of uops is delivered by the LSD (Loop-stream detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of Uops delivered by the LSD.", + "EventCode": "0xa8", + "EventName": "LSD.UOPS", + "PublicDescription": "Counts the number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Number of machine clears (nukes) of any type.", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.COUNT", + "PublicDescription": "Counts the number of machine clears (nukes) of any type.", + "SampleAfterValue": "100003", + "UMask": "0x1" + }, + { + "BriefDescription": "Self-modifying code (SMC) detected.", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "LFENCE instructions retired", + "EventCode": "0xe0", + "EventName": "MISC2_RETIRED.LFENCE", + "PublicDescription": "number of LFENCE retired instructions", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "Increments whenever there is an update to the LBR array.", + "EventCode": "0xcc", + "EventName": "MISC_RETIRED.LBR_INSERTS", + "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.SB", + "PublicDescription": "Counts allocation stall cycles caused by the store buffer (SB) being full. This counts cycles that the pipeline back-end blocked uop delivery from the front-end.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Counts cycles where the pipeline is stalled due to serializing operations.", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.SCOREBOARD", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "TMA slots where no uops were being issued due to lack of back-end resources.", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", + "PublicDescription": "Number of slots in TMA method where no micro-operations were being issued from front-end to back-end of the machine due to lack of back-end resources.", + "SampleAfterValue": "10000003", + "UMask": "0x2" + }, + { + "BriefDescription": "TMA slots wasted due to incorrect speculations.", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BAD_SPEC_SLOTS", + "PublicDescription": "Number of slots of TMA method that were wasted due to incorrect speculation. It covers all types of control-flow or data-related mis-speculations.", + "SampleAfterValue": "10000003", + "UMask": "0x4" + }, + { + "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS", + "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by (any type of) branch mispredictions. This event estimates number of speculative operations that were issued but not retired as well as the out-of-order engine recovery past a branch misprediction.", + "SampleAfterValue": "10000003", + "UMask": "0x8" + }, + { + "BriefDescription": "TOPDOWN.MEMORY_BOUND_SLOTS", + "EventCode": "0xa4", + "EventName": "TOPDOWN.MEMORY_BOUND_SLOTS", + "SampleAfterValue": "10000003", + "UMask": "0x10" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", + "EventName": "TOPDOWN.SLOTS", + "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core. Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", + "SampleAfterValue": "10000003", + "UMask": "0x4" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event", + "EventCode": "0xa4", + "EventName": "TOPDOWN.SLOTS_P", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core.", + "SampleAfterValue": "10000003", + "UMask": "0x1" + }, + { + "BriefDescription": "UOPS_DECODED.DEC0_UOPS", + "EventCode": "0x76", + "EventName": "UOPS_DECODED.DEC0_UOPS", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops executed on port 0", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_0", + "PublicDescription": "Number of uops dispatch to execution port 0.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops executed on port 1", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_1", + "PublicDescription": "Number of uops dispatch to execution port 1.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Uops executed on ports 2, 3 and 10", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_2_3_10", + "PublicDescription": "Number of uops dispatch to execution ports 2, 3 and 10", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Uops executed on ports 4 and 9", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_4_9", + "PublicDescription": "Number of uops dispatch to execution ports 4 and 9", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Uops executed on ports 5 and 11", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_5_11", + "PublicDescription": "Number of uops dispatch to execution ports 5 and 11", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Uops executed on port 6", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_6", + "PublicDescription": "Number of uops dispatch to execution port 6.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Uops executed on ports 7 and 8", + "EventCode": "0xb2", + "EventName": "UOPS_DISPATCHED.PORT_7_8", + "PublicDescription": "Number of uops dispatch to execution ports 7 and 8.", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of uops executed on the core.", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Counts the number of uops executed from any thread.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", + "PublicDescription": "Counts cycles when at least 1 micro-op is executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "CounterMask": "2", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "PublicDescription": "Counts cycles when at least 2 micro-ops are executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "CounterMask": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "PublicDescription": "Counts cycles when at least 3 micro-ops are executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", + "CounterMask": "4", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", + "PublicDescription": "Counts cycles when at least 4 micro-ops are executed from any thread on physical core.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "CounterMask": "2", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", + "CounterMask": "3", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "CounterMask": "4", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "CounterMask": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.STALLS", + "Invert": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UOPS_EXECUTED.STALLS", + "CounterMask": "1", + "Deprecated": "1", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "Invert": "1", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.THREAD", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of x87 uops dispatched.", + "EventCode": "0xb1", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Uops that RAT issues to RS", + "EventCode": "0xae", + "EventName": "UOPS_ISSUED.ANY", + "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with retired uop(s).", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.CYCLES", + "PublicDescription": "Counts cycles where at least one uop has retired.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired uops except the last uop of each instruction.", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.HEAVY", + "PublicDescription": "Counts the number of retired micro-operations (uops) except the last uop of each instruction. An instruction that is decoded into less than two uops does not contribute to the count.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "UOPS_RETIRED.MS", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MS", + "MSRIndex": "0x3F7", + "MSRValue": "0x8", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Retirement slots used.", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.SLOTS", + "PublicDescription": "Counts the retirement slots used each cycle.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles without actually retired uops.", + "CounterMask": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.STALLS", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", + "SampleAfterValue": "1000003", + "UMask": "0x2" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event UOPS_RETIRED.STALLS", + "CounterMask": "1", + "Deprecated": "1", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "Invert": "1", + "SampleAfterValue": "1000003", + "UMask": "0x2" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json new file mode 100644 index 000000000000..bf5a511b99d1 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json @@ -0,0 +1,5988 @@ +[ + { + "BriefDescription": "CHA to iMC Bypass : Intermediate bypass Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.INTERMEDIATE", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Intermediate bypass Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the intermediate bypass.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass : Not Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.NOT_TAKEN", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Not Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that could not take the bypass, and issues a read to memory. Note that transactions that did not take the bypass but did not issue read to memory will not be counted.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Bypass : Taken", + "EventCode": "0x57", + "EventName": "UNC_CHA_BYPASS_CHA_IMC.TAKEN", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Bypass : Taken : Counts the number of times when the CHA was able to bypass HA pipe on the way to iMC. This is a latency optimization for situations when there is light loadings on the memory subsystem. This can be filtered by when the bypass was taken and when it was not. : Filter for transactions that succeeded in taking the full bypass.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA Clockticks", + "EventCode": "0x01", + "EventName": "UNC_CHA_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of CHA clock cycles while the event is enabled", + "Unit": "CHA" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_CHA_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Any Cycle with Multiple Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xf2", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Any Single Snoop", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.ANY_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Any Single Snoop : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0xf1", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x42", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Core Requests", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.CORE_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Core Requests : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x41", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x82", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Eviction", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EVICT_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Eviction : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x81", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x22", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single External Snoops", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.EXT_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single External Snoops : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x21", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Multiple Snoop Targets from Remote", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.REMOTE_GTONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Multiple Snoop Targets from Remote : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x12", + "Unit": "CHA" + }, + { + "BriefDescription": "Core Cross Snoops Issued : Single Snoop Target from Remote", + "EventCode": "0x33", + "EventName": "UNC_CHA_CORE_SNP.REMOTE_ONE", + "PerPkg": "1", + "PublicDescription": "Core Cross Snoops Issued : Single Snoop Target from Remote : Counts the number of transactions that trigger a configurable number of cross snoops. Cores are snooped if the transaction looks up the cache and determines that it is necessary based on the operation type and what CoreValid bits are set. For example, if 2 CV bits are set on a data read, the cores must have the data in S state so it is not necessary to snoop them. However, if only 1 CV bit is set the core my have modified the data. If the transaction was an RFO, it would need to invalidate the lines. This event can be filtered based on who triggered the initial snoop(s).", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6e", + "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_DRD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6e", + "EventName": "UNC_CHA_DIRECT_GO.HA_SUPPRESS_NO_D2C", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6e", + "EventName": "UNC_CHA_DIRECT_GO.HA_TOR_DEALLOC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.EXTCMP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.FAST_GO_PULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.GO", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.GO_PULL", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.IDLE_DUE_SUPPRESS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.NOP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Direct GO", + "EventCode": "0x6d", + "EventName": "UNC_CHA_DIRECT_GO_OPC.PULL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Not Needed", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.NO_SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and therefore did not send a snoop because the Directory indicated it was not needed.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state lookups; Snoop Needed", + "EventCode": "0x53", + "EventName": "UNC_CHA_DIR_LOOKUP.SNP", + "PerPkg": "1", + "PublicDescription": "Counts transactions that looked into the multi-socket cacheline Directory state, and sent one or more snoops, because the Directory indicated it was needed.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from the HA pipe", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.HA", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates memory writes issued from the HA pipe. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Multi-socket cacheline Directory state updates; Directory Updated memory write from TOR pipe", + "EventCode": "0x54", + "EventName": "UNC_CHA_DIR_UPDATE.TOR", + "PerPkg": "1", + "PublicDescription": "Counts only multi-socket cacheline Directory state updates due to memory writes issued from the TOR pipe which are the result of remote transaction hitting the SF/LLC and returning data Core2Core. This does not include memory write requests which are for I (Invalid) or E (Exclusive) cachelines.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_CHA_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Read request from a remote socket which hit in the HitMe Cache to a line In the E state", + "EventCode": "0x5f", + "EventName": "UNC_CHA_HITME_HIT.EX_RDS", + "PerPkg": "1", + "PublicDescription": "Counts read requests from a remote socket which hit in the HitME cache (used to cache the multi-socket Directory state) to a line in the E(Exclusive) state. This includes the following read opcodes (RdCode, RdData, RdDataMigratory, RdCur, RdInv*, Inv*).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache : Shared hit and op is RdInvOwn, RdInv, Inv*", + "EventCode": "0x5f", + "EventName": "UNC_CHA_HITME_HIT.SHARED_OWNREQ", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache : op is WbMtoE", + "EventCode": "0x5f", + "EventName": "UNC_CHA_HITME_HIT.WBMTOE", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Hits in HitMe Cache : op is WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", + "EventCode": "0x5f", + "EventName": "UNC_CHA_HITME_HIT.WBMTOI_OR_S", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times HitMe Cache is accessed : op is RdCode, RdData, RdDataMigratory, RdCur, RdInvOwn, RdInv, Inv*", + "EventCode": "0x5e", + "EventName": "UNC_CHA_HITME_LOOKUP.READ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of times HitMe Cache is accessed : op is WbMtoE, WbMtoI, WbPushMtoI, WbFlush, or WbMtoS", + "EventCode": "0x5e", + "EventName": "UNC_CHA_HITME_LOOKUP.WRITE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache : No SF/LLC HitS/F and op is RdInvOwn", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.NOTSHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache : op is RdCode, RdData, RdDataMigratory, RdCur, RdInv, Inv*", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.READ_OR_INV", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts Number of Misses in HitMe Cache : SF/LLC HitS/F and op is RdInvOwn", + "EventCode": "0x60", + "EventName": "UNC_CHA_HITME_MISS.SHARED_RDINVOWN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Deallocate HitME$ on Reads without RspFwdI*", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a local request", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.DEALLOCATE_RSPFWDI_LOC", + "PerPkg": "1", + "PublicDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a local request : Received RspFwdI* for a local request, but converted HitME$ to SF entry", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Update HitMe Cache on RdInvOwn even if not RspFwdI*", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.RDINVOWN", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a remote request", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.RSPFWDI_REM", + "PerPkg": "1", + "PublicDescription": "Counts the number of Allocate/Update to HitMe Cache : op is RspIFwd or RspIFwdWb for a remote request : Updated HitME$ on RspFwdI* or local HitM/E received for a remote request", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Counts the number of Allocate/Update to HitMe Cache : Update HitMe Cache to SHARed", + "EventCode": "0x61", + "EventName": "UNC_CHA_HITME_UPDATE.SHARED", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Normal priority reads issued to the memory controller from the CHA", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.NORMAL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) read is issued to any of the memory controller channels from the CHA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "HA to iMC Reads Issued : ISOCH", + "EventCode": "0x59", + "EventName": "UNC_CHA_IMC_READS_COUNT.PRIORITY", + "PerPkg": "1", + "PublicDescription": "HA to iMC Reads Issued : ISOCH : Count of the number of reads issued to any of the memory controller channels. This can be filtered by the priority of the reads.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued; Full Line Non-ISOCH", + "EventCode": "0x5b", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL", + "PerPkg": "1", + "PublicDescription": "Counts when a normal (Non-Isochronous) full line write is issued from the CHA to the any of the memory controller channels.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line", + "EventCode": "0x5b", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.FULL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Full Line : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH", + "EventCode": "0x5b", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : Partial Non-ISOCH : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial", + "EventCode": "0x5b", + "EventName": "UNC_CHA_IMC_WRITES_COUNT.PARTIAL_PRIORITY", + "PerPkg": "1", + "PublicDescription": "CHA to iMC Full Line Writes Issued : ISOCH Partial : Counts the total number of full line writes issued from the HA into the memory controller.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Any Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", + "UMask": "0x1fffff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All transactions from Remote Agents", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ALL_REMOTE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : All transactions from Remote Agents : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x17e0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.ANY_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : All Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Any local or remote transaction to the LLC, including prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x1bd0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.CODE_READ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Local non-prefetch requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.COREPREF_OR_DMND_LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Local non-prefetch requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Any local transaction to the LLC, not including prefetch", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1bc1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Data Reads", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_ALL", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Data Reads : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1fc1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Data Read Request", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Data Read Request : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Read transactions.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Demand Data Reads, Core and LLC prefetches", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_LOCAL", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Demand Data Reads, Core and LLC prefetches : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x841ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Data Read Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_MISS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Data Read Misses : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1fc101", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : E State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.E", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Hit Exclusive State", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : F State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : F State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Hit Forward State", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_INV", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "UMask": "0x1a44ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.FLUSH_OR_INV_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : I State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.I", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : I State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Miss", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Local LLC prefetch requests (from LLC)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LLCPREF_LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Local LLC prefetch requests (from LLC) : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Any local LLC prefetch to the LLC", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed locally", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCALLY_HOMED_ADDRESS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed locally : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in the local MC.", + "UMask": "0xbdfff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_CODE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x19d0ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Request that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_DATA_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x19c1ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Demand CRd Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_DMND_CODE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x1850ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Demand Data Reads that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_DMND_DATA_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1841ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Demand RFO Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_DMND_RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1848ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed locally", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed locally : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in the local MC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_FLUSH_INV", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "UMask": "0x1844ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Prefetch requests to the LLC that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_LLC_PF", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x189dff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Prefetches that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_PF", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x199dff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Prefetches that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_PF_CODE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x1910ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Prefetches that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_PF_DATA_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1981ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Prefetches that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_PF_RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1908ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Requests that come from the local socket (usually the core)", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.LOCAL_RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x19c8ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : M State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.M", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : M State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Hit Modified State", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : All Misses", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.MISS_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x1fe001", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Write Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.OTHER_REQ_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Write Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remote non-snoop requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.PREF_OR_DMND_REMOTE_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remote non-snoop requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Remote non-snoop transactions to the LLC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed remotely", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTELY_HOMED_ADDRESS", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed remotely : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in a remote MC", + "UMask": "0x15dfff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : CRd Requests that come from a Remote socket.", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_CODE", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : CRd Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote CRd transactions to the LLC. This includes CRd prefetch.", + "UMask": "0x1a10ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Data Read Requests that come from a Remote socket", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_DATA_RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state. Read transactions", + "UMask": "0x1a01ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Transactions homed remotely", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Transactions homed remotely : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Transaction whose address resides in a remote MC", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Flush or Invalidate requests that come from a Remote socket.", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_FLUSH_INV", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Flush : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing.", + "UMask": "0x1a04ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Filters Requests for those that write info into the cache that come from a remote socket", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_OTHER", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Write Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Writeback transactions from L2 to the LLC This includes all write transactions -- both Cacheable and UC.", + "UMask": "0x1a02ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Requests that come from a Remote socket.", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1a08ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remote snoop requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNOOP_F", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : Remote snoop requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Remote snoop transactions to the LLC.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache and Snoop Filter Lookups; Snoop Requests from a Remote Socket", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.REMOTE_SNP", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. CHAFilter0[24:21,17] bits correspond to [FMESI] state.; Filters for any transaction originating from the IPQ or IRQ. This does not include lookups originating from the ISMQ.", + "UMask": "0x1c19ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Requests", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : RFO Requests : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "UMask": "0x1bc8ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : RFO Request Filter", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_F", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Local or remote RFO transactions to the LLC. This includes RFO prefetch.", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Locally HOMed RFOs - Demand and Prefetches", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.RFO_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x9c8ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : S State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.S", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : Hit Shared State", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - E State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_E", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - E State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : SF Hit Exclusive State", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - H State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_H", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - H State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : SF Hit HitMe State", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : SnoopFilter - S State", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.SF_S", + "PerPkg": "1", + "PublicDescription": "Cache Lookups : SnoopFilter - S State : Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS set umask bit 0 and select a state or states to match. Otherwise, the event will count nothing. : SF Hit Shared State", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Writes", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing. : Requests that install or change a line in the LLC. Examples: Writebacks from Core L2's and UPI. Prefetches into the LLC.", + "UMask": "0x842ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Cache Lookups : Remote Writes", + "EventCode": "0x34", + "EventName": "UNC_CHA_LLC_LOOKUP.WRITE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of times the LLC was accessed - this includes code, data, prefetches and hints coming from L2. This has numerous filters available. Note the non-standard filtering equation. This event will count requests that lookup the cache multiple times with multiple increments. One must ALWAYS select a state or states (in the umask field) to match. Otherwise, the event will count nothing.", + "UMask": "0x17c2ff", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in E state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.E_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in E state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : IA traffic", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IA", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : IA traffic : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : IO traffic", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IO", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : IO traffic : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in E state that are victimized on a fill from an IO device", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IO_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x12", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in F or S state that are victimized on a fill from an IO device", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IO_FS", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1c", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in M state that are victimized on a fill from an IO device", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IO_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x11", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in any state that are victimized on a fill from an IO device", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.IO_MESF", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Local - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x200f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_E", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2002", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_M", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2001", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Local Only", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_ONLY", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Local Only : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.LOCAL_S", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2004", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in M state", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.M_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in M state : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized; Remote - All Lines", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x800f", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_E", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8002", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_M", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8001", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Remote Only", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_ONLY", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Remote Only : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.REMOTE_S", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x8004", + "Unit": "CHA" + }, + { + "BriefDescription": "Lines Victimized : Lines in S State", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.S_STATE", + "PerPkg": "1", + "PublicDescription": "Lines Victimized : Lines in S State : Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in E state that are victimized on a fill", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_E", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in M state that are victimized on a fill", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_M", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "All LLC lines in S state that are victimized on a fill", + "EventCode": "0x37", + "EventName": "UNC_CHA_LLC_VICTIMS.TOTAL_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of lines that were victimized on a fill. This can be filtered by the state that the line was in.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : CV0 Prefetch Miss", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_MISS", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : CV0 Prefetch Miss : Miscellaneous events in the Cbo.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : CV0 Prefetch Victim", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.CV0_PREF_VIC", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : CV0 Prefetch Victim : Miscellaneous events in the Cbo.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of times that an RFO hit in S state.", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RFO_HIT_S", + "PerPkg": "1", + "PublicDescription": "Counts when a RFO (the Read for Ownership issued before a write) request hit a cacheline in the S (Shared) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : Silent Snoop Eviction", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.RSPI_WAS_FSE", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : Silent Snoop Eviction : Miscellaneous events in the Cbo. : Counts the number of times when a Snoop hit in FSE states and triggered a silent eviction. This is useful because this information is lost in the PRE encodings.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Cbo Misc : Write Combining Aliasing", + "EventCode": "0x39", + "EventName": "UNC_CHA_MISC.WC_ALIASING", + "PerPkg": "1", + "PublicDescription": "Cbo Misc : Write Combining Aliasing : Miscellaneous events in the Cbo. : Counts the number of times that a USWC write (WCIL(F)) transaction hit in the LLC in M state, triggering a WBMtoI followed by the USWC write. This occurs when there is WC aliasing.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Local InvItoE", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.LOCAL_INVITOE", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Local InvItoE : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Local Rd", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.LOCAL_READ", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Local Rd : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Off", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.OFF_PWRHEURISTIC", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Off : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Remote Rd", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.REMOTE_READ", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Remote Rd : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : Remote Rd InvItoE", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.REMOTE_READINVITOE", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : Remote Rd InvItoE : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "OSB Snoop Broadcast : RFO HitS Snoop Broadcast", + "EventCode": "0x55", + "EventName": "UNC_CHA_OSB.RFO_HITS_SNP_BCAST", + "PerPkg": "1", + "PublicDescription": "OSB Snoop Broadcast : RFO HitS Snoop Broadcast : Count of OSB snoop broadcasts. Counts by 1 per request causing OSB snoops to be broadcast. Does not count all the snoops generated by OSB.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.LOCAL", + "EventCode": "0x65", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.REMOTE", + "EventCode": "0x65", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.REMOTE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.SETCONFLICT", + "EventCode": "0x65", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_INVITOX.SETCONFLICT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw a Near Memory set conflict in SF/LLC", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.LLC", + "PerPkg": "1", + "PublicDescription": "Near Memory evictions due to another read to the same Near Memory set in the LLC.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw a Near memory set conflict in SF/LLC", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.SF", + "PerPkg": "1", + "PublicDescription": "Near Memory evictions due to another read to the same Near Memory set in the SF", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Memory Mode related events; Counts the number of times CHA saw a Near Memory set conflict in TOR", + "EventCode": "0x64", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS.TOR", + "PerPkg": "1", + "PublicDescription": "No Reject in the CHA due to a pending read to the same Near Memory set in the TOR.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.IODC", + "EventCode": "0x70", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.IODC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWR", + "EventCode": "0x70", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWRNI", + "EventCode": "0x70", + "EventName": "UNC_CHA_PMM_MEMMODE_NM_SETCONFLICTS2.MEMWRNI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.DDR4_FAST_INSERT", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.DDR4_FAST_INSERT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.REJ_IRQ", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.REJ_IRQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.SLOWTORQ_SKIP", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.SLOWTORQ_SKIP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.SLOW_INSERT", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.SLOW_INSERT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.THROTTLE", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE_IRQ", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.THROTTLE_IRQ", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS.THROTTLE_PRQ", + "EventCode": "0x66", + "EventName": "UNC_CHA_PMM_QOS.THROTTLE_PRQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_FAST_FIFO", + "EventCode": "0x67", + "EventName": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_FAST_FIFO", + "PerPkg": "1", + "PublicDescription": ": count # of FAST TOR Request inserted to ha_tor_req_fifo", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Number of SLOW TOR Request inserted to ha_pmm_tor_req_fifo", + "EventCode": "0x67", + "EventName": "UNC_CHA_PMM_QOS_OCCUPANCY.DDR_SLOW_FIFO", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC0", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC0", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC0 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC1", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC1", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC1 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC2", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC2", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC2 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC3", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC3", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC3 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC4", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC4", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC4 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx READ Credits Empty : MC5", + "EventCode": "0x58", + "EventName": "UNC_CHA_READ_NO_CREDITS.MC5", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx READ Credits Empty : MC5 : Counts the number of times when there are no credits available for sending reads from the CHA into the iMC. In order to send reads into the memory controller, the HA must first acquire a credit for the iMC's AD Ingress queue. : Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Requests for exclusive ownership of a cache line without receiving data", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x30", + "Unit": "CHA" + }, + { + "BriefDescription": "Local requests for exclusive ownership of a cache line without receiving data", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a unit on this socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Remote requests for exclusive ownership of a cache line without receiving data", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.INVITOE_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of requests coming from a remote socket for exclusive ownership of a cache line without receiving data (INVITOE) to the CHA.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests made into the CHA", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS", + "PerPkg": "1", + "PublicDescription": "Counts read requests made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write) .", + "UMask": "0x3", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests from a unit on this socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts read requests coming from a unit on this socket made into this CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Read requests from a remote socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.READS_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts read requests coming from a remote socket made into the CHA. Reads include all read opcodes (including RFO: the Read for Ownership issued before a write).", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Write requests made into the CHA", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES", + "PerPkg": "1", + "PublicDescription": "Counts write requests made into the CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0xc", + "Unit": "CHA" + }, + { + "BriefDescription": "Write Requests from a unit on this socket", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts write requests coming from a unit on this socket made into this CHA, including streaming, evictions, HitM (Reads from another core to a Modified cacheline), etc.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Read and Write Requests; Writes Remote", + "EventCode": "0x50", + "EventName": "UNC_CHA_REQUESTS.WRITES_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the total number of read requests made into the Home Agent. Reads include all read opcodes (including RFO). Writes include all writes (streaming, evictions, HitM, etc).", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IPQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IPQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : IRQ Rejected", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.IRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : IRQ Rejected : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : PRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.PRQ_REJ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : PRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : RRQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.RRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : RRQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Allocations : WBQ", + "EventCode": "0x13", + "EventName": "UNC_CHA_RxC_INSERTS.WBQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Allocations : WBQ : Counts number of allocations per cycle into the specified Ingress queue.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x22", + "EventName": "UNC_CHA_RxC_IPQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the IPQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "IPQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IPQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x23", + "EventName": "UNC_CHA_RxC_IPQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x18", + "EventName": "UNC_CHA_RxC_IRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the IRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC or SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Request Queue Rejects; PhyAddr Match", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "IRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "IRQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x19", + "EventName": "UNC_CHA_RxC_IRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : BL WB on VN0", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request", + "EventCode": "0x24", + "EventName": "UNC_CHA_RxC_ISMQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2c", + "EventName": "UNC_CHA_RxC_ISMQ0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 1 : ANY0", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Rejects - Set 1 : HA", + "EventCode": "0x25", + "EventName": "UNC_CHA_RxC_ISMQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "ISMQ Rejects - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 1 : ANY0", + "EventCode": "0x2d", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 1 : ANY0 : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores. : Any condition listed in the ISMQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "ISMQ Retries - Set 1 : HA", + "EventCode": "0x2d", + "EventName": "UNC_CHA_RxC_ISMQ1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "ISMQ Retries - Set 1 : HA : Number of times a transaction flowing through the ISMQ had to retry. Transaction pass through the ISMQ as responses for requests that already exist in the Cbo. Some examples include: when data is returned or when snoop responses come back from the cores.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : IPQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : IPQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : RRQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.RRQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : RRQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Ingress (from CMS) Occupancy : WBQ", + "EventCode": "0x11", + "EventName": "UNC_CHA_RxC_OCCUPANCY.WBQ", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Occupancy : WBQ : Counts number of entries in the specified Ingress queue in each cycle.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : AD REQ on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : AD RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : Non UPI AK Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL NCB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL NCS on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL RSP on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : BL WB on VN0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2e", + "EventName": "UNC_CHA_RxC_OTHER0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 0 : Non UPI IV Request : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : Allow Snoop", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : Allow Snoop : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : ANY0", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : ANY0 : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Any condition listed in the Other0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : HA", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : HA : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : LLC OR SF Way", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : LLC OR SF Way : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : LLC Victim", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : LLC Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : PhyAddr Match", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : PhyAddr Match : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : SF Victim", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : SF Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject) : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Other Retries - Set 1 : Victim", + "EventCode": "0x2f", + "EventName": "UNC_CHA_RxC_OTHER1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "Other Retries - Set 1 : Victim : Retry Queue Inserts of Transactions that were already in another Retry Q (sub-events encode the reason for the next reject)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD REQ on VN0 : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : AD RSP on VN0 : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI AK Request : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCB on VN0 : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL NCS on VN0 : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL RSP on VN0 : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : BL WB on VN0 : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request", + "EventCode": "0x20", + "EventName": "UNC_CHA_RxC_PRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 0 : Non UPI IV Request : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Allow Snoop", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : ANY0 : Any condition listed in the PRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : HA", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.HA", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC OR SF Way : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : LLC Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : PhyAddr Match : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "PRQ Requests (from CMS) Rejected - Set 1 : SF Victim : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "PRQ Requests (from CMS) Rejected - Set 1 : Victim", + "EventCode": "0x21", + "EventName": "UNC_CHA_RxC_PRQ1_REJECT.VICTIM", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : AD REQ on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : AD REQ on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : AD RSP on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : AD RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : Non UPI AK Request", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : Non UPI AK Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL NCB on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL NCB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL NCS on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL NCS on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL RSP on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL RSP on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : BL WB on VN0", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : BL WB on VN0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 0 : Non UPI IV Request", + "EventCode": "0x2a", + "EventName": "UNC_CHA_RxC_REQ_Q0_RETRY.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 0 : Non UPI IV Request : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : Allow Snoop", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : Allow Snoop : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : ANY0", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.ANY0", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : ANY0 : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Any condition listed in the WBQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : HA", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.HA", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : HA : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : LLC OR SF Way", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : LLC OR SF Way : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : LLC Victim", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : LLC Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : PhyAddr Match", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : PhyAddr Match : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : SF Victim", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : SF Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ) : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Request Queue Retries - Set 1 : Victim", + "EventCode": "0x2b", + "EventName": "UNC_CHA_RxC_REQ_Q1_RETRY.VICTIM", + "PerPkg": "1", + "PublicDescription": "Request Queue Retries - Set 1 : Victim : REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : AD REQ on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : AD RSP on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : Non UPI AK Request", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL NCB on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL NCS on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL RSP on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : BL WB on VN0", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 0 : Non UPI IV Request", + "EventCode": "0x26", + "EventName": "UNC_CHA_RxC_RRQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : Allow Snoop", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : Allow Snoop : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : ANY0", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Any condition listed in the RRQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : HA", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : HA : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : LLC OR SF Way", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : LLC OR SF Way : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : LLC Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : LLC Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : PhyAddr Match", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : PhyAddr Match : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : SF Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : SF Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry. : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "RRQ Rejects - Set 1 : Victim", + "EventCode": "0x27", + "EventName": "UNC_CHA_RxC_RRQ1_REJECT.VICTIM", + "PerPkg": "1", + "PublicDescription": "RRQ Rejects - Set 1 : Victim : Number of times a transaction flowing through the RRQ (Remote Response Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : AD REQ on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_REQ_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : AD REQ on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No AD VN0 credit for generating a request", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : AD RSP on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AD_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : AD RSP on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No AD VN0 credit for generating a response", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : Non UPI AK Request", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.AK_NON_UPI", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : Non UPI AK Request : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Can't inject AK ring message", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL NCB on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCB_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL NCB on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for NCB", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL NCS on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_NCS_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL NCS on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for NCS", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL RSP on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_RSP_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL RSP on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for generating a response", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : BL WB on VN0", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.BL_WB_VN0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : BL WB on VN0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : No BL VN0 credit for generating a writeback", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 0 : Non UPI IV Request", + "EventCode": "0x28", + "EventName": "UNC_CHA_RxC_WBQ0_REJECT.IV_NON_UPI", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 0 : Non UPI IV Request : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Can't inject IV ring message", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : Allow Snoop", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ALLOW_SNP", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : Allow Snoop : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : ANY0", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.ANY0", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : ANY0 : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Any condition listed in the WBQ0 Reject counter was true", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : HA", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.HA", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : HA : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : LLC OR SF Way", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_OR_SF_WAY", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : LLC OR SF Way : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Way conflict with another request that caused the reject", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : LLC Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.LLC_VICTIM", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : LLC Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : PhyAddr Match", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.PA_MATCH", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : PhyAddr Match : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Address match with an outstanding request that was rejected.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : SF Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.SF_VICTIM", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : SF Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry. : Requests did not generate Snoop filter victim", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "WBQ Rejects - Set 1 : Victim", + "EventCode": "0x29", + "EventName": "UNC_CHA_RxC_WBQ1_REJECT.VICTIM", + "PerPkg": "1", + "PublicDescription": "WBQ Rejects - Set 1 : Victim : Number of times a transaction flowing through the WBQ (Writeback Queue) had to retry.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : All", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : All : Counts the number of snoops issued by the HA.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast snoop for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast snoop for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast snoops issued by the HA. This filter includes only requests coming from local sockets.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast snoops for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.BCST_REMOTE", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast snoops for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast snoops issued by the HA.This filter includes only requests coming from remote sockets.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Directed snoops for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Directed snoops for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of directed snoops issued by the HA. This filter includes only requests coming from local sockets.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Directed snoops for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.DIRECT_REMOTE", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Directed snoops for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of directed snoops issued by the HA. This filter includes only requests coming from remote sockets.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast or directed Snoops sent for Local Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.LOCAL", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast or directed Snoops sent for Local Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the local socket.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoops Sent : Broadcast or directed Snoops sent for Remote Requests", + "EventCode": "0x51", + "EventName": "UNC_CHA_SNOOPS_SENT.REMOTE", + "PerPkg": "1", + "PublicDescription": "Snoops Sent : Broadcast or directed Snoops sent for Remote Requests : Counts the number of snoops issued by the HA. : Counts the number of broadcast or directed snoops issued by the HA per request. This filter includes only requests coming from the remote socket.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RSPCNFLCT*", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : RSPCNFLCT* : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for snoops responses of RspConflict. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : RspFwd", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : RspFwd : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of RspFwd to a CA request. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : Rsp*Fwd*WB", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPFWDWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : Rsp*Fwd*WB : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of Rsp*Fwd*WB. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "RspI Snoop Responses Received", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPI", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspI Snoop Response was received which indicates the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO: the Read for Ownership issued before a write hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "RspIFwd Snoop Responses Received", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspIFwd Snoop Response was received which indicates a remote caching agent forwarded the data and the requesting agent is able to acquire the data in E (Exclusive) or M (modified) states. This is commonly returned with RFO (the Read for Ownership issued before a write) transactions. The snoop could have either been to a cacheline in the M,E,F (Modified, Exclusive or Forward) states.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "RspS Snoop Responses Received", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPS", + "PerPkg": "1", + "PublicDescription": "Counts when a transaction with the opcode type RspS Snoop Response was received which indicates when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "RspSFwd Snoop Responses Received", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Counts when a a transaction with the opcode type RspSFwd Snoop Response was received which indicates a remote caching agent forwarded the data but held on to its current copy. This is common for data and code reads that hit in a remote socket in E (Exclusive) or F (Forward) state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received : Rsp*WB", + "EventCode": "0x5c", + "EventName": "UNC_CHA_SNOOP_RESP.RSPWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received : Rsp*WB : Counts the total number of RspI snoop responses received. Whenever a snoops are issued, one or more snoop responses will be returned depending on the topology of the system. In systems larger than 2s, when multiple snoops are returned this will count all the snoops that are received. For example, if 3 snoops were issued and returned RspI, RspS, and RspSFwd; then each of these sub-events would increment by 1. : Filters for a snoop response of RspIWB or RspSWB. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspCnflct", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPCNFLCT", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspCnflct : Number of snoop responses received for a Local request : Filters for snoops responses of RspConflict to local CA requests. This is returned when a snoop finds an existing outstanding transaction in a remote caching agent when it CAMs that caching agent. This triggers conflict resolution hardware. This covers both RspCnflct and RspCnflctWbI.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspFwd", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspFwd to local CA requests. This snoop response is only possible for RdCur when a snoop HITM/E in a remote caching agent and it directly forwards data to a requestor without changing the requestor's cache line state.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : Rsp*FWD*WB", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPFWDWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : Rsp*FWD*WB : Number of snoop responses received for a Local request : Filters for a snoop response of Rsp*Fwd*WB to local CA requests. This snoop response is only used in 4s systems. It is used when a snoop HITM's in a remote caching agent and it directly forwards data to a requestor, and simultaneously returns data to the home to be written back to memory.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspI", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPI", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspI : Number of snoop responses received for a Local request : Filters for snoops responses of RspI to local CA requests. RspI is returned when the remote cache does not have the data, or when the remote cache silently evicts data (such as when an RFO hits non-modified data).", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspIFwd", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPIFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspIFwd : Number of snoop responses received for a Local request : Filters for snoop responses of RspIFwd to local CA requests. This is returned when a remote caching agent forwards data and the requesting agent is able to acquire the data in E or M states. This is commonly returned with RFO transactions. It can be either a HitM or a HitFE.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspS", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPS", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspS : Number of snoop responses received for a Local request : Filters for snoop responses of RspS to local CA requests. RspS is returned when a remote cache has data but is not forwarding it. It is a way to let the requesting socket know that it cannot allocate the data in E state. No data is sent with S RspS.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : RspSFwd", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPSFWD", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : RspSFwd : Number of snoop responses received for a Local request : Filters for a snoop response of RspSFwd to local CA requests. This is returned when a remote caching agent forwards data but holds on to its current copy. This is common for data and code reads that hit in a remote socket in E or F state.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Snoop Responses Received Local : Rsp*WB", + "EventCode": "0x5d", + "EventName": "UNC_CHA_SNOOP_RESP_LOCAL.RSPWB", + "PerPkg": "1", + "PublicDescription": "Snoop Responses Received Local : Rsp*WB : Number of snoop responses received for a Local request : Filters for a snoop response of RspIWB or RspSWB to local CA requests. This is returned when a non-RFO request hits in M state. Data and Code Reads can return either RspIWB or RspSWB depending on how the system has been configured. InvItoE transactions will also return RspIWB because they must acquire ownership.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : MtoI RspIDataM", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPDATAM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : MtoI RspIFwdM", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.MTOI_RSPIFWDM", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit LLC", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITLLC", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : Pull Data Partial - Hit SF", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.PULLDATAPTL_HITSF", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit LLC", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITLLC", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "Misc Snoop Responses Received : RspIFwdPtl Hit SF", + "EventCode": "0x6b", + "EventName": "UNC_CHA_SNOOP_RSP_MISC.RSPIFWDMPTL_HITSF", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0xc001ffff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DDR Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.DDR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DDR Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : SF/LLC Evictions", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.EVICT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : SF/LLC Evictions : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Hits", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.HIT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Hits : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; All locally initiated requests from IA Cores", + "UMask": "0xc001ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;CLFlush from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; CLFlush events that are initiated from the Core", + "UMask": "0xc8c7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;CLFlushOpt from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CLFLUSHOPT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; CLFlushOpt events that are initiated from the Core", + "UMask": "0xc8d7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read from local IA that misses in the snoop filter", + "UMask": "0xc80fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that misses in the snoop filter", + "UMask": "0xc817ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt from local IA that misses in the snoop filter", + "UMask": "0xc827ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt Pref from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8a7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Pref from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc897ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0xc001fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read from local IA that hits in the snoop filter", + "UMask": "0xc80ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read prefetch from local IA that hits in the snoop filter", + "UMask": "0xc88ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "All requests issued from IA cores to CXL accelerator memory regions that hit the LLC.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c0018101", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_HIT_CXL_ACC_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c0008101", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read from local IA that hits in the snoop filter", + "UMask": "0xc817fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to page walks that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt from local IA that hits in the snoop filter", + "UMask": "0xc827fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt Pref hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt prefetch from local IA that hits in the snoop filter", + "UMask": "0xc8a7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Pref hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read prefetch from local IA that hits in the snoop filter", + "UMask": "0xc897fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Hit LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefCode hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch code read from local IA that hits in the snoop filter", + "UMask": "0xcccffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefData hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch data read from local IA that hits in the snoop filter", + "UMask": "0xccd7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefRFO hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch read for ownership from local IA that hits in the snoop filter", + "UMask": "0xccc7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership from local IA that hits in the snoop filter", + "UMask": "0xc807fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO Pref hits from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_HIT_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that hits in the snoop filter", + "UMask": "0xc887fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;ItoM from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; ItoM events that are initiated from the Core", + "UMask": "0xcc47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefCode from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch code read from local IA.", + "UMask": "0xcccfff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefData from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch data read from local IA.", + "UMask": "0xccd7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefRFO from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", + "UMask": "0xccc7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; misses from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All requests from iA Cores that Missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for CRd misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode CRd", + "UMask": "0xc80ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "CRds and equivalent opcodes issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRDMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c80b8201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; CRd Pref misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CRd issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "All requests issued from IA cores to CXL accelerator memory regions that miss the LLC.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c0018201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_CXL_ACC_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c0008201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd", + "UMask": "0xc817fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "DRds and equivalent opcodes issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRDMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8138201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd PTEs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRDPTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : DRd PTEs issued by iA Cores due to a page walk that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "DRds issued from an IA core which miss the L3 and target memory in a CXL type 2 memory expander card.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8178201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_CXL_ACC_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8168201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_CXL_EXP_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_CXL_EXP_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x20c8168201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRds issued by IA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_DDR", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target DDR memory", + "UMask": "0xc8178601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd misses from local IA targeting local memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target local memory", + "UMask": "0xc816fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt from local IA that misses in the snoop filter", + "UMask": "0xc827fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_CXL_ACC_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8268201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; DRd Opt Pref misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Data read opt prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8a7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_CXL_ACC_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_OPT_PREF_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8a68201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRds issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PMM", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target PMM memory", + "UMask": "0xc8178a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd Pref misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRD_PREF", + "UMask": "0xc897fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "L2 data prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8978201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_CXL_ACC_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8968201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd Pref misses from local IA targeting local memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRD_PREF, and target local memory", + "UMask": "0xc896fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd Pref misses from local IA targeting remote memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRD_PREF, and target remote memory", + "UMask": "0xc8977e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_PREF_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for DRd misses from local IA targeting remote memory", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and target remote memory", + "UMask": "0xc8177e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefCode misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch code read from local IA that misses in the snoop filter", + "UMask": "0xcccffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "LLC Prefetch Code transactions issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFCODE_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10cccf8201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefData misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch data read from local IA that misses in the snoop filter", + "UMask": "0xccd7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "LLC data prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10ccd78201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA_CXL_ACC_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFDATA_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10ccd68201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; LLCPrefRFO misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", + "UMask": "0xccc7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "L2 RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8878201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO_CXL_ACC_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LLCPREFRFO_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8868201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_LOCAL_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_REMOTE_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc807fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "RFO and L2 RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFOMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8038201", + "Unit": "CHA" + }, + { + "BriefDescription": "RFOs issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8078201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_CXL_ACC_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8068201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_CXL_EXP_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_CXL_EXP_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x20c8068201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts RFO misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc806fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO pref misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc887fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "LLC RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10ccc78201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_CXL_ACC_LOCAL", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10ccc68201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO prefetch misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc886fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO prefetch misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8877e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_RFO_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Inserts Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc8077e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : UCRdFs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_UCRDF", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc877de01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores that Missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLFs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WiLs issued by iA Cores that Missed LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_MISS_WIL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc87fde01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc807ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO pref from local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc887ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts;SpecItoM from Local IA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_SPECITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.; SpecItoM events that are initiated from the Core", + "UMask": "0xcc57ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOE", + "PerPkg": "1", + "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc3fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBEFTOI", + "PerPkg": "1", + "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc37ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOE", + "PerPkg": "1", + "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc2fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WbMtoIs issued by an iA Cores. Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBMTOI", + "PerPkg": "1", + "PublicDescription": "WbMtoIs issued by iA Cores . (Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc27ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBEFtoEs issued by an IA Core. Non Modified Write Backs", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WBSTOI", + "PerPkg": "1", + "PublicDescription": "WbEFtoEs issued by iA Cores . (Non Modified Write Backs) :Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc67ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLs issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WCIL", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WCiLF issued by iA Cores", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IA_WCILF", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : CLFlushes issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Hits from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; ItoM hits from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RdCur and FsRdCur hits from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that hit the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO hits from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for ItoM from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IO with the opcode ItoM", + "UMask": "0xcc43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for ItoMCacheNears from IO devices.", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IO devices with the opcode ItoMCacheNears. This event indicates a partial write request.", + "UMask": "0xcd43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; Misses from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; ItoM misses from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RdCur and FsRdCur misses from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO misses from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts for RdCur from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "Inserts into the TOR from local IO with the opcode RdCur", + "UMask": "0xc8f3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; RFO from local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RFOs issued by IO Devices : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WbMtoIs issued by IO Devices", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IO_WBMTOI", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc23ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IPQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IPQ", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IPQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IRQ - iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IRQ - iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : From an iA Core", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : IRQ - Non iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.IRQ_NON_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : IRQ - Non iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just ISOC", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.ISOC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just ISOC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Local Targets", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOCAL_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Local Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local iA and IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local iA and IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All locally initiated requests", + "UMask": "0xc000ff05", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local iA", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_IA", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local iA : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All locally initiated requests from iA Cores", + "UMask": "0xc000ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Local IO", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.LOC_IO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Local IO : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All locally generated IO traffic", + "UMask": "0xc000ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MATCH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Match the Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Misses", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MISS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Misses : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : MMCFG Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MMCFG", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : MMCFG Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : MMIO Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.MMIO", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : MMIO Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NearMem", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NonCoherent", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NONCOH", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NonCoherent : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just NotNearMem", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.NOT_NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just NotNearMem : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PMM Access", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PMM", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PM Access : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PREMORPH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Match the PreMorphed Opcode in b[29:19] of the extended umask field : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PRQ - IOSF", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PRQ - IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : From a PCIe Device", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : PRQ - Non IOSF", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.PRQ_NON_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : PRQ - Non IOSF : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : Just Remote Targets", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REMOTE_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : Just Remote Targets : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All from Remote", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REM_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All from Remote : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All remote requests (e.g. snoops, writebacks) that came from remote sockets", + "UMask": "0xc001ffc8", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : All Snoops from Remote", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.REM_SNPS", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : All Snoops from Remote : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. : All snoops to this LLC that came from remote sockets", + "UMask": "0xc001ff08", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : RRQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.RRQ", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : RRQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts; All Snoops from Remote", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.SNPS_FROM_REM", + "PerPkg": "1", + "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent. All snoops to this LLC that came from remote sockets.", + "UMask": "0xc001ff08", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Inserts : WBQ", + "EventCode": "0x35", + "EventName": "UNC_CHA_TOR_INSERTS.WBQ", + "PerPkg": "1", + "PublicDescription": "TOR Inserts : WBQ : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ALL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0xc001ffff", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DDR Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DDR Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : SF/LLC Evictions", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.EVICT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : SF/LLC Evictions : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : TOR allocation occurred as a result of SF/LLC evictions (came from the ISMQ)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Hits", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Hits : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushes issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushes issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CLFLUSHOPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushOpts issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8d7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read from local IA that misses in the snoop filter", + "UMask": "0xc80fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that misses in the snoop filter", + "UMask": "0xc817ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRDPTE", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt from local IA that misses in the snoop filter", + "UMask": "0xc827ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt Pref from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8a7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc897ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read from local IA that hits in the snoop filter", + "UMask": "0xc80ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that hits in the snoop filter", + "UMask": "0xc88ffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for All requests issued from IA cores to CXL accelerator memory regions that hit the LLC.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c0018101", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CXL_ACC_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c0008101", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read from local IA that hits in the snoop filter", + "UMask": "0xc817fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRDPTE", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt from local IA that hits in the snoop filter", + "UMask": "0xc827fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt Pref hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt prefetch from local IA that hits in the snoop filter", + "UMask": "0xc8a7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that hits in the snoop filter", + "UMask": "0xc897fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores that Hit LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefCode hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch code read from local IA that hits in the snoop filter", + "UMask": "0xcccffd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefData hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA that hits in the snoop filter", + "UMask": "0xccd7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefRFO hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch read for ownership from local IA that hits in the snoop filter", + "UMask": "0xccc7fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership from local IA that hits in the snoop filter", + "UMask": "0xc807fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO Pref hits from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that hits in the snoop filter", + "UMask": "0xc887fd01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd47ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefCode from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA.", + "UMask": "0xcccfff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefData from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA that misses in the snoop filter", + "UMask": "0xccd7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefRFO from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", + "UMask": "0xccc7ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from Local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read from local IA that misses in the snoop filter", + "UMask": "0xc80ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for CRds and equivalent opcodes issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRDMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c80b8201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; CRd Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Code read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc88ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88efe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd_Prefs issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc88f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CRd issued by iA Cores that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc80f7e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for All requests issued from IA cores to CXL accelerator memory regions that miss the LLC.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c0018201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CXL_ACC_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c0008201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRd misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD", + "PerPkg": "1", + "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd", + "UMask": "0xc817fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRds and equivalent opcodes issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRDMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8138201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRDPTE", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "TOR Occupancy : DRdPte issued by iA Cores due to a page walk that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc837fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRds and equivalent opcodes issued from an IA core which miss the L3 and target memory in a CXL type 2 memory expander card.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8178201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_CXL_ACC_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8168201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_CXL_EXP_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_CXL_EXP_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x20c8168201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRds issued by iA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_DDR", + "PerPkg": "1", + "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target DDR memory", + "UMask": "0xc8178601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRd misses from local IA targeting local memory", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL", + "PerPkg": "1", + "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target local memory", + "UMask": "0xc816fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8168a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt from local IA that misses in the snoop filter", + "UMask": "0xc827fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_CXL_ACC_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8268201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Opt Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read opt prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8a7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF_CXL_ACC_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8a68201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRds issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PMM", + "PerPkg": "1", + "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target PMM memory", + "UMask": "0xc8178a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc897fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for L2 data prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8978201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_CXL_ACC_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8968201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc896fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_LOCAL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8968a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8978a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; DRd Pref misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Data read prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8977e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRd_Prefs issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8970a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for DRd misses from local IA targeting remote memory", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE", + "PerPkg": "1", + "PublicDescription": "Number of cycles for elements in the TOR from local IA cores which miss the LLC and snoop filter with the opcode DRd, and which target remote memory", + "UMask": "0xc8177e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting DDR Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : DRds issued by iA Cores targeting PMM Mem that Missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8170a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc47fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefCode misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFCODE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch code read from local IA that misses in the snoop filter", + "UMask": "0xcccffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for LLC Prefetch Code transactions issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFCODE_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10cccf8201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefData misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch data read from local IA that misses in the snoop filter", + "UMask": "0xccd7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for LLC data prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10ccd78201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA_CXL_ACC_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10ccd68201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; LLCPrefRFO misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Last level cache prefetch read for ownership from local IA that misses in the snoop filter", + "UMask": "0xccc7fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for L2 RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8878201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO_CXL_ACC_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8868201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8668a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LOCAL_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed locally : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86e8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8670a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_REMOTE_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC - HOMed remotely : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f0a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc807fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for RFO and L2 RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFOMORPH_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8038201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for RFOs issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10c8078201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_CXL_ACC_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10c8068201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_CXL_EXP_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_CXL_EXP_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x20c8068201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc806fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc887fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy for LLC RFO prefetches issued from an IA core which miss the L3 and target memory in a CXL type 2 accelerator.", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_CXL_ACC", + "PerPkg": "1", + "UMask": "0x10ccc78201", + "Unit": "CHA" + }, + { + "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_CXL_ACC_LOCAL", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_CXL_ACC_LOCAL", + "PerPkg": "1", + "PortMask": "0x000", + "UMask": "0x10ccc68201", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_LOCAL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc886fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc8877e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_REMOTE", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc8077e01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_UCRDF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : UCRdFs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc877de01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86ffe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores that Missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867fe01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting DDR that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCILF_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLFs issued by iA Cores targeting PMM that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8678a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_DDR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting DDR that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8601", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WCIL_PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores targeting PMM that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86f8a01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_WIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WiLs issued by iA Cores that Missed LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc87fde01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership from local IA that misses in the snoop filter", + "UMask": "0xc807ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO prefetch from local IA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_RFO_PREF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy; Read for ownership prefetch from local IA that misses in the snoop filter", + "UMask": "0xc887ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : SpecItoMs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_SPECITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : SpecItoMs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc57ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WbMtoIs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WBMTOI", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WbMtoIs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc27ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLs issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCIL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLs issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc86fff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WCiLF issued by iA Cores", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_WCILF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WCiLF issued by iA Cores : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc867ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : CLFlushes issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_CLFLUSH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : CLFlushes issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8c3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Hits from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM hits from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that Hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RdCur and FsRdCur hits from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO hits from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_HIT_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that hit the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fd04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_ITOMCACHENEAR", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; Misses from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All requests from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc001fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ITOM misses from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcd43fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RFO misses from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices that missed the LLC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803fe04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; RdCur and FsRdCur from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_PCIRDCUR", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PCIRdCurs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc8f3ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; ItoM from local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_RFO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RFOs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xc803ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WbMtoIs issued by IO Devices", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_WBMTOI", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WbMtoIs issued by IO Devices : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. Does not include addressless requests such as locks and interrupts.", + "UMask": "0xcc23ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IPQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IPQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IPQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IRQ - iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IRQ - iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : From an iA Core", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : IRQ - Non iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.IRQ_NON_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : IRQ - Non iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just ISOC", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.ISOC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just ISOC : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Local Targets", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOCAL_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Local Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local iA and IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local iA and IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All locally initiated requests", + "UMask": "0xc000ff05", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local iA", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IA", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local iA : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All locally initiated requests from iA Cores", + "UMask": "0xc000ff01", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Local IO", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.LOC_IO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Local IO : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All locally generated IO traffic", + "UMask": "0xc000ff04", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MATCH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Match the Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Misses", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MISS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Misses : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : MMCFG Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MMCFG", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : MMCFG Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : MMIO Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.MMIO", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : MMIO Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NearMem", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NonCoherent", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NONCOH", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NonCoherent : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just NotNearMem", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.NOT_NEARMEM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just NotNearMem : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PMM Access", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PMM", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PMM Access : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PREMORPH_OPC", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Match the PreMorphed Opcode in b[29:19] of the extended umask field : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PRQ - IOSF", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PRQ - IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : From a PCIe Device", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : PRQ - Non IOSF", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.PRQ_NON_IOSF", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : PRQ - Non IOSF : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : Just Remote Targets", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.REMOTE_TGT", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : Just Remote Targets : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All from Remote", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.REM_ALL", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All from Remote : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All remote requests (e.g. snoops, writebacks) that came from remote sockets", + "UMask": "0xc001ffc8", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : All Snoops from Remote", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.REM_SNPS", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : All Snoops from Remote : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T : All snoops to this LLC that came from remote sockets", + "UMask": "0xc001ff08", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : RRQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.RRQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : RRQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy; All Snoops from Remote", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.SNPS_FROM_REM", + "PerPkg": "1", + "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. All snoops to this LLC that came from remote sockets.", + "UMask": "0xc001ff08", + "Unit": "CHA" + }, + { + "BriefDescription": "TOR Occupancy : WBQ", + "EventCode": "0x36", + "EventName": "UNC_CHA_TOR_OCCUPANCY.WBQ", + "PerPkg": "1", + "PublicDescription": "TOR Occupancy : WBQ : For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent. T", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI : Pushed to LLC", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.LLC", + "PerPkg": "1", + "PublicDescription": "WbPushMtoI : Pushed to LLC : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was able to push WbPushMToI to LLC", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "WbPushMtoI : Pushed to Memory", + "EventCode": "0x56", + "EventName": "UNC_CHA_WB_PUSH_MTOI.MEM", + "PerPkg": "1", + "PublicDescription": "WbPushMtoI : Pushed to Memory : Counts the number of times when the CHA was received WbPushMtoI : Counts the number of times when the CHA was unable to push WbPushMToI to LLC (hence pushed it to MEM)", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC0", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC0", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC0 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 0 only.", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC1", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC1", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC1 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 1 only.", + "UMask": "0x2", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC2", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC2", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC2 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 2 only.", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC3", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC3", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC3 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 3 only.", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC4", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC4", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC4 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 4 only.", + "UMask": "0x10", + "Unit": "CHA" + }, + { + "BriefDescription": "CHA iMC CHNx WRITE Credits Empty : MC5", + "EventCode": "0x5a", + "EventName": "UNC_CHA_WRITE_NO_CREDITS.MC5", + "PerPkg": "1", + "PublicDescription": "CHA iMC CHNx WRITE Credits Empty : MC5 : Counts the number of times when there are no credits available for sending WRITEs from the CHA into the iMC. In order to send WRITEs into the memory controller, the HA must first acquire a credit for the iMC's BL Ingress queue. : Filter for memory controller 5 only.", + "UMask": "0x20", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 0?) - Conflict", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP0_CONFLICT", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 0?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", + "UMask": "0x8", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 0?) - No Credits", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP0_NOCRD", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 0?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", + "UMask": "0x4", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 1?) - Conflict", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP1_CONFLICT", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 1?) - Conflict : Number of XPT prefetches dropped due to AD CMS write port contention", + "UMask": "0x80", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Dropped (on 1?) - No Credits", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.DROP1_NOCRD", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Dropped (on 1?) - No Credits : Number of XPT prefetches dropped due to lack of XPT AD egress credits", + "UMask": "0x40", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Sent (on 0?)", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.SENT0", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Sent (on 0?) : Number of XPT prefetches sent", + "UMask": "0x1", + "Unit": "CHA" + }, + { + "BriefDescription": "XPT Prefetches : Sent (on 1?)", + "EventCode": "0x6f", + "EventName": "UNC_CHA_XPT_PREF.SENT1", + "PerPkg": "1", + "PublicDescription": "XPT Prefetches : Sent (on 1?) : Number of XPT prefetches sent", + "UMask": "0x10", + "Unit": "CHA" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cxl.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cxl.json new file mode 100644 index 000000000000..f3e84fd88de3 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cxl.json @@ -0,0 +1,450 @@ +[ + { + "BriefDescription": "Counts the number of lfclk ticks", + "EventCode": "0x01", + "EventName": "UNC_CXLCM_CLOCKTICKS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Rxx AGF 0", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.CACHE_DATA", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Req AGF0", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.CACHE_REQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Rsp AGF", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.CACHE_REQ1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Data AGF", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.CACHE_RSP0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Rsp AGF", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.CACHE_RSP1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Req AGF 1", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.MEM_DATA", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Data AGF", + "EventCode": "0x43", + "EventName": "UNC_CXLCM_RxC_AGF_INSERTS.MEM_REQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with AK set", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.AK_HDR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with BE set", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.BE_HDR", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of control flits received", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.CTRL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Headerless flits received", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.NO_HDR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of protocol flits received", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.PROT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with SZ set", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.SZ_HDR", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of flits received", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.VALID", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of valid messages in the flit", + "EventCode": "0x4b", + "EventName": "UNC_CXLCM_RxC_FLITS.VALID_MSG", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of CRC errors detected", + "EventCode": "0x40", + "EventName": "UNC_CXLCM_RxC_MISC.CRC_ERRORS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Init flits sent", + "EventCode": "0x40", + "EventName": "UNC_CXLCM_RxC_MISC.INIT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of LLCRD flits sent", + "EventCode": "0x40", + "EventName": "UNC_CXLCM_RxC_MISC.LLCRD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Retry flits sent", + "EventCode": "0x40", + "EventName": "UNC_CXLCM_RxC_MISC.RETRY", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles the Packing Buffer is Full", + "EventCode": "0x52", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_FULL.CACHE_DATA", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles the Packing Buffer is Full", + "EventCode": "0x52", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_FULL.CACHE_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles the Packing Buffer is Full", + "EventCode": "0x52", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_FULL.CACHE_RSP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles the Packing Buffer is Full", + "EventCode": "0x52", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_FULL.MEM_DATA", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles the Packing Buffer is Full", + "EventCode": "0x52", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_FULL.MEM_REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Data Packing buffer", + "EventCode": "0x41", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.CACHE_DATA", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Req Packing buffer", + "EventCode": "0x41", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.CACHE_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Rsp Packing buffer", + "EventCode": "0x41", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.CACHE_RSP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Data Packing buffer", + "EventCode": "0x41", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.MEM_DATA", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Rxx Packing buffer", + "EventCode": "0x41", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_INSERTS.MEM_REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles of Not Empty for Cache Data Packing buffer", + "EventCode": "0x42", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_NE.CACHE_DATA", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles of Not Empty for Cache Req Packing buffer", + "EventCode": "0x42", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_NE.CACHE_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles of Not Empty for Cache Rsp Packing buffer", + "EventCode": "0x42", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_NE.CACHE_RSP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles of Not Empty for Mem Data Packing buffer", + "EventCode": "0x42", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_NE.MEM_DATA", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of cycles of Not Empty for Mem Rxx Packing buffer", + "EventCode": "0x42", + "EventName": "UNC_CXLCM_RxC_PACK_BUF_NE.MEM_REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with AK set", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.AK_HDR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with BE set", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.BE_HDR", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of control flits packed", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.CTRL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Headerless flits packed", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.NO_HDR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of protocol flits packed", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.PROT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of Flits with SZ set", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.SZ_HDR", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Count the number of flits packed", + "EventCode": "0x05", + "EventName": "UNC_CXLCM_TxC_FLITS.VALID", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Data Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.CACHE_DATA", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Req Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.CACHE_REQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Rsp1 Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.CACHE_REQ1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Rsp0 Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.CACHE_RSP0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Cache Req Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.CACHE_RSP1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Data Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.MEM_DATA", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Number of Allocation to Mem Rxx Packing buffer", + "EventCode": "0x02", + "EventName": "UNC_CXLCM_TxC_PACK_BUF_INSERTS.MEM_REQ", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLCM" + }, + { + "BriefDescription": "Counts the number of uclk ticks", + "EventCode": "0x01", + "EventName": "UNC_CXLDP_CLOCKTICKS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to M2S Data AGF", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.M2S_DATA", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to M2S Req AGF", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.M2S_REQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to U2C Data AGF", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.U2C_DATA", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to U2C Req AGF", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.U2C_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to U2C Rsp AGF 0", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.U2C_RSP0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "CXLDP" + }, + { + "BriefDescription": "Number of Allocation to U2C Rsp AGF 1", + "EventCode": "0x02", + "EventName": "UNC_CXLDP_TxC_AGF_INSERTS.U2C_RSP1", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "CXLDP" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json new file mode 100644 index 000000000000..09d840c7da4c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json @@ -0,0 +1,6199 @@ +[ + { + "BriefDescription": "Total IRP occupancy of inbound read and write requests to coherent memory.", + "EventCode": "0x0f", + "EventName": "UNC_I_CACHE_TOTAL_OCCUPANCY.MEM", + "PerPkg": "1", + "PublicDescription": "Total IRP occupancy of inbound read and write requests to coherent memory. This is effectively the sum of read occupancy and write occupancy.", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "IRP Clockticks", + "EventCode": "0x01", + "EventName": "UNC_I_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of IRP clock cycles while the event is enabled", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF RF full", + "EventCode": "0x17", + "EventName": "UNC_I_FAF_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF - request insert from TC.", + "EventCode": "0x18", + "EventName": "UNC_I_FAF_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF occupancy", + "EventCode": "0x19", + "EventName": "UNC_I_FAF_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "FAF allocation -- sent to ADQ", + "EventCode": "0x16", + "EventName": "UNC_I_FAF_TRANSACTIONS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.EVICTS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Inbound (p2p + faf + cset)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.INBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": ": All Inserts Outbound (BL, AK, Snoops)", + "EventCode": "0x20", + "EventName": "UNC_I_IRP_ALL.OUTBOUND_INSERTS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Atomic Transactions as Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.2ND_ATOMIC_INSERT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Read Transactions as Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.2ND_RD_INSERT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Cache Inserts of Write Transactions as Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.2ND_WR_INSERT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Rejects", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.FAST_REJ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Requests", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.FAST_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Fastpath Transfers From Primary to Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.FAST_XFER", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Prefetch Ack Hints From Primary to Secondary", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.PF_ACK_HINT", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Counts Timeouts - Set 0 : Slow path fwpf didn't find prefetch", + "EventCode": "0x1e", + "EventName": "UNC_I_MISC0.SLOWPATH_FWPF_NO_PRF", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Lost Forward", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.LOST_FWD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Lost Forward : Snoop pulled away ownership before a write was committed", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Received Invalid", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SEC_RCVD_INVLD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Received Invalid : Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Received Valid", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SEC_RCVD_VLD", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Received Valid : Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of E Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_E", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of E Line : Secondary received a transfer that did have sufficient MESI state", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of I Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_I", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of I Line : Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of M Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_M", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of M Line : Snoop took cacheline ownership before write from data was committed.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Misc Events - Set 1 : Slow Transfer of S Line", + "EventCode": "0x1f", + "EventName": "UNC_I_MISC1.SLOW_S", + "PerPkg": "1", + "PublicDescription": "Misc Events - Set 1 : Slow Transfer of S Line : Secondary received a transfer that did not have sufficient MESI state", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M, E, S or I line in the IIO", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M, E, S or I line in the IIO", + "UMask": "0x7e", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit E or S line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_ES", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit E or S line in the IIO cache", + "UMask": "0x74", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit I line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_I", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit I line in the IIO cache", + "UMask": "0x72", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that hit M line in the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_HIT_M", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that hit M line in the IIO cache", + "UMask": "0x78", + "Unit": "IRP" + }, + { + "BriefDescription": "Responses to snoops of any type that miss the IIO cache", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.ALL_MISS", + "PerPkg": "1", + "PublicDescription": "Responses to snoops of any type (code, data, invalidate) that miss the IIO cache", + "UMask": "0x71", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit E or S", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_ES", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit I", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_I", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Hit M", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.HIT_M", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : Miss", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.MISS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpCode", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPCODE", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpData", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPDATA", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "IRP" + }, + { + "BriefDescription": "Snoop Responses : SnpInv", + "EventCode": "0x12", + "EventName": "UNC_I_SNOOP_RESP.SNPINV", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "IRP" + }, + { + "BriefDescription": "Inbound write (fast path) requests received by the IRP.", + "EventCode": "0x11", + "EventName": "UNC_I_TRANSACTIONS.WR_PREF", + "PerPkg": "1", + "PublicDescription": "Inbound write (fast path) requests to coherent memory, received by the IRP resulting in write ownership requests issued by IRP to the mesh.", + "UMask": "0x8", + "Unit": "IRP" + }, + { + "BriefDescription": "AK Egress Allocations", + "EventCode": "0x0b", + "EventName": "UNC_I_TxC_AK_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Cycles Full", + "EventCode": "0x05", + "EventName": "UNC_I_TxC_BL_DRS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Inserts", + "EventCode": "0x02", + "EventName": "UNC_I_TxC_BL_DRS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL DRS Egress Occupancy", + "EventCode": "0x08", + "EventName": "UNC_I_TxC_BL_DRS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Cycles Full", + "EventCode": "0x06", + "EventName": "UNC_I_TxC_BL_NCB_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Inserts", + "EventCode": "0x03", + "EventName": "UNC_I_TxC_BL_NCB_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCB Egress Occupancy", + "EventCode": "0x09", + "EventName": "UNC_I_TxC_BL_NCB_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Cycles Full", + "EventCode": "0x07", + "EventName": "UNC_I_TxC_BL_NCS_CYCLES_FULL", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Inserts", + "EventCode": "0x04", + "EventName": "UNC_I_TxC_BL_NCS_INSERTS", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "BL NCS Egress Occupancy", + "EventCode": "0x0a", + "EventName": "UNC_I_TxC_BL_NCS_OCCUPANCY", + "PerPkg": "1", + "Unit": "IRP" + }, + { + "BriefDescription": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", + "EventCode": "0x1c", + "EventName": "UNC_I_TxR2_AD01_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": ": Counts the number times when it is not possible to issue a request to the M2PCIe because there are no Egress Credits available on AD0, A1 or AD0AD1 both. Stalls on both AD0 and AD1 will count as 2", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD0 Egress Credits Stalls", + "EventCode": "0x1a", + "EventName": "UNC_I_TxR2_AD0_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No AD0 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD0 Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No AD1 Egress Credits Stalls", + "EventCode": "0x1b", + "EventName": "UNC_I_TxR2_AD1_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No AD1 Egress Credits Stalls : Counts the number times when it is not possible to issue a request to the M2PCIe because there are no AD1 Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "No BL Egress Credit Stalls", + "EventCode": "0x1d", + "EventName": "UNC_I_TxR2_BL_STALL_CREDIT_CYCLES", + "PerPkg": "1", + "PublicDescription": "No BL Egress Credit Stalls : Counts the number times when it is not possible to issue data to the R2PCIe because there are no BL Egress Credits available.", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0x0d", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCB", + "PerPkg": "1", + "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Read Requests", + "EventCode": "0x0e", + "EventName": "UNC_I_TxS_DATA_INSERTS_NCS", + "PerPkg": "1", + "PublicDescription": "Outbound Read Requests : Counts the number of requests issued to the switch (towards the devices).", + "Unit": "IRP" + }, + { + "BriefDescription": "Outbound Request Queue Occupancy", + "EventCode": "0x0c", + "EventName": "UNC_I_TxS_REQUEST_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Outbound Request Queue Occupancy : Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", + "Unit": "IRP" + }, + { + "BriefDescription": "M2M Clockticks", + "EventCode": "0x01", + "EventName": "UNC_M2M_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Clockticks of the mesh to memory (M2M)", + "Unit": "M2M" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M2M_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", + "EventCode": "0x17", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to core mode, which bypasses the CHA, was disabled : Non Cisgress", + "EventCode": "0x17", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_DIRSTATE.NON_CISGRESS", + "PerPkg": "1", + "PublicDescription": "Cycles when direct to core mode, which bypasses the CHA, was disabled : Non Cisgress : Counts the number of time non cisgress D2C was not honoured by egress due to directory state constraints", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Counts the time when FM didn't do d2c for fill reads (cross tile case)", + "EventCode": "0x4a", + "EventName": "UNC_M2M_DIRECT2CORE_NOT_TAKEN_NOTFORKED", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction were overridden", + "EventCode": "0x18", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction was overridden : Cisgress", + "EventCode": "0x18", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE.CISGRESS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction was overridden : 2LM Hit?", + "EventCode": "0x18", + "EventName": "UNC_M2M_DIRECT2CORE_TXN_OVERRIDE.PMM_HIT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of times a direct to UPI transaction was overridden.", + "EventCode": "0x1C", + "EventName": "UNC_M2M_DIRECT2UPITXN_OVERRIDE.PMM_HIT", + "PerPkg": "1", + "PublicDescription": "Number of times a direct to UPI transaction was overridden. : Counts the number of times D2K wasn't honored even though the incoming request had d2k set", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "EventCode": "0x1b", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when direct to Intel UPI was disabled", + "EventCode": "0x1a", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Cisgress D2U Ignored", + "EventCode": "0x1A", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE.CISGRESS", + "PerPkg": "1", + "PublicDescription": "Cycles when Direct2UPI was Disabled : Cisgress D2U Ignored : Counts cisgress d2K that was not honored due to directory constraints", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Egress Ignored D2U", + "EventCode": "0x1A", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE.EGRESS", + "PerPkg": "1", + "PublicDescription": "Cycles when Direct2UPI was Disabled : Egress Ignored D2U : Counts the number of time D2K was not honoured by egress due to directory state constraints", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Non Cisgress D2U Ignored", + "EventCode": "0x1A", + "EventName": "UNC_M2M_DIRECT2UPI_NOT_TAKEN_DIRSTATE.NON_CISGRESS", + "PerPkg": "1", + "PublicDescription": "Cycles when Direct2UPI was Disabled : Non Cisgress D2U Ignored : Counts non cisgress d2K that was not honored due to directory constraints", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Messages sent direct to the Intel UPI", + "EventCode": "0x19", + "EventName": "UNC_M2M_DIRECT2UPI_TAKEN", + "PerPkg": "1", + "PublicDescription": "Counts the number of times egress did D2K (Direct to KTI)", + "UMask": "0x7", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "EventCode": "0x1c", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "Number of times a direct to UPI transaction was overridden.", + "EventCode": "0x1C", + "EventName": "UNC_M2M_DIRECT2UPI_TXN_OVERRIDE.CISGRESS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in A State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in I State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in L State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in S State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in A State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in I State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in L State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in S State", + "EventCode": "0x1d", + "EventName": "UNC_M2M_DIRECTORY_HIT.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with any directory to non persistent memory", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory A to non persistent memory", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory I to non persistent memory", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", + "EventCode": "0x20", + "EventName": "UNC_M2M_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory S to non persistent memory", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in A State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in I State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in L State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in S State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in A State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in I State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in L State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in S State", + "EventCode": "0x1e", + "EventName": "UNC_M2M_DIRECTORY_MISS.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to I", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "UMask": "0x320", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to S", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "UMask": "0x340", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "UMask": "0x301", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A_TO_I_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from A to I to non persistent memory (DRAM or HBM)", + "UMask": "0x120", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A_TO_I_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from A to I to non persistent memory (DRAM or HBM)", + "UMask": "0x220", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A_TO_S_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from A to S to non persistent memory (DRAM or HBM)", + "UMask": "0x140", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.A_TO_S_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from A to S to non persistent memory (DRAM or HBM)", + "UMask": "0x240", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts any 1lm or 2lm hit data return that would result in directory update to non persistent memory (DRAM or HBM)", + "UMask": "0x101", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to A", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "UMask": "0x304", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to S", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "UMask": "0x302", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I_TO_A_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from I to A to non persistent memory (DRAM or HBM)", + "UMask": "0x104", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I_TO_A_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from I to A to non persistent memory (DRAM or HBM)", + "UMask": "0x204", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I_TO_S_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from I to S to non persistent memory (DRAM or HBM)", + "UMask": "0x102", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.I_TO_S_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from I to S to non persistent memory (DRAM or HBM)", + "UMask": "0x202", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts any 2lm miss data return that would result in directory update to non persistent memory (DRAM or HBM)", + "UMask": "0x201", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to A", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "UMask": "0x310", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to I", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "UMask": "0x308", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S_TO_A_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from S to A to non persistent memory (DRAM or HBM)", + "UMask": "0x110", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S_TO_A_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from S to A to non persistent memory (DRAM or HBM)", + "UMask": "0x210", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S_TO_I_HIT_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from S to I to non persistent memory (DRAM or HBM)", + "UMask": "0x108", + "Unit": "M2M" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2M_DIRECTORY_UPDATE.S_TO_I_MISS_NON_PMM", + "PerPkg": "1", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from S to I to non persistent memory (DRAM or HBM)", + "UMask": "0x208", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x80000004", + "Unit": "M2M" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_M2M_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x80000001", + "Unit": "M2M" + }, + { + "BriefDescription": "Count when Starve Glocab counter is at 7", + "EventCode": "0x44", + "EventName": "UNC_M2M_IGR_STARVE_WINNER.MASK7", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2M" + }, + { + "BriefDescription": "Reads to iMC issued", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.ALL", + "PerPkg": "1", + "UMask": "0x304", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0.TO_NM1LM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0.TO_NM1LM", + "PerPkg": "1", + "UMask": "0x108", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0.TO_NMCache", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0.TO_NMCache", + "PerPkg": "1", + "UMask": "0x110", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_ALL", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x104", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_FROM_TGR", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_FROM_TGR", + "PerPkg": "1", + "UMask": "0x140", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_ISOCH", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_ISOCH", + "PerPkg": "1", + "UMask": "0x102", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_NORMAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x101", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_CACHE", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x110", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_MEM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x108", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH0_TO_PMM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH0_TO_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x120", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1.TO_NM1LM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1.TO_NM1LM", + "PerPkg": "1", + "UMask": "0x208", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1.TO_NMCache", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1.TO_NMCache", + "PerPkg": "1", + "UMask": "0x210", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_ALL", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x204", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_FROM_TGR", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_FROM_TGR", + "PerPkg": "1", + "UMask": "0x240", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_ISOCH", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_ISOCH", + "PerPkg": "1", + "UMask": "0x202", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_NORMAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x201", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_CACHE", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x210", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_MEM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x208", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.CH1_TO_PMM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.CH1_TO_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x220", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.FROM_TGR", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.FROM_TGR", + "PerPkg": "1", + "UMask": "0x340", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.ISOCH", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.ISOCH", + "PerPkg": "1", + "UMask": "0x302", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.NORMAL", + "PerPkg": "1", + "UMask": "0x301", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.TO_DDR_AS_CACHE", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x310", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.TO_DDR_AS_MEM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x308", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.TO_NM1LM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.TO_NM1LM", + "PerPkg": "1", + "UMask": "0x308", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.TO_NMCACHE", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.TO_NMCACHE", + "PerPkg": "1", + "UMask": "0x310", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_READS.TO_PMM", + "EventCode": "0x24", + "EventName": "UNC_M2M_IMC_READS.TO_PMM", + "PerPkg": "1", + "UMask": "0x320", + "Unit": "M2M" + }, + { + "BriefDescription": "All Writes - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.ALL", + "PerPkg": "1", + "UMask": "0x1810", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0.NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_ALL", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x810", + "Unit": "M2M" + }, + { + "BriefDescription": "From TGR - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_FULL", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x801", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_FULL_ISOCH", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x804", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive Miss - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_PARTIAL", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x802", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_PARTIAL_ISOCH", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x808", + "Unit": "M2M" + }, + { + "BriefDescription": "DDR, acting as Cache - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x840", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_IMC_WRITES.CH0_TO_DDR_AS_MEM", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x820", + "Unit": "M2M" + }, + { + "BriefDescription": "PMM - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH0_TO_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "PMM - Ch0 : Counts all PMM dimm writes requests(full line and partial) sent from M2M to iMC", + "UMask": "0x880", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1.NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "All Writes - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1010", + "Unit": "M2M" + }, + { + "BriefDescription": "From TGR - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Full Line Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1001", + "Unit": "M2M" + }, + { + "BriefDescription": "ISOCH Full Line - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x1004", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive Miss - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Partial Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1002", + "Unit": "M2M" + }, + { + "BriefDescription": "ISOCH Partial - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x1008", + "Unit": "M2M" + }, + { + "BriefDescription": "DDR, acting as Cache - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x1040", + "Unit": "M2M" + }, + { + "BriefDescription": "DDR - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x1020", + "Unit": "M2M" + }, + { + "BriefDescription": "PMM - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.CH1_TO_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "PMM - Ch1 : Counts all PMM dimm writes requests(full line and partial) sent from M2M to iMC", + "UMask": "0x1080", + "Unit": "M2M" + }, + { + "BriefDescription": "From TGR - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.FROM_TGR", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Full Non-ISOCH - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.FULL", + "PerPkg": "1", + "UMask": "0x1801", + "Unit": "M2M" + }, + { + "BriefDescription": "ISOCH Full Line - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x1804", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.NI", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Non-Inclusive Miss - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.NI_MISS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Partial Non-ISOCH - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "UMask": "0x1802", + "Unit": "M2M" + }, + { + "BriefDescription": "ISOCH Partial - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x1808", + "Unit": "M2M" + }, + { + "BriefDescription": "DDR, acting as Cache - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.TO_DDR_AS_CACHE", + "PerPkg": "1", + "UMask": "0x1840", + "Unit": "M2M" + }, + { + "BriefDescription": "DDR - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.TO_DDR_AS_MEM", + "PerPkg": "1", + "UMask": "0x1820", + "Unit": "M2M" + }, + { + "BriefDescription": "PMM - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2M_IMC_WRITES.TO_PMM", + "PerPkg": "1", + "UMask": "0x1880", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_CIS_DROPS", + "EventCode": "0x5c", + "EventName": "UNC_M2M_PREFCAM_CIS_DROPS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped : UPI - All Channels", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2M" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2M_PREFCAM_DEMAND_DROPS.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "M2M" + }, + { + "BriefDescription": ": UPI - All Channels", + "EventCode": "0x5d", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2M" + }, + { + "BriefDescription": ": XPT - All Channels", + "EventCode": "0x5d", + "EventName": "UNC_M2M_PREFCAM_DEMAND_MERGE.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5E", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.RD_MERGED", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5E", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.WR_MERGED", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2M" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5E", + "EventName": "UNC_M2M_PREFCAM_DEMAND_NO_MERGE.WR_SQUASHED", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 0", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 0", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 1", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 1", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - All Channels", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - All Channels", + "EventCode": "0x56", + "EventName": "UNC_M2M_PREFCAM_INSERTS.XPT_ALLCH", + "PerPkg": "1", + "PublicDescription": "Prefetch CAM Inserts : XPT -All Channels", + "UMask": "0x5", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : All Channels", + "EventCode": "0x54", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.ALLCH", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 0", + "EventCode": "0x54", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 1", + "EventCode": "0x54", + "EventName": "UNC_M2M_PREFCAM_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "All Channels", + "EventCode": "0x5F", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.ALLCH", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": ": Channel 0", + "EventCode": "0x5f", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": ": Channel 1", + "EventCode": "0x5f", + "EventName": "UNC_M2M_PREFCAM_RESP_MISS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "EventCode": "0x62", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", + "EventCode": "0x62", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.CIS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.PMM_MEMMODE_ACCEPT", + "EventCode": "0x62", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.PMM_MEMMODE_ACCEPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", + "EventCode": "0x62", + "EventName": "UNC_M2M_PREFCAM_RxC_DEALLOCS.SQUASHED", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy - Prefetches", + "EventCode": "0x60", + "EventName": "UNC_M2M_PREFCAM_RxC_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) : AD Ingress (from CMS) Allocations", + "EventCode": "0x02", + "EventName": "UNC_M2M_RxC_AD_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "EventCode": "0x03", + "EventName": "UNC_M2M_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Clean NearMem Read Hit", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_CLEAN", + "PerPkg": "1", + "PublicDescription": "Counts clean full line read hits (reads and RFOs).", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Dirty NearMem Read Hit", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TAG_HIT.NM_RD_HIT_DIRTY", + "PerPkg": "1", + "PublicDescription": "Counts dirty full line read hits (reads and RFOs).", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Tag Hit : Clean NearMem Underfill Hit", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_CLEAN", + "PerPkg": "1", + "PublicDescription": "Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts clean underfill hits due to a partial write", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Tag Hit : Dirty NearMem Underfill Hit", + "EventCode": "0x1F", + "EventName": "UNC_M2M_TAG_HIT.NM_UFILL_HIT_DIRTY", + "PerPkg": "1", + "PublicDescription": "Tag Hit indicates when a request sent to the iMC hit in Near Memory. : Counts dirty underfill read hits due to a partial write", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "UNC_M2M_TAG_MISS", + "EventCode": "0x4b", + "EventName": "UNC_M2M_TAG_MISS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2M" + }, + { + "BriefDescription": "Number AD Ingress Credits", + "EventCode": "0x2e", + "EventName": "UNC_M2M_TGR_AD_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Number BL Ingress Credits", + "EventCode": "0x2f", + "EventName": "UNC_M2M_TGR_BL_CREDITS", + "PerPkg": "1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 0", + "EventCode": "0x32", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x104", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Inserts : Channel 1", + "EventCode": "0x32", + "EventName": "UNC_M2M_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x204", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 0", + "EventCode": "0x33", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 1", + "EventCode": "0x33", + "EventName": "UNC_M2M_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "WPQ Flush : Channel 0", + "EventCode": "0x42", + "EventName": "UNC_M2M_WPQ_FLUSH.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "WPQ Flush : Channel 1", + "EventCode": "0x42", + "EventName": "UNC_M2M_WPQ_FLUSH.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 0", + "EventCode": "0x37", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Regular : Channel 1", + "EventCode": "0x37", + "EventName": "UNC_M2M_WPQ_NO_REG_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 0", + "EventCode": "0x38", + "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "M2M->iMC WPQ Cycles w/Credits - Special : Channel 1", + "EventCode": "0x38", + "EventName": "UNC_M2M_WPQ_NO_SPEC_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 0", + "EventCode": "0x40", + "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 1", + "EventCode": "0x40", + "EventName": "UNC_M2M_WR_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Channel 0", + "EventCode": "0x35", + "EventName": "UNC_M2M_WR_TRACKER_NE.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Channel 1", + "EventCode": "0x35", + "EventName": "UNC_M2M_WR_TRACKER_NE.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty : Mirror", + "EventCode": "0x35", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty", + "EventCode": "0x35", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_NONTGR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Cycles Not Empty", + "EventCode": "0x35", + "EventName": "UNC_M2M_WR_TRACKER_NE.MIRR_PWR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 0", + "EventCode": "0x4d", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 1", + "EventCode": "0x4d", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 0", + "EventCode": "0x4c", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 1", + "EventCode": "0x4c", + "EventName": "UNC_M2M_WR_TRACKER_NONPOSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 0", + "EventCode": "0x48", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 1", + "EventCode": "0x48", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 0", + "EventCode": "0x47", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2M" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 1", + "EventCode": "0x47", + "EventName": "UNC_M2M_WR_TRACKER_POSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2M" + }, + { + "BriefDescription": "CBox AD Credits Empty : Requests", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.REQ", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : Requests : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty : Snoops", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.SNP", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : Snoops : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty : VNA Messages", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : VNA Messages : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "CBox AD Credits Empty : Writebacks", + "EventCode": "0x22", + "EventName": "UNC_M3UPI_CHA_AD_CREDITS_EMPTY.WB", + "PerPkg": "1", + "PublicDescription": "CBox AD Credits Empty : Writebacks : No credits available to send to Cbox on the AD Ring (covers higher CBoxes)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M3UPI Clockticks", + "EventCode": "0x01", + "EventName": "UNC_M3UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of M2UPI clock cycles while the event is enabled", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M3UPI CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M3UPI_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2C Sent", + "EventCode": "0x2b", + "EventName": "UNC_M3UPI_D2C_SENT", + "PerPkg": "1", + "PublicDescription": "D2C Sent : Count cases BL sends direct to core", + "Unit": "M3UPI" + }, + { + "BriefDescription": "D2U Sent", + "EventCode": "0x2a", + "EventName": "UNC_M3UPI_D2U_SENT", + "PerPkg": "1", + "PublicDescription": "D2U Sent : Cases where SMI3 sends D2U command", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_M3UPI_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO0 and IIO1 share the same ring destination. (1 VN0 credit only)", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO1_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO0 and IIO1 share the same ring destination. (1 VN0 credit only) : No vn0 and vna credits available to send to M2", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO2", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO2_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO2 : No vn0 and vna credits available to send to M2", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO3", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO3_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO3 : No vn0 and vna credits available to send to M2", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO4", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO4_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO4 : No vn0 and vna credits available to send to M2", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO5", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.IIO5_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO5 : No vn0 and vna credits available to send to M2", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : All IIO targets for NCS are in single mask. ORs them together", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : All IIO targets for NCS are in single mask. ORs them together : No vn0 and vna credits available to send to M2", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : Selected M2p BL NCS credits", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.NCS_SEL", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : Selected M2p BL NCS credits : No vn0 and vna credits available to send to M2", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "M2 BL Credits Empty : IIO5", + "EventCode": "0x23", + "EventName": "UNC_M3UPI_M2_BL_CREDITS_EMPTY.UBOX_NCB", + "PerPkg": "1", + "PublicDescription": "M2 BL Credits Empty : IIO5 : No vn0 and vna credits available to send to M2", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AD - Slot 0", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AD - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AD - Slot 1", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT1", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AD - Slot 1 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AD - Slot 2", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AD_SLOT2", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AD - Slot 2 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AK - Slot 0", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AK - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : AK - Slot 2", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.AK_SLOT2", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : AK - Slot 2 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Multi Slot Flit Received : BL - Slot 0", + "EventCode": "0x3e", + "EventName": "UNC_M3UPI_MULTI_SLOT_RCVD.BL_SLOT0", + "PerPkg": "1", + "PublicDescription": "Multi Slot Flit Received : BL - Slot 0 : Multi slot flit received - S0, S1 and/or S2 populated (can use AK S0/S1 masks for AK allocations)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : REQ on AD", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : REQ on AD : VN0 message requested but lost arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : RSP on AD", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : RSP on AD : VN0 message requested but lost arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : SNP on AD", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : SNP on AD : VN0 message requested but lost arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : NCB on BL", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : NCB on BL : VN0 message requested but lost arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : NCS on BL", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : NCS on BL : VN0 message requested but lost arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : RSP on BL", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : RSP on BL : VN0 message requested but lost arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN0 : WB on BL", + "EventCode": "0x4b", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN0 : WB on BL : VN0 message requested but lost arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : REQ on AD", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : REQ on AD : VN1 message requested but lost arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : RSP on AD", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : RSP on AD : VN1 message requested but lost arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : SNP on AD", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : SNP on AD : VN1 message requested but lost arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : NCB on BL", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : NCB on BL : VN1 message requested but lost arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : NCS on BL", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : NCS on BL : VN1 message requested but lost arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : RSP on BL", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : RSP on BL : VN1 message requested but lost arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Lost Arb for VN1 : WB on BL", + "EventCode": "0x4c", + "EventName": "UNC_M3UPI_RxC_ARB_LOST_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Lost Arb for VN1 : WB on BL : VN1 message requested but lost arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : AD, BL Parallel Win VN0", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN_VN0", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : AD, BL Parallel Win VN0 : AD and BL messages won arbitration concurrently / in parallel", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : AD, BL Parallel Win VN1", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ADBL_PARALLEL_WIN_VN1", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : AD, BL Parallel Win VN1 : AD and BL messages won arbitration concurrently / in parallel", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : Max Parallel Win", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.ALL_PARALLEL_WIN", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : Max Parallel Win : VN0 and VN1 arbitration sub-pipelines both produced AD and BL winners (maximum possible parallel winners)", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending AD VN0", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN0", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending AD VN0 : Arbitration stage made no progress on pending ad vn0 messages because slotting stage cannot accept new message", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending AD VN1", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_AD_VN1", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending AD VN1 : Arbitration stage made no progress on pending ad vn1 messages because slotting stage cannot accept new message", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending BL VN0", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN0", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending BL VN0 : Arbitration stage made no progress on pending bl vn0 messages because slotting stage cannot accept new message", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : No Progress on Pending BL VN1", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.NO_PROG_BL_VN1", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : No Progress on Pending BL VN1 : Arbitration stage made no progress on pending bl vn1 messages because slotting stage cannot accept new message", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Arb Miscellaneous : VN0, VN1 Parallel Win", + "EventCode": "0x4d", + "EventName": "UNC_M3UPI_RxC_ARB_MISC.VN01_PARALLEL_WIN", + "PerPkg": "1", + "PublicDescription": "Arb Miscellaneous : VN0, VN1 Parallel Win : VN0 and VN1 arbitration sub-pipelines had parallel winners (at least one AD or BL on each side)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : REQ on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : REQ on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : RSP on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : RSP on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : SNP on AD", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : SNP on AD : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : NCB on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : NCB on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : NCS on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : NCS on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : RSP on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : RSP on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN0 : WB on BL", + "EventCode": "0x47", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN0 : WB on BL : VN0 message is blocked from requesting arbitration due to lack of remote UPI credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : REQ on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : REQ on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : RSP on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : RSP on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : SNP on AD", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : SNP on AD : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : NCB on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : NCB on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : NCS on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : NCS on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : RSP on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : RSP on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "No Credits to Arb for VN1 : WB on BL", + "EventCode": "0x48", + "EventName": "UNC_M3UPI_RxC_ARB_NOCRD_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "No Credits to Arb for VN1 : WB on BL : VN1 message is blocked from requesting arbitration due to lack of remote UPI credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : REQ on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : REQ on AD : VN0 message was not able to request arbitration while some other message won arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : RSP on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : RSP on AD : VN0 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : SNP on AD", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : SNP on AD : VN0 message was not able to request arbitration while some other message won arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : NCB on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : NCB on BL : VN0 message was not able to request arbitration while some other message won arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : NCS on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : NCS on BL : VN0 message was not able to request arbitration while some other message won arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : RSP on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : RSP on BL : VN0 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN0 : WB on BL", + "EventCode": "0x49", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN0 : WB on BL : VN0 message was not able to request arbitration while some other message won arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : REQ on AD", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : REQ on AD : VN1 message was not able to request arbitration while some other message won arbitration : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : RSP on AD", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : RSP on AD : VN1 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : SNP on AD", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : SNP on AD : VN1 message was not able to request arbitration while some other message won arbitration : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : NCB on BL", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : NCB on BL : VN1 message was not able to request arbitration while some other message won arbitration : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : NCS on BL", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : NCS on BL : VN1 message was not able to request arbitration while some other message won arbitration : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : RSP on BL", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : RSP on BL : VN1 message was not able to request arbitration while some other message won arbitration : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Can't Arb for VN1 : WB on BL", + "EventCode": "0x4a", + "EventName": "UNC_M3UPI_RxC_ARB_NOREQ_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "Can't Arb for VN1 : WB on BL : VN1 message was not able to request arbitration while some other message won arbitration : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD to Slot 0 on BL Arb", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_BL_ARB", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD to Slot 0 on BL Arb : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to slot 0 of independent flit while bl message is in arbitration", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD to Slot 0 on Idle", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S0_IDLE", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD to Slot 0 on Idle : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to slot 0 of independent flit while pipeline is idle", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD + BL to Slot 1", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S1_BL_SLOT", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD + BL to Slot 1 : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to flit slot 1 while merging with bl message in same flit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Ingress Queue Bypasses : AD + BL to Slot 2", + "EventCode": "0x40", + "EventName": "UNC_M3UPI_RxC_BYPASSED.AD_S2_BL_SLOT", + "PerPkg": "1", + "PublicDescription": "Ingress Queue Bypasses : AD + BL to Slot 2 : Number of times message is bypassed around the Ingress Queue : AD is taking bypass to flit slot 2 while merging with bl message in same flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events : Any In BGF FIFO", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_FIFO", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : Any In BGF FIFO : Indication that at least one packet (flit) is in the bgf (fifo only)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events : Any in BGF Path", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.ANY_BGF_PATH", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : Any in BGF Path : Indication that at least one packet (flit) is in the bgf path (i.e. pipe to fifo)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.LT1_FOR_D2K", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : d2k credit count is less than 1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.LT2_FOR_D2K", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : d2k credit count is less than 2", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events : No D2K For Arb", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.VN0_NO_D2K_FOR_ARB", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : No D2K For Arb : VN0 BL RSP message was blocked from arbitration request due to lack of D2K CMP credit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Miscellaneous Credit Events", + "EventCode": "0x5f", + "EventName": "UNC_M3UPI_RxC_CRD_MISC.VN1_NO_D2K_FOR_ARB", + "PerPkg": "1", + "PublicDescription": "Miscellaneous Credit Events : VN1 BL RSP message was blocked from arbitration request due to lack of D2K CMP credits", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Credits Consumed", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.CONSUMED", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Credits Consumed : number of remote vna credits consumed per cycle", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : D2K Credits", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.D2K_CRD", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : D2K Credits : D2K completion fifo credit occupancy (credits in use), accumulated across all cycles", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Packets in BGF FIFO", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_FIFO", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Packets in BGF FIFO : Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in fifo", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Packets in BGF Path", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.FLITS_IN_PATH", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Packets in BGF Path : Occupancy of m3upi ingress -> upi link layer bgf; packets (flits) in path (i.e. pipe to fifo or fifo)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_FIFO", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : count of bl messages in pump-1-pending state, in completion fifo only", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.P1P_TOTAL", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : count of bl messages in pump-1-pending state, in marker table and in fifo", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : Transmit Credits", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.TxQ_CRD", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : Transmit Credits : Link layer transmit queue credit occupancy (credits in use), accumulated across all cycles", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Credit Occupancy : VNA In Use", + "EventCode": "0x60", + "EventName": "UNC_M3UPI_RxC_CRD_OCC.VNA_IN_USE", + "PerPkg": "1", + "PublicDescription": "Credit Occupancy : VNA In Use : Remote UPI VNA credit occupancy (number of credits in use), accumulated across all cycles", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : REQ on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : SNP on AD : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCB on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : NCS on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : RSP on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL", + "EventCode": "0x43", + "EventName": "UNC_M3UPI_RxC_CYCLES_NE_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 Ingress (from CMS) Queue - Cycles Not Empty : WB on BL : Counts the number of cycles when the UPI Ingress is not empty. This tracks one of the three rings that are used by the UPI agent. This can be used in conjunction with the UPI Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple ingress buffers can be tracked at a given time using multiple counters. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : All", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : All : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but could not be sent for any reason, e.g. low credits, low tsv, stall injection", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : No BGF Credits", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.NO_BGF", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : No BGF Credits : Data flit is ready for transmission but could not be sent", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : No TxQ Credits", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.NO_TXQ", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : No TxQ Credits : Data flit is ready for transmission but could not be sent", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : TSV High", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.TSV_HI", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : TSV High : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but was not sent while tsv high", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Data Flit Not Sent : Cycle valid for Flit", + "EventCode": "0x55", + "EventName": "UNC_M3UPI_RxC_DATA_FLITS_NOT_SENT.VALID_FOR_FLIT", + "PerPkg": "1", + "PublicDescription": "Data Flit Not Sent : Cycle valid for Flit : Data flit is ready for transmission but could not be sent : data flit is ready for transmission but was not sent while cycle is valid for flit transmission", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence : Wait on Pump 0", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P0_WAIT", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : Wait on Pump 0 : generating bl data flit sequence; waiting for data pump 0", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_AT_LIMIT", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is at capacity (pending table plus completion fifo at limit)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_BUSY", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is tracking at least one message", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_FIFO_FULL", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending completion fifo is full", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_HOLD_P0", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : pump-1-pending logic is at or near capacity, such that pump-0-only bl messages are getting stalled in slotting stage", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1P_TO_LIMBO", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : a bl message finished but is in limbo and moved to pump-1-pending logic", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Generating BL Data Flit Sequence : Wait on Pump 1", + "EventCode": "0x57", + "EventName": "UNC_M3UPI_RxC_FLITS_GEN_BL.P1_WAIT", + "PerPkg": "1", + "PublicDescription": "Generating BL Data Flit Sequence : Wait on Pump 1 : generating bl data flit sequence; waiting for data pump 1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_HOLDOFF", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_HOLDOFF", + "PerPkg": "1", + "PublicDescription": ": slot 2 request naturally serviced during hold-off period", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_SERVICE", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_IN_SERVICE", + "PerPkg": "1", + "PublicDescription": ": slot 2 request forcibly serviced during service window", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_RECEIVED", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_RECEIVED", + "PerPkg": "1", + "PublicDescription": ": slot 2 request received from link layer while idle (with no slot 2 request active immediately prior)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_WITHDRAWN", + "EventCode": "0x58", + "EventName": "UNC_M3UPI_RxC_FLITS_MISC.S2REQ_WITHDRAWN", + "PerPkg": "1", + "PublicDescription": ": slot 2 request withdrawn during hold-off period or service window", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : All", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Needs Data Flit", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.NEED_DATA", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Needs Data Flit : BL message requires data flit sequence", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Wait on Pump 0", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P0_WAIT", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Wait on Pump 0 : Waiting for header pump 0", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 : Header pump 1 is not required for flit", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Bubble", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_BUT_BUBBLE", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Bubble : Header pump 1 is not required for flit but flit transmission delayed", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Not Avail", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_NOT_REQ_NOT_AVAIL", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Don't Need Pump 1 - Not Avail : Header pump 1 is not required for flit and not available", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Slotting BL Message Into Header Flit : Wait on Pump 1", + "EventCode": "0x56", + "EventName": "UNC_M3UPI_RxC_FLITS_SLOT_BL.P1_WAIT", + "PerPkg": "1", + "PublicDescription": "Slotting BL Message Into Header Flit : Wait on Pump 1 : Waiting for header pump 1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Accumulate", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Accumulate : Events related to Header Flit Generation - Set 1 : Header flit slotting control state machine is in any accumulate state; multi-message flit may be assembled over multiple cycles", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Accumulate Ready", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_READ", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Accumulate Ready : Events related to Header Flit Generation - Set 1 : header flit slotting control state machine is in accum_ready state; flit is ready to send but transmission is blocked; more messages may be slotted into flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Accumulate Wasted", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.ACCUM_WASTED", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Accumulate Wasted : Events related to Header Flit Generation - Set 1 : Flit is being assembled over multiple cycles, but no additional message is being slotted into flit in current cycle; accumulate cycle is wasted", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Run-Ahead - Blocked", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_BLOCKED", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Run-Ahead - Blocked : Events related to Header Flit Generation - Set 1 : Header flit slotting entered run-ahead state; new header flit is started while transmission of prior, fully assembled flit is blocked", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG1_AFTER", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: message was slotted only after run-ahead was over; run-ahead mode definitely wasted", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1 : Run-Ahead - Message", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG1_DURING", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Run-Ahead - Message : Events related to Header Flit Generation - Set 1 : run-ahead mode: one message slotted during run-ahead", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG2_AFTER", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: second message slotted immediately after run-ahead; potential run-ahead success", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 1", + "EventCode": "0x51", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR1.AHEAD_MSG2_SENT", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 1 : Events related to Header Flit Generation - Set 1 : run-ahead mode: two (or three) message flit sent immediately after run-ahead; complete run-ahead success", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Parallel Ok", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Parallel Ok : Events related to Header Flit Generation - Set 2 : new header flit construction may proceed in parallel with data flit sequence", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Parallel Flit Finished", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR_FLIT", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Parallel Flit Finished : Events related to Header Flit Generation - Set 2 : header flit finished assembly in parallel with data flit sequence", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Parallel Message", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.PAR_MSG", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Parallel Message : Events related to Header Flit Generation - Set 2 : message is slotted into header flit in parallel with data flit sequence", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Rate-matching Stall", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Rate-matching Stall : Events related to Header Flit Generation - Set 2 : Rate-matching stall injected", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Flit Gen - Header 2 : Rate-matching Stall - No Message", + "EventCode": "0x52", + "EventName": "UNC_M3UPI_RxC_FLIT_GEN_HDR2.RMSTALL_NOMSG", + "PerPkg": "1", + "PublicDescription": "Flit Gen - Header 2 : Rate-matching Stall - No Message : Events related to Header Flit Generation - Set 2 : Rate matching stall injected, but no additional message slotted during stall cycle", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : One Message", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.1_MSG", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : One Message : One message in flit; VNA or non-VNA flit", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : One Message in non-VNA", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.1_MSG_VNX", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : One Message in non-VNA : One message in flit; non-VNA flit", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : Two Messages", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.2_MSGS", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : Two Messages : Two messages in flit; VNA flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : Three Messages", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.3_MSGS", + "PerPkg": "1", + "PublicDescription": "Sent Header Flit : Three Messages : Three messages in flit; VNA flit", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : One Slot Taken", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : Two Slots Taken", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_2", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Sent Header Flit : All Slots Taken", + "EventCode": "0x54", + "EventName": "UNC_M3UPI_RxC_HDR_FLITS_SENT.SLOTS_3", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : All", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.ALL", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : All : header flit is ready for transmission but could not be sent : header flit is ready for transmission but could not be sent for any reason, e.g. no credits, low tsv, stall injection", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No BGF Credits", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_BGF_CRD", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No BGF Credits : header flit is ready for transmission but could not be sent : No BGF credits available", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No BGF Credits + No Extra Message Slotted", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_BGF_NO_MSG", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No BGF Credits + No Extra Message Slotted : header flit is ready for transmission but could not be sent : No BGF credits available; no additional message slotted into flit", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No TxQ Credits", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_TXQ_CRD", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No TxQ Credits : header flit is ready for transmission but could not be sent : No TxQ credits available", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : No TxQ Credits + No Extra Message Slotted", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.NO_TXQ_NO_MSG", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : No TxQ Credits + No Extra Message Slotted : header flit is ready for transmission but could not be sent : No TxQ credits available; no additional message slotted into flit", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : TSV High", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.TSV_HI", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : TSV High : header flit is ready for transmission but could not be sent : header flit is ready for transmission but was not sent while tsv high", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Header Not Sent : Cycle valid for Flit", + "EventCode": "0x53", + "EventName": "UNC_M3UPI_RxC_HDR_FLIT_NOT_SENT.VALID_FOR_FLIT", + "PerPkg": "1", + "PublicDescription": "Header Not Sent : Cycle valid for Flit : header flit is ready for transmission but could not be sent : header flit is ready for transmission but was not sent while cycle is valid for flit transmission", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Can't Slot AD", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_AD", + "PerPkg": "1", + "PublicDescription": "Message Held : Can't Slot AD : some AD message could not be slotted (logical OR of all AD events under INGR_SLOT_CANT_MC_VN{0,1})", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Can't Slot BL", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.CANT_SLOT_BL", + "PerPkg": "1", + "PublicDescription": "Message Held : Can't Slot BL : some BL message could not be slotted (logical OR of all BL events under INGR_SLOT_CANT_MC_VN{0,1})", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Parallel Attempt", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_ATTEMPT", + "PerPkg": "1", + "PublicDescription": "Message Held : Parallel Attempt : ad and bl messages attempted to slot into the same flit in parallel", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : Parallel Success", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS", + "PerPkg": "1", + "PublicDescription": "Message Held : Parallel Success : ad and bl messages were actually slotted into the same flit in parallel", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : VN0", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.VN0", + "PerPkg": "1", + "PublicDescription": "Message Held : VN0 : vn0 message(s) that couldn't be slotted into last vn0 flit are held in slotting stage while processing vn1 flit", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Message Held : VN1", + "EventCode": "0x50", + "EventName": "UNC_M3UPI_RxC_HELD.VN1", + "PerPkg": "1", + "PublicDescription": "Message Held : VN1 : vn1 message(s) that couldn't be slotted into last vn1 flit are held in slotting stage while processing vn0 flit", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : REQ on AD", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : REQ on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : RSP on AD", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : RSP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : SNP on AD", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : SNP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : NCB on BL", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : NCB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : NCS on BL", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : NCS on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : RSP on BL", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : RSP on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 message can't slot into flit : WB on BL", + "EventCode": "0x4e", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN0.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN0 message can't slot into flit : WB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : REQ on AD", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_REQ", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : REQ on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : RSP on AD", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : RSP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : SNP on AD", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.AD_SNP", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : SNP on AD : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : NCB on BL", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCB", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : NCB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : NCS on BL", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_NCS", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : NCS on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Non-Coherent Standard (NCS) messages on BL.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : RSP on BL", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_RSP", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : RSP on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 message can't slot into flit : WB on BL", + "EventCode": "0x4f", + "EventName": "UNC_M3UPI_RxC_PACKING_MISS_VN1.BL_WB", + "PerPkg": "1", + "PublicDescription": "VN1 message can't slot into flit : WB on BL : Count cases where Ingress has packets to send but did not have time to pack into flit before sending to Agent so slot was left NULL which could have been used. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Any In Use", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.ANY_IN_USE", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Any In Use : At least one remote vna credit is in use", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Corrected", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.CORRECTED", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Corrected : Number of remote vna credits corrected (local return) per cycle", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 1", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT1", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 1 : Remote vna credit level is less than 1 (i.e. no vna credits available)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 10", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT10", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 10 : remote vna credit level is less than 10; parallel vn0/vn1 arb not possible", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 4", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT4", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 4 : Remote vna credit level is less than 4; bl (or ad requiring 4 vna) cannot arb on vna", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Remote VNA Credits : Level < 5", + "EventCode": "0x5a", + "EventName": "UNC_M3UPI_RxC_VNA_CRD.LT5", + "PerPkg": "1", + "PublicDescription": "Remote VNA Credits : Level < 5 : Remote vna credit level is less than 5; parallel ad/bl arb on vna not possible", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_ADBL_ALLOC_L5", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_ADBL_ALLOC_L5", + "PerPkg": "1", + "PublicDescription": ": remote vna credit count was less than 5 and allocation to ad or bl messages was required", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_VN01_ALLOC_LT10", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.REQ_VN01_ALLOC_LT10", + "PerPkg": "1", + "PublicDescription": ": remote vna credit count was less than 10 and allocation to vn0 or vn1 was required", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_AD", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_AD", + "PerPkg": "1", + "PublicDescription": ": on vn0, remote vna credits were allocated only to ad messages, not to bl", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_BL", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_JUST_BL", + "PerPkg": "1", + "PublicDescription": ": on vn0, remote vna credits were allocated only to bl messages, not to ad", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_ONLY", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN0_ONLY", + "PerPkg": "1", + "PublicDescription": ": remote vna credits were allocated only to vn0, not to vn1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_AD", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_AD", + "PerPkg": "1", + "PublicDescription": ": on vn1, remote vna credits were allocated only to ad messages, not to bl", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_BL", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_JUST_BL", + "PerPkg": "1", + "PublicDescription": ": on vn1, remote vna credits were allocated only to bl messages, not to ad", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_ONLY", + "EventCode": "0x59", + "EventName": "UNC_M3UPI_RxC_VNA_CRD_MISC.VN1_ONLY", + "PerPkg": "1", + "PublicDescription": ": remote vna credits were allocated only to vn1, not to vn0", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 REQ Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 REQ Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 RSP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 RSP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 SNP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 SNP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN0 WB Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN0 WB Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 REQ Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 REQ Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 RSP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 RSP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 SNP Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 SNP Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for AD : VN1 WB Messages", + "EventCode": "0x30", + "EventName": "UNC_M3UPI_TxC_AD_ARB_FAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for AD : VN1 WB Messages : AD arb but no win; arb request asserted but not won", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2C", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT0", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT1", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.AD_SLOT2", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD FlowQ Bypass", + "EventCode": "0x2c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_BYPASS.BL_EARLY_RSP", + "PerPkg": "1", + "PublicDescription": "AD FlowQ Bypass : Counts cases when the AD flowQ is bypassed (S0, S1 and S2 indicate which slot was bypassed with S0 having the highest priority and S2 the least)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 REQ Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 REQ Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 RSP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 RSP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 SNP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 SNP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN0 WB Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN0 WB Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 REQ Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 REQ Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 RSP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 RSP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 SNP Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 SNP Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Not Empty : VN1 WB Messages", + "EventCode": "0x27", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_CYCLES_NE.VN1_WB", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Not Empty : VN1 WB Messages : Number of cycles the AD Egress queue is Not Empty", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 REQ Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 REQ Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 RSP Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 SNP Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 SNP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN0 WB Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN0_WB", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN0 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN1 REQ Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN1 REQ Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN1 RSP Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN1 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Inserts : VN1 SNP Messages", + "EventCode": "0x2d", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_INSERTS.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "AD Flow Q Inserts : VN1 SNP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 REQ Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_REQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 RSP Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_RSP", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 SNP Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_SNP", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN0 WB Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN0_WB", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN1 REQ Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_REQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN1 RSP Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_RSP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AD Flow Q Occupancy : VN1 SNP Messages", + "EventCode": "0x1c", + "EventName": "UNC_M3UPI_TxC_AD_FLQ_OCCUPANCY.VN1_SNP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AK Flow Q Inserts", + "EventCode": "0x2f", + "EventName": "UNC_M3UPI_TxC_AK_FLQ_INSERTS", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "AK Flow Q Occupancy", + "EventCode": "0x1e", + "EventName": "UNC_M3UPI_TxC_AK_FLQ_OCCUPANCY", + "PerPkg": "1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 NCB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 NCB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 NCS Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 NCS Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 RSP Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 RSP Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN0 WB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN0_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN0 WB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 NCS Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 NCS Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 NCB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 NCB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 RSP Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 RSP Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Failed ARB for BL : VN1 WB Messages", + "EventCode": "0x35", + "EventName": "UNC_M3UPI_TxC_BL_ARB_FAIL.VN1_WB", + "PerPkg": "1", + "PublicDescription": "Failed ARB for BL : VN1 WB Messages : BL arb but no win; arb request asserted but not won", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 REQ Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 REQ Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 RSP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 RSP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 SNP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 SNP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN0 WB Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN0 WB Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 REQ Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 REQ Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 RSP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 RSP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 SNP Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 SNP Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Not Empty : VN1 WB Messages", + "EventCode": "0x28", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_CYCLES_NE.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Not Empty : VN1 WB Messages : Number of cycles the BL Egress queue is Not Empty", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 RSP Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 WB Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_NCS", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 NCS Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 NCS Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN0 NCB Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN0_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN0 NCB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1 RSP Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1 RSP Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1 WB Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_NCS", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1 WB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1_NCB Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1_NCB Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Inserts : VN1_NCS Messages", + "EventCode": "0x2e", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_INSERTS.VN1_WB", + "PerPkg": "1", + "PublicDescription": "BL Flow Q Inserts : VN1_NCS Messages : Counts the number of allocations into the QPI FlowQ. This can be used in conjunction with the QPI FlowQ Occupancy Accumulator event in order to calculate average queue latency. Only a single FlowQ queue can be tracked at any given time. It is not possible to filter based on direction or polarity.", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 NCB Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 NCS Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 RSP Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_RSP", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 WB Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN0_WB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1_NCS Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1_NCB Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 RSP Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_RSP", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 WB Messages", + "EventCode": "0x1d", + "EventName": "UNC_M3UPI_TxC_BL_FLQ_OCCUPANCY.VN1_WB", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 RSP Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_LOCAL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 WB Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_THROUGH", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN0 NCB Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN0_WRPULL", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 RSP Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_LOCAL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1 WB Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_THROUGH", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "BL Flow Q Occupancy : VN1_NCS Messages", + "EventCode": "0x1f", + "EventName": "UNC_M3UPI_TxC_BL_WB_FLQ_OCCUPANCY.VN1_WRPULL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN0 REQ Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_REQ", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN0 REQ Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN0 RSP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN0 RSP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN0 SNP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN0_SNP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN0 SNP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN1 REQ Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_REQ", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN1 REQ Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN1 RSP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN1 RSP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VN1 SNP Messages", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VN1_SNP", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VN1 SNP Messages : No credits available to send to UPIs on the AD Ring", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 AD Credits Empty : VNA", + "EventCode": "0x20", + "EventName": "UNC_M3UPI_UPI_PEER_AD_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "UPI0 AD Credits Empty : VNA : No credits available to send to UPIs on the AD Ring", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN0 RSP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_NCS_NCB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN0 RSP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN0 REQ Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN0 REQ Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN0 SNP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN0_WB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN0 SNP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN1 RSP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_NCS_NCB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN1 RSP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN1 REQ Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_RSP", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN1 REQ Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VN1 SNP Messages", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VN1_WB", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VN1 SNP Messages : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UPI0 BL Credits Empty : VNA", + "EventCode": "0x21", + "EventName": "UNC_M3UPI_UPI_PEER_BL_CREDITS_EMPTY.VNA", + "PerPkg": "1", + "PublicDescription": "UPI0 BL Credits Empty : VNA : No credits available to send to UPI on the BL Ring (diff between non-SMI and SMI mode)", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "FlowQ Generated Prefetch", + "EventCode": "0x29", + "EventName": "UNC_M3UPI_UPI_PREFETCH_SPAWN", + "PerPkg": "1", + "PublicDescription": "FlowQ Generated Prefetch : Count cases where FlowQ causes spawn of Prefetch to iMC/SMI3 target", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : WB on BL", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : WB on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : NCB on BL", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : NCB on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : REQ on AD", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.REQ", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : REQ on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : RSP on AD", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.RSP", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : RSP on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : SNP on AD", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : SNP on AD : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 Credit Used : RSP on BL", + "EventCode": "0x5b", + "EventName": "UNC_M3UPI_VN0_CREDITS_USED.WB", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Used : RSP on BL : Number of times a VN0 credit was used on the DRS message channel. In order for a request to be transferred across UPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN0. VNA is a shared pool used to achieve high performance. The VN0 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN0 if they fail. This counts the number of times a VN0 credit was used. Note that a single VN0 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN0 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : WB on BL", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCB", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : WB on BL : Number of Cycles there were no VN0 Credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : NCB on BL", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.NCS", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : NCB on BL : Number of Cycles there were no VN0 Credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : REQ on AD", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.REQ", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : REQ on AD : Number of Cycles there were no VN0 Credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : RSP on AD", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.RSP", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : RSP on AD : Number of Cycles there were no VN0 Credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : SNP on AD", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.SNP", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : SNP on AD : Number of Cycles there were no VN0 Credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN0 No Credits : RSP on BL", + "EventCode": "0x5d", + "EventName": "UNC_M3UPI_VN0_NO_CREDITS.WB", + "PerPkg": "1", + "PublicDescription": "VN0 No Credits : RSP on BL : Number of Cycles there were no VN0 Credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : WB on BL", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCB", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : WB on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : NCB on BL", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.NCS", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : NCB on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : REQ on AD", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.REQ", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : REQ on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : RSP on AD", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.RSP", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : RSP on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : SNP on AD", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.SNP", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : SNP on AD : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 Credit Used : RSP on BL", + "EventCode": "0x5c", + "EventName": "UNC_M3UPI_VN1_CREDITS_USED.WB", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Used : RSP on BL : Number of times a VN1 credit was used on the WB message channel. In order for a request to be transferred across QPI, it must be guaranteed to have a flit buffer on the remote socket to sink into. There are two credit pools, VNA and VN1. VNA is a shared pool used to achieve high performance. The VN1 pool has reserved entries for each message class and is used to prevent deadlock. Requests first attempt to acquire a VNA credit, and then fall back to VN1 if they fail. This counts the number of times a VN1 credit was used. Note that a single VN1 credit holds access to potentially multiple flit buffers. For example, a transfer that uses VNA could use 9 flit buffers and in that case uses 9 credits. A transfer on VN1 will only count a single credit even though it may use multiple buffers. : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : WB on BL", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCB", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : WB on BL : Number of Cycles there were no VN1 Credits : Data Response (WB) messages on BL. WB is generally used to transmit data with coherency. For example, remote reads and writes, or cache to cache transfers will transmit their data using WB.", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : NCB on BL", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.NCS", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : NCB on BL : Number of Cycles there were no VN1 Credits : Non-Coherent Broadcast (NCB) messages on BL. NCB is generally used to transmit data without coherency. For example, non-coherent read data returns.", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : REQ on AD", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.REQ", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : REQ on AD : Number of Cycles there were no VN1 Credits : Home (REQ) messages on AD. REQ is generally used to send requests, request responses, and snoop responses.", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : RSP on AD", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.RSP", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : RSP on AD : Number of Cycles there were no VN1 Credits : Response (RSP) messages on AD. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : SNP on AD", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.SNP", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : SNP on AD : Number of Cycles there were no VN1 Credits : Snoops (SNP) messages on AD. SNP is used for outgoing snoops.", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "VN1 No Credits : RSP on BL", + "EventCode": "0x5e", + "EventName": "UNC_M3UPI_VN1_NO_CREDITS.WB", + "PerPkg": "1", + "PublicDescription": "VN1 No Credits : RSP on BL : Number of Cycles there were no VN1 Credits : Response (RSP) messages on BL. RSP packets are used to transmit a variety of protocol flits including grants and completions (CMP).", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x82", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_EQ_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0xa0", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x81", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_GT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x90", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x84", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.BOTHNONZERO_RT_LT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0xc0", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_EQ_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_GT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN0", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN1", + "EventCode": "0x7e", + "EventName": "UNC_M3UPI_WB_OCC_COMPARE.RT_LT_LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN0", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN1", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.LOCALDEST_VN1", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN0", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN1", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.LOCAL_AND_RT_VN1", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN0", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN1", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.ROUTETHRU_VN1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN0", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN1", + "EventCode": "0x7d", + "EventName": "UNC_M3UPI_WB_PENDING.WAITING4PULL_VN1", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.ARB", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.ARB", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message is making arbitration request", + "UMask": "0x4", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.ARRIVED", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.ARRIVED", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message arrived in ingress pipeline", + "UMask": "0x1", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.BYPASS", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.BYPASS", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message took bypass path", + "UMask": "0x2", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.FLITTED", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.FLITTED", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message was slotted into flit (non bypass)", + "UMask": "0x10", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_ARB", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_ARB", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message lost arbitration", + "UMask": "0x8", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_OLD", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_OLD", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message was dropped because it became too old", + "UMask": "0x20", + "Unit": "M3UPI" + }, + { + "BriefDescription": "UNC_M3UPI_XPT_PFTCH.LOST_QFULL", + "EventCode": "0x61", + "EventName": "UNC_M3UPI_XPT_PFTCH.LOST_QFULL", + "PerPkg": "1", + "PublicDescription": ": xpt prefetch message was dropped because it was overwritten by new message while prefetch queue was full", + "UMask": "0x40", + "Unit": "M3UPI" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (AD Bouncable)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.AD_BNC", + "PerPkg": "1", + "PublicDescription": "AD Bouncable : Number of allocations into the CRS Egress", + "UMask": "0x1", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (AD credited)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.AD_CRD", + "PerPkg": "1", + "PublicDescription": "AD credited : Number of allocations into the CRS Egress", + "UMask": "0x2", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (AK)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.AK", + "PerPkg": "1", + "PublicDescription": "AK : Number of allocations into the CRS Egress", + "UMask": "0x10", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (AKC)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.AKC", + "PerPkg": "1", + "PublicDescription": "AKC : Number of allocations into the CRS Egress", + "UMask": "0x40", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (BL Bouncable)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.BL_BNC", + "PerPkg": "1", + "PublicDescription": "BL Bouncable : Number of allocations into the CRS Egress", + "UMask": "0x4", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (BL credited)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.BL_CRD", + "PerPkg": "1", + "PublicDescription": "BL credited : Number of allocations into the CRS Egress", + "UMask": "0x8", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of allocations into the CRS Egress used to queue up requests destined to the mesh (IV)", + "EventCode": "0x47", + "EventName": "UNC_MDF_CRS_TxR_INSERTS.IV", + "PerPkg": "1", + "PublicDescription": "IV : Number of allocations into the CRS Egress", + "UMask": "0x20", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AD)", + "EventCode": "0x4B", + "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AD", + "PerPkg": "1", + "PublicDescription": "AD : Number of cycles incoming messages from the vertical ring that are bounced at the SBO", + "UMask": "0x1", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AK)", + "EventCode": "0x4B", + "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AK", + "PerPkg": "1", + "PublicDescription": "AK : Number of cycles incoming messages from the vertical ring that are bounced at the SBO", + "UMask": "0x4", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AKC)", + "EventCode": "0x4B", + "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AKC", + "PerPkg": "1", + "PublicDescription": "AKC : Number of cycles incoming messages from the vertical ring that are bounced at the SBO", + "UMask": "0x10", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (BL)", + "EventCode": "0x4B", + "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.BL", + "PerPkg": "1", + "PublicDescription": "BL : Number of cycles incoming messages from the vertical ring that are bounced at the SBO", + "UMask": "0x2", + "Unit": "MDF" + }, + { + "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (IV)", + "EventCode": "0x4B", + "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.IV", + "PerPkg": "1", + "PublicDescription": "IV : Number of cycles incoming messages from the vertical ring that are bounced at the SBO", + "UMask": "0x8", + "Unit": "MDF" + }, + { + "BriefDescription": "Counts the number of cycles when the distress signals are asserted based on SBO Ingress threshold", + "EventCode": "0x15", + "EventName": "UNC_MDF_FAST_ASSERTED.AD_BNC", + "PerPkg": "1", + "PublicDescription": "AD bnc : Counts the number of cycles when the distress signals are asserted based on SBO Ingress threshold", + "UMask": "0x1", + "Unit": "MDF" + }, + { + "BriefDescription": "Counts the number of cycles when the distress signals are asserted based on SBO Ingress threshold", + "EventCode": "0x15", + "EventName": "UNC_MDF_FAST_ASSERTED.BL_CRD", + "PerPkg": "1", + "PublicDescription": "BL bnc : Counts the number of cycles when the distress signals are asserted based on SBO Ingress threshold", + "UMask": "0x2", + "Unit": "MDF" + }, + { + "BriefDescription": "UPI Clockticks", + "EventCode": "0x01", + "EventName": "UNC_UPI_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of UPI LL clock cycles while the event is enabled", + "Unit": "UPI" + }, + { + "BriefDescription": "Direct packet attempts : D2C", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2C", + "PerPkg": "1", + "PublicDescription": "Direct packet attempts : D2C : Counts the number of DRS packets that we attempted to do direct2core/direct2UPI on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Direct packet attempts : D2K", + "EventCode": "0x12", + "EventName": "UNC_UPI_DIRECT_ATTEMPTS.D2K", + "PerPkg": "1", + "PublicDescription": "Direct packet attempts : D2K : Counts the number of DRS packets that we attempted to do direct2core/direct2UPI on. There are 4 mutually exclusive filters. Filter [0] can be used to get successful spawns, while [1:3] provide the different failure cases. Note that this does not count packets that are not candidates for Direct2Core. The only candidates for Direct2Core are DRS packets destined for Cbos.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AD_VNA_EQ2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ2", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.AK_VNA_EQ3", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", + "EventCode": "0x18", + "EventName": "UNC_UPI_FLOWQ_NO_VNA_CRD.BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L1", + "EventCode": "0x21", + "EventName": "UNC_UPI_L1_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L1 : Number of UPI qfclk cycles spent in L1 power mode. L1 is a mode that totally shuts down a UPI link. Use edge detect to count the number of instances when the UPI link entered L1. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. Because L1 totally shuts down the link, it takes a good amount of time to exit this mode.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.BGF_CRD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AD_VNA_LE2", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_AK_VNA_LE3", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.FLOWQ_BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", + "EventCode": "0x14", + "EventName": "UNC_UPI_M3_BYP_BLOCKED.GV_BLOCK", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_CRD_RETURN_BLOCKED", + "EventCode": "0x16", + "EventName": "UNC_UPI_M3_CRD_RETURN_BLOCKED", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.BGF_CRD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_BTW_2_THRESH", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AD_VNA_LE2", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_AK_VNA_LE3", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_BTW_0_THRESH", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.FLOWQ_BL_VNA_EQ0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", + "EventCode": "0x15", + "EventName": "UNC_UPI_M3_RXQ_BLOCKED.GV_BLOCK", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles where phy is not in L0, L0c, L0p, L1", + "EventCode": "0x20", + "EventName": "UNC_UPI_PHY_INIT_CYCLES", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "L1 Req Nack", + "EventCode": "0x23", + "EventName": "UNC_UPI_POWER_L1_NACK", + "PerPkg": "1", + "PublicDescription": "L1 Req Nack : Counts the number of times a link sends/receives a LinkReqNAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqNAck refers to receiving an NAck (meaning this agent's Tx originally requested the power change). A Tx LinkReqNAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", + "Unit": "UPI" + }, + { + "BriefDescription": "L1 Req (same as L1 Ack).", + "EventCode": "0x22", + "EventName": "UNC_UPI_POWER_L1_REQ", + "PerPkg": "1", + "PublicDescription": "L1 Req (same as L1 Ack). : Counts the number of times a link sends/receives a LinkReqAck. When the UPI links would like to change power state, the Tx side initiates a request to the Rx side requesting to change states. This requests can either be accepted or denied. If the Rx side replies with an Ack, the power mode will change. If it replies with NAck, no change will take place. This can be filtered based on Rx and Tx. An Rx LinkReqAck refers to receiving an Ack (meaning this agent's Tx originally requested the power change). A Tx LinkReqAck refers to sending this command (meaning the peer agent's Tx originally requested the power change and this agent accepted it).", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.ACK", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN0", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VN1", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", + "EventCode": "0x46", + "EventName": "UNC_UPI_REQ_SLOT2_FROM_M3.VNA", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0p", + "EventCode": "0x25", + "EventName": "UNC_UPI_RxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0p : Number of UPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the UPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize UPI for snoops and their responses. Use edge detect to count the number of instances when the UPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0", + "EventCode": "0x24", + "EventName": "UNC_UPI_RxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0 : Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.DATA", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.DATA", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.LLCRD", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.LLCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.LLCTRL", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.LLCTRL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.NULL", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.NULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.PROTHDR", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.PROTHDR", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.SLOT0", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.SLOT0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.SLOT1", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.SLOT1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_ANY_FLITS.SLOT2", + "EventCode": "0x4B", + "EventName": "UNC_UPI_RxL_ANY_FLITS.SLOT2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10e", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode", + "EventCode": "0x05", + "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10f", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 0", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT0", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 0 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 1", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT1", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 1 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Bypassed : Slot 2", + "EventCode": "0x31", + "EventName": "UNC_UPI_RxL_BYPASSED.SLOT2", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Bypassed : Slot 2 : Counts the number of times that an incoming flit was able to bypass the flit buffer and pass directly across the BGF and into the Egress. This is a latency optimization, and should generally be the common case. If this value is less than the number of flits transferred, it implies that there was queueing getting onto the ring, and thus the transactions saw higher latency.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "CRC Errors Detected", + "EventCode": "0x0b", + "EventName": "UNC_UPI_RxL_CRC_ERRORS", + "PerPkg": "1", + "PublicDescription": "CRC Errors Detected : Number of CRC errors detected in the UPI Agent. Each UPI flit incorporates 8 bits of CRC for error detection. This counts the number of flits where the CRC was able to detect an error. After an error has been detected, the UPI agent will send a request to the transmitting socket to resend the flit (as well as any flits that came after it).", + "Unit": "UPI" + }, + { + "BriefDescription": "LLR Requests Sent", + "EventCode": "0x08", + "EventName": "UNC_UPI_RxL_CRC_LLR_REQ_TRANSMIT", + "PerPkg": "1", + "PublicDescription": "LLR Requests Sent : Number of LLR Requests were transmitted. This should generally be <= the number of CRC errors detected. If multiple errors are detected before the Rx side receives a LLC_REQ_ACK from the Tx side, there is no need to send more LLR_REQ_NACKs..", + "Unit": "UPI" + }, + { + "BriefDescription": "VN0 Credit Consumed", + "EventCode": "0x39", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN0", + "PerPkg": "1", + "PublicDescription": "VN0 Credit Consumed : Counts the number of times that an RxQ VN0 credit was consumed (i.e. message uses a VN0 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "VN1 Credit Consumed", + "EventCode": "0x3a", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VN1", + "PerPkg": "1", + "PublicDescription": "VN1 Credit Consumed : Counts the number of times that an RxQ VN1 credit was consumed (i.e. message uses a VN1 credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "VNA Credit Consumed", + "EventCode": "0x38", + "EventName": "UNC_UPI_RxL_CREDITS_CONSUMED_VNA", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of times that an RxQ VNA credit was consumed (i.e. message uses a VNA credit for the Rx Buffer). This includes packets that went through the RxQ and those that were bypasssed.", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : All Data", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : All Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Null FLITs received from any slot", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.ALL_NULL", + "PerPkg": "1", + "UMask": "0x27", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Data", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Data : Shows legal flit time (hides impact of L0p and L0c). : Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Idle", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Idle : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : LLCRD Not Empty", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.LLCRD", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : LLCRD Not Empty : Shows legal flit time (hides impact of L0p and L0c). : Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : LLCTRL", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.LLCTRL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : LLCTRL : Shows legal flit time (hides impact of L0p and L0c). : Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : All Non Data", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : All Non Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x97", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot NULL or LLCRD Empty", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.NULL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot NULL or LLCRD Empty : Shows legal flit time (hides impact of L0p and L0c). : LLCRD with all zeros is treated as NULL. Slot 1 is not treated as NULL if slot 0 is a dual slot. This can apply to slot 0,1, or 2.", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Protocol Header", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.PROTHDR", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Protocol Header : Shows legal flit time (hides impact of L0p and L0c). : Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot 0", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot 0 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 0 - Other mask bits determine types of headers to count.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot 1", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot 1 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 1 - Other mask bits determine types of headers to count.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Received : Slot 2", + "EventCode": "0x03", + "EventName": "UNC_UPI_RxL_FLITS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Valid Flits Received : Slot 2 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 2 - Other mask bits determine types of headers to count.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 0", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT0", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Allocations : Slot 0 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 1", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT1", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Allocations : Slot 1 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Flit Buffer Allocations : Slot 2", + "EventCode": "0x30", + "EventName": "UNC_UPI_RxL_INSERTS.SLOT2", + "PerPkg": "1", + "PublicDescription": "RxQ Flit Buffer Allocations : Slot 2 : Number of allocations into the UPI Rx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 0", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT0", + "PerPkg": "1", + "PublicDescription": "RxQ Occupancy - All Packets : Slot 0 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 1", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT1", + "PerPkg": "1", + "PublicDescription": "RxQ Occupancy - All Packets : Slot 1 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "RxQ Occupancy - All Packets : Slot 2", + "EventCode": "0x32", + "EventName": "UNC_UPI_RxL_OCCUPANCY.SLOT2", + "PerPkg": "1", + "PublicDescription": "RxQ Occupancy - All Packets : Slot 2 : Accumulates the number of elements in the UPI RxQ in each cycle. Generally, when data is transmitted across UPI, it will bypass the RxQ and pass directly to the ring interface. If things back up getting transmitted onto the ring, however, it may need to allocate into this buffer, thus increasing the latency. This event can be used in conjunction with the Flit Buffer Not Empty event to calculate average occupancy, or with the Flit Buffer Allocations event to track average lifetime.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ1", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S0_RXQ2", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ0", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S1_RXQ2", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ0", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", + "EventCode": "0x33", + "EventName": "UNC_UPI_RxL_SLOT_BYPASS.S2_RXQ1", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.CFG_CTL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.DFX", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RETRY", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_BYPASS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.RXQ_CRED", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.SPARE", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", + "EventCode": "0x2a", + "EventName": "UNC_UPI_TxL0P_CLK_ACTIVE.TXQ", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0p", + "EventCode": "0x27", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0p : Number of UPI qfclk cycles spent in L0p power mode. L0p is a mode where we disable 1/2 of the UPI lanes, decreasing our bandwidth in order to save power. It increases snoop and data transfer latencies and decreases overall bandwidth. This mode can be very useful in NUMA optimized workloads that largely only utilize UPI for snoops and their responses. Use edge detect to count the number of instances when the UPI link entered L0p. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "EventCode": "0x28", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_LL_ENTER", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "EventCode": "0x29", + "EventName": "UNC_UPI_TxL0P_POWER_CYCLES_M3_EXIT", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "Cycles in L0", + "EventCode": "0x26", + "EventName": "UNC_UPI_TxL0_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles in L0 : Number of UPI qfclk cycles spent in L0 power mode in the Link Layer. L0 is the default mode which provides the highest performance with the most power. Use edge detect to count the number of instances that the link entered L0. Link power states are per link and per direction, so for example the Tx direction could be in one state while Rx was in another. The phy layer sometimes leaves L0 for training, which will not be captured by this event.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.DATA", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.DATA", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.LLCRD", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.LLCRD", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.LLCTRL", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.LLCTRL", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.NULL", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.NULL", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.PROTHDR", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.PROTHDR", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.SLOT0", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.SLOT0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.SLOT1", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.SLOT1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_TxL_ANY_FLITS.SLOT2", + "EventCode": "0x4A", + "EventName": "UNC_UPI_TxL_ANY_FLITS.SLOT2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xe", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10e", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode", + "EventCode": "0x04", + "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC", + "PerPkg": "1", + "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.", + "UMask": "0x10f", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Bypassed", + "EventCode": "0x41", + "EventName": "UNC_UPI_TxL_BYPASSED", + "PerPkg": "1", + "PublicDescription": "Tx Flit Buffer Bypassed : Counts the number of times that an incoming flit was able to bypass the Tx flit buffer and pass directly out the UPI Link. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link.", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All Data", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All Data : Counts number of data flits across this UPI link.", + "UMask": "0xf", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All LLCRD Not Empty", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_LLCRD", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x17", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All LLCTRL", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_LLCTRL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All LLCTRL : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "All Null Flits", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_NULL", + "PerPkg": "1", + "UMask": "0x27", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All Protocol Header", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.ALL_PROTHDR", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All ProtDDR : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x87", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Data", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Data : Shows legal flit time (hides impact of L0p and L0c). : Count Data Flits (which consume all slots), but how much to count is based on Slot0-2 mask, so count can be 0-3 depending on which slots are enabled for counting..", + "UMask": "0x8", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Idle", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.IDLE", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Idle : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x47", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : LLCRD Not Empty", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.LLCRD", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : LLCRD Not Empty : Shows legal flit time (hides impact of L0p and L0c). : Enables counting of LLCRD (with non-zero payload). This only applies to slot 2 since LLCRD is only allowed in slot 2", + "UMask": "0x10", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : LLCTRL", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.LLCTRL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : LLCTRL : Shows legal flit time (hides impact of L0p and L0c). : Equivalent to an idle packet. Enables counting of slot 0 LLCTRL messages.", + "UMask": "0x40", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : All Non Data", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.NON_DATA", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : All Non Data : Shows legal flit time (hides impact of L0p and L0c).", + "UMask": "0x97", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.NULL", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot NULL or LLCRD Empty : Shows legal flit time (hides impact of L0p and L0c). : LLCRD with all zeros is treated as NULL. Slot 1 is not treated as NULL if slot 0 is a dual slot. This can apply to slot 0,1, or 2.", + "UMask": "0x20", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Protocol Header", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.PROTHDR", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Protocol Header : Shows legal flit time (hides impact of L0p and L0c). : Enables count of protocol headers in slot 0,1,2 (depending on slot uMask bits)", + "UMask": "0x80", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 0", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT0", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot 0 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 0 - Other mask bits determine types of headers to count.", + "UMask": "0x1", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 1", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT1", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot 1 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 1 - Other mask bits determine types of headers to count.", + "UMask": "0x2", + "Unit": "UPI" + }, + { + "BriefDescription": "Valid Flits Sent : Slot 2", + "EventCode": "0x02", + "EventName": "UNC_UPI_TxL_FLITS.SLOT2", + "PerPkg": "1", + "PublicDescription": "Valid Flits Sent : Slot 2 : Shows legal flit time (hides impact of L0p and L0c). : Count Slot 2 - Other mask bits determine types of headers to count.", + "UMask": "0x4", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Allocations", + "EventCode": "0x40", + "EventName": "UNC_UPI_TxL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Tx Flit Buffer Allocations : Number of allocations into the UPI Tx Flit Buffer. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This event can be used in conjunction with the Flit Buffer Occupancy event in order to calculate the average flit buffer lifetime.", + "Unit": "UPI" + }, + { + "BriefDescription": "Tx Flit Buffer Occupancy", + "EventCode": "0x42", + "EventName": "UNC_UPI_TxL_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "Tx Flit Buffer Occupancy : Accumulates the number of flits in the TxQ. Generally, when data is transmitted across UPI, it will bypass the TxQ and pass directly to the link. However, the TxQ will be used with L0p and when LLR occurs, increasing latency to transfer out to the link. This can be used with the cycles not empty event to track average occupancy, or the allocations event to track average lifetime in the TxQ.", + "Unit": "UPI" + }, + { + "BriefDescription": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", + "EventCode": "0x45", + "EventName": "UNC_UPI_VNA_CREDIT_RETURN_BLOCKED_VN01", + "PerPkg": "1", + "Unit": "UPI" + }, + { + "BriefDescription": "VNA Credits Pending Return - Occupancy", + "EventCode": "0x44", + "EventName": "UNC_UPI_VNA_CREDIT_RETURN_OCCUPANCY", + "PerPkg": "1", + "PublicDescription": "VNA Credits Pending Return - Occupancy : Number of VNA credits in the Rx side that are waitng to be returned back across the link.", + "Unit": "UPI" + }, + { + "BriefDescription": "Message Received : Doorbell", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.DOORBELL_RCVD", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : Interrupt", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.INT_PRIO", + "PerPkg": "1", + "PublicDescription": "Message Received : Interrupt : Interrupts", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : IPI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.IPI_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : IPI : Inter Processor Interrupts", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : MSI", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.MSI_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : MSI : Message Signaled Interrupts - interrupts sent by devices (including PCIe via IOxAPIC) (Socket Mode only)", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Message Received : VLW", + "EventCode": "0x42", + "EventName": "UNC_U_EVENT_MSG.VLW_RCVD", + "PerPkg": "1", + "PublicDescription": "Message Received : VLW : Virtual Logical Wire (legacy) message were received from Uncore.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_CBO_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCB", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCS", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.RxC_CYCLES_NE_UPI_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_CBO_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCB", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCS", + "EventCode": "0x4d", + "EventName": "UNC_U_M2U_MISC1.TxC_CYCLES_CRD_OVF_UPI_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_EMPTY_BL", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.RxC_CYCLES_FULL_BL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_CRD_OVF_VN0_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AK", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_AKC", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_EMPTY_BL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", + "EventCode": "0x4e", + "EventName": "UNC_U_M2U_MISC2.TxC_CYCLES_FULL_BL", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", + "EventCode": "0x4f", + "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AK", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", + "EventCode": "0x4f", + "EventName": "UNC_U_M2U_MISC3.TxC_CYCLES_FULL_AKC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "Cycles PHOLD Assert to Ack : Assert to ACK", + "EventCode": "0x45", + "EventName": "UNC_U_PHOLD_CYCLES.ASSERT_TO_ACK", + "PerPkg": "1", + "PublicDescription": "Cycles PHOLD Assert to Ack : Assert to ACK : PHOLD cycles.", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "EventCode": "0x4c", + "EventName": "UNC_U_RACU_DRNG.PFTCH_BUF_EMPTY", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDRAND", + "EventCode": "0x4c", + "EventName": "UNC_U_RACU_DRNG.RDRAND", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "UBOX" + }, + { + "BriefDescription": "UNC_U_RACU_DRNG.RDSEED", + "EventCode": "0x4c", + "EventName": "UNC_U_RACU_DRNG.RDSEED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "UBOX" + }, + { + "BriefDescription": "RACU Request", + "EventCode": "0x46", + "EventName": "UNC_U_RACU_REQUESTS", + "PerPkg": "1", + "PublicDescription": "RACU Request : Number outstanding register requests within message channel tracker", + "Unit": "UBOX" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json new file mode 100644 index 000000000000..557080b74ee5 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json @@ -0,0 +1,3587 @@ +[ + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART0_FREERUN", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART1_FREERUN", + "PerPkg": "1", + "UMask": "0x21", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART2_FREERUN", + "PerPkg": "1", + "UMask": "0x22", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART3_FREERUN", + "PerPkg": "1", + "UMask": "0x23", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART4_FREERUN", + "PerPkg": "1", + "UMask": "0x24", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART5_FREERUN", + "PerPkg": "1", + "UMask": "0x25", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART6_FREERUN", + "PerPkg": "1", + "UMask": "0x26", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "Free running counter that increments for every 32 bytes of data sent from the IO agent to the SOC", + "EventCode": "0xff", + "EventName": "UNC_IIO_BANDWIDTH_IN.PART7_FREERUN", + "PerPkg": "1", + "UMask": "0x27", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "IIO Clockticks", + "EventCode": "0x01", + "EventName": "UNC_IIO_CLOCKTICKS", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "Number of IIO clock cycles while the event is enabled", + "Unit": "IIO" + }, + { + "BriefDescription": "Free running counter that increments for IIO clocktick", + "EventCode": "0xff", + "EventName": "UNC_IIO_CLOCKTICKS_FREERUN", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iio_free_running" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0-7", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xff", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0-7", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 0", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7001004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 1", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 1", + "UMask": "0x7002004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 2", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 2", + "UMask": "0x7004004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 3", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 3", + "UMask": "0x7008004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 4", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 0 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 4", + "UMask": "0x7010004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 5", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 1 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 5", + "UMask": "0x7020004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 6", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 6", + "UMask": "0x7040004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Inserts of completions with data: Part 7", + "EventCode": "0xc2", + "EventName": "UNC_IIO_COMP_BUF_INSERTS.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "PCIe Completion Buffer Inserts of completions with data : Part 2 : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 7", + "UMask": "0x7080004", + "Unit": "IIO" + }, + { + "BriefDescription": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "UMask": "0xff", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 0", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7000001", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 1", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x4 card is plugged in to slot 1", + "UMask": "0x7000002", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 2", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7000004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 3", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x4 card is plugged in to slot 3", + "UMask": "0x7000008", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 4", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7000010", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 5", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x4 card is plugged in to slot 1", + "UMask": "0x7000020", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 6", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7000040", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Completion Buffer Occupancy : Part 7", + "EventCode": "0xd5", + "EventName": "UNC_IIO_COMP_BUF_OCCUPANCY.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "x4 card is plugged in to slot 3", + "UMask": "0x7000080", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0-7", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00ff", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part0", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7001004", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part1", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7002004", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part2", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7004004", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by the CPU to IIO Part3", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested by the CPU : Core reading from Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7008004", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7010004", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7020004", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7040004", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested by the CPU : Core reading from Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7080004", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part0-7 by the CPU", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00ff", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0100", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.IOMMU1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0200", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : IOMMU - Type 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part0 by the CPU", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part1 by the CPU", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part2 by the CPU", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made to IIO Part3 by the CPU", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested by the CPU : Core writing to Card's MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested by the CPU : Core writing to Cards MMIO space : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7001008", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7002008", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7004008", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7008008", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7010008", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7020008", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7040008", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) reading from this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7080008", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7001002", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7002002", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7004002", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7008002", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7010002", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7020002", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x7040002", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc0", + "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested by the CPU : Another card (different IIO stack) writing to this card. : Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7080002", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0xff", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested of the CPU : CmpD - device sending completion to CPU request : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part0-7 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00ff", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part0 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part1 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part2 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for 4 bytes made by IIO Part3 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card reading from DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested of the CPU : Card reading from DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part0-7 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.ALL_PARTS", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00ff", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part0 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part1 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part2 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of 4 bytes made by IIO Part3 to Memory", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to DRAM", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested of the CPU : Card writing to DRAM : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Data requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x83", + "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Data requested of the CPU : Card writing to another Card (same or different stack) : Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Passing data to be written", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Passing data to be written : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x70ff020", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Issuing final read or write of line", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Issuing final read or write of line : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Processing response from IOMMU", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Processing response from IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Issuing to IOMMU", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Issuing to IOMMU : How often different queues (e.g. channel / fc) ask to send request into pipeline", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Request Ownership", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Request Ownership : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x70ff004", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests : Writing line", + "EventCode": "0x86", + "EventName": "UNC_IIO_INBOUND_ARB_REQ.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests : Writing line : How often different queues (e.g. channel / fc) ask to send request into pipeline : Only for posted requests", + "UMask": "0x70ff010", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Passing data to be written", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Passing data to be written : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x70ff020", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Issuing final read or write of line", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Issuing final read or write of line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x70ff008", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Processing response from IOMMU", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Processing response from IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x70ff002", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Issuing to IOMMU", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Issuing to IOMMU : How often different queues (e.g. channel / fc) are allowed to send request into pipeline", + "UMask": "0x70ff001", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Request Ownership", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Request Ownership : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x70ff004", + "Unit": "IIO" + }, + { + "BriefDescription": "Incoming arbitration requests granted : Writing line", + "EventCode": "0x87", + "EventName": "UNC_IIO_INBOUND_ARB_WON.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Incoming arbitration requests granted : Writing line : How often different queues (e.g. channel / fc) are allowed to send request into pipeline : Only for posted requests", + "UMask": "0x70ff010", + "Unit": "IIO" + }, + { + "BriefDescription": ": Context cache hits", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_HITS", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": ": Context cache hits : Counts each time a first look up of the transaction hits the RCC.", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": ": Context cache lookups", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.CTXT_CACHE_LOOKUPS", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": ": Context cache lookups : Counts each time a transaction looks up root context cache.", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOTLB lookups first", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.FIRST_LOOKUPS", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": ": IOTLB lookups first : Some transactions have to look up IOTLB multiple times. Counts the first time a request looks up IOTLB.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "IOTLB Fills (same as IOTLB miss)", + "EventCode": "0x40", + "EventName": "UNC_IIO_IOMMU0.MISSES", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "IOTLB Fills (same as IOTLB miss) : When a transaction misses IOTLB, it does a page walk to look up memory and bring in the relevant page translation. Counts when this page translation is written to IOTLB.", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": IOMMU memory access", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.NUM_MEM_ACCESSES", + "PerPkg": "1", + "PublicDescription": ": IOMMU memory access : IOMMU sends out memory fetches when it misses the cache look up which is indicated by this signal. M2IOSF only uses low priority channel", + "UMask": "0xc0", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 2M page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_1G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWT Hit to a 256T page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_256T_HITS", + "PerPkg": "1", + "PublicDescription": ": PWT Hit to a 256T page : Counts each time a transaction's first look up hits the SLPWC at the 512G level", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 4K page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_2M_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 4K page : Counts each time a transaction's first look up hits the SLPWC at the 4K level", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 1G page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_512G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 1G page : Counts each time a transaction's first look up hits the SLPWC at the 1G level", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": PageWalk cache fill", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWC_CACHE_FILLS", + "PerPkg": "1", + "PublicDescription": ": PageWalk cache fill : When a transaction misses SLPWC, it does a page walk to look up memory and bring in the relevant page translation. When this page translation is written to SLPWC, ObsPwcFillValid_nnnH is asserted.", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": ": PageWalk cache lookup", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.PWT_CACHE_LOOKUPS", + "PerPkg": "1", + "PublicDescription": ": PageWalk cache lookup : Counts each time a transaction looks up second level page walk cache.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 2M page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.SLPWC_1G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 2M page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.SLPWC_256T_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 2M page : Counts each time a transaction's first look up hits the SLPWC at the 2M level", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": ": PWC Hit to a 1G page", + "EventCode": "0x41", + "EventName": "UNC_IIO_IOMMU1.SLPWC_512G_HITS", + "PerPkg": "1", + "PublicDescription": ": PWC Hit to a 1G page : Counts each time a transaction's first look up hits the SLPWC at the 1G level", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": ": Global IOTLB invalidation cycles", + "EventCode": "0x43", + "EventName": "UNC_IIO_IOMMU3.PWT_OCCUPANCY_MSB", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": ": Global IOTLB invalidation cycles : Indicates that IOMMU is doing global invalidation.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS0_NOT_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if all bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if all bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", + "EventCode": "0x02", + "EventName": "UNC_IIO_MASK_MATCH_AND.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "AND Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if all bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus)", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS0_NOT_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : Non-PCIE bus and !(PCIE bus) : Asserted if any bits specified by mask match", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and PCIE bus : Asserted if any bits specified by mask match", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus)", + "EventCode": "0x03", + "EventName": "UNC_IIO_MASK_MATCH_OR.NOT_BUS0_NOT_BUS1", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "OR Mask/match for debug bus : !(Non-PCIE bus) and !(PCIE bus) : Asserted if any bits specified by mask match", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Number requests PCIe makes of the main die : All", + "EventCode": "0x85", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU.COMMIT.ALL", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0FFF", + "PublicDescription": "Number requests PCIe makes of the main die : All : Counts full PCIe requests before they're broken into a series of cache-line size requests as measured by DATA_REQ_OF_CPU and TXN_REQ_OF_CPU.", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Abort", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.ABORT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Confined P2P", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.CONFINED_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x40", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Local P2P", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.LOC_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x20", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Multi-cast", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MCAST", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Memory", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MEM", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : MsgB", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.MSGB", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Remote P2P", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.REM_P2P", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x10", + "Unit": "IIO" + }, + { + "BriefDescription": "Num requests sent by PCIe - by target : Ubox", + "EventCode": "0x8e", + "EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.UBOX", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "ITC address map 1", + "EventCode": "0x8f", + "EventName": "UNC_IIO_NUM_TGT_MATCHED_REQ_OF_CPU", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "UNC_IIO_NUM_TGT_MATCHED_REQ_OF_CPU", + "Unit": "IIO" + }, + { + "BriefDescription": "Outbound cacheline requests issued : 64B requests issued to device", + "EventCode": "0xd0", + "EventName": "UNC_IIO_OUTBOUND_CL_REQS_ISSUED.TO_IO", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Outbound cacheline requests issued : 64B requests issued to device : Each outbound cacheline granular request may need to make multiple passes through the pipeline. Each time a cacheline completes all its passes it advances line", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "Outbound TLP (transaction layer packet) requests issued : To device", + "EventCode": "0xd1", + "EventName": "UNC_IIO_OUTBOUND_TLP_REQS_ISSUED.TO_IO", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Outbound TLP (transaction layer packet) requests issued : To device : Each time an outbound completes all its passes it advances the pointer", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PWT occupancy. Does not include 9th bit of occupancy (will undercount if PWT is greater than 255 per cycle).", + "EventCode": "0x42", + "EventName": "UNC_IIO_PWT_OCCUPANCY", + "PerPkg": "1", + "PortMask": "0x0000", + "PublicDescription": "PWT occupancy : Indicates how many page walks are outstanding at any point in time.", + "UMask": "0xff", + "Unit": "IIO" + }, + { + "BriefDescription": "Request Ownership : PCIe Request complete", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Request Ownership : PCIe Request complete : Only for posted requests : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a single PCIe request completes all its cacheline granular requests, it advances pointer.", + "UMask": "0x70ff020", + "Unit": "IIO" + }, + { + "BriefDescription": "Request Ownership : Writing line", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Request Ownership : Writing line : Only for posted requests : Only for posted requests", + "UMask": "0x70ff008", + "Unit": "IIO" + }, + { + "BriefDescription": "Request Ownership : Issuing final read or write of line", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Request Ownership : Issuing final read or write of line : Only for posted requests", + "UMask": "0x70ff004", + "Unit": "IIO" + }, + { + "BriefDescription": "Request Ownership : Passing data to be written", + "EventCode": "0x91", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CL_CMPL.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Request Ownership : Passing data to be written : Only for posted requests : Only for posted requests", + "UMask": "0x70ff010", + "Unit": "IIO" + }, + { + "BriefDescription": "Processing response from IOMMU : Passing data to be written", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Processing response from IOMMU : Passing data to be written : Only for posted requests", + "UMask": "0x70ff008", + "Unit": "IIO" + }, + { + "BriefDescription": "Processing response from IOMMU : Issuing final read or write of line", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_HIT", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "UMask": "0x70ff002", + "Unit": "IIO" + }, + { + "BriefDescription": "Processing response from IOMMU : Request Ownership", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.IOMMU_REQ", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Processing response from IOMMU : Request Ownership : Only for posted requests", + "UMask": "0x70ff001", + "Unit": "IIO" + }, + { + "BriefDescription": "Processing response from IOMMU : Writing line", + "EventCode": "0x92", + "EventName": "UNC_IIO_REQ_FROM_PCIE_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "Processing response from IOMMU : Writing line : Only for posted requests", + "UMask": "0x70ff004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Passing data to be written", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.DATA", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "PCIe Request - pass complete : Passing data to be written : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x70ff020", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Issuing final read or write of line", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.FINAL_RD_WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "PCIe Request - pass complete : Issuing final read or write of line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state", + "UMask": "0x8", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Request Ownership", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.REQ_OWN", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "PCIe Request - pass complete : Request Ownership : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x70ff004", + "Unit": "IIO" + }, + { + "BriefDescription": "PCIe Request - pass complete : Writing line", + "EventCode": "0x90", + "EventName": "UNC_IIO_REQ_FROM_PCIE_PASS_CMPL.WR", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x00FF", + "PublicDescription": "PCIe Request - pass complete : Writing line : Each PCIe request is broken down into a series of cacheline granular requests and each cacheline size request may need to make multiple passes through the pipeline (e.g. for posted interrupts or multi-cast). Each time a cacheline completes a single pass (e.g. posts a write to single multi-cast target) it advances state : Only for posted requests", + "UMask": "0x70ff010", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part0", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part1", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part2", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by the CPU to IIO Part3", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested by the CPU : Core reading from Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part0 by the CPU", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part1 by the CPU", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part2 by the CPU", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made to IIO Part3 by the CPU", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Card's MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested by the CPU : Core writing to Cards MMIO space : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x7001002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x7002002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x7004002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x7008002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x7010002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x7020002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x7040002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card.", + "EventCode": "0xc1", + "EventName": "UNC_IIO_TXN_REQ_BY_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested by the CPU : Another card (different IIO stack) writing to this card. : Also known as Outbound. Number of requests initiated by the main die, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x7080002", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.CMPD.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested of the CPU : CmpD - device sending completion to CPU request : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x80", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part0 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part1 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part2 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Read request for up to a 64 byte transaction is made by IIO Part3 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card reading from DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_READ.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested of the CPU : Card reading from DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x4", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part0 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part1 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part2 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Write request of up to a 64 byte transaction is made by IIO Part3 to Memory", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 1", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to DRAM", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.MEM_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to DRAM : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x1", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART0", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0001", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 0/1/2/3, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART1", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0002", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 1", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART2", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0004", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 2/3, Or x4 card is plugged in to slot 2", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART3", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0008", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 3", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART4", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0010", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x16 card plugged in to Lane 4/5/6/7, Or x8 card plugged in to Lane 4/5, Or x4 card is plugged in to slot 4", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART5", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0020", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 5", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART6", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0040", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x8 card plugged in to Lane 6/7, Or x4 card is plugged in to slot 6", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack)", + "EventCode": "0x84", + "EventName": "UNC_IIO_TXN_REQ_OF_CPU.PEER_WRITE.PART7", + "FCMask": "0x07", + "PerPkg": "1", + "PortMask": "0x0080", + "PublicDescription": "Number Transactions requested of the CPU : Card writing to another Card (same or different stack) : Also known as Inbound. Number of 64B cache line requests initiated by the Card, including reads and writes. : x4 card is plugged in to slot 7", + "UMask": "0x2", + "Unit": "IIO" + }, + { + "BriefDescription": "M2P Clockticks", + "EventCode": "0x01", + "EventName": "UNC_M2P_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of M2P clock cycles while the event is enabled", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M2P_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_M2P_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : DRS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.DRS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : DRS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCB", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCB_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCB : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credit Acquired : NCS", + "EventCode": "0x33", + "EventName": "UNC_M2P_IIO_CREDITS_ACQUIRED.NCS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credit Acquired : NCS : Counts the number of credits that are acquired in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.DRS", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : DRS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the DRS message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCB", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCB : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCB message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS", + "EventCode": "0x34", + "EventName": "UNC_M2P_IIO_CREDITS_REJECT.NCS", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Failed to Acquire a Credit : NCS : Counts the number of times that a request pending in the BL Ingress attempted to acquire either a NCB or NCS credit to transmit into the IIO, but was rejected because no credits were available. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.DRS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : DRS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the DRS message class.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCB_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCB to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCB message class.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_0", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 0 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credits for transfer through CMS Port 0 to the IIO for the NCS message class.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1", + "EventCode": "0x32", + "EventName": "UNC_M2P_IIO_CREDITS_USED.NCS_1", + "PerPkg": "1", + "PublicDescription": "M2PCIe IIO Credits in Use : NCS to CMS Port 1 : Counts the number of cycles when one or more credits in the M2PCIe agent for sending transactions into the IIO on either NCB or NCS are in use. Transactions from the BL ring going into the IIO Agent must first acquire a credit. These credits are for either the NCB or NCS message classes. NCB, or non-coherent bypass messages are used to transmit data without coherency (and are common). NCS is used for reads to PCIe (and should be used sparingly). : Credit for transfer through CMS Port 0s to the IIO for the NCS message class.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF0 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF1 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF2 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCB", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 0 : M2IOSF3 - NCS", + "EventCode": "0x46", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCB", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF4 - NCS", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCB", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Dedicated P2P Credit Taken - 1 : M2IOSF5 - NCS", + "EventCode": "0x47", + "EventName": "UNC_M2P_LOCAL_DED_P2P_CRD_TAKEN_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF0 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF1 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF2 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCB", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 0 : M2IOSF3 - NCS", + "EventCode": "0x19", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_0.MS2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCB", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF4 - NCS", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCB", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Dedicated Credits Returned - 1 : M2IOSF5 - NCS", + "EventCode": "0x1a", + "EventName": "UNC_M2P_LOCAL_P2P_DED_RETURNED_1.MS2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent0", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent1", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local P2P Shared Credits Returned : Agent2", + "EventCode": "0x17", + "EventName": "UNC_M2P_LOCAL_P2P_SHAR_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent0", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent1", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent2", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent3", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_3", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent4", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_4", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Returned to credit ring : Agent5", + "EventCode": "0x44", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_RETURNED.AGENT_5", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF0 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF1 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF2 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCB", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 0 : M2IOSF3 - NCS", + "EventCode": "0x40", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCB", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF4 - NCS", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCB", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Local Shared P2P Credit Taken - 1 : M2IOSF5 - NCS", + "EventCode": "0x41", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_TAKEN_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF0 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF1 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF2 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCB", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCB", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 0 : M2IOSF3 - NCS", + "EventCode": "0x4a", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_0.M2IOSF3_NCS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCB", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF4 - NCS", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF4_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCB", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Local Shared P2P Credit - 1 : M2IOSF5 - NCS", + "EventCode": "0x4b", + "EventName": "UNC_M2P_LOCAL_SHAR_P2P_CRD_WAIT_1.M2IOSF5_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : All", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Local NCB", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Local NCS", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Remote NCB", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "P2P Credit Occupancy : Remote NCS", + "EventCode": "0x14", + "EventName": "UNC_M2P_P2P_CRD_OCCUPANCY.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : All", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Local NCB", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Local NCS", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Remote NCB", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Dedicated Credits Received : Remote NCS", + "EventCode": "0x16", + "EventName": "UNC_M2P_P2P_DED_RECEIVED.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : All", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.ALL", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Local NCB", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Local NCS", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.LOCAL_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Remote NCB", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Shared Credits Received : Remote NCS", + "EventCode": "0x15", + "EventName": "UNC_M2P_P2P_SHAR_RECEIVED.REMOTE_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - DRS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - NCB", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI0 - NCS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - DRS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_DRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - NCB", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 0 : UPI1 - NCS", + "EventCode": "0x48", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_0.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - DRS", + "EventCode": "0x49", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - NCB", + "EventCode": "0x49", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Dedicated P2P Credit Taken - 1 : UPI2 - NCS", + "EventCode": "0x49", + "EventName": "UNC_M2P_REMOTE_DED_P2P_CRD_TAKEN_1.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI0 - NCB", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI0 - NCS", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI1 - NCB", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI1 - NCS", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI2 - NCB", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Dedicated Credits Returned : UPI2 - NCS", + "EventCode": "0x1b", + "EventName": "UNC_M2P_REMOTE_P2P_DED_RETURNED.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent0", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent1", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote P2P Shared Credits Returned : Agent2", + "EventCode": "0x18", + "EventName": "UNC_M2P_REMOTE_P2P_SHAR_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent0", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent1", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Returned to credit ring : Agent2", + "EventCode": "0x45", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_RETURNED.AGENT_2", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - DRS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - NCB", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI0 - NCS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - DRS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_DRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - NCB", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 0 : UPI1 - NCS", + "EventCode": "0x42", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_0.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - DRS", + "EventCode": "0x43", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - NCB", + "EventCode": "0x43", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Remote Shared P2P Credit Taken - 1 : UPI2 - NCS", + "EventCode": "0x43", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_TAKEN_1.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - DRS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - NCB", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI0 - NCS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI0_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - DRS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_DRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - NCB", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_NCB", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 0 : UPI1 - NCS", + "EventCode": "0x4c", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_0.UPI1_NCS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - DRS", + "EventCode": "0x4d", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_DRS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - NCB", + "EventCode": "0x4d", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_NCB", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Waiting on Remote Shared P2P Credit - 1 : UPI2 - NCS", + "EventCode": "0x4d", + "EventName": "UNC_M2P_REMOTE_SHAR_P2P_CRD_WAIT_1.UPI2_NCS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.ALL", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_IDI", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.CHA_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.IIO_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.UPI_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Cycles Not Empty", + "EventCode": "0x10", + "EventName": "UNC_M2P_RxC_CYCLES_NE.UPI_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Cycles Not Empty : Counts the number of cycles when the M2PCIe Ingress is not empty.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.ALL", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_IDI", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.CHA_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x4", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x20", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.IIO_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x40", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.UPI_NCB", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Ingress (from CMS) Queue Inserts", + "EventCode": "0x11", + "EventName": "UNC_M2P_RxC_INSERTS.UPI_NCS", + "PerPkg": "1", + "PublicDescription": "Ingress (from CMS) Queue Inserts : Counts the number of entries inserted into the M2PCIe Ingress Queue. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue latency.", + "UMask": "0x10", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "UNC_M2P_TxC_CREDITS.PMM", + "EventCode": "0x2d", + "EventName": "UNC_M2P_TxC_CREDITS.PMM", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "UNC_M2P_TxC_CREDITS.PRQ", + "EventCode": "0x2d", + "EventName": "UNC_M2P_TxC_CREDITS.PRQ", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.PMM_BLOCK_0", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Full", + "EventCode": "0x25", + "EventName": "UNC_M2P_TxC_CYCLES_FULL.PMM_BLOCK_1", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Egress (to CMS) Cycles Full : Counts the number of cycles when the M2PCIe Egress is full. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent.", + "UMask": "0x8", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.PMM_DISTRESS_0", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x80", + "Unit": "M2PCIe" + }, + { + "BriefDescription": "Egress (to CMS) Cycles Not Empty", + "EventCode": "0x23", + "EventName": "UNC_M2P_TxC_CYCLES_NE.PMM_DISTRESS_1", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Egress (to CMS) Cycles Not Empty : Counts the number of cycles when the M2PCIe Egress is not empty. This tracks messages for one of the two CMS ports that are used by the M2PCIe agent. This can be used in conjunction with the M2PCIe Ingress Occupancy Accumulator event in order to calculate average queue occupancy. Multiple egress buffers can be tracked at a given time using multiple counters.", + "UMask": "0x8", + "Unit": "M2PCIe" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-memory.json new file mode 100644 index 000000000000..3ff9e9b722c8 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-memory.json @@ -0,0 +1,3308 @@ +[ + { + "BriefDescription": "Cycles - at UCLK", + "EventCode": "0x01", + "EventName": "UNC_M2HBM_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "CMS Clockticks", + "EventCode": "0xc0", + "EventName": "UNC_M2HBM_CMS_CLOCKTICKS", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when direct to core mode (which bypasses the CHA) was disabled", + "EventCode": "0x17", + "EventName": "UNC_M2HBM_DIRECT2CORE_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when direct to core mode, which bypasses the CHA, was disabled : Non Cisgress", + "EventCode": "0x17", + "EventName": "UNC_M2HBM_DIRECT2CORE_NOT_TAKEN_DIRSTATE.NON_CISGRESS", + "PerPkg": "1", + "PublicDescription": "Counts the number of time non cisgress D2C was not honoured by egress due to directory state constraints", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Counts the time when FM didn't do d2c for fill reads (cross tile case)", + "EventCode": "0x4a", + "EventName": "UNC_M2HBM_DIRECT2CORE_NOT_TAKEN_NOTFORKED", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction were overridden", + "EventCode": "0x18", + "EventName": "UNC_M2HBM_DIRECT2CORE_TXN_OVERRIDE", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number of reads in which direct to core transaction was overridden : Cisgress", + "EventCode": "0x18", + "EventName": "UNC_M2HBM_DIRECT2CORE_TXN_OVERRIDE.CISGRESS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number of reads in which direct to Intel UPI transactions were overridden", + "EventCode": "0x1b", + "EventName": "UNC_M2HBM_DIRECT2UPI_NOT_TAKEN_CREDITS", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when direct to Intel UPI was disabled", + "EventCode": "0x1a", + "EventName": "UNC_M2HBM_DIRECT2UPI_NOT_TAKEN_DIRSTATE", + "PerPkg": "1", + "UMask": "0x7", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Cisgress D2U Ignored", + "EventCode": "0x1A", + "EventName": "UNC_M2HBM_DIRECT2UPI_NOT_TAKEN_DIRSTATE.CISGRESS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts cisgress d2K that was not honored due to directory constraints", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Egress Ignored D2U", + "EventCode": "0x1A", + "EventName": "UNC_M2HBM_DIRECT2UPI_NOT_TAKEN_DIRSTATE.EGRESS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of time D2K was not honoured by egress due to directory state constraints", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Cycles when Direct2UPI was Disabled : Non Cisgress D2U Ignored", + "EventCode": "0x1A", + "EventName": "UNC_M2HBM_DIRECT2UPI_NOT_TAKEN_DIRSTATE.NON_CISGRESS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts non cisgress d2K that was not honored due to directory constraints", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number of reads that a message sent direct2 Intel UPI was overridden", + "EventCode": "0x1c", + "EventName": "UNC_M2HBM_DIRECT2UPI_TXN_OVERRIDE", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number of times a direct to UPI transaction was overridden.", + "EventCode": "0x1c", + "EventName": "UNC_M2HBM_DIRECT2UPI_TXN_OVERRIDE.CISGRESS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in A State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in I State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in L State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On NonDirty Line in S State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in A State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in I State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in L State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Hit : On Dirty Line in S State", + "EventCode": "0x1d", + "EventName": "UNC_M2HBM_DIRECTORY_HIT.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (any state found)", + "EventCode": "0x20", + "EventName": "UNC_M2HBM_DIRECTORY_LOOKUP.ANY", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with any directory to non persistent memory", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookups (cacheline found in A state)", + "EventCode": "0x20", + "EventName": "UNC_M2HBM_DIRECTORY_LOOKUP.STATE_A", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory A to non persistent memory", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in I state)", + "EventCode": "0x20", + "EventName": "UNC_M2HBM_DIRECTORY_LOOKUP.STATE_I", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory I to non persistent memory", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory lookup (cacheline found in S state)", + "EventCode": "0x20", + "EventName": "UNC_M2HBM_DIRECTORY_LOOKUP.STATE_S", + "PerPkg": "1", + "PublicDescription": "Counts the number of hit data returns to egress with directory S to non persistent memory", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in A State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.CLEAN_A", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in I State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.CLEAN_I", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in L State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.CLEAN_P", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On NonDirty Line in S State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.CLEAN_S", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in A State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.DIRTY_A", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in I State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.DIRTY_I", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in L State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.DIRTY_P", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Directory Miss : On Dirty Line in S State", + "EventCode": "0x1e", + "EventName": "UNC_M2HBM_DIRECTORY_MISS.DIRTY_S", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to I", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A2I", + "PerPkg": "1", + "UMask": "0x320", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from A to S", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A2S", + "PerPkg": "1", + "UMask": "0x340", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from/to Any state", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.ANY", + "PerPkg": "1", + "UMask": "0x301", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A_TO_I_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from A to I to non persistent memory", + "UMask": "0x120", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A_TO_I_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from A to I to non persistent memory", + "UMask": "0x220", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A_TO_S_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from A to S to non persistent memory", + "UMask": "0x140", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.A_TO_S_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from A to S to non persistent memory", + "UMask": "0x240", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts any 1lm or 2lm hit data return that would result in directory update to non persistent memory", + "UMask": "0x101", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to A", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I2A", + "PerPkg": "1", + "UMask": "0x304", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from I to S", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I2S", + "PerPkg": "1", + "UMask": "0x302", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I_TO_A_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from I to A to non persistent memory", + "UMask": "0x104", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I_TO_A_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from I to A to non persistent memory", + "UMask": "0x204", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I_TO_S_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from I to S to non persistent memory", + "UMask": "0x102", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.I_TO_S_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from I to S to non persistent memory", + "UMask": "0x202", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts any 2lm miss data return that would result in directory update to non persistent memory", + "UMask": "0x201", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to A", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S2A", + "PerPkg": "1", + "UMask": "0x310", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory update from S to I", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S2I", + "PerPkg": "1", + "UMask": "0x308", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S_TO_A_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from S to A to non persistent memory", + "UMask": "0x110", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S_TO_A_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from S to A to non persistent memory", + "UMask": "0x210", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S_TO_I_HIT_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 1lm or 2lm hit data returns that would result in directory update from S to I to non persistent memory", + "UMask": "0x108", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Multi-socket cacheline Directory Updates", + "EventCode": "0x21", + "EventName": "UNC_M2HBM_DIRECTORY_UPDATE.S_TO_I_MISS_NON_PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts 2lm miss data returns that would result in directory update from S to I to non persistent memory", + "UMask": "0x208", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on AkAd cmp message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.AD", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on any packet type", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on Bl Cmp message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.BL_CMP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on NM fill write message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.CROSSTILE_NMWR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on D2Cha message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.D2CHA", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on D2c message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.D2CORE", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count distress signalled on D2k message", + "EventCode": "0x67", + "EventName": "UNC_M2HBM_DISTRESS.D2UPI", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Down", + "EventCode": "0xba", + "EventName": "UNC_M2HBM_EGRESS_ORDERING.IV_SNOOPGO_DN", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Down : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x80000004", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Egress Blocking due to Ordering requirements : Up", + "EventCode": "0xba", + "EventName": "UNC_M2HBM_EGRESS_ORDERING.IV_SNOOPGO_UP", + "PerPkg": "1", + "PublicDescription": "Egress Blocking due to Ordering requirements : Up : Counts number of cycles IV was blocked in the TGR Egress due to SNP/GO Ordering requirements", + "UMask": "0x80000001", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Count when Starve Glocab counter is at 7", + "EventCode": "0x44", + "EventName": "UNC_M2HBM_IGR_STARVE_WINNER.MASK7", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x80", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Reads to iMC issued", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.ALL", + "PerPkg": "1", + "UMask": "0x304", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH0.ALL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0.ALL", + "PerPkg": "1", + "UMask": "0x104", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH0.NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0.NORMAL", + "PerPkg": "1", + "UMask": "0x101", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH0_ALL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x104", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH0_FROM_TGR", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0_FROM_TGR", + "PerPkg": "1", + "UMask": "0x140", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Critical Priority - Ch0", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0_ISOCH", + "PerPkg": "1", + "UMask": "0x102", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH0_NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH0_NORMAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x101", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH1.ALL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1.ALL", + "PerPkg": "1", + "UMask": "0x204", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH1.NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1.NORMAL", + "PerPkg": "1", + "UMask": "0x201", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH1_ALL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x204", + "Unit": "M2HBM" + }, + { + "BriefDescription": "From TGR - Ch1", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1_FROM_TGR", + "PerPkg": "1", + "UMask": "0x240", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Critical Priority - Ch1", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1_ISOCH", + "PerPkg": "1", + "UMask": "0x202", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.CH1_NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.CH1_NORMAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x201", + "Unit": "M2HBM" + }, + { + "BriefDescription": "From TGR - All Channels", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.FROM_TGR", + "PerPkg": "1", + "UMask": "0x340", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Critical Priority - All Channels", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.ISOCH", + "PerPkg": "1", + "UMask": "0x302", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_READS.NORMAL", + "EventCode": "0x24", + "EventName": "UNC_M2HBM_IMC_READS.NORMAL", + "PerPkg": "1", + "UMask": "0x301", + "Unit": "M2HBM" + }, + { + "BriefDescription": "All Writes - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.ALL", + "PerPkg": "1", + "UMask": "0x1810", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0.ALL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0.ALL", + "PerPkg": "1", + "UMask": "0x810", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0.FULL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0.FULL", + "PerPkg": "1", + "UMask": "0x801", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0.PARTIAL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0.PARTIAL", + "PerPkg": "1", + "UMask": "0x802", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0_ALL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x810", + "Unit": "M2HBM" + }, + { + "BriefDescription": "From TGR - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_FROM_TGR", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0_FULL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_FULL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x801", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Full Line - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x804", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_NI", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive Miss - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_NI_MISS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_IMC_WRITES.CH0_PARTIAL", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_PARTIAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x802", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Partial - Ch0", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH0_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x808", + "Unit": "M2HBM" + }, + { + "BriefDescription": "All Writes - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1.ALL", + "PerPkg": "1", + "UMask": "0x1010", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Full Line Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1.FULL", + "PerPkg": "1", + "UMask": "0x1001", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Partial Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1.PARTIAL", + "PerPkg": "1", + "UMask": "0x1002", + "Unit": "M2HBM" + }, + { + "BriefDescription": "All Writes - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_ALL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1010", + "Unit": "M2HBM" + }, + { + "BriefDescription": "From TGR - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_FROM_TGR", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Full Line Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_FULL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1001", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Full Line - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x1004", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_NI", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive Miss - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_NI_MISS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Partial Non-ISOCH - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_PARTIAL", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1002", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Partial - Ch1", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.CH1_PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x1008", + "Unit": "M2HBM" + }, + { + "BriefDescription": "From TGR - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.FROM_TGR", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Full Non-ISOCH - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.FULL", + "PerPkg": "1", + "UMask": "0x1801", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Full Line - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.FULL_ISOCH", + "PerPkg": "1", + "UMask": "0x1804", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.NI", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Non-Inclusive Miss - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.NI_MISS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Partial Non-ISOCH - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.PARTIAL", + "PerPkg": "1", + "UMask": "0x1802", + "Unit": "M2HBM" + }, + { + "BriefDescription": "ISOCH Partial - All Channels", + "EventCode": "0x25", + "EventName": "UNC_M2HBM_IMC_WRITES.PARTIAL_ISOCH", + "PerPkg": "1", + "UMask": "0x1808", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_PREFCAM_CIS_DROPS", + "EventCode": "0x5c", + "EventName": "UNC_M2HBM_PREFCAM_CIS_DROPS", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped : UPI - All Channels", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Data Prefetches Dropped", + "EventCode": "0x58", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_DROPS.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "M2HBM" + }, + { + "BriefDescription": ": UPI - All Channels", + "EventCode": "0x5d", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_MERGE.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2HBM" + }, + { + "BriefDescription": ": XPT - All Channels", + "EventCode": "0x5d", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_MERGE.XPT_ALLCH", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5e", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_NO_MERGE.RD_MERGED", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5e", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_NO_MERGE.WR_MERGED", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Demands Not Merged with CAMed Prefetches", + "EventCode": "0x5e", + "EventName": "UNC_M2HBM_PREFCAM_DEMAND_NO_MERGE.WR_SQUASHED", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 0", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.CH0_UPI", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 0", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.CH0_XPT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - Ch 1", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.CH1_UPI", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - Ch 1", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.CH1_XPT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : UPI - All Channels", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.UPI_ALLCH", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Inserts : XPT - All Channels", + "EventCode": "0x56", + "EventName": "UNC_M2HBM_PREFCAM_INSERTS.XPT_ALLCH", + "PerPkg": "1", + "PublicDescription": "Prefetch CAM Inserts : XPT -All Channels", + "UMask": "0x5", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : All Channels", + "EventCode": "0x54", + "EventName": "UNC_M2HBM_PREFCAM_OCCUPANCY.ALLCH", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 0", + "EventCode": "0x54", + "EventName": "UNC_M2HBM_PREFCAM_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Prefetch CAM Occupancy : Channel 1", + "EventCode": "0x54", + "EventName": "UNC_M2HBM_PREFCAM_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "All Channels", + "EventCode": "0x5f", + "EventName": "UNC_M2HBM_PREFCAM_RESP_MISS.ALLCH", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2HBM" + }, + { + "BriefDescription": ": Channel 0", + "EventCode": "0x5f", + "EventName": "UNC_M2HBM_PREFCAM_RESP_MISS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": ": Channel 1", + "EventCode": "0x5f", + "EventName": "UNC_M2HBM_PREFCAM_RESP_MISS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "EventCode": "0x62", + "EventName": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.1LM_POSTED", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.CIS", + "EventCode": "0x62", + "EventName": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.CIS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.SQUASHED", + "EventCode": "0x62", + "EventName": "UNC_M2HBM_PREFCAM_RxC_DEALLOCS.SQUASHED", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "UNC_M2HBM_PREFCAM_RxC_OCCUPANCY", + "EventCode": "0x60", + "EventName": "UNC_M2HBM_PREFCAM_RxC_OCCUPANCY", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Ingress (from CMS) : AD Ingress (from CMS) Allocations", + "EventCode": "0x02", + "EventName": "UNC_M2HBM_RxC_AD.INSERTS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Ingress (from CMS) : AD Ingress (from CMS) Allocations", + "EventCode": "0x02", + "EventName": "UNC_M2HBM_RxC_AD_INSERTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Ingress (from CMS) Occupancy", + "EventCode": "0x03", + "EventName": "UNC_M2HBM_RxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Ingress (from CMS) : BL Ingress (from CMS) Allocations", + "EventCode": "0x04", + "EventName": "UNC_M2HBM_RxC_BL.INSERTS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts anytime a BL packet is added to Ingress", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Ingress (from CMS) : BL Ingress (from CMS) Allocations", + "EventCode": "0x04", + "EventName": "UNC_M2HBM_RxC_BL_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts anytime a BL packet is added to Ingress", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Ingress (from CMS) Occupancy", + "EventCode": "0x05", + "EventName": "UNC_M2HBM_RxC_BL_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number AD Ingress Credits", + "EventCode": "0x2e", + "EventName": "UNC_M2HBM_TGR_AD_CREDITS", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Number BL Ingress Credits", + "EventCode": "0x2f", + "EventName": "UNC_M2HBM_TGR_BL_CREDITS", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Tracker Inserts : Channel 0", + "EventCode": "0x32", + "EventName": "UNC_M2HBM_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x104", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Tracker Inserts : Channel 1", + "EventCode": "0x32", + "EventName": "UNC_M2HBM_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x204", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 0", + "EventCode": "0x33", + "EventName": "UNC_M2HBM_TRACKER_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Tracker Occupancy : Channel 1", + "EventCode": "0x33", + "EventName": "UNC_M2HBM_TRACKER_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Egress (to CMS) : AD Egress (to CMS) Allocations", + "EventCode": "0x06", + "EventName": "UNC_M2HBM_TxC_AD.INSERTS", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts anytime a AD packet is added to Egress", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Egress (to CMS) : AD Egress (to CMS) Allocations", + "EventCode": "0x06", + "EventName": "UNC_M2HBM_TxC_AD_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts anytime a AD packet is added to Egress", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "AD Egress (to CMS) Occupancy", + "EventCode": "0x07", + "EventName": "UNC_M2HBM_TxC_AD_OCCUPANCY", + "PerPkg": "1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Egress (to CMS) : Inserts - CMS0 - Near Side", + "EventCode": "0x0E", + "EventName": "UNC_M2HBM_TxC_BL.INSERTS_CMS0", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of BL transactions to CMS add port 0", + "UMask": "0x101", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Egress (to CMS) : Inserts - CMS1 - Far Side", + "EventCode": "0x0E", + "EventName": "UNC_M2HBM_TxC_BL.INSERTS_CMS1", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of BL transactions to CMS add port 1", + "UMask": "0x201", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy : All", + "EventCode": "0x0f", + "EventName": "UNC_M2HBM_TxC_BL_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy : Common Mesh Stop - Near Side", + "EventCode": "0x0f", + "EventName": "UNC_M2HBM_TxC_BL_OCCUPANCY.CMS0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "BL Egress (to CMS) Occupancy : Common Mesh Stop - Far Side", + "EventCode": "0x0f", + "EventName": "UNC_M2HBM_TxC_BL_OCCUPANCY.CMS1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "WPQ Flush : Channel 0", + "EventCode": "0x42", + "EventName": "UNC_M2HBM_WPQ_FLUSH.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "WPQ Flush : Channel 1", + "EventCode": "0x42", + "EventName": "UNC_M2HBM_WPQ_FLUSH.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "M2M and iMC WPQ Cycles w/Credits - Regular : Channel 0", + "EventCode": "0x37", + "EventName": "UNC_M2HBM_WPQ_NO_REG_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "M2M and iMC WPQ Cycles w/Credits - Regular : Channel 1", + "EventCode": "0x37", + "EventName": "UNC_M2HBM_WPQ_NO_REG_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "M2M and iMC WPQ Cycles w/Credits - Special : Channel 0", + "EventCode": "0x38", + "EventName": "UNC_M2HBM_WPQ_NO_SPEC_CRD.CHN0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "M2M and iMC WPQ Cycles w/Credits - Special : Channel 1", + "EventCode": "0x38", + "EventName": "UNC_M2HBM_WPQ_NO_SPEC_CRD.CHN1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 0", + "EventCode": "0x40", + "EventName": "UNC_M2HBM_WR_TRACKER_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Inserts : Channel 1", + "EventCode": "0x40", + "EventName": "UNC_M2HBM_WR_TRACKER_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 0", + "EventCode": "0x4d", + "EventName": "UNC_M2HBM_WR_TRACKER_NONPOSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Non-Posted Inserts : Channel 1", + "EventCode": "0x4d", + "EventName": "UNC_M2HBM_WR_TRACKER_NONPOSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 0", + "EventCode": "0x4c", + "EventName": "UNC_M2HBM_WR_TRACKER_NONPOSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Non-Posted Occupancy : Channel 1", + "EventCode": "0x4c", + "EventName": "UNC_M2HBM_WR_TRACKER_NONPOSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 0", + "EventCode": "0x48", + "EventName": "UNC_M2HBM_WR_TRACKER_POSTED_INSERTS.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Posted Inserts : Channel 1", + "EventCode": "0x48", + "EventName": "UNC_M2HBM_WR_TRACKER_POSTED_INSERTS.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 0", + "EventCode": "0x47", + "EventName": "UNC_M2HBM_WR_TRACKER_POSTED_OCCUPANCY.CH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Write Tracker Posted Occupancy : Channel 1", + "EventCode": "0x47", + "EventName": "UNC_M2HBM_WR_TRACKER_POSTED_OCCUPANCY.CH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "M2HBM" + }, + { + "BriefDescription": "Activate due to read, write, underfill, or bypass", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0xff", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Activate due to read", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x11", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count : Activate due to Read in PCH0", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.RD_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count : Activate due to Read in PCH1", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.RD_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x10", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count : Underfill Read transaction on Page Empty or Page Miss", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.UFILL", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x44", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.UFILL_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x4", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.UFILL_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x40", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Activate due to write", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x22", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count : Activate due to Write in PCH0", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.WR_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Activate Count : Activate due to Write in PCH1", + "EventCode": "0x02", + "EventName": "UNC_MCHBM_ACT_COUNT.WR_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Activate commands sent on this channel. Activate commands are issued to open up a page on the HBM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0x20", + "Unit": "MCHBM" + }, + { + "BriefDescription": "All CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.ALL", + "PerPkg": "1", + "UMask": "0xff", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Pseudo Channel 0", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.PCH0", + "PerPkg": "1", + "PublicDescription": "HBM RD_CAS and WR_CAS Commands", + "UMask": "0x40", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Pseudo Channel 1", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.PCH1", + "PerPkg": "1", + "PublicDescription": "HBM RD_CAS and WR_CAS Commands", + "UMask": "0x80", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read CAS commands issued (regular and underfill)", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD", + "PerPkg": "1", + "UMask": "0xcf", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Regular read CAS commands with precharge", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD_PRE_REG", + "PerPkg": "1", + "UMask": "0xc2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Underfill read CAS commands with precharge", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD_PRE_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc8", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Regular read CAS commands issued (does not include underfills)", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD_REG", + "PerPkg": "1", + "UMask": "0xc1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Underfill read CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.RD_UNDERFILL", + "PerPkg": "1", + "UMask": "0xc4", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.WR", + "PerPkg": "1", + "UMask": "0xf0", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM RD_CAS and WR_CAS Commands. : HBM WR_CAS commands w/o auto-pre", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.WR_NONPRE", + "PerPkg": "1", + "UMask": "0xd0", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write CAS commands with precharge", + "EventCode": "0x05", + "EventName": "UNC_MCHBM_CAS_COUNT.WR_PRE", + "PerPkg": "1", + "UMask": "0xe0", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Pseudo Channel 0", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.PCH0", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Pseudo Channel 1", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.PCH1", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.RD_32B", + "PerPkg": "1", + "UMask": "0xc8", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read CAS Command in Regular Mode (64B) in Pseudochannel 0", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.RD_64B", + "PerPkg": "1", + "UMask": "0xc1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Underfill Read CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.RD_UFILL_32B", + "PerPkg": "1", + "UMask": "0xd0", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Underfill Read CAS Command in Regular Mode (64B) in Pseudochannel 1", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.RD_UFILL_64B", + "PerPkg": "1", + "UMask": "0xc2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.WR_32B", + "PerPkg": "1", + "UMask": "0xe0", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write CAS Command in Regular Mode (64B) in Pseudochannel 0", + "EventCode": "0x06", + "EventName": "UNC_MCHBM_CAS_ISSUED_REQ_LEN.WR_64B", + "PerPkg": "1", + "UMask": "0xc4", + "Unit": "MCHBM" + }, + { + "BriefDescription": "IMC Clockticks at DCLK frequency", + "EventCode": "0x01", + "EventName": "UNC_MCHBM_CLOCKTICKS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge All Commands", + "EventCode": "0x44", + "EventName": "UNC_MCHBM_HBM_PREALL.PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that the precharge all command was sent.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge All Commands", + "EventCode": "0x44", + "EventName": "UNC_MCHBM_HBM_PREALL.PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of times that the precharge all command was sent.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "All Precharge Commands", + "EventCode": "0x44", + "EventName": "UNC_MCHBM_HBM_PRE_ALL", + "PerPkg": "1", + "PublicDescription": "Precharge All Commands: Counts the number of times that the precharge all command was sent.", + "UMask": "0x3", + "Unit": "MCHBM" + }, + { + "BriefDescription": "IMC Clockticks at HCLK frequency", + "EventCode": "0x01", + "EventName": "UNC_MCHBM_HCLOCKTICKS", + "PerPkg": "1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "All precharge events", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0xff", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Precharge from MC page table", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.PGT", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x88", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands. : Precharges from Page Table", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.PGT_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel. : Equivalent to PAGE_EMPTY", + "UMask": "0x8", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.PGT_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x80", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Precharge due to read on page miss", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x11", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands. : Precharge due to read", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.RD_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel. : Precharge from read bank scheduler", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.RD_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x10", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.UFILL", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x44", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.UFILL_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x4", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.UFILL_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x40", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Precharge due to write on page miss", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x22", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands. : Precharge due to write", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.WR_PCH0", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel. : Precharge from write bank scheduler", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "HBM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_MCHBM_PRE_COUNT.WR_PCH1", + "PerPkg": "1", + "PublicDescription": "Counts the number of HBM Precharge commands sent on this channel.", + "UMask": "0x20", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Counts the number of cycles where the read buffer has greater than UMASK elements. NOTE: Umask must be set to the maximum number of elements in the queue (24 entries for SPR).", + "EventCode": "0x19", + "EventName": "UNC_MCHBM_RDB_FULL", + "PerPkg": "1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Counts the number of inserts into the read buffer.", + "EventCode": "0x17", + "EventName": "UNC_MCHBM_RDB_INSERTS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Data Buffer Inserts", + "EventCode": "0x17", + "EventName": "UNC_MCHBM_RDB_INSERTS.PCH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Data Buffer Inserts", + "EventCode": "0x17", + "EventName": "UNC_MCHBM_RDB_INSERTS.PCH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Counts the number of elements in the read buffer per cycle.", + "EventCode": "0x1a", + "EventName": "UNC_MCHBM_RDB_OCCUPANCY", + "PerPkg": "1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "EventCode": "0x10", + "EventName": "UNC_MCHBM_RPQ_INSERTS.PCH0", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Allocations: Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "EventCode": "0x10", + "EventName": "UNC_MCHBM_RPQ_INSERTS.PCH1", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Allocations: Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "EventCode": "0x80", + "EventName": "UNC_MCHBM_RPQ_OCCUPANCY_PCH0", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Occupancy: Accumulates the occupancies of the Read Pending Queue each cycle. This can then be used to calculate both the average occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "EventCode": "0x81", + "EventName": "UNC_MCHBM_RPQ_OCCUPANCY_PCH1", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Occupancy: Accumulates the occupancies of the Read Pending Queue each cycle. This can then be used to calculate both the average occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "EventCode": "0x20", + "EventName": "UNC_MCHBM_WPQ_INSERTS.PCH0", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Allocations: Counts the number of allocations into the Write Pending Queue. This can then be used to calculate the average queuing latency (in conjunction with the WPQ occupancy count). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate after being issued. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "EventCode": "0x20", + "EventName": "UNC_MCHBM_WPQ_INSERTS.PCH1", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Allocations: Counts the number of allocations into the Write Pending Queue. This can then be used to calculate the average queuing latency (in conjunction with the WPQ occupancy count). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate after being issued. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "EventCode": "0x82", + "EventName": "UNC_MCHBM_WPQ_OCCUPANCY_PCH0", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Occupancy: Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to memory. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "EventCode": "0x83", + "EventName": "UNC_MCHBM_WPQ_OCCUPANCY_PCH1", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Occupancy: Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to memory. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x23", + "EventName": "UNC_MCHBM_WPQ_READ_HIT", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x23", + "EventName": "UNC_MCHBM_WPQ_READ_HIT.PCH0", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue CAM Match: Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x23", + "EventName": "UNC_MCHBM_WPQ_READ_HIT.PCH1", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue CAM Match: Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x24", + "EventName": "UNC_MCHBM_WPQ_WRITE_HIT", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x24", + "EventName": "UNC_MCHBM_WPQ_WRITE_HIT.PCH0", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue CAM Match: Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "UMask": "0x1", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x24", + "EventName": "UNC_MCHBM_WPQ_WRITE_HIT.PCH1", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue CAM Match: Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "UMask": "0x2", + "Unit": "MCHBM" + }, + { + "BriefDescription": "Activate due to read, write, underfill, or bypass", + "EventCode": "0x02", + "EventName": "UNC_M_ACT_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "DRAM Activate Count : Counts the number of DRAM Activate commands sent on this channel. Activate commands are issued to open up a page on the DRAM devices so that it can be read or written to with a CAS. One can calculate the number of Page Misses by subtracting the number of Page Miss precharges from the number of Activates.", + "UMask": "0xff", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : All DRAM Read and Write actions : DRAM RD_CAS and WR_CAS Commands : Counts the total number of DRAM CAS commands issued on this channel.", + "UMask": "0xff", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 0", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.PCH0", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 0 : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 1", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.PCH1", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : Pseudo Channel 1 : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM read CAS commands issued (including underfills)", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands : Counts the total number of DRAM Read CAS commands issued on this channel. This includes underfills.", + "UMask": "0xcf", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_PRE_REG", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0xc2", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_PRE_UNDERFILL", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0xc8", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM read CAS commands issued (does not include underfills)", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_REG", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS commands w/out auto-pre : DRAM RD_CAS and WR_CAS Commands : Counts the total number or DRAM Read CAS commands issued on this channel. This includes both regular RD CAS commands as well as those with implicit Precharge. We do not filter based on major mode, as RD_CAS is not issued during WMM (with the exception of underfills).", + "UMask": "0xc1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM underfill read CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.RD_UNDERFILL", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : Underfill Read Issued : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0xc4", + "Unit": "iMC" + }, + { + "BriefDescription": "All DRAM write CAS commands issued", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands : Counts the total number of DRAM Write CAS commands issued on this channel.", + "UMask": "0xf0", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM WR_CAS commands w/o auto-pre", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.WR_NONPRE", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM WR_CAS commands w/o auto-pre : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0xd0", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM RD_CAS and WR_CAS Commands.", + "EventCode": "0x05", + "EventName": "UNC_M_CAS_COUNT.WR_PRE", + "PerPkg": "1", + "PublicDescription": "DRAM RD_CAS and WR_CAS Commands. : DRAM RD_CAS and WR_CAS Commands", + "UMask": "0xe0", + "Unit": "iMC" + }, + { + "BriefDescription": "Pseudo Channel 0", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.PCH0", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "Pseudo Channel 1", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.PCH1", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "Read CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.RD_32B", + "PerPkg": "1", + "UMask": "0xc8", + "Unit": "iMC" + }, + { + "BriefDescription": "Read CAS Command in Regular Mode (64B) in Pseudochannel 0", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.RD_64B", + "PerPkg": "1", + "UMask": "0xc1", + "Unit": "iMC" + }, + { + "BriefDescription": "Underfill Read CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.RD_UFILL_32B", + "PerPkg": "1", + "UMask": "0xd0", + "Unit": "iMC" + }, + { + "BriefDescription": "Underfill Read CAS Command in Regular Mode (64B) in Pseudochannel 1", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.RD_UFILL_64B", + "PerPkg": "1", + "UMask": "0xc2", + "Unit": "iMC" + }, + { + "BriefDescription": "Write CAS Command in Interleaved Mode (32B)", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.WR_32B", + "PerPkg": "1", + "UMask": "0xe0", + "Unit": "iMC" + }, + { + "BriefDescription": "Write CAS Command in Regular Mode (64B) in Pseudochannel 0", + "EventCode": "0x06", + "EventName": "UNC_M_CAS_ISSUED_REQ_LEN.WR_64B", + "PerPkg": "1", + "UMask": "0xc4", + "Unit": "iMC" + }, + { + "BriefDescription": "IMC Clockticks at DCLK frequency", + "EventCode": "0x01", + "EventName": "UNC_M_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of DRAM DCLK clock cycles while the event is enabled", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge All Commands", + "EventCode": "0x44", + "EventName": "UNC_M_DRAM_PRE_ALL", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge All Commands : Counts the number of times that the precharge all command was sent.", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "IMC Clockticks at HCLK frequency", + "EventCode": "0x01", + "EventName": "UNC_M_HCLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of DRAM HCLK clock cycles while the event is enabled", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_PCLS.RD", + "EventCode": "0xa0", + "EventName": "UNC_M_PCLS.RD", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_PCLS.TOTAL", + "EventCode": "0xa0", + "EventName": "UNC_M_PCLS.TOTAL", + "PerPkg": "1", + "UMask": "0xf", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_PCLS.WR", + "EventCode": "0xa0", + "EventName": "UNC_M_PCLS.WR", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue inserts", + "EventCode": "0xe3", + "EventName": "UNC_M_PMM_RPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts number of read requests allocated in the PMM Read Pending Queue.", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue occupancy", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.ALL_SCH0", + "PerPkg": "1", + "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue occupancy", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.ALL_SCH1", + "PerPkg": "1", + "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "EventCode": "0xE0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.GNT_WAIT_SCH0", + "PerPkg": "1", + "PublicDescription": "PMM Read Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "EventCode": "0xE0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.GNT_WAIT_SCH1", + "PerPkg": "1", + "PublicDescription": "PMM Read Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.NO_GNT_SCH0", + "PerPkg": "1", + "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Read Pending Queue Occupancy", + "EventCode": "0xe0", + "EventName": "UNC_M_PMM_RPQ_OCCUPANCY.NO_GNT_SCH1", + "PerPkg": "1", + "PublicDescription": "Accumulates the per cycle occupancy of the PMM Read Pending Queue.", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM (for IXP) Write Queue Cycles Not Empty", + "EventCode": "0xe5", + "EventName": "UNC_M_PMM_WPQ_CYCLES_NE", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue inserts", + "EventCode": "0xe7", + "EventName": "UNC_M_PMM_WPQ_INSERTS", + "PerPkg": "1", + "PublicDescription": "Counts number of write requests allocated in the PMM Write Pending Queue.", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue Occupancy", + "EventCode": "0xe4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL", + "PerPkg": "1", + "PublicDescription": "PMM Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the Write Pending Queue to the PMM DIMM.", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue Occupancy", + "EventCode": "0xE4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL_SCH0", + "PerPkg": "1", + "PublicDescription": "PMM Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Write Pending Queue.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM Write Pending Queue Occupancy", + "EventCode": "0xE4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.ALL_SCH1", + "PerPkg": "1", + "PublicDescription": "PMM Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the PMM Write Pending Queue.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM (for IXP) Write Pending Queue Occupancy", + "EventCode": "0xe4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.CAS", + "PerPkg": "1", + "PublicDescription": "PMM (for IXP) Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the Write Pending Queue to the IXP DIMM.", + "UMask": "0xc", + "Unit": "iMC" + }, + { + "BriefDescription": "PMM (for IXP) Write Pending Queue Occupancy", + "EventCode": "0xe4", + "EventName": "UNC_M_PMM_WPQ_OCCUPANCY.PWR", + "PerPkg": "1", + "PublicDescription": "PMM (for IXP) Write Pending Queue Occupancy : Accumulates the per cycle occupancy of the Write Pending Queue to the IXP DIMM.", + "UMask": "0x30", + "Unit": "iMC" + }, + { + "BriefDescription": "Channel PPD Cycles", + "EventCode": "0x85", + "EventName": "UNC_M_POWER_CHANNEL_PPD", + "PerPkg": "1", + "PublicDescription": "Channel PPD Cycles : Number of cycles when all the ranks in the channel are in PPD mode. If IBT=off is enabled, then this can be used to count those cycles. If it is not enabled, then this can count the number of cycles when that could have been taken advantage of.", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", + "EventCode": "0x47", + "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_0", + "PerPkg": "1", + "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", + "EventCode": "0x47", + "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_1", + "PerPkg": "1", + "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", + "EventCode": "0x47", + "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_2", + "PerPkg": "1", + "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "CKE_ON_CYCLES by Rank : DIMM ID", + "EventCode": "0x47", + "EventName": "UNC_M_POWER_CKE_CYCLES.LOW_3", + "PerPkg": "1", + "PublicDescription": "CKE_ON_CYCLES by Rank : DIMM ID : Number of cycles spent in CKE ON mode. The filter allows you to select a rank to monitor. If multiple ranks are in CKE ON mode at one time, the counter will ONLY increment by one rather than doing accumulation. Multiple counters will need to be used to track multiple ranks simultaneously. There is no distinction between the different CKE modes (APD, PPDS, PPDF). This can be determined based on the system programming. These events should commonly be used with Invert to get the number of cycles in power saving mode. Edge Detect is also useful here. Make sure that you do NOT use Invert with Edge Detect (this just confuses the system and is not necessary).", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRIT_THROTTLE_CYCLES.SLOT0", + "PerPkg": "1", + "PublicDescription": "Throttle Cycles for Rank 0 : Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1. : Thermal throttling is performed per DIMM. We support 3 DIMMs per channel. This ID allows us to filter by ID.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Throttle Cycles for Rank 0", + "EventCode": "0x86", + "EventName": "UNC_M_POWER_CRIT_THROTTLE_CYCLES.SLOT1", + "PerPkg": "1", + "PublicDescription": "Throttle Cycles for Rank 0 : Counts the number of cycles while the iMC is being throttled by either thermal constraints or by the PCU throttling. It is not possible to distinguish between the two. This can be filtered by rank. If multiple ranks are selected and are being throttled at the same time, the counter will only increment by 1.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Clock-Enabled Self-Refresh", + "EventCode": "0x43", + "EventName": "UNC_M_POWER_SELF_REFRESH", + "PerPkg": "1", + "PublicDescription": "Clock-Enabled Self-Refresh : Counts the number of cycles when the iMC is in self-refresh and the iMC still has a clock. This happens in some package C-states. For example, the PCU may ask the iMC to enter self-refresh even though some of the cores are still processing. One use of this is for Monroe technology. Self-refresh is required during package C3 and C6, but there is no clock in the iMC at this time, so it is not possible to count these cases.", + "Unit": "iMC" + }, + { + "BriefDescription": "Precharge due to read, write, underfill, or PGT.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.ALL", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0xff", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.PGT", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x88", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharges from Page Table", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.PGT_PCH0", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Precharges from Page Table : Counts the number of DRAM Precharge commands sent on this channel. : Equivalent to PAGE_EMPTY", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.PGT_PCH1", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "Precharge due to read on page miss", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.RD", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x11", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharge due to read", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.RD_PCH0", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Precharge due to read : Counts the number of DRAM Precharge commands sent on this channel. : Precharge from read bank scheduler", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.RD_PCH1", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.UFILL", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x44", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.UFILL_PCH0", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.UFILL_PCH1", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "Precharge due to write on page miss", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.WR", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x22", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands. : Precharge due to write", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.WR_PCH0", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Precharge due to write : Counts the number of DRAM Precharge commands sent on this channel. : Precharge from write bank scheduler", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "DRAM Precharge commands.", + "EventCode": "0x03", + "EventName": "UNC_M_PRE_COUNT.WR_PCH1", + "PerPkg": "1", + "PublicDescription": "DRAM Precharge commands. : Counts the number of DRAM Precharge commands sent on this channel.", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Counts the number of cycles where the read buffer has greater than UMASK elements. This includes reads to both DDR and PMEM. NOTE: Umask must be set to the maximum number of elements in the queue (24 entries for SPR).", + "EventCode": "0x19", + "EventName": "UNC_M_RDB_FULL", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Counts the number of inserts into the read buffer destined for DDR. Does not count reads destined for PMEM.", + "EventCode": "0x17", + "EventName": "UNC_M_RDB_INSERTS", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Data Buffer Inserts", + "EventCode": "0x17", + "EventName": "UNC_M_RDB_INSERTS.PCH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Data Buffer Inserts", + "EventCode": "0x17", + "EventName": "UNC_M_RDB_INSERTS.PCH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Counts the number of cycles where there's at least one element in the read buffer. This includes reads to both DDR and PMEM.", + "EventCode": "0x18", + "EventName": "UNC_M_RDB_NE", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Data Buffer Not Empty", + "EventCode": "0x18", + "EventName": "UNC_M_RDB_NE.PCH0", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Data Buffer Not Empty", + "EventCode": "0x18", + "EventName": "UNC_M_RDB_NE.PCH1", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Counts the number of cycles where there's at least one element in the read buffer. This includes reads to both DDR and PMEM.", + "EventCode": "0x18", + "EventName": "UNC_M_RDB_NOT_EMPTY", + "PerPkg": "1", + "UMask": "0x3", + "Unit": "iMC" + }, + { + "BriefDescription": "Counts the number of elements in the read buffer, including reads to both DDR and PMEM.", + "EventCode": "0x1a", + "EventName": "UNC_M_RDB_OCCUPANCY", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "EventCode": "0x10", + "EventName": "UNC_M_RPQ_INSERTS.PCH0", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Allocations : Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Allocations", + "EventCode": "0x10", + "EventName": "UNC_M_RPQ_INSERTS.PCH1", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Allocations : Counts the number of allocations into the Read Pending Queue. This queue is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory. This includes both ISOCH and non-ISOCH requests.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "EventCode": "0x80", + "EventName": "UNC_M_RPQ_OCCUPANCY_PCH0", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Occupancy : Accumulates the occupancies of the Read Pending Queue each cycle. This can then be used to calculate both the average occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory.", + "Unit": "iMC" + }, + { + "BriefDescription": "Read Pending Queue Occupancy", + "EventCode": "0x81", + "EventName": "UNC_M_RPQ_OCCUPANCY_PCH1", + "PerPkg": "1", + "PublicDescription": "Read Pending Queue Occupancy : Accumulates the occupancies of the Read Pending Queue each cycle. This can then be used to calculate both the average occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The RPQ is used to schedule reads out to the memory controller and to track the requests. Requests allocate into the RPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after the CAS command has been issued to memory.", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard accepts", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.ACCEPTS", + "PerPkg": "1", + "UMask": "0x5", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : Write Accepts", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.FM_RD_CMPS", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : Write Rejects", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.FM_WR_CMPS", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : FM read completions", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.NM_RD_CMPS", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : FM write completions", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.NM_WR_CMPS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : Read Accepts", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.RD_ACCEPTS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : Read Rejects", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.RD_REJECTS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard rejects", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.REJECTS", + "PerPkg": "1", + "UMask": "0xa", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : NM read completions", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.WR_ACCEPTS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Accesses : NM write completions", + "EventCode": "0xd2", + "EventName": "UNC_M_SB_ACCESSES.WR_REJECTS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": ": Alloc", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.ALLOC", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": ": Dealloc", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.DEALLOC", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Write Starved", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.FM_RD_STARVED", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Write Starved", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.FM_TGR_WR_STARVED", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Read Starved", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.FM_WR_STARVED", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": ": Valid", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.NM_RD_STARVED", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Read Starved", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.NM_WR_STARVED", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": ": Reject", + "EventCode": "0xd9", + "EventName": "UNC_M_SB_CANARY.VLD", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Cycles Full", + "EventCode": "0xd1", + "EventName": "UNC_M_SB_CYCLES_FULL", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Cycles Not-Empty", + "EventCode": "0xd0", + "EventName": "UNC_M_SB_CYCLES_NE", + "PerPkg": "1", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Inserts : Block region reads", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.BLOCK_RDS", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Inserts : Block region writes", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.BLOCK_WRS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Inserts : Persistent Mem reads", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.PMM_RDS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Inserts : Persistent Mem writes", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.PMM_WRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Inserts : Reads", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.RDS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Inserts : Writes", + "EventCode": "0xd6", + "EventName": "UNC_M_SB_INSERTS.WRS", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Occupancy : Block region reads", + "EventCode": "0xd5", + "EventName": "UNC_M_SB_OCCUPANCY.BLOCK_RDS", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Occupancy : Block region writes", + "EventCode": "0xd5", + "EventName": "UNC_M_SB_OCCUPANCY.BLOCK_WRS", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Occupancy : Persistent Mem reads", + "EventCode": "0xd5", + "EventName": "UNC_M_SB_OCCUPANCY.PMM_RDS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Occupancy : Persistent Mem writes", + "EventCode": "0xd5", + "EventName": "UNC_M_SB_OCCUPANCY.PMM_WRS", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Occupancy : Reads", + "EventCode": "0xd5", + "EventName": "UNC_M_SB_OCCUPANCY.RDS", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Prefetch Inserts : All", + "EventCode": "0xda", + "EventName": "UNC_M_SB_PREF_INSERTS.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Prefetch Inserts : DDR4", + "EventCode": "0xda", + "EventName": "UNC_M_SB_PREF_INSERTS.DDR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Prefetch Inserts : PMM", + "EventCode": "0xda", + "EventName": "UNC_M_SB_PREF_INSERTS.PMM", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Prefetch Occupancy : All", + "EventCode": "0xdb", + "EventName": "UNC_M_SB_PREF_OCCUPANCY.ALL", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Prefetch Occupancy : DDR4", + "EventCode": "0xdb", + "EventName": "UNC_M_SB_PREF_OCCUPANCY.DDR", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Scoreboard Prefetch Occupancy : Persistent Mem", + "EventCode": "0xDB", + "EventName": "UNC_M_SB_PREF_OCCUPANCY.PMM", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of Scoreboard Requests Rejected", + "EventCode": "0xd4", + "EventName": "UNC_M_SB_REJECT.CANARY", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of Scoreboard Requests Rejected", + "EventCode": "0xd4", + "EventName": "UNC_M_SB_REJECT.DDR_EARLY_CMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of Scoreboard Requests Rejected : FM requests rejected due to full address conflict", + "EventCode": "0xd4", + "EventName": "UNC_M_SB_REJECT.FM_ADDR_CNFLT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of Scoreboard Requests Rejected : NM requests rejected due to set conflict", + "EventCode": "0xd4", + "EventName": "UNC_M_SB_REJECT.NM_SET_CNFLT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Number of Scoreboard Requests Rejected : Patrol requests rejected due to set conflict", + "EventCode": "0xd4", + "EventName": "UNC_M_SB_REJECT.PATROL_SET_CNFLT", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Read - Set", + "EventCode": "0xd7", + "EventName": "UNC_M_SB_STRV_ALLOC.FM_RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Read - Clear", + "EventCode": "0xd7", + "EventName": "UNC_M_SB_STRV_ALLOC.FM_TGR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Write - Set", + "EventCode": "0xd7", + "EventName": "UNC_M_SB_STRV_ALLOC.FM_WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Read - Set", + "EventCode": "0xd7", + "EventName": "UNC_M_SB_STRV_ALLOC.NM_RD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Write - Set", + "EventCode": "0xd7", + "EventName": "UNC_M_SB_STRV_ALLOC.NM_WR", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Read - Set", + "EventCode": "0xde", + "EventName": "UNC_M_SB_STRV_DEALLOC.FM_RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Read - Clear", + "EventCode": "0xde", + "EventName": "UNC_M_SB_STRV_DEALLOC.FM_TGR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Write - Set", + "EventCode": "0xde", + "EventName": "UNC_M_SB_STRV_DEALLOC.FM_WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Read - Set", + "EventCode": "0xde", + "EventName": "UNC_M_SB_STRV_DEALLOC.NM_RD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Write - Set", + "EventCode": "0xde", + "EventName": "UNC_M_SB_STRV_DEALLOC.NM_WR", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Read", + "EventCode": "0xd8", + "EventName": "UNC_M_SB_STRV_OCC.FM_RD", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Read - Clear", + "EventCode": "0xd8", + "EventName": "UNC_M_SB_STRV_OCC.FM_TGR", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": ": Far Mem Write", + "EventCode": "0xd8", + "EventName": "UNC_M_SB_STRV_OCC.FM_WR", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Read", + "EventCode": "0xd8", + "EventName": "UNC_M_SB_STRV_OCC.NM_RD", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": ": Near Mem Write", + "EventCode": "0xd8", + "EventName": "UNC_M_SB_STRV_OCC.NM_WR", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_SB_TAGGED.DDR4_CMP", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.DDR4_CMP", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_SB_TAGGED.NEW", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.NEW", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_SB_TAGGED.OCC", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.OCC", + "PerPkg": "1", + "UMask": "0x80", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_SB_TAGGED.PMM0_CMP", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.PMM0_CMP", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_SB_TAGGED.PMM1_CMP", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.PMM1_CMP", + "PerPkg": "1", + "UMask": "0x20", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_SB_TAGGED.PMM2_CMP", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.PMM2_CMP", + "PerPkg": "1", + "UMask": "0x40", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_SB_TAGGED.RD_HIT", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.RD_HIT", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "UNC_M_SB_TAGGED.RD_MISS", + "EventCode": "0xdd", + "EventName": "UNC_M_SB_TAGGED.RD_MISS", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "2LM Tag check hit in near memory cache (DDR4)", + "EventCode": "0xd3", + "EventName": "UNC_M_TAGCHK.HIT", + "PerPkg": "1", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "2LM Tag check miss, no data at this line", + "EventCode": "0xd3", + "EventName": "UNC_M_TAGCHK.MISS_CLEAN", + "PerPkg": "1", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "2LM Tag check miss, existing data may be evicted to PMM", + "EventCode": "0xd3", + "EventName": "UNC_M_TAGCHK.MISS_DIRTY", + "PerPkg": "1", + "UMask": "0x4", + "Unit": "iMC" + }, + { + "BriefDescription": "2LM Tag check hit due to memory read", + "EventCode": "0xd3", + "EventName": "UNC_M_TAGCHK.NM_RD_HIT", + "PerPkg": "1", + "UMask": "0x8", + "Unit": "iMC" + }, + { + "BriefDescription": "2LM Tag check hit due to memory write", + "EventCode": "0xd3", + "EventName": "UNC_M_TAGCHK.NM_WR_HIT", + "PerPkg": "1", + "UMask": "0x10", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "EventCode": "0x20", + "EventName": "UNC_M_WPQ_INSERTS.PCH0", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Allocations : Counts the number of allocations into the Write Pending Queue. This can then be used to calculate the average queuing latency (in conjunction with the WPQ occupancy count). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC.", + "UMask": "0x1", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Allocations", + "EventCode": "0x20", + "EventName": "UNC_M_WPQ_INSERTS.PCH1", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Allocations : Counts the number of allocations into the Write Pending Queue. This can then be used to calculate the average queuing latency (in conjunction with the WPQ occupancy count). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the CHA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC.", + "UMask": "0x2", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "EventCode": "0x82", + "EventName": "UNC_M_WPQ_OCCUPANCY_PCH0", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Occupancy : Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue Occupancy", + "EventCode": "0x83", + "EventName": "UNC_M_WPQ_OCCUPANCY_PCH1", + "PerPkg": "1", + "PublicDescription": "Write Pending Queue Occupancy : Accumulates the occupancies of the Write Pending Queue each cycle. This can then be used to calculate both the average queue occupancy (in conjunction with the number of cycles not empty) and the average latency (in conjunction with the number of allocations). The WPQ is used to schedule write out to the memory controller and to track the writes. Requests allocate into the WPQ soon after they enter the memory controller, and need credits for an entry in this buffer before being sent from the HA to the iMC. They deallocate after being issued to DRAM. Write requests themselves are able to complete (from the perspective of the rest of the system) as soon they have posted to the iMC. This is not to be confused with actually performing the write to DRAM. Therefore, the average latency for this queue is actually not useful for deconstruction intermediate write latencies. So, we provide filtering based on if the request has posted or not. By using the not posted filter, we can track how long writes spent in the iMC before completions were sent to the HA. The posted filter, on the other hand, provides information about how much queueing is actually happening in the iMC for writes before they are actually issued to memory. High average occupancies will generally coincide with high write major mode counts.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x23", + "EventName": "UNC_M_WPQ_READ_HIT", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "Unit": "iMC" + }, + { + "BriefDescription": "Write Pending Queue CAM Match", + "EventCode": "0x24", + "EventName": "UNC_M_WPQ_WRITE_HIT", + "FCMask": "0x00000000", + "PerPkg": "1", + "PortMask": "0x00000000", + "PublicDescription": "Counts the number of times a request hits in the WPQ (write-pending queue). The iMC allows writes and reads to pass up other writes to different addresses. Before a read or a write is issued, it will first CAM the WPQ to see if there is a write pending to that address. When reads hit, they are able to directly pull their data from the WPQ instead of going to memory. Writes that hit will overwrite the existing data. Partial writes that hit will not need to do underfill reads and will simply update their relevant sections.", + "Unit": "iMC" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-power.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-power.json new file mode 100644 index 000000000000..8948e85074f0 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-power.json @@ -0,0 +1,197 @@ +[ + { + "BriefDescription": "PCU PCLK Clockticks", + "EventCode": "0x01", + "EventName": "UNC_P_CLOCKTICKS", + "PerPkg": "1", + "PublicDescription": "Number of PCU PCLK Clock cycles while the event is enabled", + "Unit": "PCU" + }, + { + "BriefDescription": "UNC_P_CORE_TRANSITION_CYCLES", + "EventCode": "0x60", + "EventName": "UNC_P_CORE_TRANSITION_CYCLES", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "UNC_P_DEMOTIONS", + "EventCode": "0x30", + "EventName": "UNC_P_DEMOTIONS", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Phase Shed 0 Cycles", + "EventCode": "0x75", + "EventName": "UNC_P_FIVR_PS_PS0_CYCLES", + "PerPkg": "1", + "PublicDescription": "Phase Shed 0 Cycles : Cycles spent in phase-shedding power state 0", + "Unit": "PCU" + }, + { + "BriefDescription": "Phase Shed 1 Cycles", + "EventCode": "0x76", + "EventName": "UNC_P_FIVR_PS_PS1_CYCLES", + "PerPkg": "1", + "PublicDescription": "Phase Shed 1 Cycles : Cycles spent in phase-shedding power state 1", + "Unit": "PCU" + }, + { + "BriefDescription": "Phase Shed 2 Cycles", + "EventCode": "0x77", + "EventName": "UNC_P_FIVR_PS_PS2_CYCLES", + "PerPkg": "1", + "PublicDescription": "Phase Shed 2 Cycles : Cycles spent in phase-shedding power state 2", + "Unit": "PCU" + }, + { + "BriefDescription": "Phase Shed 3 Cycles", + "EventCode": "0x78", + "EventName": "UNC_P_FIVR_PS_PS3_CYCLES", + "PerPkg": "1", + "PublicDescription": "Phase Shed 3 Cycles : Cycles spent in phase-shedding power state 3", + "Unit": "PCU" + }, + { + "BriefDescription": "AVX256 Frequency Clipping", + "EventCode": "0x49", + "EventName": "UNC_P_FREQ_CLIP_AVX256", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "AVX512 Frequency Clipping", + "EventCode": "0x4a", + "EventName": "UNC_P_FREQ_CLIP_AVX512", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Thermal Strongest Upper Limit Cycles", + "EventCode": "0x04", + "EventName": "UNC_P_FREQ_MAX_LIMIT_THERMAL_CYCLES", + "PerPkg": "1", + "PublicDescription": "Thermal Strongest Upper Limit Cycles : Number of cycles any frequency is reduced due to a thermal limit. Count only if throttling is occurring.", + "Unit": "PCU" + }, + { + "BriefDescription": "Power Strongest Upper Limit Cycles", + "EventCode": "0x05", + "EventName": "UNC_P_FREQ_MAX_POWER_CYCLES", + "PerPkg": "1", + "PublicDescription": "Power Strongest Upper Limit Cycles : Counts the number of cycles when power is the upper limit on frequency.", + "Unit": "PCU" + }, + { + "BriefDescription": "IO P Limit Strongest Lower Limit Cycles", + "EventCode": "0x73", + "EventName": "UNC_P_FREQ_MIN_IO_P_CYCLES", + "PerPkg": "1", + "PublicDescription": "IO P Limit Strongest Lower Limit Cycles : Counts the number of cycles when IO P Limit is preventing us from dropping the frequency lower. This algorithm monitors the needs to the IO subsystem on both local and remote sockets and will maintain a frequency high enough to maintain good IO BW. This is necessary for when all the IA cores on a socket are idle but a user still would like to maintain high IO Bandwidth.", + "Unit": "PCU" + }, + { + "BriefDescription": "Cycles spent changing Frequency", + "EventCode": "0x74", + "EventName": "UNC_P_FREQ_TRANS_CYCLES", + "PerPkg": "1", + "PublicDescription": "Cycles spent changing Frequency : Counts the number of cycles when the system is changing frequency. This can not be filtered by thread ID. One can also use it with the occupancy counter that monitors number of threads in C0 to estimate the performance impact that frequency transitions had on the system.", + "Unit": "PCU" + }, + { + "BriefDescription": "Memory Phase Shedding Cycles", + "EventCode": "0x2f", + "EventName": "UNC_P_MEMORY_PHASE_SHEDDING_CYCLES", + "PerPkg": "1", + "PublicDescription": "Memory Phase Shedding Cycles : Counts the number of cycles that the PCU has triggered memory phase shedding. This is a mode that can be run in the iMC physicals that saves power at the expense of additional latency.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C0", + "EventCode": "0x2a", + "EventName": "UNC_P_PKG_RESIDENCY_C0_CYCLES", + "PerPkg": "1", + "PublicDescription": "Package C State Residency - C0 : Counts the number of cycles when the package was in C0. This event can be used in conjunction with edge detect to count C0 entrances (or exits using invert). Residency events do not include transition times.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C2E", + "EventCode": "0x2b", + "EventName": "UNC_P_PKG_RESIDENCY_C2E_CYCLES", + "PerPkg": "1", + "PublicDescription": "Package C State Residency - C2E : Counts the number of cycles when the package was in C2E. This event can be used in conjunction with edge detect to count C2E entrances (or exits using invert). Residency events do not include transition times.", + "Unit": "PCU" + }, + { + "BriefDescription": "Package C State Residency - C6", + "EventCode": "0x2d", + "EventName": "UNC_P_PKG_RESIDENCY_C6_CYCLES", + "PerPkg": "1", + "PublicDescription": "Package C State Residency - C6 : Counts the number of cycles when the package was in C6. This event can be used in conjunction with edge detect to count C6 entrances (or exits using invert). Residency events do not include transition times.", + "Unit": "PCU" + }, + { + "BriefDescription": "UNC_P_PMAX_THROTTLED_CYCLES", + "EventCode": "0x06", + "EventName": "UNC_P_PMAX_THROTTLED_CYCLES", + "PerPkg": "1", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C0", + "EventCode": "0x35", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C0", + "PerPkg": "1", + "PublicDescription": "Number of cores in C0 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C3", + "EventCode": "0x36", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C3", + "PerPkg": "1", + "PublicDescription": "Number of cores in C3 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "Number of cores in C6", + "EventCode": "0x37", + "EventName": "UNC_P_POWER_STATE_OCCUPANCY_CORES_C6", + "PerPkg": "1", + "PublicDescription": "Number of cores in C6 : This is an occupancy event that tracks the number of cores that are in the chosen C-State. It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.", + "Unit": "PCU" + }, + { + "BriefDescription": "External Prochot", + "EventCode": "0x0a", + "EventName": "UNC_P_PROCHOT_EXTERNAL_CYCLES", + "PerPkg": "1", + "PublicDescription": "External Prochot : Counts the number of cycles that we are in external PROCHOT mode. This mode is triggered when a sensor off the die determines that something off-die (like DRAM) is too hot and must throttle to avoid damaging the chip.", + "Unit": "PCU" + }, + { + "BriefDescription": "Internal Prochot", + "EventCode": "0x09", + "EventName": "UNC_P_PROCHOT_INTERNAL_CYCLES", + "PerPkg": "1", + "PublicDescription": "Internal Prochot : Counts the number of cycles that we are in Internal PROCHOT mode. This mode is triggered when a sensor on the die determines that we are too hot and must throttle to avoid damaging the chip.", + "Unit": "PCU" + }, + { + "BriefDescription": "Total Core C State Transition Cycles", + "EventCode": "0x72", + "EventName": "UNC_P_TOTAL_TRANSITION_CYCLES", + "PerPkg": "1", + "PublicDescription": "Total Core C State Transition Cycles : Number of cycles spent performing core C state transitions across all cores.", + "Unit": "PCU" + }, + { + "BriefDescription": "VR Hot", + "EventCode": "0x42", + "EventName": "UNC_P_VR_HOT_CYCLES", + "PerPkg": "1", + "PublicDescription": "VR Hot : Number of cycles that a CPU SVID VR is hot. Does not cover DRAM VRs", + "Unit": "PCU" + } +] diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json new file mode 100644 index 000000000000..a1e3b8d2ebe7 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/virtual-memory.json @@ -0,0 +1,165 @@ +[ + { + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a demand load.", + "CounterMask": "1", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a demand load.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 1G page.", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 2M/4M page.", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Page walks completed due to a demand data load to a 4K page.", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data loads. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of page walks outstanding for a demand load in the PMH each cycle.", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for a demand load in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Stores that miss the DTLB and hit the STLB.", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.STLB_HIT", + "PublicDescription": "Counts stores that miss the DTLB (Data TLB) and hit the STLB (2nd Level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store.", + "CounterMask": "1", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a store.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 1G page.", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x8" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 2M/4M page.", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Page walks completed due to a demand data store to a 4K page.", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K sizes) caused by demand data stores. This implies address translations missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of page walks outstanding for a store in the PMH each cycle.", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for a store in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.STLB_HIT", + "PublicDescription": "Counts instruction fetch requests that miss the ITLB (Instruction TLB) and hit the STLB (Second-level TLB).", + "SampleAfterValue": "100003", + "UMask": "0x20" + }, + { + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request.", + "CounterMask": "1", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "PublicDescription": "Counts cycles when at least one PMH (Page Miss Handler) is busy with a page walk for a code (instruction fetch) request.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", + "PublicDescription": "Counts completed page walks (2M/4M page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", + "PublicDescription": "Counts completed page walks (4K page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of page walks outstanding for an outstanding code request in the PMH each cycle.", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts the number of page walks outstanding for an outstanding code (instruction fetch) request in the PMH (Page Miss Handler) each cycle.", + "SampleAfterValue": "100003", + "UMask": "0x10" + } +] diff --git a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json index 954e8198c7a5..bef1f5ef6f31 100644 --- a/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/haswellx/uncore-interconnect.json @@ -271,7 +271,7 @@ "EventCode": "0x4", "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -279,7 +279,7 @@ "EventCode": "0x1", "EventName": "UNC_I_RxR_BL_DRS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -287,7 +287,7 @@ "EventCode": "0x7", "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -295,7 +295,7 @@ "EventCode": "0x5", "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -303,7 +303,7 @@ "EventCode": "0x2", "EventName": "UNC_I_RxR_BL_NCB_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -311,7 +311,7 @@ "EventCode": "0x8", "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -319,7 +319,7 @@ "EventCode": "0x6", "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -327,7 +327,7 @@ "EventCode": "0x3", "EventName": "UNC_I_RxR_BL_NCS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -335,7 +335,7 @@ "EventCode": "0x9", "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json index a6eed0d9a26d..b43a6c6d8b7f 100644 --- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json @@ -1525,7 +1525,7 @@ }, { "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", - "MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)", + "MetricExpr": "(cycles\\-t / el\\-start if has_event(el\\-start) else 0)", "MetricGroup": "transaction", "MetricName": "tsx_cycles_per_elision", "ScaleUnit": "1cycles / elision" diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json index 7082ad5ba961..e98602c66707 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json @@ -1821,7 +1821,7 @@ }, { "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", - "MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)", + "MetricExpr": "(cycles\\-t / el\\-start if has_event(el\\-start) else 0)", "MetricGroup": "transaction", "MetricName": "tsx_cycles_per_elision", "ScaleUnit": "1cycles / elision" diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json index 6ddc7d1c61d5..46570b522095 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json @@ -8,16 +8,16 @@ "UMask": "0x1" }, { - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "PublicDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", "SampleAfterValue": "2000003", "UMask": "0x2" }, { - "BriefDescription": "L1D miss oustandings duration in cycles", + "BriefDescription": "L1D miss outstanding duration in cycles", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.PENDING", "PublicDescription": "Increments the number of outstanding L1D misses every cycle. Set Cmask = 1 and Edge =1 to count occurrences.", @@ -506,7 +506,7 @@ "UMask": "0x8" }, { - "BriefDescription": "Cacheable and noncachaeble code read requests", + "BriefDescription": "Cacheable and noncacheable code read requests", "EventCode": "0xB0", "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", "PublicDescription": "Demand code read requests sent to uncore.", diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json b/tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json index 87c958213c7a..89c6d47cc077 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json @@ -73,7 +73,7 @@ "UMask": "0x20" }, { - "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULsand IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s", + "BriefDescription": "Number of FP Computational Uops Executed this cycle. The number of FADD, FSUB, FCOM, FMULs, integer MULs and IMULs, FDIVs, FPREMs, FSQRTS, integer DIVs, and IDIVs. This event does not distinguish an FADD used in the middle of a transcendental flow from a s", "EventCode": "0x10", "EventName": "FP_COMP_OPS_EXE.X87", "PublicDescription": "Counts number of X87 uops executed.", diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json b/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json index 89004a6c9ed1..4ee100024ca9 100644 --- a/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json +++ b/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json @@ -142,35 +142,35 @@ "UMask": "0x4" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_CYCLES", - "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "PublicDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "SampleAfterValue": "2000003", "UMask": "0x30" }, { - "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_CYCLES", - "PublicDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy.", + "PublicDescription": "Cycles when uops initiated by Decode Stream Buffer (DSB) are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy.", "SampleAfterValue": "2000003", "UMask": "0x10" }, { - "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy", "CounterMask": "1", "EdgeDetect": "1", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_OCCUR", - "PublicDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequenser (MS) is busy.", + "PublicDescription": "Deliveries to Instruction Decode Queue (IDQ) initiated by Decode Stream Buffer (DSB) while Microcode Sequencer (MS) is busy.", "SampleAfterValue": "2000003", "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by Decode Stream Buffer (DSB) that are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_DSB_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by DSB. Set Cmask = 1 to count cycles. Add Edge=1 to count # of delivery.", @@ -178,7 +178,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_MITE_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ when MS_busy by MITE. Set Cmask = 1 to count cycles.", @@ -196,7 +196,7 @@ "UMask": "0x30" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequencer (MS) is busy", "EventCode": "0x79", "EventName": "IDQ.MS_UOPS", "PublicDescription": "Increment each cycle # of uops delivered to IDQ from MS by either DSB or MITE. Set Cmask = 1 to count cycles.", diff --git a/tools/perf/pmu-events/arch/x86/ivytown/cache.json b/tools/perf/pmu-events/arch/x86/ivytown/cache.json index c8f7d5e66504..0e8e77253978 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/cache.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/cache.json @@ -8,11 +8,11 @@ "UMask": "0x1" }, { - "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability", + "BriefDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability", "CounterMask": "1", "EventCode": "0x48", "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Cycles a demand request was blocked due to Fill Buffers inavailability.", + "PublicDescription": "Cycles a demand request was blocked due to Fill Buffers unavailability.", "SampleAfterValue": "2000003", "UMask": "0x2" }, diff --git a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json index ccf451534d16..914d2cfb3d3d 100644 --- a/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/ivytown/uncore-interconnect.json @@ -140,7 +140,7 @@ "EventCode": "0x4", "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -148,21 +148,21 @@ "EventCode": "0x1", "EventName": "UNC_I_RxR_BL_DRS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { "EventCode": "0x7", "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { "EventCode": "0x5", "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -170,21 +170,21 @@ "EventCode": "0x2", "EventName": "UNC_I_RxR_BL_NCB_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { "EventCode": "0x8", "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { "EventCode": "0x6", "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -192,14 +192,14 @@ "EventCode": "0x3", "EventName": "UNC_I_RxR_BL_NCS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { "EventCode": "0x9", "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -293,7 +293,7 @@ "EventCode": "0xd", "EventName": "UNC_I_TxR_REQUEST_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumultes the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjuection with the allocations event in order to calculate average latency of outbound requests.", + "PublicDescription": "Accumulates the number of outstanding outbound requests from the IRP to the switch (towards the devices). This can be used in conjunction with the allocations event in order to calculate average latency of outbound requests.", "Unit": "IRP" }, { diff --git a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json index 874f15ea8228..0fc907e5cf3c 100644 --- a/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/jaketown/uncore-interconnect.json @@ -140,7 +140,7 @@ "EventCode": "0x4", "EventName": "UNC_I_RxR_BL_DRS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -148,21 +148,21 @@ "EventCode": "0x1", "EventName": "UNC_I_RxR_BL_DRS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { "EventCode": "0x7", "EventName": "UNC_I_RxR_BL_DRS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { "EventCode": "0x5", "EventName": "UNC_I_RxR_BL_NCB_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -170,21 +170,21 @@ "EventCode": "0x2", "EventName": "UNC_I_RxR_BL_NCB_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { "EventCode": "0x8", "EventName": "UNC_I_RxR_BL_NCB_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { "EventCode": "0x6", "EventName": "UNC_I_RxR_BL_NCS_CYCLES_FULL", "PerPkg": "1", - "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of cycles when the BL Ingress is full. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { @@ -192,14 +192,14 @@ "EventCode": "0x3", "EventName": "UNC_I_RxR_BL_NCS_INSERTS", "PerPkg": "1", - "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Counts the number of allocations into the BL Ingress. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { "EventCode": "0x9", "EventName": "UNC_I_RxR_BL_NCS_OCCUPANCY", "PerPkg": "1", - "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requets as well as outbound MMIO writes.", + "PublicDescription": "Accumulates the occupancy of the BL Ingress in each cycles. This queue is where the IRP receives data from R2PCIe (the ring). It is used for data returns from read requests as well as outbound MMIO writes.", "Unit": "IRP" }, { diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json index d9876cb06b08..8da3a5a7be73 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/cache.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/cache.json @@ -6,14 +6,20 @@ "SampleAfterValue": "200003" }, { - "BriefDescription": "Counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of core cycles the fetch stalled for all icache misses.", + "BriefDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.", "EventCode": "0x86", "EventName": "FETCH_STALL.ICACHE_FILL_PENDING_CYCLES", - "PublicDescription": "This event counts the number of core cycles the fetch stalls because of an icache miss. This is a cumulative count of cycles the NIP stalled for all icache misses.", "SampleAfterValue": "200003", "UMask": "0x4" }, { + "BriefDescription": "Counts the number of L2HWP allocated into XQ GP", + "EventCode": "0x3E", + "EventName": "L2_PREFETCHER.ALLOC_XQ", + "SampleAfterValue": "100007", + "UMask": "0x4" + }, + { "BriefDescription": "Counts the number of L2 cache misses", "EventCode": "0x2E", "EventName": "L2_REQUESTS.MISS", @@ -28,7 +34,7 @@ "UMask": "0x4f" }, { - "BriefDescription": "Counts the number of MEC requests from the L2Q that reference a cache line (cacheable requests) excluding SW prefetches filling only to L2 cache and L1 evictions (automatically exlcudes L2HWP, UC, WC) that were rejected - Multiple repeated rejects should be counted multiple times", + "BriefDescription": "Counts the number of MEC requests from the L2Q that reference a cache line (cacheable requests) excluding SW prefetches filling only to L2 cache and L1 evictions (automatically excludes L2HWP, UC, WC) that were rejected - Multiple repeated rejects should be counted multiple times", "EventCode": "0x30", "EventName": "L2_REQUESTS_REJECT.ALL", "SampleAfterValue": "200003" @@ -50,11 +56,12 @@ "UMask": "0x80" }, { - "BriefDescription": "Counts the loads retired that get the data from the other core in the same tile in M state", + "BriefDescription": "Counts the loads retired that get the data from the other core in the same tile in M state (Precise Event)", "Data_LA": "1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.HITM", "PEBS": "1", + "PublicDescription": "This event counts the number of load micro-ops retired that got data from another core's cache. (Precise Event).", "SampleAfterValue": "200003", "UMask": "0x20" }, @@ -67,20 +74,22 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts the number of load micro-ops retired that hit in the L2", + "BriefDescription": "Counts the number of load micro-ops retired that hit in the L2 (Precise Event)", "Data_LA": "1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.L2_HIT_LOADS", "PEBS": "1", + "PublicDescription": "This event counts the number of load micro-uops retired that hit in the L2 (Precise Event)", "SampleAfterValue": "200003", "UMask": "0x2" }, { - "BriefDescription": "Counts the number of load micro-ops retired that miss in the L2", + "BriefDescription": "Counts the number of load micro-ops retired that miss in the L2 (Precise Event)", "Data_LA": "1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.L2_MISS_LOADS", "PEBS": "1", + "PublicDescription": "This event counts the number of load micro-ops retired that miss in the L2 (Precise Event)", "SampleAfterValue": "100007", "UMask": "0x4" }, @@ -621,6 +630,15 @@ "UMask": "0x1" }, { + "BriefDescription": "Accounts for responses which miss its own tile's L2.", + "EventCode": "0xB7", + "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.L2_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x18001981F8", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { "BriefDescription": "Counts any request that are outstanding, per weighted cycle, from the time of the request to when any response is received. The outstanding response should be programmed only on PMC0.", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.ANY_REQUEST.OUTSTANDING", @@ -1665,15 +1683,6 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts L2 data RFO prefetches (includes PREFETCHW instruction) that provides no supplier details", - "EventCode": "0xB7", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.SUPPLIER_NONE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000020020", - "SampleAfterValue": "100007", - "UMask": "0x1" - }, - { "BriefDescription": "Counts Software Prefetches that accounts for any response", "EventCode": "0xB7", "EventName": "OFFCORE_RESPONSE.PF_SOFTWARE.ANY_RESPONSE", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/floating-point.json b/tools/perf/pmu-events/arch/x86/knightslanding/floating-point.json index ecc96f32f167..089aa3ef345d 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/floating-point.json @@ -8,18 +8,18 @@ "UMask": "0x4" }, { - "BriefDescription": "Counts the number of vector SSE, AVX, AVX2, AVX-512 micro-ops retired. More specifically, it counts packed SSE, AVX, AVX2, AVX-512 micro-ops (both floating point and integer) except for loads (memory-to-register mov-type micro-ops), packed byte and word multiplies.", + "BriefDescription": "Counts the number of packed SSE, AVX, AVX2, AVX-512 micro-ops (both floating point and integer) except for loads (memory-to-register mov-type micro-ops), packed byte and word multiplies.", "EventCode": "0xC2", "EventName": "UOPS_RETIRED.PACKED_SIMD", - "PublicDescription": "This event counts the number of packed vector SSE, AVX, AVX2, and AVX-512 micro-ops retired (floating point, integer and store) except for loads (memory-to-register mov-type micro-ops), packed byte and word multiplies.", + "PublicDescription": "The length of the packed operation (128bits, 256bits or 512bits) is not taken into account when updating the counter; all count the same (+1). \r\nMask (k) registers are ignored. For example: a micro-op operating with a mask that only enables one element or even zero elements will still trigger this counter (+1)\r\nThis event is defined at the micro-op level and not instruction level. Most instructions are implemented with one micro-op but not all.", "SampleAfterValue": "200003", "UMask": "0x40" }, { - "BriefDescription": "Counts the number of scalar SSE, AVX, AVX2, AVX-512 micro-ops retired. More specifically, it counts scalar SSE, AVX, AVX2, AVX-512 micro-ops except for loads (memory-to-register mov-type micro ops), division, sqrt.", + "BriefDescription": "Counts the number of scalar SSE, AVX, AVX2, AVX-512 micro-ops except for loads (memory-to-register mov-type micro ops), division, sqrt.", "EventCode": "0xC2", "EventName": "UOPS_RETIRED.SCALAR_SIMD", - "PublicDescription": "This event counts the number of scalar SSE, AVX, AVX2, AVX-512 micro-ops retired (floating point, integer and store) except for loads (memory-to-register mov-type micro ops), division, sqrt.", + "PublicDescription": "This event is defined at the micro-op level and not instruction level. Most instructions are implemented with one micro-op but not all.", "SampleAfterValue": "200003", "UMask": "0x20" } diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json index 3dc532107ead..5b2e71750976 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/pipeline.json @@ -1,13 +1,13 @@ [ { - "BriefDescription": "Counts the number of branch instructions retired", + "BriefDescription": "Counts the number of branch instructions retired (Precise Event)", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.ALL_BRANCHES", "PEBS": "1", "SampleAfterValue": "200003" }, { - "BriefDescription": "Counts the number of near CALL branch instructions retired.", + "BriefDescription": "Counts the number of near CALL branch instructions retired. (Precise Event)", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.CALL", "PEBS": "1", @@ -15,7 +15,7 @@ "UMask": "0xf9" }, { - "BriefDescription": "Counts the number of far branch instructions retired.", + "BriefDescription": "Counts the number of far branch instructions retired. (Precise Event)", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.FAR_BRANCH", "PEBS": "1", @@ -23,7 +23,7 @@ "UMask": "0xbf" }, { - "BriefDescription": "Counts the number of near indirect CALL branch instructions retired.", + "BriefDescription": "Counts the number of near indirect CALL branch instructions retired. (Precise Event)", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.IND_CALL", "PEBS": "1", @@ -31,7 +31,7 @@ "UMask": "0xfb" }, { - "BriefDescription": "Counts the number of branch instructions retired that were conditional jumps.", + "BriefDescription": "Counts the number of branch instructions retired that were conditional jumps. (Precise Event)", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.JCC", "PEBS": "1", @@ -39,7 +39,7 @@ "UMask": "0x7e" }, { - "BriefDescription": "Counts the number of branch instructions retired that were near indirect CALL or near indirect JMP.", + "BriefDescription": "Counts the number of branch instructions retired that were near indirect CALL or near indirect JMP. (Precise Event)", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.NON_RETURN_IND", "PEBS": "1", @@ -47,7 +47,7 @@ "UMask": "0xeb" }, { - "BriefDescription": "Counts the number of near relative CALL branch instructions retired.", + "BriefDescription": "Counts the number of near relative CALL branch instructions retired. (Precise Event)", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.REL_CALL", "PEBS": "1", @@ -55,7 +55,7 @@ "UMask": "0xfd" }, { - "BriefDescription": "Counts the number of near RET branch instructions retired.", + "BriefDescription": "Counts the number of near RET branch instructions retired. (Precise Event)", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.RETURN", "PEBS": "1", @@ -63,7 +63,7 @@ "UMask": "0xf7" }, { - "BriefDescription": "Counts the number of branch instructions retired that were conditional jumps and predicted taken.", + "BriefDescription": "Counts the number of branch instructions retired that were conditional jumps and predicted taken. (Precise Event)", "EventCode": "0xC4", "EventName": "BR_INST_RETIRED.TAKEN_JCC", "PEBS": "1", @@ -71,14 +71,14 @@ "UMask": "0xfe" }, { - "BriefDescription": "Counts the number of mispredicted branch instructions retired", + "BriefDescription": "Counts the number of mispredicted branch instructions retired (Precise Event)", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", "PEBS": "1", "SampleAfterValue": "200003" }, { - "BriefDescription": "Counts the number of mispredicted near CALL branch instructions retired.", + "BriefDescription": "Counts the number of mispredicted near CALL branch instructions retired. (Precise Event)", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.CALL", "PEBS": "1", @@ -86,7 +86,7 @@ "UMask": "0xf9" }, { - "BriefDescription": "Counts the number of mispredicted far branch instructions retired.", + "BriefDescription": "Counts the number of mispredicted far branch instructions retired. (Precise Event)", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.FAR_BRANCH", "PEBS": "1", @@ -94,7 +94,7 @@ "UMask": "0xbf" }, { - "BriefDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired.", + "BriefDescription": "Counts the number of mispredicted near indirect CALL branch instructions retired. (Precise Event)", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.IND_CALL", "PEBS": "1", @@ -102,7 +102,7 @@ "UMask": "0xfb" }, { - "BriefDescription": "Counts the number of mispredicted branch instructions retired that were conditional jumps.", + "BriefDescription": "Counts the number of mispredicted branch instructions retired that were conditional jumps. (Precise Event)", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.JCC", "PEBS": "1", @@ -110,7 +110,7 @@ "UMask": "0x7e" }, { - "BriefDescription": "Counts the number of mispredicted branch instructions retired that were near indirect CALL or near indirect JMP.", + "BriefDescription": "Counts the number of mispredicted branch instructions retired that were near indirect CALL or near indirect JMP. (Precise Event)", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.NON_RETURN_IND", "PEBS": "1", @@ -118,7 +118,7 @@ "UMask": "0xeb" }, { - "BriefDescription": "Counts the number of mispredicted near relative CALL branch instructions retired.", + "BriefDescription": "Counts the number of mispredicted near relative CALL branch instructions retired. (Precise Event)", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.REL_CALL", "PEBS": "1", @@ -126,7 +126,7 @@ "UMask": "0xfd" }, { - "BriefDescription": "Counts the number of mispredicted near RET branch instructions retired.", + "BriefDescription": "Counts the number of mispredicted near RET branch instructions retired. (Precise Event)", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.RETURN", "PEBS": "1", @@ -134,7 +134,7 @@ "UMask": "0xf7" }, { - "BriefDescription": "Counts the number of mispredicted branch instructions retired that were conditional jumps and predicted taken.", + "BriefDescription": "Counts the number of mispredicted branch instructions retired that were conditional jumps and predicted taken. (Precise Event)", "EventCode": "0xC5", "EventName": "BR_MISP_RETIRED.TAKEN_JCC", "PEBS": "1", @@ -189,7 +189,14 @@ "SampleAfterValue": "2000003" }, { - "BriefDescription": "Counts all nukes", + "BriefDescription": "Counts the number of instructions retired (Precise Event)", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.ANY_PS", + "PEBS": "2", + "SampleAfterValue": "2000003" + }, + { + "BriefDescription": "Counts all machine clears", "EventCode": "0xC3", "EventName": "MACHINE_CLEARS.ALL", "SampleAfterValue": "200003", @@ -261,20 +268,22 @@ "UMask": "0x2" }, { - "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with a store", + "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with a store (Precise Event)", "Data_LA": "1", "EventCode": "0x03", "EventName": "RECYCLEQ.LD_BLOCK_ST_FORWARD", "PEBS": "1", + "PublicDescription": "This event counts the number of retired loads that were prohibited from receiving forwarded data from a previous store because of address mismatch.", "SampleAfterValue": "200003", "UMask": "0x1" }, { - "BriefDescription": "Counts the number of occurrences a retired load that is a cache line split. Each split should be counted only once.", + "BriefDescription": "Counts the number of occurrences a retired load was pushed into the rehab queue because it sees a cache line split. Each split should be counted only once. (Precise Event)", "Data_LA": "1", "EventCode": "0x03", "EventName": "RECYCLEQ.LD_SPLITS", "PEBS": "1", + "PublicDescription": "This event counts the number of retired loads which was pushed into the recycled queue that experienced cache line boundary splits (Precise event). Not that each split should be counted only once.", "SampleAfterValue": "200003", "UMask": "0x8" }, @@ -286,7 +295,7 @@ "UMask": "0x10" }, { - "BriefDescription": "Counts the store micro-ops retired that were pushed in the rehad queue because the store address buffer is full", + "BriefDescription": "Counts the store micro-ops retired that were pushed in the rehab queue because the store address buffer is full", "EventCode": "0x03", "EventName": "RECYCLEQ.STA_FULL", "SampleAfterValue": "200003", @@ -301,7 +310,7 @@ "UMask": "0x4" }, { - "BriefDescription": "Counts the total number of core cycles the Alloc pipeline is stalled when any one of the reservation stations is full.", + "BriefDescription": "Counts the total number of core cycles allocation pipeline is stalled when any one of the reservation stations is full.", "EventCode": "0xCB", "EventName": "RS_FULL_STALL.ALL", "SampleAfterValue": "200003", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-cache.json b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-cache.json index 1b8dcfa5461c..120e4813d82a 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/uncore-cache.json @@ -2558,7 +2558,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2A", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.AD_REQ_VN0", "PerPkg": "1", @@ -2566,7 +2566,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2A", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.AD_RSP_VN0", "PerPkg": "1", @@ -2574,7 +2574,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2A", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.AK_NON_UPI", "PerPkg": "1", @@ -2582,7 +2582,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2A", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.BL_NCB_VN0", "PerPkg": "1", @@ -2590,7 +2590,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2A", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.BL_NCS_VN0", "PerPkg": "1", @@ -2598,7 +2598,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2A", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.BL_RSP_VN0", "PerPkg": "1", @@ -2606,7 +2606,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2A", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.BL_WB_VN0", "PerPkg": "1", @@ -2614,7 +2614,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2A", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q0_RETRY.IV_NON_UPI", "PerPkg": "1", @@ -2622,7 +2622,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2B", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q1_RETRY.ALLOW_SNP", "PerPkg": "1", @@ -2630,7 +2630,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2B", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q1_RETRY.ANY_REJECT_IRQ0", "PerPkg": "1", @@ -2638,7 +2638,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2B", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q1_RETRY.PA_MATCH", "PerPkg": "1", @@ -2646,7 +2646,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2B", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q1_RETRY.SF_VICTIM", "PerPkg": "1", @@ -2654,7 +2654,7 @@ "Unit": "CHA" }, { - "BriefDescription": "REQUESTQ'' includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", + "BriefDescription": "REQUESTQ includes: IRQ, PRQ, IPQ, RRQ, WBQ (everything except for ISMQ)", "EventCode": "0x2B", "EventName": "UNC_H_INGRESS_RETRY_REQ_Q1_RETRY.SF_WAY", "PerPkg": "1", diff --git a/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json b/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json index 99a8fa8f19cc..9be30a33b43b 100644 --- a/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/knightslanding/virtual-memory.json @@ -1,6 +1,6 @@ [ { - "BriefDescription": "Counts the number of load micro-ops retired that cause a DTLB miss", + "BriefDescription": "Counts the number of load micro-ops retired that cause a DTLB miss (Precise Event)", "Data_LA": "1", "EventCode": "0x04", "EventName": "MEM_UOPS_RETIRED.DTLB_MISS_LOADS", diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json new file mode 100644 index 000000000000..1823149067b5 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json @@ -0,0 +1,219 @@ +[ + { + "BriefDescription": "Counts the number of L2 Cache Accesses Counts the total number of L2 Cache Accesses - sum of hits, misses, rejects front door requests for CRd/DRd/RFO/ItoM/L2 Prefetches only, per core event", + "EventCode": "0x24", + "EventName": "L2_REQUEST.ALL", + "PublicDescription": "Counts the number of L2 Cache Accesses Counts the total number of L2 Cache Accesses - sum of hits, misses, rejects front door requests for CRd/DRd/RFO/ItoM/L2 Prefetches only.", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of cacheable memory requests that miss in the LLC. Counts on a per core basis.", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts the number of cacheable memory requests that miss in the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "SampleAfterValue": "200003", + "UMask": "0x41", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.MISS", + "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x41", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of cacheable memory requests that access the LLC. Counts on a per core basis.", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.", + "SampleAfterValue": "1000003", + "UMask": "0x4f", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Core-originated cacheable requests that refer to L3 (Except hardware prefetches to the L3)", + "EventCode": "0x2e", + "EventName": "LONGEST_LAT_CACHE.REFERENCE", + "PublicDescription": "Counts core-originated cacheable requests to the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x4f", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired load instructions.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", + "PEBS": "1", + "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.", + "SampleAfterValue": "1000003", + "UMask": "0x81", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired store instructions.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "PEBS": "1", + "PublicDescription": "Counts all retired store instructions.", + "SampleAfterValue": "1000003", + "UMask": "0x82", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of load uops retired.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_LOADS", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0x81", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of store uops retired.", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.ALL_STORES", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0x82", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_1024", + "MSRIndex": "0x3F6", + "MSRValue": "0x400", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_2048", + "MSRIndex": "0x3F6", + "MSRValue": "0x800", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of tagged load uops retired that exceed the latency threshold defined in MEC_CR_PEBS_LD_LAT_THRESHOLD - Only counts with PEBS enabled", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of stores uops retired same as MEM_UOPS_RETIRED.ALL_STORES", + "Data_LA": "1", + "EventCode": "0xd0", + "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY", + "PEBS": "2", + "SampleAfterValue": "1000003", + "UMask": "0x6", + "Unit": "cpu_atom" + } +] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json new file mode 100644 index 000000000000..5e4ef81b43d6 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json @@ -0,0 +1,27 @@ +[ + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump.", + "EventCode": "0x80", + "EventName": "ICACHE.ACCESSES", + "SampleAfterValue": "200003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts every time the code stream enters into a new cache line by walking sequential from the previous line or being redirected by a jump and the instruction cache registers bytes are not present. -", + "EventCode": "0x80", + "EventName": "ICACHE.MISSES", + "SampleAfterValue": "200003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CORE", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nSoftware can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + } +] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json new file mode 100644 index 000000000000..51d70ba00bd4 --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json @@ -0,0 +1,183 @@ +[ + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_1024", + "MSRIndex": "0x3F6", + "MSRValue": "0x400", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "53", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_128", + "MSRIndex": "0x3F6", + "MSRValue": "0x80", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "1009", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_16", + "MSRIndex": "0x3F6", + "MSRValue": "0x10", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "20011", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048", + "MSRIndex": "0x3F6", + "MSRValue": "0x800", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "23", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_256", + "MSRIndex": "0x3F6", + "MSRValue": "0x100", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "503", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_32", + "MSRIndex": "0x3F6", + "MSRValue": "0x20", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100007", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_4", + "MSRIndex": "0x3F6", + "MSRValue": "0x4", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_512", + "MSRIndex": "0x3F6", + "MSRValue": "0x200", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "101", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_64", + "MSRIndex": "0x3F6", + "MSRValue": "0x40", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "2003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_8", + "MSRIndex": "0x3F6", + "MSRValue": "0x8", + "PEBS": "2", + "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles. Reported latency may be longer than just the memory latency.", + "SampleAfterValue": "50021", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Retired memory store access operations. A PDist event for PEBS Store Latency Facility.", + "Data_LA": "1", + "EventCode": "0xcd", + "EventName": "MEM_TRANS_RETIRED.STORE_SAMPLE", + "PEBS": "2", + "PublicDescription": "Counts Retired memory accesses with at least 1 store operation. This PEBS event is the precisely-distributed (PDist) trigger covering all stores uops for sampling by the PEBS Store Latency Facility. The facility is described in Intel SDM Volume 3 section 19.9.8", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cacheable demand data reads were not supplied by the L3 cache.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO were not supplied by the L3 cache.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + } +] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/other.json b/tools/perf/pmu-events/arch/x86/lunarlake/other.json new file mode 100644 index 000000000000..69adaed5686d --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/other.json @@ -0,0 +1,62 @@ +[ + { + "BriefDescription": "Counts cacheable demand data reads Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts cacheable demand data reads were supplied by DRAM.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand reads for ownership, including SWPREFETCHW which is an RFO Catch all value for any response types - this includes response types not define in the OCR. If this is set all other response types will be ignored", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + } +] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json new file mode 100644 index 000000000000..2bde664fdc0f --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json @@ -0,0 +1,217 @@ +[ + { + "BriefDescription": "Counts the total number of branch instructions retired for all branch types.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts the total number of instructions in which the instruction pointer (IP) of the processor is resteered due to a branch instruction and the branch instruction successfully retires. All branch type instructions are accounted for.", + "SampleAfterValue": "200003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "All branch instructions retired.", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts all branch instructions retired.", + "SampleAfterValue": "400009", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the total number of mispredicted branch instructions retired for all branch types.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts the total number of mispredicted branch instructions retired. All branch type instructions are accounted for. Prediction of the branch target address enables the processor to begin executing instructions before the non-speculative execution path is known. The branch prediction unit (BPU) predicts the target address based on the instruction pointer (IP) of the branch and on the execution path through which execution reached this IP. A branch misprediction occurs when the prediction is wrong, and results in discarding all instructions executed in the speculative path and re-fetching from the correct path.", + "SampleAfterValue": "200003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "All mispredicted branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "PEBS": "1", + "PublicDescription": "Counts all the retired branch instructions that were mispredicted by the processor. A branch misprediction occurs when the processor incorrectly predicts the destination of the branch. When the misprediction is discovered at execution, all the instructions executed in the wrong (speculative) path must be discarded, and the processor must start fetching from the correct path.", + "SampleAfterValue": "400009", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles", + "EventName": "CPU_CLK_UNHALTED.CORE", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.CORE_P", + "SampleAfterValue": "2000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "SampleAfterValue": "1000003", + "UMask": "0x3", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "EventName": "CPU_CLK_UNHALTED.REF_TSC", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "SampleAfterValue": "2000003", + "UMask": "0x3", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Reference cycles when the core is not in halt state.", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.REF_TSC_P", + "PublicDescription": "Counts the number of reference cycles when the core is not in a halt state. The core enters the halt state when it is running the HLT instruction or the MWAIT instruction. This event is not affected by core frequency changes (for example, P states, TM2 transitions) but has the same incrementing frequency as the time stamp counter. This event can approximate elapsed time while the core was not in a halt state. Note: On all current platforms this event stops counting during 'throttling (TM)' states duty off periods the processor is 'halted'. The counter update is done at a lower clock rate then the core clock the overflow status bit for this counter may appear 'sticky'. After the counter has overflowed and software clears the overflow status bit and resets the counter to less than MAX. The reset value to the counter is not clocked immediately so the overflow status bit will flip 'high (1)' and generate another PMI (if enabled) after which the reset value gets clocked into the counter. Therefore, software will get the interrupt, read the overflow status bit '1 for bit 34 while the counter value is less than MAX. Software should ignore this case.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Core cycles when the thread is not in halt state", + "EventName": "CPU_CLK_UNHALTED.THREAD", + "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.CORE_P]", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "SampleAfterValue": "2000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Thread cycles when thread is not in halt state", + "EventCode": "0x3c", + "EventName": "CPU_CLK_UNHALTED.THREAD_P", + "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.", + "SampleAfterValue": "2000003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of instructions retired", + "EventName": "INST_RETIRED.ANY", + "PEBS": "1", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of instructions retired. Fixed Counter - architectural event", + "EventName": "INST_RETIRED.ANY", + "PEBS": "1", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "SampleAfterValue": "2000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of instructions retired", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "PEBS": "1", + "SampleAfterValue": "2000003", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "EventCode": "0xc0", + "EventName": "INST_RETIRED.ANY_P", + "PEBS": "1", + "PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.", + "SampleAfterValue": "2000003", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of occurrences a retired load gets blocked because its address partially overlaps with an older store (size mismatch) - unknown_sta/bad_forward", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PEBS": "1", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Loads blocked due to overlapping with a preceding store that cannot be forwarded.", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.STORE_FORWARD", + "PublicDescription": "Counts the number of times where store forwarding was prevented for a load operation. The most common case is a load blocked due to the address of memory access (partially) overlapping with a preceding uncompleted store. Note: See the table of not supported store forwards in the Optimization Guide.", + "SampleAfterValue": "100003", + "UMask": "0x82", + "Unit": "cpu_core" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.", + "EventCode": "0xa4", + "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS", + "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.\nSoftware can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "10000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event", + "EventName": "TOPDOWN.SLOTS", + "PublicDescription": "Number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method (TMA). Software can use this event as the denominator for the top-level metrics of the TMA method. This architectural event is counted on a designated fixed counter (Fixed Counter 3).", + "SampleAfterValue": "10000003", + "UMask": "0x4", + "Unit": "cpu_core" + }, + { + "BriefDescription": "TMA slots available for an unhalted logical processor. General counter - architectural event", + "EventCode": "0xa4", + "EventName": "TOPDOWN.SLOTS_P", + "PublicDescription": "Counts the number of available slots for an unhalted logical processor. The event increments by machine-width of the narrowest pipeline as employed by the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "10000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.", + "EventName": "TOPDOWN_BAD_SPECULATION.ALL", + "PublicDescription": "Fixed Counter: Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the IQ. Also, includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.", + "SampleAfterValue": "1000003", + "UMask": "0x5", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls", + "EventCode": "0xa4", + "EventName": "TOPDOWN_BE_BOUND.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls", + "EventName": "TOPDOWN_FE_BOUND.ALL", + "SampleAfterValue": "1000003", + "UMask": "0x6", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots. Similar to UOPS_RETIRED.ALL", + "EventName": "TOPDOWN_RETIRING.ALL", + "PEBS": "1", + "SampleAfterValue": "1000003", + "UMask": "0x7", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.SLOTS", + "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance for example, as measured by the instructions-per-cycle metric.\nSoftware can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.", + "SampleAfterValue": "2000003", + "UMask": "0x2", + "Unit": "cpu_core" + } +] diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json new file mode 100644 index 000000000000..bb9458799f1c --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/lunarlake/virtual-memory.json @@ -0,0 +1,56 @@ +[ + { + "BriefDescription": "Counts the number of page walks completed due to load DTLB misses to any page size.", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to loads (including SW prefetches) whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", + "SampleAfterValue": "200003", + "UMask": "0xe", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x12", + "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data loads. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to store DTLB misses to any page size.", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to stores whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0xe", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x13", + "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by demand data stores. This implies it missed in the DTLB and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts the number of page walks completed due to instruction fetch misses to any page size.", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts the number of page walks completed due to instruction fetches whose address translations missed in all Translation Lookaside Buffer (TLB) levels and were mapped to any page size. Includes page walks that page fault.", + "SampleAfterValue": "2000003", + "UMask": "0xe", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "EventCode": "0x11", + "EventName": "ITLB_MISSES.WALK_COMPLETED", + "PublicDescription": "Counts completed page walks (all page sizes) caused by a code fetch. This implies it missed in the ITLB (Instruction TLB) and further levels of TLB. The page walk can end with or without a fault.", + "SampleAfterValue": "100003", + "UMask": "0xe", + "Unit": "cpu_core" + } +] diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index 3a8770e29fe8..e571683f59f3 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -1,39 +1,41 @@ Family-model,Version,Filename,EventType -GenuineIntel-6-(97|9A|B7|BA|BF),v1.21,alderlake,core -GenuineIntel-6-BE,v1.21,alderlaken,core -GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core +GenuineIntel-6-(97|9A|B7|BA|BF),v1.23,alderlake,core +GenuineIntel-6-BE,v1.23,alderlaken,core +GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core GenuineIntel-6-(3D|47),v28,broadwell,core -GenuineIntel-6-56,v10,broadwellde,core -GenuineIntel-6-4F,v21,broadwellx,core -GenuineIntel-6-55-[56789ABCDEF],v1.19,cascadelakex,core +GenuineIntel-6-56,v11,broadwellde,core +GenuineIntel-6-4F,v22,broadwellx,core +GenuineIntel-6-55-[56789ABCDEF],v1.20,cascadelakex,core GenuineIntel-6-9[6C],v1.04,elkhartlake,core +GenuineIntel-6-CF,v1.01,emeraldrapids,core GenuineIntel-6-5[CF],v13,goldmont,core GenuineIntel-6-7A,v1.01,goldmontplus,core GenuineIntel-6-B6,v1.00,grandridge,core GenuineIntel-6-A[DE],v1.01,graniterapids,core GenuineIntel-6-(3C|45|46),v33,haswell,core -GenuineIntel-6-3F,v27,haswellx,core +GenuineIntel-6-3F,v28,haswellx,core GenuineIntel-6-7[DE],v1.19,icelake,core GenuineIntel-6-6[AC],v1.21,icelakex,core GenuineIntel-6-3A,v24,ivybridge,core -GenuineIntel-6-3E,v23,ivytown,core -GenuineIntel-6-2D,v23,jaketown,core -GenuineIntel-6-(57|85),v10,knightslanding,core -GenuineIntel-6-A[AC],v1.04,meteorlake,core -GenuineIntel-6-1[AEF],v3,nehalemep,core -GenuineIntel-6-2E,v3,nehalemex,core +GenuineIntel-6-3E,v24,ivytown,core +GenuineIntel-6-2D,v24,jaketown,core +GenuineIntel-6-(57|85),v16,knightslanding,core +GenuineIntel-6-BD,v1.00,lunarlake,core +GenuineIntel-6-A[AC],v1.06,meteorlake,core +GenuineIntel-6-1[AEF],v4,nehalemep,core +GenuineIntel-6-2E,v4,nehalemex,core GenuineIntel-6-A7,v1.01,rocketlake,core GenuineIntel-6-2A,v19,sandybridge,core -GenuineIntel-6-(8F|CF),v1.15,sapphirerapids,core +GenuineIntel-6-8F,v1.16,sapphirerapids,core GenuineIntel-6-AF,v1.00,sierraforest,core GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v57,skylake,core -GenuineIntel-6-55-[01234],v1.31,skylakex,core +GenuineIntel-6-55-[01234],v1.32,skylakex,core GenuineIntel-6-86,v1.21,snowridgex,core GenuineIntel-6-8[CD],v1.13,tigerlake,core -GenuineIntel-6-2C,v4,westmereep-dp,core -GenuineIntel-6-25,v3,westmereep-sp,core -GenuineIntel-6-2F,v3,westmereex,core +GenuineIntel-6-2C,v5,westmereep-dp,core +GenuineIntel-6-25,v4,westmereep-sp,core +GenuineIntel-6-2F,v4,westmereex,core AuthenticAMD-23-([12][0-9A-F]|[0-9A-F]),v2,amdzen1,core AuthenticAMD-23-[[:xdigit:]]+,v1,amdzen2,core AuthenticAMD-25-([245][[:xdigit:]]|[[:xdigit:]]),v1,amdzen3,core diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json index 1de0200b32f6..5fef87502d4b 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json @@ -967,6 +967,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified.", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM", @@ -977,6 +987,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x8003C0001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", @@ -987,6 +1007,16 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.", + "EventCode": "0xB7", + "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified.", "EventCode": "0x2A,0x2B", "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json index 8264419500a5..9da8689eda81 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json @@ -461,6 +461,27 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "CounterMask": "6", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "CounterMask": "1", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", + "Invert": "1", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "SampleAfterValue": "1000003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", @@ -470,22 +491,22 @@ "Unit": "cpu_core" }, { - "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled", + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" }, { - "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled", + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "CounterMask": "1", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1", "Unit": "cpu_core" diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json index 2605e1d0ba9f..a5b83293f157 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json @@ -67,6 +67,14 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of machine clears due to memory ordering caused by a snoop from an external agent. Does not count internally generated machine clears such as those due to memory disambiguation.", + "EventCode": "0xc3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "SampleAfterValue": "20003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Number of machine clears due to memory ordering conflicts.", "EventCode": "0xc3", "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", @@ -76,6 +84,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "CounterMask": "2", + "EventCode": "0x47", + "EventName": "MEMORY_ACTIVITY.CYCLES_L1D_MISS", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_core" + }, + { "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", "CounterMask": "3", "EventCode": "0x47", @@ -280,6 +297,26 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.L3_MISS", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBFC00002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { "BriefDescription": "Counts demand data read requests that miss the L3 cache.", "EventCode": "0x21", "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json index f4c603599df4..d55e792c0c43 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json @@ -8,6 +8,46 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts demand data reads that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand data reads that were supplied by DRAM.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_DATA_RD.DRAM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x184000001", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.", + "EventCode": "0x2A,0x2B", + "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10002", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_core" + }, + { + "BriefDescription": "Counts streaming stores that have any type of response.", + "EventCode": "0xB7", + "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10800", + "SampleAfterValue": "100003", + "UMask": "0x1", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts streaming stores that have any type of response.", "EventCode": "0x2A,0x2B", "EventName": "OCR.STREAMING_WR.ANY_RESPONSE", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json index 352c5efafc06..deaa7aba93f7 100644 --- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json @@ -218,6 +218,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.COND_TAKEN", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0xfe", + "Unit": "cpu_atom" + }, + { "BriefDescription": "number of branch instructions retired that were mispredicted and taken.", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.COND_TAKEN", @@ -293,6 +302,15 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the number of mispredicted near taken branch instructions retired.", + "EventCode": "0xc5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "200003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", "EventCode": "0xc5", "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", @@ -733,7 +751,7 @@ "Unit": "cpu_core" }, { - "BriefDescription": "INT_MISC.UNKNOWN_BRANCH_CYCLES", + "BriefDescription": "Bubble cycles of BAClear (Unknown Branch).", "EventCode": "0xad", "EventName": "INT_MISC.UNKNOWN_BRANCH_CYCLES", "MSRIndex": "0x3F7", @@ -1046,6 +1064,14 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Branch Mispredict", + "EventCode": "0x73", + "EventName": "TOPDOWN_BAD_SPECULATION.MISPREDICT", + "SampleAfterValue": "1000003", + "UMask": "0x4", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to a machine clear (nuke).", "EventCode": "0x73", "EventName": "TOPDOWN_BAD_SPECULATION.NUKE", @@ -1069,6 +1095,22 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop). This could be caused by RSV full or load/store buffer block.", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER", + "SampleAfterValue": "1000003", + "UMask": "0x2", + "Unit": "cpu_atom" + }, + { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to IEC and FPC RAT stalls - which can be due to the FIQ and IEC reservation station stall (integer, FP and SIMD scheduler not being able to accept another uop. )", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER", + "SampleAfterValue": "1000003", + "UMask": "0x8", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to mrbl stall. A 'marble' refers to a physical register file entry, also known as the physical destination (PDST).", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.REGISTER", @@ -1077,6 +1119,14 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to ROB full", + "EventCode": "0x74", + "EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER", + "SampleAfterValue": "1000003", + "UMask": "0x40", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to iq/jeu scoreboards or ms scb", "EventCode": "0x74", "EventName": "TOPDOWN_BE_BOUND.SERIALIZATION", @@ -1157,6 +1207,14 @@ "Unit": "cpu_atom" }, { + "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend that do not categorize into any other common frontend stall", + "EventCode": "0x71", + "EventName": "TOPDOWN_FE_BOUND.OTHER", + "SampleAfterValue": "1000003", + "UMask": "0x80", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to predecode wrong", "EventCode": "0x71", "EventName": "TOPDOWN_FE_BOUND.PREDECODE", @@ -1399,6 +1457,14 @@ "Unit": "cpu_core" }, { + "BriefDescription": "Counts the total number of uops retired.", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.ALL", + "PEBS": "1", + "SampleAfterValue": "2000003", + "Unit": "cpu_atom" + }, + { "BriefDescription": "Cycles with retired uop(s).", "CounterMask": "1", "EventCode": "0xc2", diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json new file mode 100644 index 000000000000..2af92e43b28a --- /dev/null +++ b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-other.json @@ -0,0 +1,9 @@ +[ + { + "BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.", + "EventCode": "0xff", + "EventName": "UNC_CLOCK.SOCKET", + "PerPkg": "1", + "Unit": "CLOCK" + } +] diff --git a/tools/perf/pmu-events/arch/x86/nehalemep/cache.json b/tools/perf/pmu-events/arch/x86/nehalemep/cache.json index 1a132fcda964..5113a4e059e4 100644 --- a/tools/perf/pmu-events/arch/x86/nehalemep/cache.json +++ b/tools/perf/pmu-events/arch/x86/nehalemep/cache.json @@ -287,7 +287,7 @@ "UMask": "0x20" }, { - "BriefDescription": "L2 lines alloacated", + "BriefDescription": "L2 lines allocated", "EventCode": "0xF1", "EventName": "L2_LINES_IN.ANY", "SampleAfterValue": "100000", diff --git a/tools/perf/pmu-events/arch/x86/nehalemep/floating-point.json b/tools/perf/pmu-events/arch/x86/nehalemep/floating-point.json index c03f8990fa82..196ae1d9b157 100644 --- a/tools/perf/pmu-events/arch/x86/nehalemep/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/nehalemep/floating-point.json @@ -8,7 +8,7 @@ "UMask": "0x1" }, { - "BriefDescription": "X87 Floating poiint assists for invalid input value (Precise Event)", + "BriefDescription": "X87 Floating point assists for invalid input value (Precise Event)", "EventCode": "0xF7", "EventName": "FP_ASSIST.INPUT", "PEBS": "1", diff --git a/tools/perf/pmu-events/arch/x86/nehalemex/cache.json b/tools/perf/pmu-events/arch/x86/nehalemex/cache.json index a4142cd2ca86..0042e53fdc78 100644 --- a/tools/perf/pmu-events/arch/x86/nehalemex/cache.json +++ b/tools/perf/pmu-events/arch/x86/nehalemex/cache.json @@ -287,7 +287,7 @@ "UMask": "0x20" }, { - "BriefDescription": "L2 lines alloacated", + "BriefDescription": "L2 lines allocated", "EventCode": "0xF1", "EventName": "L2_LINES_IN.ANY", "SampleAfterValue": "100000", diff --git a/tools/perf/pmu-events/arch/x86/nehalemex/floating-point.json b/tools/perf/pmu-events/arch/x86/nehalemex/floating-point.json index c03f8990fa82..196ae1d9b157 100644 --- a/tools/perf/pmu-events/arch/x86/nehalemex/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/nehalemex/floating-point.json @@ -8,7 +8,7 @@ "UMask": "0x1" }, { - "BriefDescription": "X87 Floating poiint assists for invalid input value (Precise Event)", + "BriefDescription": "X87 Floating point assists for invalid input value (Precise Event)", "EventCode": "0xF7", "EventName": "FP_ASSIST.INPUT", "PEBS": "1", diff --git a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json index a0191c8b708d..0c880e415669 100644 --- a/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/rocketlake/rkl-metrics.json @@ -1551,7 +1551,7 @@ }, { "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", - "MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)", + "MetricExpr": "(cycles\\-t / el\\-start if has_event(el\\-start) else 0)", "MetricGroup": "transaction", "MetricName": "tsx_cycles_per_elision", "ScaleUnit": "1cycles / elision" diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json index 860a415e5e79..9e53da55d0c1 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json @@ -333,29 +333,56 @@ "UMask": "0x20" }, { - "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled", + "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CORE", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "CounterMask": "6", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "CounterMask": "1", + "EventCode": "0x9c", + "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK", + "Invert": "1", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]", + "SampleAfterValue": "1000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CORE]", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "PublicDescription": "Counts the number of uops not delivered to by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, { - "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled", + "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "CounterMask": "6", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]", "SampleAfterValue": "1000003", "UMask": "0x1" }, { - "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled", + "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "CounterMask": "1", "EventCode": "0x9c", "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK", "Invert": "1", - "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.", + "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]", "SampleAfterValue": "1000003", "UMask": "0x1" } diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json index 222212abd811..06c6d67cb76b 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json @@ -1945,13 +1945,6 @@ "ScaleUnit": "100%" }, { - "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", - "MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)", - "MetricGroup": "transaction", - "MetricName": "tsx_cycles_per_elision", - "ScaleUnit": "1cycles / elision" - }, - { "BriefDescription": "Number of cycles within a transaction divided by the number of transactions.", "MetricExpr": "(cycles\\-t / tx\\-start if has_event(cycles\\-t) else 0)", "MetricGroup": "transaction", diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json index 3fa660694bc7..cf6fa70f37c1 100644 --- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json +++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json @@ -4591,7 +4591,7 @@ }, { "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CXL_ACC_LOCAL", - "EventCode": "0x35", + "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_CXL_ACC_LOCAL", "PerPkg": "1", "PortMask": "0x000", @@ -4825,7 +4825,7 @@ }, { "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CXL_ACC_LOCAL", - "EventCode": "0x35", + "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_CXL_ACC_LOCAL", "PerPkg": "1", "PortMask": "0x000", @@ -4870,7 +4870,7 @@ }, { "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_CXL_ACC_LOCAL", - "EventCode": "0x35", + "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_CXL_ACC_LOCAL", "PerPkg": "1", "PortMask": "0x000", @@ -4924,7 +4924,7 @@ }, { "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_CXL_ACC_LOCAL", - "EventCode": "0x35", + "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_CXL_ACC_LOCAL", "PerPkg": "1", "PortMask": "0x000", @@ -4942,7 +4942,7 @@ }, { "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF_CXL_ACC_LOCAL", - "EventCode": "0x35", + "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF_CXL_ACC_LOCAL", "PerPkg": "1", "PortMask": "0x000", @@ -4977,7 +4977,7 @@ }, { "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_CXL_ACC_LOCAL", - "EventCode": "0x35", + "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_PREF_CXL_ACC_LOCAL", "PerPkg": "1", "PortMask": "0x000", @@ -5128,7 +5128,7 @@ }, { "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA_CXL_ACC_LOCAL", - "EventCode": "0x35", + "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFDATA_CXL_ACC_LOCAL", "PerPkg": "1", "PortMask": "0x000", @@ -5154,7 +5154,7 @@ }, { "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO_CXL_ACC_LOCAL", - "EventCode": "0x35", + "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_LLCPREFRFO_CXL_ACC_LOCAL", "PerPkg": "1", "PortMask": "0x000", @@ -5260,7 +5260,7 @@ }, { "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_CXL_ACC_LOCAL", - "EventCode": "0x35", + "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_CXL_ACC_LOCAL", "PerPkg": "1", "PortMask": "0x000", @@ -5295,7 +5295,7 @@ }, { "BriefDescription": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_CXL_ACC_LOCAL", - "EventCode": "0x35", + "EventCode": "0x36", "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_RFO_PREF_CXL_ACC_LOCAL", "PerPkg": "1", "PortMask": "0x000", diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json index 2795a404bb58..faa615c57893 100644 --- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json @@ -1473,7 +1473,7 @@ }, { "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", - "MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)", + "MetricExpr": "(cycles\\-t / el\\-start if has_event(el\\-start) else 0)", "MetricGroup": "transaction", "MetricName": "tsx_cycles_per_elision", "ScaleUnit": "1cycles / elision" diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index fa4209809c57..4a8f8eeb7525 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -1781,7 +1781,7 @@ }, { "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", - "MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)", + "MetricExpr": "(cycles\\-t / el\\-start if has_event(el\\-start) else 0)", "MetricGroup": "transaction", "MetricName": "tsx_cycles_per_elision", "ScaleUnit": "1cycles / elision" diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json index fab084e1bc69..f11860f39c18 100644 --- a/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json +++ b/tools/perf/pmu-events/arch/x86/tigerlake/tgl-metrics.json @@ -63,6 +63,12 @@ "ScaleUnit": "100%" }, { + "BriefDescription": "Uncore frequency per die [GHZ]", + "MetricExpr": "tma_info_system_socket_clks / #num_dies / duration_time / 1e9", + "MetricGroup": "SoC", + "MetricName": "UNCORE_FREQ" + }, + { "BriefDescription": "Percentage of cycles spent in System Management Interrupts.", "MetricExpr": "((msr@aperf@ - cycles) / msr@aperf@ if msr@smi@ > 0 else 0)", "MetricGroup": "smi", @@ -1027,6 +1033,12 @@ "MetricName": "tma_info_system_smt_2t_utilization" }, { + "BriefDescription": "Socket actual clocks when any core is active on that socket", + "MetricExpr": "UNC_CLOCK.SOCKET", + "MetricGroup": "SoC", + "MetricName": "tma_info_system_socket_clks" + }, + { "BriefDescription": "Average Frequency Utilization relative nominal frequency", "MetricExpr": "tma_info_thread_clks / CPU_CLK_UNHALTED.REF_TSC", "MetricGroup": "Power", @@ -1539,7 +1551,7 @@ }, { "BriefDescription": "Number of cycles within a transaction divided by the number of elisions.", - "MetricExpr": "(cycles\\-t / el\\-start if has_event(cycles\\-t) else 0)", + "MetricExpr": "(cycles\\-t / el\\-start if has_event(el\\-start) else 0)", "MetricGroup": "transaction", "MetricName": "tsx_cycles_per_elision", "ScaleUnit": "1cycles / elision" diff --git a/tools/perf/pmu-events/arch/x86/westmereep-dp/floating-point.json b/tools/perf/pmu-events/arch/x86/westmereep-dp/floating-point.json index c03f8990fa82..196ae1d9b157 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-dp/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-dp/floating-point.json @@ -8,7 +8,7 @@ "UMask": "0x1" }, { - "BriefDescription": "X87 Floating poiint assists for invalid input value (Precise Event)", + "BriefDescription": "X87 Floating point assists for invalid input value (Precise Event)", "EventCode": "0xF7", "EventName": "FP_ASSIST.INPUT", "PEBS": "1", diff --git a/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json b/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json index e00c301640f3..d025e2c0cf1c 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-sp/cache.json @@ -182,7 +182,7 @@ "UMask": "0x20" }, { - "BriefDescription": "L2 lines alloacated", + "BriefDescription": "L2 lines allocated", "EventCode": "0xF1", "EventName": "L2_LINES_IN.ANY", "SampleAfterValue": "100000", diff --git a/tools/perf/pmu-events/arch/x86/westmereep-sp/floating-point.json b/tools/perf/pmu-events/arch/x86/westmereep-sp/floating-point.json index c03f8990fa82..196ae1d9b157 100644 --- a/tools/perf/pmu-events/arch/x86/westmereep-sp/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/westmereep-sp/floating-point.json @@ -8,7 +8,7 @@ "UMask": "0x1" }, { - "BriefDescription": "X87 Floating poiint assists for invalid input value (Precise Event)", + "BriefDescription": "X87 Floating point assists for invalid input value (Precise Event)", "EventCode": "0xF7", "EventName": "FP_ASSIST.INPUT", "PEBS": "1", diff --git a/tools/perf/pmu-events/arch/x86/westmereex/cache.json b/tools/perf/pmu-events/arch/x86/westmereex/cache.json index 6c7c52733dda..18d61d43e4c9 100644 --- a/tools/perf/pmu-events/arch/x86/westmereex/cache.json +++ b/tools/perf/pmu-events/arch/x86/westmereex/cache.json @@ -182,7 +182,7 @@ "UMask": "0x20" }, { - "BriefDescription": "L2 lines alloacated", + "BriefDescription": "L2 lines allocated", "EventCode": "0xF1", "EventName": "L2_LINES_IN.ANY", "SampleAfterValue": "100000", diff --git a/tools/perf/pmu-events/arch/x86/westmereex/floating-point.json b/tools/perf/pmu-events/arch/x86/westmereex/floating-point.json index c03f8990fa82..196ae1d9b157 100644 --- a/tools/perf/pmu-events/arch/x86/westmereex/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/westmereex/floating-point.json @@ -8,7 +8,7 @@ "UMask": "0x1" }, { - "BriefDescription": "X87 Floating poiint assists for invalid input value (Precise Event)", + "BriefDescription": "X87 Floating point assists for invalid input value (Precise Event)", "EventCode": "0xF7", "EventName": "FP_ASSIST.INPUT", "PEBS": "1", diff --git a/tools/perf/pmu-events/arch/x86/westmereex/pipeline.json b/tools/perf/pmu-events/arch/x86/westmereex/pipeline.json index 1c61d18a4b5f..026236558d05 100644 --- a/tools/perf/pmu-events/arch/x86/westmereex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/westmereex/pipeline.json @@ -45,7 +45,7 @@ "UMask": "0x1" }, { - "BriefDescription": "Early Branch Prediciton Unit clears", + "BriefDescription": "Early Branch Prediction Unit clears", "EventCode": "0xE8", "EventName": "BPU_CLEARS.EARLY", "SampleAfterValue": "2000000", diff --git a/tools/perf/pmu-events/empty-pmu-events.c b/tools/perf/pmu-events/empty-pmu-events.c index 12bd043a05e3..13727421d424 100644 --- a/tools/perf/pmu-events/empty-pmu-events.c +++ b/tools/perf/pmu-events/empty-pmu-events.c @@ -245,6 +245,14 @@ static const struct pmu_event pmu_events__test_soc_sys[] = { .pmu = "uncore_sys_ccn_pmu", }, { + .name = "sys_cmn_pmu.hnf_cache_miss", + .event = "eventid=0x1,type=0x5", + .desc = "Counts total cache misses in first lookup result (high priority). Unit: uncore_sys_cmn_pmu ", + .compat = "(434|436|43c|43a).*", + .topic = "uncore", + .pmu = "uncore_sys_cmn_pmu", + }, + { .name = 0, .event = 0, .desc = 0, diff --git a/tools/perf/pmu-events/jevents.py b/tools/perf/pmu-events/jevents.py index 72ba4a9239c6..3c091ab75305 100755 --- a/tools/perf/pmu-events/jevents.py +++ b/tools/perf/pmu-events/jevents.py @@ -289,6 +289,7 @@ class JsonEvent: 'cpu_core': 'cpu_core', 'cpu_atom': 'cpu_atom', 'ali_drw': 'ali_drw', + 'arm_cmn': 'arm_cmn', } return table[unit] if unit in table else f'uncore_{unit.lower()}' @@ -298,6 +299,7 @@ class JsonEvent: if 'ExtSel' in jd: eventcode |= int(jd['ExtSel']) << 8 configcode = int(jd['ConfigCode'], 0) if 'ConfigCode' in jd else None + eventidcode = int(jd['EventidCode'], 0) if 'EventidCode' in jd else None self.name = jd['EventName'].lower() if 'EventName' in jd else None self.topic = '' self.compat = jd.get('Compat') @@ -335,7 +337,13 @@ class JsonEvent: if precise and self.desc and '(Precise Event)' not in self.desc: extra_desc += ' (Must be precise)' if precise == '2' else (' (Precise ' 'event)') - event = f'config={llx(configcode)}' if configcode is not None else f'event={llx(eventcode)}' + event = None + if configcode is not None: + event = f'config={llx(configcode)}' + elif eventidcode is not None: + event = f'eventid={llx(eventidcode)}' + else: + event = f'event={llx(eventcode)}' event_fields = [ ('AnyThread', 'any='), ('PortMask', 'ch_mask='), @@ -345,6 +353,7 @@ class JsonEvent: ('Invert', 'inv='), ('SampleAfterValue', 'period='), ('UMask', 'umask='), + ('NodeType', 'type='), ] for key, value in event_fields: if key in jd and jd[key] != '0': @@ -764,8 +773,8 @@ static const struct pmu_sys_events pmu_sys_event_tables[] = { continue _args.output_file.write(f"""\t{{ \t\t.metric_table = {{ -\t\t\t.entries = {tblname}, -\t\t\t.length = ARRAY_SIZE({tblname}) +\t\t\t.pmus = {tblname}, +\t\t\t.num_pmus = ARRAY_SIZE({tblname}) \t\t}}, \t\t.name = \"{tblname}\", \t}}, @@ -967,68 +976,99 @@ int pmu_metrics_table__for_each_metric(const struct pmu_metrics_table *table, return 0; } -const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) +static const struct pmu_events_map *map_for_pmu(struct perf_pmu *pmu) { - const struct pmu_events_table *table = NULL; - char *cpuid = perf_pmu__getcpuid(pmu); + static struct { + const struct pmu_events_map *map; + struct perf_pmu *pmu; + } last_result; + static struct { + const struct pmu_events_map *map; + char *cpuid; + } last_map_search; + static bool has_last_result, has_last_map_search; + const struct pmu_events_map *map = NULL; + char *cpuid = NULL; size_t i; - /* on some platforms which uses cpus map, cpuid can be NULL for + if (has_last_result && last_result.pmu == pmu) + return last_result.map; + + cpuid = perf_pmu__getcpuid(pmu); + + /* + * On some platforms which uses cpus map, cpuid can be NULL for * PMUs other than CORE PMUs. */ if (!cpuid) - return NULL; + goto out_update_last_result; + + if (has_last_map_search && !strcmp(last_map_search.cpuid, cpuid)) { + map = last_map_search.map; + free(cpuid); + } else { + i = 0; + for (;;) { + map = &pmu_events_map[i++]; + + if (!map->arch) { + map = NULL; + break; + } + + if (!strcmp_cpuid_str(map->cpuid, cpuid)) + break; + } + free(last_map_search.cpuid); + last_map_search.cpuid = cpuid; + last_map_search.map = map; + has_last_map_search = true; + } +out_update_last_result: + last_result.pmu = pmu; + last_result.map = map; + has_last_result = true; + return map; +} - i = 0; - for (;;) { - const struct pmu_events_map *map = &pmu_events_map[i++]; - if (!map->arch) - break; +const struct pmu_events_table *perf_pmu__find_events_table(struct perf_pmu *pmu) +{ + const struct pmu_events_map *map = map_for_pmu(pmu); - if (!strcmp_cpuid_str(map->cpuid, cpuid)) { - table = &map->event_table; - break; - } - } - free(cpuid); - if (!pmu || !table) - return table; + if (!map) + return NULL; - for (i = 0; i < table->num_pmus; i++) { - const struct pmu_table_entry *table_pmu = &table->pmus[i]; + if (!pmu) + return &map->event_table; + + for (size_t i = 0; i < map->event_table.num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &map->event_table.pmus[i]; const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; if (pmu__name_match(pmu, pmu_name)) - return table; + return &map->event_table; } return NULL; } const struct pmu_metrics_table *perf_pmu__find_metrics_table(struct perf_pmu *pmu) { - const struct pmu_metrics_table *table = NULL; - char *cpuid = perf_pmu__getcpuid(pmu); - int i; + const struct pmu_events_map *map = map_for_pmu(pmu); - /* on some platforms which uses cpus map, cpuid can be NULL for - * PMUs other than CORE PMUs. - */ - if (!cpuid) + if (!map) return NULL; - i = 0; - for (;;) { - const struct pmu_events_map *map = &pmu_events_map[i++]; - if (!map->arch) - break; + if (!pmu) + return &map->metric_table; - if (!strcmp_cpuid_str(map->cpuid, cpuid)) { - table = &map->metric_table; - break; - } + for (size_t i = 0; i < map->metric_table.num_pmus; i++) { + const struct pmu_table_entry *table_pmu = &map->metric_table.pmus[i]; + const char *pmu_name = &big_c_string[table_pmu->pmu_name.offset]; + + if (pmu__name_match(pmu, pmu_name)) + return &map->metric_table; } - free(cpuid); - return table; + return NULL; } const struct pmu_events_table *find_core_events_table(const char *arch, const char *cpuid) diff --git a/tools/perf/pmu-events/metric.py b/tools/perf/pmu-events/metric.py index 3e673f25d5fd..92acd89ed97a 100644 --- a/tools/perf/pmu-events/metric.py +++ b/tools/perf/pmu-events/metric.py @@ -558,8 +558,7 @@ def ParsePerfJson(orig: str) -> Expression: # Convert accidentally converted scientific notation constants back py = re.sub(r'([0-9]+)Event\(r"(e[0-9]+)"\)', r'\1\2', py) # Convert all the known keywords back from events to just the keyword - keywords = ['if', 'else', 'min', 'max', 'd_ratio', 'source_count', 'has_event', 'strcmp_cpuid_str', - 'cpuid_not_more_than'] + keywords = ['if', 'else', 'min', 'max', 'd_ratio', 'source_count', 'has_event', 'strcmp_cpuid_str'] for kw in keywords: py = re.sub(rf'Event\(r"{kw}"\)', kw, py) try: diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build index 63d5e6d5f165..2b45ffa462a6 100644 --- a/tools/perf/tests/Build +++ b/tools/perf/tests/Build @@ -66,6 +66,7 @@ perf-y += dlfilter-test.o perf-y += sigtrap.o perf-y += event_groups.o perf-y += symbols.o +perf-y += util.o ifeq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc)) perf-$(CONFIG_DWARF_UNWIND) += dwarf-unwind.o diff --git a/tools/perf/tests/attr/system-wide-dummy b/tools/perf/tests/attr/system-wide-dummy index 2f3e3eb728eb..a1e1d6a263bf 100644 --- a/tools/perf/tests/attr/system-wide-dummy +++ b/tools/perf/tests/attr/system-wide-dummy @@ -9,8 +9,10 @@ flags=8 type=1 size=136 config=9 -sample_period=4000 -sample_type=455 +sample_period=1 +# PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME | +# PERF_SAMPLE_CPU | PERF_SAMPLE_IDENTIFIER +sample_type=65671 read_format=4|20 # Event will be enabled right away. disabled=0 @@ -18,12 +20,12 @@ inherit=1 pinned=0 exclusive=0 exclude_user=0 -exclude_kernel=0 -exclude_hv=0 +exclude_kernel=1 +exclude_hv=1 exclude_idle=0 mmap=1 comm=1 -freq=1 +freq=0 inherit_stat=0 enable_on_exec=0 task=1 @@ -32,7 +34,7 @@ precise_ip=0 mmap_data=0 sample_id_all=1 exclude_host=0 -exclude_guest=0 +exclude_guest=1 exclude_callchain_kernel=0 exclude_callchain_user=0 mmap2=1 diff --git a/tools/perf/tests/attr/test-record-C0 b/tools/perf/tests/attr/test-record-C0 index 317730b906dd..198e8429a1bf 100644 --- a/tools/perf/tests/attr/test-record-C0 +++ b/tools/perf/tests/attr/test-record-C0 @@ -10,9 +10,9 @@ cpu=0 enable_on_exec=0 # PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME | -# PERF_SAMPLE_ID | PERF_SAMPLE_PERIOD +# PERF_SAMPLE_PERIOD | PERF_SAMPLE_IDENTIFIER # + PERF_SAMPLE_CPU added by -C 0 -sample_type=455 +sample_type=65927 # Dummy event handles mmaps, comm and task. mmap=0 diff --git a/tools/perf/tests/attr/test-record-dummy-C0 b/tools/perf/tests/attr/test-record-dummy-C0 new file mode 100644 index 000000000000..576ec48b3aaf --- /dev/null +++ b/tools/perf/tests/attr/test-record-dummy-C0 @@ -0,0 +1,55 @@ +[config] +command = record +args = --no-bpf-event -e dummy -C 0 kill >/dev/null 2>&1 +ret = 1 + +[event] +fd=1 +group_fd=-1 +cpu=0 +pid=-1 +flags=8 +type=1 +size=136 +config=9 +sample_period=4000 +# PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_TIME | +# PERF_SAMPLE_PERIOD +# + PERF_SAMPLE_CPU added by -C 0 +sample_type=391 +read_format=4|20 +disabled=0 +inherit=1 +pinned=0 +exclusive=0 +exclude_user=0 +exclude_kernel=0 +exclude_hv=0 +exclude_idle=0 +mmap=1 +comm=1 +freq=1 +inherit_stat=0 +enable_on_exec=0 +task=1 +watermark=0 +precise_ip=0 +mmap_data=0 +sample_id_all=1 +exclude_host=0 +exclude_guest=1 +exclude_callchain_kernel=0 +exclude_callchain_user=0 +mmap2=1 +comm_exec=1 +context_switch=0 +write_backward=0 +namespaces=0 +use_clockid=0 +wakeup_events=0 +bp_type=0 +config1=0 +config2=0 +branch_sample_type=0 +sample_regs_user=0 +sample_stack_user=0 diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c index 0ad18cf6dd22..cb6f1dd00dc4 100644 --- a/tools/perf/tests/builtin-test.c +++ b/tools/perf/tests/builtin-test.c @@ -123,6 +123,7 @@ static struct test_suite *generic_tests[] = { &suite__sigtrap, &suite__event_groups, &suite__symbols, + &suite__util, NULL, }; diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c index ed3815163d1b..3af81012014e 100644 --- a/tools/perf/tests/code-reading.c +++ b/tools/perf/tests/code-reading.c @@ -269,6 +269,16 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode, if (addr + len > map__end(al.map)) len = map__end(al.map) - addr; + /* + * Some architectures (ex: powerpc) have stubs (trampolines) in kernel + * modules to manage long jumps. Check if the ip offset falls in stubs + * sections for kernel modules. And skip module address after text end + */ + if (dso->is_kmod && al.addr > dso->text_end) { + pr_debug("skipping the module address %#"PRIx64" after text end\n", al.addr); + goto out; + } + /* Read the object code using perf */ ret_len = dso__data_read_offset(dso, maps__machine(thread__maps(thread)), al.addr, buf1, len); diff --git a/tools/perf/tests/expr.c b/tools/perf/tests/expr.c index 81229fa4f1e9..e3aa9d4fcf3a 100644 --- a/tools/perf/tests/expr.c +++ b/tools/perf/tests/expr.c @@ -9,6 +9,7 @@ #include <math.h> #include <stdlib.h> #include <string.h> +#include <string2.h> #include <linux/zalloc.h> static int test_ids_union(void) @@ -74,10 +75,13 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u int ret; struct expr_parse_ctx *ctx; bool is_intel = false; - char buf[128]; + char strcmp_cpuid_buf[256]; + struct perf_pmu *pmu = perf_pmus__find_core_pmu(); + char *cpuid = perf_pmu__getcpuid(pmu); + char *escaped_cpuid1, *escaped_cpuid2; - if (!get_cpuid(buf, sizeof(buf))) - is_intel = strstr(buf, "Intel") != NULL; + TEST_ASSERT_VAL("get_cpuid", cpuid); + is_intel = strstr(cpuid, "Intel") != NULL; TEST_ASSERT_EQUAL("ids_union", test_ids_union(), 0); @@ -257,13 +261,32 @@ static int test__expr(struct test_suite *t __maybe_unused, int subtest __maybe_u TEST_ASSERT_VAL("source count", hashmap__size(ctx->ids) == 1); TEST_ASSERT_VAL("source count", hashmap__find(ctx->ids, "EVENT1", &val_ptr)); + + /* Test no cpuid match */ + ret = test(ctx, "strcmp_cpuid_str(0x0)", 0); + + /* + * Test cpuid match with current cpuid. Special chars have to be + * escaped. + */ + escaped_cpuid1 = strreplace_chars('-', cpuid, "\\-"); + free(cpuid); + escaped_cpuid2 = strreplace_chars(',', escaped_cpuid1, "\\,"); + free(escaped_cpuid1); + escaped_cpuid1 = strreplace_chars('=', escaped_cpuid2, "\\="); + free(escaped_cpuid2); + scnprintf(strcmp_cpuid_buf, sizeof(strcmp_cpuid_buf), + "strcmp_cpuid_str(%s)", escaped_cpuid1); + free(escaped_cpuid1); + ret |= test(ctx, strcmp_cpuid_buf, 1); + /* has_event returns 1 when an event exists. */ expr__add_id_val(ctx, strdup("cycles"), 2); - ret = test(ctx, "has_event(cycles)", 1); + ret |= test(ctx, "has_event(cycles)", 1); expr__ctx_free(ctx); - return 0; + return ret; } DEFINE_SUITE("Simple expression parser", expr); diff --git a/tools/perf/tests/hists_link.c b/tools/perf/tests/hists_link.c index 2d19657ab5e0..5b6f1e883466 100644 --- a/tools/perf/tests/hists_link.c +++ b/tools/perf/tests/hists_link.c @@ -148,8 +148,8 @@ static int find_sample(struct sample *samples, size_t nr_samples, struct thread *t, struct map *m, struct symbol *s) { while (nr_samples--) { - if (RC_CHK_ACCESS(samples->thread) == RC_CHK_ACCESS(t) && - RC_CHK_ACCESS(samples->map) == RC_CHK_ACCESS(m) && + if (RC_CHK_EQUAL(samples->thread, t) && + RC_CHK_EQUAL(samples->map, m) && samples->sym == s) return 1; samples++; diff --git a/tools/perf/tests/make b/tools/perf/tests/make index ea4c341f5af1..d9945ed25bc5 100644 --- a/tools/perf/tests/make +++ b/tools/perf/tests/make @@ -70,8 +70,8 @@ make_python_perf_so := $(python_perf_so) make_debug := DEBUG=1 make_nondistro := BUILD_NONDISTRO=1 make_extra_tests := EXTRA_TESTS=1 -make_bpf_skel := BUILD_BPF_SKEL=1 -make_gen_vmlinux_h := BUILD_BPF_SKEL=1 GEN_VMLINUX_H=1 +make_no_bpf_skel := BUILD_BPF_SKEL=0 +make_gen_vmlinux_h := GEN_VMLINUX_H=1 make_no_libperl := NO_LIBPERL=1 make_no_libpython := NO_LIBPYTHON=1 make_no_scripts := NO_LIBPYTHON=1 NO_LIBPERL=1 @@ -138,7 +138,8 @@ endif run += make_python_perf_so run += make_debug run += make_nondistro -run += make_build_bpf_skel +run += make_extra_tests +run += make_no_bpf_skel run += make_gen_vmlinux_h run += make_no_libperl run += make_no_libpython diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c index d47f1f871164..f78be21a5999 100644 --- a/tools/perf/tests/parse-events.c +++ b/tools/perf/tests/parse-events.c @@ -771,12 +771,12 @@ static int test__checkevent_pmu_events_mix(struct evlist *evlist) return TEST_OK; } -static int test__checkterms_simple(struct list_head *terms) +static int test__checkterms_simple(struct parse_events_terms *terms) { struct parse_events_term *term; /* config=10 */ - term = list_entry(terms->next, struct parse_events_term, list); + term = list_entry(terms->terms.next, struct parse_events_term, list); TEST_ASSERT_VAL("wrong type term", term->type_term == PARSE_EVENTS__TERM_TYPE_CONFIG); TEST_ASSERT_VAL("wrong type val", @@ -2363,7 +2363,7 @@ static const struct evlist_test test__events_pmu[] = { struct terms_test { const char *str; - int (*check)(struct list_head *terms); + int (*check)(struct parse_events_terms *terms); }; static const struct terms_test test__terms[] = { @@ -2467,11 +2467,11 @@ static int test__events2(struct test_suite *test __maybe_unused, int subtest __m static int test_term(const struct terms_test *t) { - struct list_head terms; + struct parse_events_terms terms; int ret; - INIT_LIST_HEAD(&terms); + parse_events_terms__init(&terms); ret = parse_events_terms(&terms, t->str, /*input=*/ NULL); if (ret) { pr_debug("failed to parse terms '%s', err %d\n", @@ -2480,7 +2480,7 @@ static int test_term(const struct terms_test *t) } ret = t->check(&terms); - parse_events_terms__purge(&terms); + parse_events_terms__exit(&terms); return ret; } @@ -2514,9 +2514,14 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest while ((pmu = perf_pmus__scan(pmu)) != NULL) { struct stat st; char path[PATH_MAX]; + char pmu_event[PATH_MAX]; + char *buf = NULL; + FILE *file; struct dirent *ent; + size_t len = 0; DIR *dir; int err; + int n; snprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/events/", sysfs__mountpoint(), pmu->name); @@ -2538,11 +2543,45 @@ static int test__pmu_events(struct test_suite *test __maybe_unused, int subtest struct evlist_test e = { .name = NULL, }; char name[2 * NAME_MAX + 1 + 12 + 3]; int test_ret; + bool is_event_parameterized = 0; /* Names containing . are special and cannot be used directly */ if (strchr(ent->d_name, '.')) continue; + /* exclude parametrized ones (name contains '?') */ + n = snprintf(pmu_event, sizeof(pmu_event), "%s%s", path, ent->d_name); + if (n >= PATH_MAX) { + pr_err("pmu event name crossed PATH_MAX(%d) size\n", PATH_MAX); + continue; + } + + file = fopen(pmu_event, "r"); + if (!file) { + pr_debug("can't open pmu event file for '%s'\n", ent->d_name); + ret = combine_test_results(ret, TEST_FAIL); + continue; + } + + if (getline(&buf, &len, file) < 0) { + pr_debug(" pmu event: %s is a null event\n", ent->d_name); + ret = combine_test_results(ret, TEST_FAIL); + fclose(file); + continue; + } + + if (strchr(buf, '?')) + is_event_parameterized = 1; + + free(buf); + buf = NULL; + fclose(file); + + if (is_event_parameterized == 1) { + pr_debug("skipping parametrized PMU event: %s which contains ?\n", pmu_event); + continue; + } + snprintf(name, sizeof(name), "%s/event=%s/u", pmu->name, ent->d_name); e.name = name; diff --git a/tools/perf/tests/pmu-events.c b/tools/perf/tests/pmu-events.c index f5321fbdee79..a56d32905743 100644 --- a/tools/perf/tests/pmu-events.c +++ b/tools/perf/tests/pmu-events.c @@ -245,7 +245,7 @@ static const struct perf_pmu_test_event sys_ddr_pmu_write_cycles = { }, .alias_str = "event=0x2b", .alias_long_desc = "ddr write-cycles event", - .matching_pmu = "uncore_sys_ddr_pmu", + .matching_pmu = "uncore_sys_ddr_pmu0", }; static const struct perf_pmu_test_event sys_ccn_pmu_read_cycles = { @@ -259,12 +259,27 @@ static const struct perf_pmu_test_event sys_ccn_pmu_read_cycles = { }, .alias_str = "config=0x2c", .alias_long_desc = "ccn read-cycles event", - .matching_pmu = "uncore_sys_ccn_pmu", + .matching_pmu = "uncore_sys_ccn_pmu4", +}; + +static const struct perf_pmu_test_event sys_cmn_pmu_hnf_cache_miss = { + .event = { + .name = "sys_cmn_pmu.hnf_cache_miss", + .event = "eventid=0x1,type=0x5", + .desc = "Counts total cache misses in first lookup result (high priority)", + .topic = "uncore", + .pmu = "uncore_sys_cmn_pmu", + .compat = "(434|436|43c|43a).*", + }, + .alias_str = "eventid=0x1,type=0x5", + .alias_long_desc = "Counts total cache misses in first lookup result (high priority)", + .matching_pmu = "uncore_sys_cmn_pmu0", }; static const struct perf_pmu_test_event *sys_events[] = { &sys_ddr_pmu_write_cycles, &sys_ccn_pmu_read_cycles, + &sys_cmn_pmu_hnf_cache_miss, NULL }; @@ -615,6 +630,12 @@ static int __test_uncore_pmu_event_aliases(struct perf_pmu_test_pmu *test_pmu) .count = &matched_count, }; + if (strcmp(pmu_name, test_event.matching_pmu)) { + pr_debug("testing aliases uncore PMU %s: mismatched matching_pmu, %s vs %s\n", + pmu_name, test_event.matching_pmu, pmu_name); + return -1; + } + err = perf_pmu__find_event(pmu, event->name, &args, test_core_pmu_event_aliases_cb); if (err) { @@ -701,6 +722,46 @@ static struct perf_pmu_test_pmu test_pmus[] = { &sys_ccn_pmu_read_cycles, }, }, + { + .pmu = { + .name = (char *)"uncore_sys_cmn_pmu0", + .is_uncore = 1, + .id = (char *)"43401", + }, + .aliases = { + &sys_cmn_pmu_hnf_cache_miss, + }, + }, + { + .pmu = { + .name = (char *)"uncore_sys_cmn_pmu0", + .is_uncore = 1, + .id = (char *)"43602", + }, + .aliases = { + &sys_cmn_pmu_hnf_cache_miss, + }, + }, + { + .pmu = { + .name = (char *)"uncore_sys_cmn_pmu0", + .is_uncore = 1, + .id = (char *)"43c03", + }, + .aliases = { + &sys_cmn_pmu_hnf_cache_miss, + }, + }, + { + .pmu = { + .name = (char *)"uncore_sys_cmn_pmu0", + .is_uncore = 1, + .id = (char *)"43a01", + }, + .aliases = { + &sys_cmn_pmu_hnf_cache_miss, + }, + } }; /* Test that aliases generated are as expected */ diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c index eb60e5f66859..8f18127d876a 100644 --- a/tools/perf/tests/pmu.c +++ b/tools/perf/tests/pmu.c @@ -128,30 +128,35 @@ static int test_format_dir_put(char *dir) return system(buf); } -static struct list_head *test_terms_list(void) +static void add_test_terms(struct parse_events_terms *terms) { - static LIST_HEAD(terms); unsigned int i; - for (i = 0; i < ARRAY_SIZE(test_terms); i++) - list_add_tail(&test_terms[i].list, &terms); + for (i = 0; i < ARRAY_SIZE(test_terms); i++) { + struct parse_events_term *clone; - return &terms; + parse_events_term__clone(&clone, &test_terms[i]); + list_add_tail(&clone->list, &terms->terms); + } } static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe_unused) { char dir[PATH_MAX]; char *format; - struct list_head *terms = test_terms_list(); + struct parse_events_terms terms; struct perf_event_attr attr; struct perf_pmu *pmu; int fd; int ret; + parse_events_terms__init(&terms); + add_test_terms(&terms); pmu = zalloc(sizeof(*pmu)); - if (!pmu) + if (!pmu) { + parse_events_terms__exit(&terms); return -ENOMEM; + } INIT_LIST_HEAD(&pmu->format); INIT_LIST_HEAD(&pmu->aliases); @@ -159,6 +164,7 @@ static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe format = test_format_dir_get(dir, sizeof(dir)); if (!format) { free(pmu); + parse_events_terms__exit(&terms); return -EINVAL; } @@ -175,7 +181,7 @@ static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe if (ret) goto out; - ret = perf_pmu__config_terms(pmu, &attr, terms, /*zero=*/false, /*err=*/NULL); + ret = perf_pmu__config_terms(pmu, &attr, &terms, /*zero=*/false, /*err=*/NULL); if (ret) goto out; @@ -191,6 +197,7 @@ static int test__pmu(struct test_suite *test __maybe_unused, int subtest __maybe out: test_format_dir_put(format); perf_pmu__delete(pmu); + parse_events_terms__exit(&terms); return ret; } diff --git a/tools/perf/tests/shell/coresight/asm_pure_loop.sh b/tools/perf/tests/shell/coresight/asm_pure_loop.sh index 779bc8608e1e..2d65defb7e0f 100755 --- a/tools/perf/tests/shell/coresight/asm_pure_loop.sh +++ b/tools/perf/tests/shell/coresight/asm_pure_loop.sh @@ -5,9 +5,13 @@ # Carsten Haitzler <carsten.haitzler@arm.com>, 2021 TEST="asm_pure_loop" + +# shellcheck source=../lib/coresight.sh . "$(dirname $0)"/../lib/coresight.sh + ARGS="" DATV="out" +# shellcheck disable=SC2153 DATA="$DATD/perf-$TEST-$DATV.data" perf record $PERFRECOPT -o "$DATA" "$BIN" $ARGS diff --git a/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh b/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh index 08a44e52ce9b..ddcc9bb850f5 100755 --- a/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh +++ b/tools/perf/tests/shell/coresight/memcpy_thread_16k_10.sh @@ -5,9 +5,13 @@ # Carsten Haitzler <carsten.haitzler@arm.com>, 2021 TEST="memcpy_thread" + +# shellcheck source=../lib/coresight.sh . "$(dirname $0)"/../lib/coresight.sh + ARGS="16 10 1" DATV="16k_10" +# shellcheck disable=SC2153 DATA="$DATD/perf-$TEST-$DATV.data" perf record $PERFRECOPT -o "$DATA" "$BIN" $ARGS diff --git a/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh b/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh index c83a200dede4..2ce5e139b2fd 100755 --- a/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh +++ b/tools/perf/tests/shell/coresight/thread_loop_check_tid_10.sh @@ -5,9 +5,13 @@ # Carsten Haitzler <carsten.haitzler@arm.com>, 2021 TEST="thread_loop" + +# shellcheck source=../lib/coresight.sh . "$(dirname $0)"/../lib/coresight.sh + ARGS="10 1" DATV="check-tid-10th" +# shellcheck disable=SC2153 DATA="$DATD/perf-$TEST-$DATV.data" STDO="$DATD/perf-$TEST-$DATV.stdout" diff --git a/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh b/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh index 6346fd5e87c8..3ad9498753d7 100755 --- a/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh +++ b/tools/perf/tests/shell/coresight/thread_loop_check_tid_2.sh @@ -5,9 +5,13 @@ # Carsten Haitzler <carsten.haitzler@arm.com>, 2021 TEST="thread_loop" + +# shellcheck source=../lib/coresight.sh . "$(dirname $0)"/../lib/coresight.sh + ARGS="2 20" DATV="check-tid-2th" +# shellcheck disable=SC2153 DATA="$DATD/perf-$TEST-$DATV.data" STDO="$DATD/perf-$TEST-$DATV.stdout" diff --git a/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh b/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh index 7304e3d3a6ff..4fbb4a29aad3 100755 --- a/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh +++ b/tools/perf/tests/shell/coresight/unroll_loop_thread_10.sh @@ -5,9 +5,13 @@ # Carsten Haitzler <carsten.haitzler@arm.com>, 2021 TEST="unroll_loop_thread" + +# shellcheck source=../lib/coresight.sh . "$(dirname $0)"/../lib/coresight.sh + ARGS="10" DATV="10" +# shellcheck disable=SC2153 DATA="$DATD/perf-$TEST-$DATV.data" perf record $PERFRECOPT -o "$DATA" "$BIN" $ARGS diff --git a/tools/perf/tests/shell/lib/coresight.sh b/tools/perf/tests/shell/lib/coresight.sh index 6c3d34ec64d8..11ed2c25ed91 100644 --- a/tools/perf/tests/shell/lib/coresight.sh +++ b/tools/perf/tests/shell/lib/coresight.sh @@ -17,6 +17,8 @@ DIR="$TOOLS/$TEST" BIN="$DIR/$TEST" # If the test tool/binary does not exist and is executable then skip the test if ! test -x "$BIN"; then exit 2; fi +# If CoreSight is not available, skip the test +perf list cs_etm | grep -q cs_etm || exit 2 DATD="." # If the data dir env is set then make the data dir use that instead of ./ if test -n "$PERF_TEST_CORESIGHT_DATADIR"; then diff --git a/tools/perf/tests/shell/lock_contention.sh b/tools/perf/tests/shell/lock_contention.sh index d120e83db7d9..c1ec5762215b 100755 --- a/tools/perf/tests/shell/lock_contention.sh +++ b/tools/perf/tests/shell/lock_contention.sh @@ -32,6 +32,13 @@ check() { err=2 exit fi + + # shellcheck disable=SC2046 + if [ `nproc` -lt 4 ]; then + echo "[Skip] Low number of CPUs (`nproc`), lock event cannot be triggered certainly" + err=2 + exit + fi } test_record() @@ -123,6 +130,24 @@ test_aggr_addr() fi } +test_aggr_cgroup() +{ + echo "Testing perf lock contention --lock-cgroup" + + if ! perf lock con -b true > /dev/null 2>&1 ; then + echo "[Skip] No BPF support" + return + fi + + # the perf lock contention output goes to the stderr + perf lock con -a -b -g -E 1 -q -- perf bench sched messaging > /dev/null 2> ${result} + if [ "$(cat "${result}" | wc -l)" != "1" ]; then + echo "[Fail] BPF result count is not 1:" "$(cat "${result}" | wc -l)" + err=1 + exit + fi +} + test_type_filter() { echo "Testing perf lock contention --type-filter (w/ spinlock)" @@ -232,6 +257,31 @@ test_aggr_task_stack_filter() exit fi } +test_cgroup_filter() +{ + echo "Testing perf lock contention --cgroup-filter" + + if ! perf lock con -b true > /dev/null 2>&1 ; then + echo "[Skip] No BPF support" + return + fi + + perf lock con -a -b -g -E 1 -F wait_total -q -- perf bench sched messaging > /dev/null 2> ${result} + if [ "$(cat "${result}" | wc -l)" != "1" ]; then + echo "[Fail] BPF result should have a cgroup result:" "$(cat "${result}")" + err=1 + exit + fi + + cgroup=$(cat "${result}" | awk '{ print $3 }') + perf lock con -a -b -g -E 1 -G "${cgroup}" -q -- perf bench sched messaging > /dev/null 2> ${result} + if [ "$(cat "${result}" | wc -l)" != "1" ]; then + echo "[Fail] BPF result should have a result with cgroup filter:" "$(cat "${cgroup}")" + err=1 + exit + fi +} + test_csv_output() { @@ -275,10 +325,12 @@ test_bpf test_record_concurrent test_aggr_task test_aggr_addr +test_aggr_cgroup test_type_filter test_lock_filter test_stack_filter test_aggr_task_stack_filter +test_cgroup_filter test_csv_output exit ${err} diff --git a/tools/perf/tests/shell/probe_vfs_getname.sh b/tools/perf/tests/shell/probe_vfs_getname.sh index 871243d6d03a..554e12e83c55 100755 --- a/tools/perf/tests/shell/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/probe_vfs_getname.sh @@ -4,10 +4,12 @@ # SPDX-License-Identifier: GPL-2.0 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 +# shellcheck source=lib/probe.sh . "$(dirname $0)"/lib/probe.sh skip_if_no_perf_probe || exit 2 +# shellcheck source=lib/probe_vfs_getname.sh . "$(dirname $0)"/lib/probe_vfs_getname.sh add_probe_vfs_getname || skip_if_no_debuginfo diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh index 89214a6d9951..eebeea6bdc76 100755 --- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh +++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh @@ -10,7 +10,9 @@ # SPDX-License-Identifier: GPL-2.0 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 +# shellcheck source=lib/probe.sh . "$(dirname "$0")/lib/probe.sh" +# shellcheck source=lib/probe_vfs_getname.sh . "$(dirname "$0")/lib/probe_vfs_getname.sh" libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g') diff --git a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh index 7f664f1889d9..5eedbe29bba1 100755 --- a/tools/perf/tests/shell/record+script_probe_vfs_getname.sh +++ b/tools/perf/tests/shell/record+script_probe_vfs_getname.sh @@ -9,10 +9,12 @@ # SPDX-License-Identifier: GPL-2.0 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 +# shellcheck source=lib/probe.sh . "$(dirname "$0")/lib/probe.sh" skip_if_no_perf_probe || exit 2 +# shellcheck source=lib/probe_vfs_getname.sh . "$(dirname "$0")/lib/probe_vfs_getname.sh" record_open_file() { diff --git a/tools/perf/tests/shell/record.sh b/tools/perf/tests/shell/record.sh index 4fbc74805d52..29443b8e8876 100755 --- a/tools/perf/tests/shell/record.sh +++ b/tools/perf/tests/shell/record.sh @@ -5,6 +5,7 @@ set -e shelldir=$(dirname "$0") +# shellcheck source=lib/waiting.sh . "${shelldir}"/lib/waiting.sh err=0 diff --git a/tools/perf/tests/shell/record_offcpu.sh b/tools/perf/tests/shell/record_offcpu.sh index a0d14cd0aa79..a1ef8f0d2b5c 100755 --- a/tools/perf/tests/shell/record_offcpu.sh +++ b/tools/perf/tests/shell/record_offcpu.sh @@ -28,7 +28,7 @@ test_offcpu_priv() { err=2 return fi - if perf record --off-cpu -o /dev/null --quiet true 2>&1 | grep BUILD_BPF_SKEL + if perf version --build-options 2>&1 | grep HAVE_BPF_SKEL | grep -q OFF then echo "off-cpu test [Skipped missing BPF support]" err=2 diff --git a/tools/perf/tests/shell/record_sideband.sh b/tools/perf/tests/shell/record_sideband.sh new file mode 100755 index 000000000000..ac70ac27d590 --- /dev/null +++ b/tools/perf/tests/shell/record_sideband.sh @@ -0,0 +1,58 @@ +#!/bin/sh +# perf record sideband tests +# SPDX-License-Identifier: GPL-2.0 + +set -e + +err=0 +perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX) + +cleanup() +{ + rm -rf ${perfdata} + trap - EXIT TERM INT +} + +trap_cleanup() +{ + cleanup + exit 1 +} +trap trap_cleanup EXIT TERM INT + +can_cpu_wide() +{ + if ! perf record -o ${perfdata} -BN --no-bpf-event -C $1 true > /dev/null 2>&1 + then + echo "record sideband test [Skipped cannot record cpu$1]" + err=2 + fi + + rm -f ${perfdata} + return $err +} + +test_system_wide_tracking() +{ + # Need CPU 0 and CPU 1 + can_cpu_wide 0 || return 0 + can_cpu_wide 1 || return 0 + + # Record on CPU 0 a task running on CPU 1 + perf record -BN --no-bpf-event -o ${perfdata} -C 0 -- taskset --cpu-list 1 true + + # Should get MMAP events from CPU 1 + mmap_cnt=`perf script -i ${perfdata} --show-mmap-events -C 1 2>/dev/null | grep MMAP | wc -l` + + if [ ${mmap_cnt} -gt 0 ] ; then + return 0 + fi + + echo "Failed to record MMAP events on CPU 1 when tracing CPU 0" + return 1 +} + +test_system_wide_tracking + +cleanup +exit $err diff --git a/tools/perf/tests/shell/stat+csv_output.sh b/tools/perf/tests/shell/stat+csv_output.sh index d890eb26e914..f1818fa6d9ce 100755 --- a/tools/perf/tests/shell/stat+csv_output.sh +++ b/tools/perf/tests/shell/stat+csv_output.sh @@ -6,6 +6,7 @@ set -e +# shellcheck source=lib/stat_output.sh . "$(dirname $0)"/lib/stat_output.sh csv_sep=@ diff --git a/tools/perf/tests/shell/stat+csv_summary.sh b/tools/perf/tests/shell/stat+csv_summary.sh index 8bae9c8a835e..323123ff4d19 100755 --- a/tools/perf/tests/shell/stat+csv_summary.sh +++ b/tools/perf/tests/shell/stat+csv_summary.sh @@ -10,7 +10,7 @@ set -e # perf stat -e cycles -x' ' -I1000 --interval-count 1 --summary 2>&1 | \ grep -e summary | \ -while read summary _num _event _run _pct +while read summary _ _ _ _ do if [ $summary != "summary" ]; then exit 1 @@ -23,7 +23,7 @@ done # perf stat -e cycles -x' ' -I1000 --interval-count 1 --summary --no-csv-summary 2>&1 | \ grep -e summary | \ -while read _num _event _run _pct +while read _ _ _ _ do exit 1 done diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh index a1918a15e36a..0c7d79a230ea 100755 --- a/tools/perf/tests/shell/stat+shadow_stat.sh +++ b/tools/perf/tests/shell/stat+shadow_stat.sh @@ -4,6 +4,8 @@ set -e +THRESHOLD=0.015 + # skip if system-wide mode is forbidden perf stat -a true > /dev/null 2>&1 || exit 2 @@ -14,7 +16,7 @@ test_global_aggr() { perf stat -a --no-big-num -e cycles,instructions sleep 1 2>&1 | \ grep -e cycles -e instructions | \ - while read num evt _hash ipc rest + while read num evt _ ipc rest do # skip not counted events if [ "$num" = "<not" ]; then @@ -33,10 +35,18 @@ test_global_aggr() fi # use printf for rounding and a leading zero - res=`printf "%.2f" "$(echo "scale=6; $num / $cyc" | bc -q)"` + res=`echo $num $cyc | awk '{printf "%.2f", $1 / $2}'` if [ "$ipc" != "$res" ]; then - echo "IPC is different: $res != $ipc ($num / $cyc)" - exit 1 + # check the difference from the real result for FP imperfections + diff=`echo $ipc $res $THRESHOLD | \ + awk '{x = ($1 - $2) < 0 ? ($2 - $1) : ($1 - $2); print (x > $3)}'` + + if [ $diff -eq 1 ]; then + echo "IPC is different: $res != $ipc ($num / $cyc)" + exit 1 + fi + + echo "Warning: Difference of IPC is under the threshold" fi done } @@ -45,7 +55,7 @@ test_no_aggr() { perf stat -a -A --no-big-num -e cycles,instructions sleep 1 2>&1 | \ grep ^CPU | \ - while read cpu num evt _hash ipc rest + while read cpu num evt _ ipc rest do # skip not counted events if [ "$num" = "<not" ]; then @@ -67,10 +77,18 @@ test_no_aggr() fi # use printf for rounding and a leading zero - res=`printf "%.2f" "$(echo "scale=6; $num / $cyc" | bc -q)"` + res=`echo $num $cyc | awk '{printf "%.2f", $1 / $2}'` if [ "$ipc" != "$res" ]; then - echo "IPC is different for $cpu: $res != $ipc ($num / $cyc)" - exit 1 + # check difference from the real result for FP imperfections + diff=`echo $ipc $res $THRESHOLD | \ + awk '{x = ($1 - $2) < 0 ? ($2 - $1) : ($1 - $2); print (x > $3)}'` + + if [ $diff -eq 1 ]; then + echo "IPC is different: $res != $ipc ($num / $cyc)" + exit 1 + fi + + echo "Warning: Difference of IPC is under the threshold" fi done } diff --git a/tools/perf/tests/shell/stat+std_output.sh b/tools/perf/tests/shell/stat+std_output.sh index fb2b10547a11..4fcdd1a9142c 100755 --- a/tools/perf/tests/shell/stat+std_output.sh +++ b/tools/perf/tests/shell/stat+std_output.sh @@ -6,6 +6,7 @@ set -e +# shellcheck source=lib/stat_output.sh . "$(dirname $0)"/lib/stat_output.sh stat_output=$(mktemp /tmp/__perf_test.stat_output.std.XXXXX) diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh index cb35e488809a..55ef9c9ded2d 100755 --- a/tools/perf/tests/shell/stat_all_metricgroups.sh +++ b/tools/perf/tests/shell/stat_all_metricgroups.sh @@ -4,9 +4,21 @@ set -e -for m in $(perf list --raw-dump metricgroups); do +ParanoidAndNotRoot() +{ + [ "$(id -u)" != 0 ] && [ "$(cat /proc/sys/kernel/perf_event_paranoid)" -gt $1 ] +} + +system_wide_flag="-a" +if ParanoidAndNotRoot 0 +then + system_wide_flag="" +fi + +for m in $(perf list --raw-dump metricgroups) +do echo "Testing $m" - perf stat -M "$m" -a true + perf stat -M "$m" $system_wide_flag sleep 0.01 done exit 0 diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index f1bf5621160f..65dd85207125 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -136,7 +136,9 @@ arm_cs_iterate_devices() { arm_cs_etm_traverse_path_test() { # Iterate for every ETM device - for dev in /sys/bus/coresight/devices/etm*; do + for dev in /sys/bus/event_source/devices/cs_etm/cpu*; do + # Canonicalize the path + dev=`readlink -f $dev` # Find the ETM device belonging to which CPU cpu=`cat $dev/cpu` diff --git a/tools/perf/tests/shell/test_intel_pt.sh b/tools/perf/tests/shell/test_intel_pt.sh index 3a8b9bffa022..723ec501f99a 100755 --- a/tools/perf/tests/shell/test_intel_pt.sh +++ b/tools/perf/tests/shell/test_intel_pt.sh @@ -8,6 +8,7 @@ set -e perf list | grep -q 'intel_pt//' || exit 2 shelldir=$(dirname "$0") +# shellcheck source=lib/waiting.sh . "${shelldir}"/lib/waiting.sh skip_cnt=0 diff --git a/tools/perf/tests/shell/trace+probe_vfs_getname.sh b/tools/perf/tests/shell/trace+probe_vfs_getname.sh index 4014487cf4d9..3146a1eece07 100755 --- a/tools/perf/tests/shell/trace+probe_vfs_getname.sh +++ b/tools/perf/tests/shell/trace+probe_vfs_getname.sh @@ -10,6 +10,7 @@ # SPDX-License-Identifier: GPL-2.0 # Arnaldo Carvalho de Melo <acme@kernel.org>, 2017 +# shellcheck source=lib/probe.sh . "$(dirname $0)"/lib/probe.sh skip_if_no_perf_probe || exit 2 diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h index f33cfc3c19a4..b394f3ac2d66 100644 --- a/tools/perf/tests/tests.h +++ b/tools/perf/tests/tests.h @@ -145,6 +145,7 @@ DECLARE_SUITE(dlfilter); DECLARE_SUITE(sigtrap); DECLARE_SUITE(event_groups); DECLARE_SUITE(symbols); +DECLARE_SUITE(util); /* * PowerPC and S390 do not support creation of instruction breakpoints using the diff --git a/tools/perf/tests/thread-maps-share.c b/tools/perf/tests/thread-maps-share.c index faf980b26252..7fa6f7c568e2 100644 --- a/tools/perf/tests/thread-maps-share.c +++ b/tools/perf/tests/thread-maps-share.c @@ -46,9 +46,9 @@ static int test__thread_maps_share(struct test_suite *test __maybe_unused, int s TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(maps)), 4); /* test the maps pointer is shared */ - TEST_ASSERT_VAL("maps don't match", RC_CHK_ACCESS(maps) == RC_CHK_ACCESS(thread__maps(t1))); - TEST_ASSERT_VAL("maps don't match", RC_CHK_ACCESS(maps) == RC_CHK_ACCESS(thread__maps(t2))); - TEST_ASSERT_VAL("maps don't match", RC_CHK_ACCESS(maps) == RC_CHK_ACCESS(thread__maps(t3))); + TEST_ASSERT_VAL("maps don't match", RC_CHK_EQUAL(maps, thread__maps(t1))); + TEST_ASSERT_VAL("maps don't match", RC_CHK_EQUAL(maps, thread__maps(t2))); + TEST_ASSERT_VAL("maps don't match", RC_CHK_EQUAL(maps, thread__maps(t3))); /* * Verify the other leader was created by previous call. @@ -73,8 +73,7 @@ static int test__thread_maps_share(struct test_suite *test __maybe_unused, int s other_maps = thread__maps(other); TEST_ASSERT_EQUAL("wrong refcnt", refcount_read(maps__refcnt(other_maps)), 2); - TEST_ASSERT_VAL("maps don't match", RC_CHK_ACCESS(other_maps) == - RC_CHK_ACCESS(thread__maps(other_leader))); + TEST_ASSERT_VAL("maps don't match", RC_CHK_EQUAL(other_maps, thread__maps(other_leader))); /* release thread group */ thread__put(t3); diff --git a/tools/perf/tests/util.c b/tools/perf/tests/util.c new file mode 100644 index 000000000000..6366db5cbf8c --- /dev/null +++ b/tools/perf/tests/util.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "tests.h" +#include "util/debug.h" + +#include <linux/compiler.h> +#include <stdlib.h> +#include <string2.h> + +static int test_strreplace(char needle, const char *haystack, + const char *replace, const char *expected) +{ + char *new = strreplace_chars(needle, haystack, replace); + int ret = strcmp(new, expected); + + free(new); + return ret == 0; +} + +static int test__util(struct test_suite *t __maybe_unused, int subtest __maybe_unused) +{ + TEST_ASSERT_VAL("empty string", test_strreplace(' ', "", "123", "")); + TEST_ASSERT_VAL("no match", test_strreplace('5', "123", "4", "123")); + TEST_ASSERT_VAL("replace 1", test_strreplace('3', "123", "4", "124")); + TEST_ASSERT_VAL("replace 2", test_strreplace('a', "abcabc", "ef", "efbcefbc")); + TEST_ASSERT_VAL("replace long", test_strreplace('a', "abcabc", "longlong", + "longlongbclonglongbc")); + + return 0; +} + +DEFINE_SUITE("util", util); diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c index 70db5a717905..f4812b226818 100644 --- a/tools/perf/ui/browsers/hists.c +++ b/tools/perf/ui/browsers/hists.c @@ -2416,12 +2416,12 @@ close_file_and_continue: struct popup_action { unsigned long time; struct thread *thread; + struct evsel *evsel; + int (*fn)(struct hist_browser *browser, struct popup_action *act); struct map_symbol ms; int socket; - struct evsel *evsel; enum rstype rstype; - int (*fn)(struct hist_browser *browser, struct popup_action *act); }; static int @@ -3302,7 +3302,7 @@ do_hotkey: // key came straight from options ui__popup_menu() &options[nr_options], &bi->to.ms, bi->to.al_addr); - } else { + } else if (browser->he_selection) { nr_options += add_annotate_opt(browser, &actions[nr_options], &options[nr_options], diff --git a/tools/perf/util/Build b/tools/perf/util/Build index 2f76230958ad..fb661c48992f 100644 --- a/tools/perf/util/Build +++ b/tools/perf/util/Build @@ -49,6 +49,7 @@ perf-y += dso.o perf-y += dsos.o perf-y += symbol.o perf-y += symbol_fprintf.o +perf-y += map_symbol.o perf-y += color.o perf-y += color_config.o perf-y += metricgroup.o @@ -165,6 +166,7 @@ endif ifeq ($(CONFIG_LIBTRACEEVENT),y) perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork.o + perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork_top.o endif perf-$(CONFIG_LIBELF) += symbol-elf.o diff --git a/tools/perf/util/arm-spe.h b/tools/perf/util/arm-spe.h index 98d3235781c3..4f4900c18f3e 100644 --- a/tools/perf/util/arm-spe.h +++ b/tools/perf/util/arm-spe.h @@ -27,5 +27,7 @@ struct auxtrace_record *arm_spe_recording_init(int *err, int arm_spe_process_auxtrace_info(union perf_event *event, struct perf_session *session); -struct perf_event_attr *arm_spe_pmu_default_config(struct perf_pmu *arm_spe_pmu); +void arm_spe_pmu_default_config(const struct perf_pmu *arm_spe_pmu, + struct perf_event_attr *attr); + #endif diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y index 5dfa948fc986..0e4d6de3c2ad 100644 --- a/tools/perf/util/bpf-filter.y +++ b/tools/perf/util/bpf-filter.y @@ -3,6 +3,10 @@ %{ +#ifndef NDEBUG +#define YYDEBUG 1 +#endif + #include <stdio.h> #include <string.h> #include <linux/compiler.h> diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c index 6732cbbcf9b3..7f9b0e46e008 100644 --- a/tools/perf/util/bpf_counter.c +++ b/tools/perf/util/bpf_counter.c @@ -104,7 +104,7 @@ static int bpf_program_profiler_load_one(struct evsel *evsel, u32 prog_id) struct bpf_prog_profiler_bpf *skel; struct bpf_counter *counter; struct bpf_program *prog; - char *prog_name; + char *prog_name = NULL; int prog_fd; int err; @@ -155,10 +155,12 @@ static int bpf_program_profiler_load_one(struct evsel *evsel, u32 prog_id) assert(skel != NULL); counter->skel = skel; list_add(&counter->list, &evsel->bpf_counter_list); + free(prog_name); close(prog_fd); return 0; err_out: bpf_prog_profiler_bpf__destroy(skel); + free(prog_name); free(counter); close(prog_fd); return -1; @@ -180,6 +182,7 @@ static int bpf_program_profiler__load(struct evsel *evsel, struct target *target (*p != '\0' && *p != ',')) { pr_err("Failed to parse bpf prog ids %s\n", target->bpf_str); + free(bpf_str_); return -1; } diff --git a/tools/perf/util/bpf_kwork_top.c b/tools/perf/util/bpf_kwork_top.c new file mode 100644 index 000000000000..035e02272790 --- /dev/null +++ b/tools/perf/util/bpf_kwork_top.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * bpf_kwork_top.c + * + * Copyright (c) 2022 Huawei Inc, Yang Jihong <yangjihong1@huawei.com> + */ + +#include <time.h> +#include <fcntl.h> +#include <signal.h> +#include <stdio.h> +#include <unistd.h> + +#include <linux/time64.h> + +#include "util/debug.h" +#include "util/evsel.h" +#include "util/kwork.h" + +#include <bpf/bpf.h> +#include <perf/cpumap.h> + +#include "util/bpf_skel/kwork_top.skel.h" + +/* + * This should be in sync with "util/kwork_top.bpf.c" + */ +#define MAX_COMMAND_LEN 16 + +struct time_data { + __u64 timestamp; +}; + +struct work_data { + __u64 runtime; +}; + +struct task_data { + __u32 tgid; + __u32 is_kthread; + char comm[MAX_COMMAND_LEN]; +}; + +struct work_key { + __u32 type; + __u32 pid; + __u64 task_p; +}; + +struct task_key { + __u32 pid; + __u32 cpu; +}; + +struct kwork_class_bpf { + struct kwork_class *class; + void (*load_prepare)(void); +}; + +static struct kwork_top_bpf *skel; + +void perf_kwork__top_start(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + skel->bss->from_timestamp = (u64)ts.tv_sec * NSEC_PER_SEC + ts.tv_nsec; + skel->bss->enabled = 1; + pr_debug("perf kwork top start at: %lld\n", skel->bss->from_timestamp); +} + +void perf_kwork__top_finish(void) +{ + struct timespec ts; + + skel->bss->enabled = 0; + clock_gettime(CLOCK_MONOTONIC, &ts); + skel->bss->to_timestamp = (u64)ts.tv_sec * NSEC_PER_SEC + ts.tv_nsec; + pr_debug("perf kwork top finish at: %lld\n", skel->bss->to_timestamp); +} + +static void irq_load_prepare(void) +{ + bpf_program__set_autoload(skel->progs.on_irq_handler_entry, true); + bpf_program__set_autoload(skel->progs.on_irq_handler_exit, true); +} + +static struct kwork_class_bpf kwork_irq_bpf = { + .load_prepare = irq_load_prepare, +}; + +static void softirq_load_prepare(void) +{ + bpf_program__set_autoload(skel->progs.on_softirq_entry, true); + bpf_program__set_autoload(skel->progs.on_softirq_exit, true); +} + +static struct kwork_class_bpf kwork_softirq_bpf = { + .load_prepare = softirq_load_prepare, +}; + +static void sched_load_prepare(void) +{ + bpf_program__set_autoload(skel->progs.on_switch, true); +} + +static struct kwork_class_bpf kwork_sched_bpf = { + .load_prepare = sched_load_prepare, +}; + +static struct kwork_class_bpf * +kwork_class_bpf_supported_list[KWORK_CLASS_MAX] = { + [KWORK_CLASS_IRQ] = &kwork_irq_bpf, + [KWORK_CLASS_SOFTIRQ] = &kwork_softirq_bpf, + [KWORK_CLASS_SCHED] = &kwork_sched_bpf, +}; + +static bool valid_kwork_class_type(enum kwork_class_type type) +{ + return type >= 0 && type < KWORK_CLASS_MAX; +} + +static int setup_filters(struct perf_kwork *kwork) +{ + u8 val = 1; + int i, nr_cpus, fd; + struct perf_cpu_map *map; + + if (kwork->cpu_list) { + fd = bpf_map__fd(skel->maps.kwork_top_cpu_filter); + if (fd < 0) { + pr_debug("Invalid cpu filter fd\n"); + return -1; + } + + map = perf_cpu_map__new(kwork->cpu_list); + if (!map) { + pr_debug("Invalid cpu_list\n"); + return -1; + } + + nr_cpus = libbpf_num_possible_cpus(); + for (i = 0; i < perf_cpu_map__nr(map); i++) { + struct perf_cpu cpu = perf_cpu_map__cpu(map, i); + + if (cpu.cpu >= nr_cpus) { + perf_cpu_map__put(map); + pr_err("Requested cpu %d too large\n", cpu.cpu); + return -1; + } + bpf_map_update_elem(fd, &cpu.cpu, &val, BPF_ANY); + } + perf_cpu_map__put(map); + + skel->bss->has_cpu_filter = 1; + } + + return 0; +} + +int perf_kwork__top_prepare_bpf(struct perf_kwork *kwork __maybe_unused) +{ + struct bpf_program *prog; + struct kwork_class *class; + struct kwork_class_bpf *class_bpf; + enum kwork_class_type type; + + skel = kwork_top_bpf__open(); + if (!skel) { + pr_debug("Failed to open kwork top skeleton\n"); + return -1; + } + + /* + * set all progs to non-autoload, + * then set corresponding progs according to config + */ + bpf_object__for_each_program(prog, skel->obj) + bpf_program__set_autoload(prog, false); + + list_for_each_entry(class, &kwork->class_list, list) { + type = class->type; + if (!valid_kwork_class_type(type) || + !kwork_class_bpf_supported_list[type]) { + pr_err("Unsupported bpf trace class %s\n", class->name); + goto out; + } + + class_bpf = kwork_class_bpf_supported_list[type]; + class_bpf->class = class; + + if (class_bpf->load_prepare) + class_bpf->load_prepare(); + } + + if (kwork_top_bpf__load(skel)) { + pr_debug("Failed to load kwork top skeleton\n"); + goto out; + } + + if (setup_filters(kwork)) + goto out; + + if (kwork_top_bpf__attach(skel)) { + pr_debug("Failed to attach kwork top skeleton\n"); + goto out; + } + + return 0; + +out: + kwork_top_bpf__destroy(skel); + return -1; +} + +static void read_task_info(struct kwork_work *work) +{ + int fd; + struct task_data data; + struct task_key key = { + .pid = work->id, + .cpu = work->cpu, + }; + + fd = bpf_map__fd(skel->maps.kwork_top_tasks); + if (fd < 0) { + pr_debug("Invalid top tasks map fd\n"); + return; + } + + if (!bpf_map_lookup_elem(fd, &key, &data)) { + work->tgid = data.tgid; + work->is_kthread = data.is_kthread; + work->name = strdup(data.comm); + } +} +static int add_work(struct perf_kwork *kwork, struct work_key *key, + struct work_data *data, int cpu) +{ + struct kwork_class_bpf *bpf_trace; + struct kwork_work *work; + struct kwork_work tmp = { + .id = key->pid, + .cpu = cpu, + .name = NULL, + }; + enum kwork_class_type type = key->type; + + if (!valid_kwork_class_type(type)) { + pr_debug("Invalid class type %d to add work\n", type); + return -1; + } + + bpf_trace = kwork_class_bpf_supported_list[type]; + tmp.class = bpf_trace->class; + + work = perf_kwork_add_work(kwork, tmp.class, &tmp); + if (!work) + return -1; + + work->total_runtime = data->runtime; + read_task_info(work); + + return 0; +} + +int perf_kwork__top_read_bpf(struct perf_kwork *kwork) +{ + int i, fd, nr_cpus; + struct work_data *data; + struct work_key key, prev; + + fd = bpf_map__fd(skel->maps.kwork_top_works); + if (fd < 0) { + pr_debug("Invalid top runtime fd\n"); + return -1; + } + + nr_cpus = libbpf_num_possible_cpus(); + data = calloc(nr_cpus, sizeof(struct work_data)); + if (!data) + return -1; + + memset(&prev, 0, sizeof(prev)); + while (!bpf_map_get_next_key(fd, &prev, &key)) { + if ((bpf_map_lookup_elem(fd, &key, data)) != 0) { + pr_debug("Failed to lookup top elem\n"); + return -1; + } + + for (i = 0; i < nr_cpus; i++) { + if (data[i].runtime == 0) + continue; + + if (add_work(kwork, &key, &data[i], i)) + return -1; + } + prev = key; + } + free(data); + + return 0; +} + +void perf_kwork__top_cleanup_bpf(void) +{ + kwork_top_bpf__destroy(skel); +} diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c index e7dddf0127bc..e105245eb905 100644 --- a/tools/perf/util/bpf_lock_contention.c +++ b/tools/perf/util/bpf_lock_contention.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include "util/cgroup.h" #include "util/debug.h" #include "util/evlist.h" #include "util/machine.h" @@ -20,7 +21,7 @@ static struct lock_contention_bpf *skel; int lock_contention_prepare(struct lock_contention *con) { int i, fd; - int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1; + int ncpus = 1, ntasks = 1, ntypes = 1, naddrs = 1, ncgrps = 1; struct evlist *evlist = con->evlist; struct target *target = con->target; @@ -50,6 +51,8 @@ int lock_contention_prepare(struct lock_contention *con) ntasks = perf_thread_map__nr(evlist->core.threads); if (con->filters->nr_types) ntypes = con->filters->nr_types; + if (con->filters->nr_cgrps) + ncgrps = con->filters->nr_cgrps; /* resolve lock name filters to addr */ if (con->filters->nr_syms) { @@ -84,6 +87,7 @@ int lock_contention_prepare(struct lock_contention *con) bpf_map__set_max_entries(skel->maps.task_filter, ntasks); bpf_map__set_max_entries(skel->maps.type_filter, ntypes); bpf_map__set_max_entries(skel->maps.addr_filter, naddrs); + bpf_map__set_max_entries(skel->maps.cgroup_filter, ncgrps); if (lock_contention_bpf__load(skel) < 0) { pr_err("Failed to load lock-contention BPF skeleton\n"); @@ -145,12 +149,29 @@ int lock_contention_prepare(struct lock_contention *con) bpf_map_update_elem(fd, &con->filters->addrs[i], &val, BPF_ANY); } + if (con->filters->nr_cgrps) { + u8 val = 1; + + skel->bss->has_cgroup = 1; + fd = bpf_map__fd(skel->maps.cgroup_filter); + + for (i = 0; i < con->filters->nr_cgrps; i++) + bpf_map_update_elem(fd, &con->filters->cgrps[i], &val, BPF_ANY); + } + /* these don't work well if in the rodata section */ skel->bss->stack_skip = con->stack_skip; skel->bss->aggr_mode = con->aggr_mode; skel->bss->needs_callstack = con->save_callstack; skel->bss->lock_owner = con->owner; + if (con->aggr_mode == LOCK_AGGR_CGROUP) { + if (cgroup_is_v2("perf_event")) + skel->bss->use_cgroup_v2 = 1; + + read_all_cgroups(&con->cgroups); + } + bpf_program__set_autoload(skel->progs.collect_lock_syms, false); lock_contention_bpf__attach(skel); @@ -209,12 +230,12 @@ static const char *lock_contention_get_name(struct lock_contention *con, return "siglock"; /* global locks with symbols */ - sym = machine__find_kernel_symbol(machine, key->lock_addr, &kmap); + sym = machine__find_kernel_symbol(machine, key->lock_addr_or_cgroup, &kmap); if (sym) return sym->name; /* try semi-global locks collected separately */ - if (!bpf_map_lookup_elem(lock_fd, &key->lock_addr, &flags)) { + if (!bpf_map_lookup_elem(lock_fd, &key->lock_addr_or_cgroup, &flags)) { if (flags == LOCK_CLASS_RQLOCK) return "rq_lock"; } @@ -222,6 +243,17 @@ static const char *lock_contention_get_name(struct lock_contention *con, return ""; } + if (con->aggr_mode == LOCK_AGGR_CGROUP) { + u64 cgrp_id = key->lock_addr_or_cgroup; + struct cgroup *cgrp = __cgroup__find(&con->cgroups, cgrp_id); + + if (cgrp) + return cgrp->name; + + snprintf(name_buf, sizeof(name_buf), "cgroup:%lu", cgrp_id); + return name_buf; + } + /* LOCK_AGGR_CALLER: skip lock internal functions */ while (machine__is_lock_function(machine, stack_trace[idx]) && idx < con->max_stack - 1) @@ -313,7 +345,8 @@ int lock_contention_read(struct lock_contention *con) ls_key = key.pid; break; case LOCK_AGGR_ADDR: - ls_key = key.lock_addr; + case LOCK_AGGR_CGROUP: + ls_key = key.lock_addr_or_cgroup; break; default: goto next; @@ -364,12 +397,20 @@ next: return err; } -int lock_contention_finish(void) +int lock_contention_finish(struct lock_contention *con) { if (skel) { skel->bss->enabled = 0; lock_contention_bpf__destroy(skel); } + while (!RB_EMPTY_ROOT(&con->cgroups)) { + struct rb_node *node = rb_first(&con->cgroups); + struct cgroup *cgrp = rb_entry(node, struct cgroup, node); + + rb_erase(node, &con->cgroups); + cgroup__put(cgrp); + } + return 0; } diff --git a/tools/perf/util/bpf_off_cpu.c b/tools/perf/util/bpf_off_cpu.c index 01f70b8e705a..6af36142dc5a 100644 --- a/tools/perf/util/bpf_off_cpu.c +++ b/tools/perf/util/bpf_off_cpu.c @@ -98,28 +98,31 @@ static void off_cpu_finish(void *arg __maybe_unused) /* v5.18 kernel added prev_state arg, so it needs to check the signature */ static void check_sched_switch_args(void) { - const struct btf *btf = bpf_object__btf(skel->obj); + struct btf *btf = btf__load_vmlinux_btf(); const struct btf_type *t1, *t2, *t3; u32 type_id; type_id = btf__find_by_name_kind(btf, "btf_trace_sched_switch", BTF_KIND_TYPEDEF); if ((s32)type_id < 0) - return; + goto cleanup; t1 = btf__type_by_id(btf, type_id); if (t1 == NULL) - return; + goto cleanup; t2 = btf__type_by_id(btf, t1->type); if (t2 == NULL || !btf_is_ptr(t2)) - return; + goto cleanup; t3 = btf__type_by_id(btf, t2->type); - if (t3 && btf_is_func_proto(t3) && btf_vlen(t3) == 4) { + /* btf_trace func proto has one more argument for the context */ + if (t3 && btf_is_func_proto(t3) && btf_vlen(t3) == 5) { /* new format: pass prev_state as 4th arg */ skel->rodata->has_prev_state = true; } +cleanup: + btf__free(btf); } int off_cpu_prepare(struct evlist *evlist, struct target *target, diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index 939ec769bf4a..52c270330ae0 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -153,7 +153,7 @@ static inline unsigned int augmented_arg__read_str(struct augmented_arg *augmented_arg, const void *arg, unsigned int arg_len) { unsigned int augmented_len = sizeof(*augmented_arg); - int string_len = bpf_probe_read_str(&augmented_arg->value, arg_len, arg); + int string_len = bpf_probe_read_user_str(&augmented_arg->value, arg_len, arg); augmented_arg->size = augmented_arg->err = 0; /* @@ -203,7 +203,7 @@ int sys_enter_connect(struct syscall_enter_args *args) _Static_assert(is_power_of_2(sizeof(augmented_args->saddr)), "sizeof(augmented_args->saddr) needs to be a power of two"); socklen &= sizeof(augmented_args->saddr) - 1; - bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg); + bpf_probe_read_user(&augmented_args->saddr, socklen, sockaddr_arg); return augmented__output(args, augmented_args, len + socklen); } @@ -221,7 +221,7 @@ int sys_enter_sendto(struct syscall_enter_args *args) socklen &= sizeof(augmented_args->saddr) - 1; - bpf_probe_read(&augmented_args->saddr, socklen, sockaddr_arg); + bpf_probe_read_user(&augmented_args->saddr, socklen, sockaddr_arg); return augmented__output(args, augmented_args, len + socklen); } @@ -311,7 +311,7 @@ int sys_enter_perf_event_open(struct syscall_enter_args *args) if (augmented_args == NULL) goto failure; - if (bpf_probe_read(&augmented_args->__data, sizeof(*attr), attr) < 0) + if (bpf_probe_read_user(&augmented_args->__data, sizeof(*attr), attr) < 0) goto failure; attr_read = (const struct perf_event_attr_size *)augmented_args->__data; @@ -325,7 +325,7 @@ int sys_enter_perf_event_open(struct syscall_enter_args *args) goto failure; // Now that we read attr->size and tested it against the size limits, read it completely - if (bpf_probe_read(&augmented_args->__data, size, attr) < 0) + if (bpf_probe_read_user(&augmented_args->__data, size, attr) < 0) goto failure; return augmented__output(args, augmented_args, len + size); @@ -347,7 +347,7 @@ int sys_enter_clock_nanosleep(struct syscall_enter_args *args) if (size > sizeof(augmented_args->__data)) goto failure; - bpf_probe_read(&augmented_args->__data, size, rqtp_arg); + bpf_probe_read_user(&augmented_args->__data, size, rqtp_arg); return augmented__output(args, augmented_args, len + size); failure: @@ -385,7 +385,7 @@ int sys_enter(struct syscall_enter_args *args) if (augmented_args == NULL) return 1; - bpf_probe_read(&augmented_args->args, sizeof(augmented_args->args), args); + bpf_probe_read_kernel(&augmented_args->args, sizeof(augmented_args->args), args); /* * Jump to syscall specific augmenter, even if the default one, @@ -406,7 +406,7 @@ int sys_exit(struct syscall_exit_args *args) if (pid_filter__has(&pids_filtered, getpid())) return 0; - bpf_probe_read(&exit_args, sizeof(exit_args), args); + bpf_probe_read_kernel(&exit_args, sizeof(exit_args), args); /* * Jump to syscall specific return augmenter, even if the default one, * "!raw_syscalls:unaugmented" that will just return 1 to return the diff --git a/tools/perf/util/bpf_skel/kwork_top.bpf.c b/tools/perf/util/bpf_skel/kwork_top.bpf.c new file mode 100644 index 000000000000..84c15ccbab44 --- /dev/null +++ b/tools/perf/util/bpf_skel/kwork_top.bpf.c @@ -0,0 +1,338 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +// Copyright (c) 2022, Huawei + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> + +/* + * This should be in sync with "util/kwork.h" + */ +enum kwork_class_type { + KWORK_CLASS_IRQ, + KWORK_CLASS_SOFTIRQ, + KWORK_CLASS_WORKQUEUE, + KWORK_CLASS_SCHED, + KWORK_CLASS_MAX, +}; + +#define MAX_ENTRIES 102400 +#define MAX_NR_CPUS 2048 +#define PF_KTHREAD 0x00200000 +#define MAX_COMMAND_LEN 16 + +struct time_data { + __u64 timestamp; +}; + +struct work_data { + __u64 runtime; +}; + +struct task_data { + __u32 tgid; + __u32 is_kthread; + char comm[MAX_COMMAND_LEN]; +}; + +struct work_key { + __u32 type; + __u32 pid; + __u64 task_p; +}; + +struct task_key { + __u32 pid; + __u32 cpu; +}; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, struct time_data); +} kwork_top_task_time SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(key_size, sizeof(struct work_key)); + __uint(value_size, sizeof(struct time_data)); + __uint(max_entries, MAX_ENTRIES); +} kwork_top_irq_time SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(struct task_key)); + __uint(value_size, sizeof(struct task_data)); + __uint(max_entries, MAX_ENTRIES); +} kwork_top_tasks SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_HASH); + __uint(key_size, sizeof(struct work_key)); + __uint(value_size, sizeof(struct work_data)); + __uint(max_entries, MAX_ENTRIES); +} kwork_top_works SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(u32)); + __uint(value_size, sizeof(u8)); + __uint(max_entries, MAX_NR_CPUS); +} kwork_top_cpu_filter SEC(".maps"); + +int enabled = 0; + +int has_cpu_filter = 0; + +__u64 from_timestamp = 0; +__u64 to_timestamp = 0; + +static __always_inline int cpu_is_filtered(__u32 cpu) +{ + __u8 *cpu_val; + + if (has_cpu_filter) { + cpu_val = bpf_map_lookup_elem(&kwork_top_cpu_filter, &cpu); + if (!cpu_val) + return 1; + } + + return 0; +} + +static __always_inline void update_task_info(struct task_struct *task, __u32 cpu) +{ + struct task_key key = { + .pid = task->pid, + .cpu = cpu, + }; + + if (!bpf_map_lookup_elem(&kwork_top_tasks, &key)) { + struct task_data data = { + .tgid = task->tgid, + .is_kthread = task->flags & PF_KTHREAD ? 1 : 0, + }; + BPF_CORE_READ_STR_INTO(&data.comm, task, comm); + + bpf_map_update_elem(&kwork_top_tasks, &key, &data, BPF_ANY); + } +} + +static __always_inline void update_work(struct work_key *key, __u64 delta) +{ + struct work_data *data; + + data = bpf_map_lookup_elem(&kwork_top_works, key); + if (data) { + data->runtime += delta; + } else { + struct work_data new_data = { + .runtime = delta, + }; + + bpf_map_update_elem(&kwork_top_works, key, &new_data, BPF_ANY); + } +} + +static void on_sched_out(struct task_struct *task, __u64 ts, __u32 cpu) +{ + __u64 delta; + struct time_data *pelem; + + pelem = bpf_task_storage_get(&kwork_top_task_time, task, NULL, 0); + if (pelem) + delta = ts - pelem->timestamp; + else + delta = ts - from_timestamp; + + struct work_key key = { + .type = KWORK_CLASS_SCHED, + .pid = task->pid, + .task_p = (__u64)task, + }; + + update_work(&key, delta); + update_task_info(task, cpu); +} + +static void on_sched_in(struct task_struct *task, __u64 ts) +{ + struct time_data *pelem; + + pelem = bpf_task_storage_get(&kwork_top_task_time, task, NULL, + BPF_LOCAL_STORAGE_GET_F_CREATE); + if (pelem) + pelem->timestamp = ts; +} + +SEC("tp_btf/sched_switch") +int on_switch(u64 *ctx) +{ + struct task_struct *prev, *next; + + prev = (struct task_struct *)ctx[1]; + next = (struct task_struct *)ctx[2]; + + if (!enabled) + return 0; + + __u32 cpu = bpf_get_smp_processor_id(); + + if (cpu_is_filtered(cpu)) + return 0; + + __u64 ts = bpf_ktime_get_ns(); + + on_sched_out(prev, ts, cpu); + on_sched_in(next, ts); + + return 0; +} + +SEC("tp_btf/irq_handler_entry") +int on_irq_handler_entry(u64 *cxt) +{ + struct task_struct *task; + + if (!enabled) + return 0; + + __u32 cpu = bpf_get_smp_processor_id(); + + if (cpu_is_filtered(cpu)) + return 0; + + __u64 ts = bpf_ktime_get_ns(); + + task = (struct task_struct *)bpf_get_current_task(); + if (!task) + return 0; + + struct work_key key = { + .type = KWORK_CLASS_IRQ, + .pid = BPF_CORE_READ(task, pid), + .task_p = (__u64)task, + }; + + struct time_data data = { + .timestamp = ts, + }; + + bpf_map_update_elem(&kwork_top_irq_time, &key, &data, BPF_ANY); + + return 0; +} + +SEC("tp_btf/irq_handler_exit") +int on_irq_handler_exit(u64 *cxt) +{ + __u64 delta; + struct task_struct *task; + struct time_data *pelem; + + if (!enabled) + return 0; + + __u32 cpu = bpf_get_smp_processor_id(); + + if (cpu_is_filtered(cpu)) + return 0; + + __u64 ts = bpf_ktime_get_ns(); + + task = (struct task_struct *)bpf_get_current_task(); + if (!task) + return 0; + + struct work_key key = { + .type = KWORK_CLASS_IRQ, + .pid = BPF_CORE_READ(task, pid), + .task_p = (__u64)task, + }; + + pelem = bpf_map_lookup_elem(&kwork_top_irq_time, &key); + if (pelem && pelem->timestamp != 0) + delta = ts - pelem->timestamp; + else + delta = ts - from_timestamp; + + update_work(&key, delta); + + return 0; +} + +SEC("tp_btf/softirq_entry") +int on_softirq_entry(u64 *cxt) +{ + struct task_struct *task; + + if (!enabled) + return 0; + + __u32 cpu = bpf_get_smp_processor_id(); + + if (cpu_is_filtered(cpu)) + return 0; + + __u64 ts = bpf_ktime_get_ns(); + + task = (struct task_struct *)bpf_get_current_task(); + if (!task) + return 0; + + struct work_key key = { + .type = KWORK_CLASS_SOFTIRQ, + .pid = BPF_CORE_READ(task, pid), + .task_p = (__u64)task, + }; + + struct time_data data = { + .timestamp = ts, + }; + + bpf_map_update_elem(&kwork_top_irq_time, &key, &data, BPF_ANY); + + return 0; +} + +SEC("tp_btf/softirq_exit") +int on_softirq_exit(u64 *cxt) +{ + __u64 delta; + struct task_struct *task; + struct time_data *pelem; + + if (!enabled) + return 0; + + __u32 cpu = bpf_get_smp_processor_id(); + + if (cpu_is_filtered(cpu)) + return 0; + + __u64 ts = bpf_ktime_get_ns(); + + task = (struct task_struct *)bpf_get_current_task(); + if (!task) + return 0; + + struct work_key key = { + .type = KWORK_CLASS_SOFTIRQ, + .pid = BPF_CORE_READ(task, pid), + .task_p = (__u64)task, + }; + + pelem = bpf_map_lookup_elem(&kwork_top_irq_time, &key); + if (pelem) + delta = ts - pelem->timestamp; + else + delta = ts - from_timestamp; + + update_work(&key, delta); + + return 0; +} + +char LICENSE[] SEC("license") = "Dual BSD/GPL"; diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c index 8d3cfbb3cc65..95cd8414f6ef 100644 --- a/tools/perf/util/bpf_skel/lock_contention.bpf.c +++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c @@ -42,6 +42,14 @@ struct { __uint(max_entries, MAX_ENTRIES); } tstamp SEC(".maps"); +/* maintain per-CPU timestamp at the beginning of contention */ +struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(key_size, sizeof(__u32)); + __uint(value_size, sizeof(struct tstamp_data)); + __uint(max_entries, 1); +} tstamp_cpu SEC(".maps"); + /* actual lock contention statistics */ struct { __uint(type, BPF_MAP_TYPE_HASH); @@ -92,6 +100,13 @@ struct { __uint(max_entries, 1); } addr_filter SEC(".maps"); +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(__u64)); + __uint(value_size, sizeof(__u8)); + __uint(max_entries, 1); +} cgroup_filter SEC(".maps"); + struct rw_semaphore___old { struct task_struct *owner; } __attribute__((preserve_access_index)); @@ -114,10 +129,14 @@ int has_cpu; int has_task; int has_type; int has_addr; +int has_cgroup; int needs_callstack; int stack_skip; int lock_owner; +int use_cgroup_v2; +int perf_subsys_id = -1; + /* determine the key of lock stat */ int aggr_mode; @@ -130,6 +149,29 @@ int data_fail; int task_map_full; int data_map_full; +static inline __u64 get_current_cgroup_id(void) +{ + struct task_struct *task; + struct cgroup *cgrp; + + if (use_cgroup_v2) + return bpf_get_current_cgroup_id(); + + task = bpf_get_current_task_btf(); + + if (perf_subsys_id == -1) { +#if __has_builtin(__builtin_preserve_enum_value) + perf_subsys_id = bpf_core_enum_value(enum cgroup_subsys_id, + perf_event_cgrp_id); +#else + perf_subsys_id = perf_event_cgrp_id; +#endif + } + + cgrp = BPF_CORE_READ(task, cgroups, subsys[perf_subsys_id], cgroup); + return BPF_CORE_READ(cgrp, kn, id); +} + static inline int can_record(u64 *ctx) { if (has_cpu) { @@ -168,6 +210,15 @@ static inline int can_record(u64 *ctx) return 0; } + if (has_cgroup) { + __u8 *ok; + __u64 cgrp = get_current_cgroup_id(); + + ok = bpf_map_lookup_elem(&cgroup_filter, &cgrp); + if (!ok) + return 0; + } + return 1; } @@ -268,30 +319,57 @@ static inline __u32 check_lock_type(__u64 lock, __u32 flags) return 0; } -SEC("tp_btf/contention_begin") -int contention_begin(u64 *ctx) +static inline struct tstamp_data *get_tstamp_elem(__u32 flags) { __u32 pid; struct tstamp_data *pelem; - if (!enabled || !can_record(ctx)) - return 0; + /* Use per-cpu array map for spinlock and rwlock */ + if (flags == (LCB_F_SPIN | LCB_F_READ) || flags == LCB_F_SPIN || + flags == (LCB_F_SPIN | LCB_F_WRITE)) { + __u32 idx = 0; + + pelem = bpf_map_lookup_elem(&tstamp_cpu, &idx); + /* Do not update the element for nested locks */ + if (pelem && pelem->lock) + pelem = NULL; + return pelem; + } pid = bpf_get_current_pid_tgid(); pelem = bpf_map_lookup_elem(&tstamp, &pid); + /* Do not update the element for nested locks */ if (pelem && pelem->lock) - return 0; + return NULL; if (pelem == NULL) { struct tstamp_data zero = {}; - bpf_map_update_elem(&tstamp, &pid, &zero, BPF_ANY); + if (bpf_map_update_elem(&tstamp, &pid, &zero, BPF_NOEXIST) < 0) { + __sync_fetch_and_add(&task_fail, 1); + return NULL; + } + pelem = bpf_map_lookup_elem(&tstamp, &pid); if (pelem == NULL) { __sync_fetch_and_add(&task_fail, 1); - return 0; + return NULL; } } + return pelem; +} + +SEC("tp_btf/contention_begin") +int contention_begin(u64 *ctx) +{ + struct tstamp_data *pelem; + + if (!enabled || !can_record(ctx)) + return 0; + + pelem = get_tstamp_elem(ctx[1]); + if (pelem == NULL) + return 0; pelem->timestamp = bpf_ktime_get_ns(); pelem->lock = (__u64)ctx[0]; @@ -330,23 +408,42 @@ int contention_begin(u64 *ctx) SEC("tp_btf/contention_end") int contention_end(u64 *ctx) { - __u32 pid; + __u32 pid = 0, idx = 0; struct tstamp_data *pelem; struct contention_key key = {}; struct contention_data *data; __u64 duration; + bool need_delete = false; if (!enabled) return 0; - pid = bpf_get_current_pid_tgid(); - pelem = bpf_map_lookup_elem(&tstamp, &pid); - if (!pelem || pelem->lock != ctx[0]) - return 0; + /* + * For spinlock and rwlock, it needs to get the timestamp for the + * per-cpu map. However, contention_end does not have the flags + * so it cannot know whether it reads percpu or hash map. + * + * Try per-cpu map first and check if there's active contention. + * If it is, do not read hash map because it cannot go to sleeping + * locks before releasing the spinning locks. + */ + pelem = bpf_map_lookup_elem(&tstamp_cpu, &idx); + if (pelem && pelem->lock) { + if (pelem->lock != ctx[0]) + return 0; + } else { + pid = bpf_get_current_pid_tgid(); + pelem = bpf_map_lookup_elem(&tstamp, &pid); + if (!pelem || pelem->lock != ctx[0]) + return 0; + need_delete = true; + } duration = bpf_ktime_get_ns() - pelem->timestamp; if ((__s64)duration < 0) { - bpf_map_delete_elem(&tstamp, &pid); + pelem->lock = 0; + if (need_delete) + bpf_map_delete_elem(&tstamp, &pid); __sync_fetch_and_add(&time_fail, 1); return 0; } @@ -358,16 +455,22 @@ int contention_end(u64 *ctx) case LOCK_AGGR_TASK: if (lock_owner) key.pid = pelem->flags; - else + else { + if (!need_delete) + pid = bpf_get_current_pid_tgid(); key.pid = pid; + } if (needs_callstack) key.stack_id = pelem->stack_id; break; case LOCK_AGGR_ADDR: - key.lock_addr = pelem->lock; + key.lock_addr_or_cgroup = pelem->lock; if (needs_callstack) key.stack_id = pelem->stack_id; break; + case LOCK_AGGR_CGROUP: + key.lock_addr_or_cgroup = get_current_cgroup_id(); + break; default: /* should not happen */ return 0; @@ -376,7 +479,9 @@ int contention_end(u64 *ctx) data = bpf_map_lookup_elem(&lock_stat, &key); if (!data) { if (data_map_full) { - bpf_map_delete_elem(&tstamp, &pid); + pelem->lock = 0; + if (need_delete) + bpf_map_delete_elem(&tstamp, &pid); __sync_fetch_and_add(&data_fail, 1); return 0; } @@ -399,7 +504,9 @@ int contention_end(u64 *ctx) data_map_full = 1; __sync_fetch_and_add(&data_fail, 1); } - bpf_map_delete_elem(&tstamp, &pid); + pelem->lock = 0; + if (need_delete) + bpf_map_delete_elem(&tstamp, &pid); return 0; } @@ -412,7 +519,9 @@ int contention_end(u64 *ctx) if (data->min_time > duration) data->min_time = duration; - bpf_map_delete_elem(&tstamp, &pid); + pelem->lock = 0; + if (need_delete) + bpf_map_delete_elem(&tstamp, &pid); return 0; } diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h index 260062a9f2ab..08482daf61be 100644 --- a/tools/perf/util/bpf_skel/lock_data.h +++ b/tools/perf/util/bpf_skel/lock_data.h @@ -6,7 +6,7 @@ struct contention_key { u32 stack_id; u32 pid; - u64 lock_addr; + u64 lock_addr_or_cgroup; }; #define TASK_COMM_LEN 16 @@ -39,6 +39,7 @@ enum lock_aggr_mode { LOCK_AGGR_ADDR = 0, LOCK_AGGR_TASK, LOCK_AGGR_CALLER, + LOCK_AGGR_CGROUP, }; enum lock_class_sym { diff --git a/tools/perf/util/bpf_skel/vmlinux/.gitignore b/tools/perf/util/bpf_skel/vmlinux/.gitignore new file mode 100644 index 000000000000..49502c04183a --- /dev/null +++ b/tools/perf/util/bpf_skel/vmlinux/.gitignore @@ -0,0 +1 @@ +!vmlinux.h diff --git a/tools/perf/util/branch.c b/tools/perf/util/branch.c index 378f16a24751..ab760e267d41 100644 --- a/tools/perf/util/branch.c +++ b/tools/perf/util/branch.c @@ -109,7 +109,7 @@ const char *get_branch_type(struct branch_entry *e) return branch_type_name(e->flags.type); } -void branch_type_stat_display(FILE *fp, struct branch_type_stat *st) +void branch_type_stat_display(FILE *fp, const struct branch_type_stat *st) { u64 total = 0; int i; @@ -171,7 +171,7 @@ static int count_str_scnprintf(int idx, const char *str, char *bf, int size) return scnprintf(bf, size, "%s%s", (idx) ? " " : " (", str); } -int branch_type_str(struct branch_type_stat *st, char *bf, int size) +int branch_type_str(const struct branch_type_stat *st, char *bf, int size) { int i, j = 0, printed = 0; u64 total = 0; diff --git a/tools/perf/util/branch.h b/tools/perf/util/branch.h index e41bfffe2217..87704d713ff6 100644 --- a/tools/perf/util/branch.h +++ b/tools/perf/util/branch.h @@ -86,8 +86,8 @@ void branch_type_count(struct branch_type_stat *st, struct branch_flags *flags, const char *branch_type_name(int type); const char *branch_new_type_name(int new_type); const char *get_branch_type(struct branch_entry *e); -void branch_type_stat_display(FILE *fp, struct branch_type_stat *st); -int branch_type_str(struct branch_type_stat *st, char *bf, int bfsize); +void branch_type_stat_display(FILE *fp, const struct branch_type_stat *st); +int branch_type_str(const struct branch_type_stat *st, char *bf, int bfsize); const char *branch_spec_desc(int spec); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index aee937d14fbb..8262f69118db 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -586,7 +586,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) call = zalloc(sizeof(*call)); if (!call) { perror("not enough memory for the code path tree"); - return -1; + return -ENOMEM; } call->ip = cursor_node->ip; call->ms = cursor_node->ms; @@ -602,7 +602,15 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) * branch_from is set with value somewhere else * to imply it's "to" of a branch. */ - call->brtype_stat.branch_to = true; + if (!call->brtype_stat) { + call->brtype_stat = zalloc(sizeof(*call->brtype_stat)); + if (!call->brtype_stat) { + perror("not enough memory for the code path branch statistics"); + free(call->brtype_stat); + return -ENOMEM; + } + } + call->brtype_stat->branch_to = true; if (cursor_node->branch_flags.predicted) call->predicted_count = 1; @@ -610,7 +618,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) if (cursor_node->branch_flags.abort) call->abort_count = 1; - branch_type_count(&call->brtype_stat, + branch_type_count(call->brtype_stat, &cursor_node->branch_flags, cursor_node->branch_from, cursor_node->ip); @@ -618,7 +626,8 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor) /* * It's "from" of a branch */ - call->brtype_stat.branch_to = false; + if (call->brtype_stat && call->brtype_stat->branch_to) + call->brtype_stat->branch_to = false; call->cycles_count = cursor_node->branch_flags.cycles; call->iter_count = cursor_node->nr_loop_iter; @@ -650,8 +659,8 @@ add_child(struct callchain_node *parent, list_for_each_entry_safe(call, tmp, &new->val, list) { list_del_init(&call->list); - map__zput(call->ms.map); - maps__zput(call->ms.maps); + map_symbol__exit(&call->ms); + zfree(&call->brtype_stat); free(call); } free(new); @@ -762,7 +771,14 @@ static enum match_result match_chain(struct callchain_cursor_node *node, /* * It's "to" of a branch */ - cnode->brtype_stat.branch_to = true; + if (!cnode->brtype_stat) { + cnode->brtype_stat = zalloc(sizeof(*cnode->brtype_stat)); + if (!cnode->brtype_stat) { + perror("not enough memory for the code path branch statistics"); + return MATCH_ERROR; + } + } + cnode->brtype_stat->branch_to = true; if (node->branch_flags.predicted) cnode->predicted_count++; @@ -770,7 +786,7 @@ static enum match_result match_chain(struct callchain_cursor_node *node, if (node->branch_flags.abort) cnode->abort_count++; - branch_type_count(&cnode->brtype_stat, + branch_type_count(cnode->brtype_stat, &node->branch_flags, node->branch_from, node->ip); @@ -778,7 +794,8 @@ static enum match_result match_chain(struct callchain_cursor_node *node, /* * It's "from" of a branch */ - cnode->brtype_stat.branch_to = false; + if (cnode->brtype_stat && cnode->brtype_stat->branch_to) + cnode->brtype_stat->branch_to = false; cnode->cycles_count += node->branch_flags.cycles; cnode->iter_count += node->nr_loop_iter; cnode->iter_cycles += node->iter_cycles; @@ -1022,10 +1039,9 @@ merge_chain_branch(struct callchain_cursor *cursor, }; callchain_cursor_append(cursor, list->ip, &ms, false, NULL, 0, 0, 0, list->srcline); list_del_init(&list->list); - map__zput(ms.map); - maps__zput(ms.maps); - map__zput(list->ms.map); - maps__zput(list->ms.maps); + map_symbol__exit(&ms); + map_symbol__exit(&list->ms); + zfree(&list->brtype_stat); free(list); } @@ -1077,8 +1093,7 @@ int callchain_cursor_append(struct callchain_cursor *cursor, } node->ip = ip; - maps__zput(node->ms.maps); - map__zput(node->ms.map); + map_symbol__exit(&node->ms); node->ms = *ms; node->ms.maps = maps__get(ms->maps); node->ms.map = map__get(ms->map); @@ -1142,7 +1157,7 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node * if (al->map == NULL) goto out; } - if (RC_CHK_ACCESS(al->maps) == RC_CHK_ACCESS(machine__kernel_maps(machine))) { + if (RC_CHK_EQUAL(al->maps, machine__kernel_maps(machine))) { if (machine__is_host(machine)) { al->cpumode = PERF_RECORD_MISC_KERNEL; al->level = 'k'; @@ -1339,7 +1354,7 @@ static int count_float_printf(int idx, const char *str, float value, static int branch_to_str(char *bf, int bfsize, u64 branch_count, u64 predicted_count, u64 abort_count, - struct branch_type_stat *brtype_stat) + const struct branch_type_stat *brtype_stat) { int printed, i = 0; @@ -1403,7 +1418,7 @@ static int counts_str_build(char *bf, int bfsize, u64 abort_count, u64 cycles_count, u64 iter_count, u64 iter_cycles, u64 from_count, - struct branch_type_stat *brtype_stat) + const struct branch_type_stat *brtype_stat) { int printed; @@ -1430,7 +1445,7 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, u64 abort_count, u64 cycles_count, u64 iter_count, u64 iter_cycles, u64 from_count, - struct branch_type_stat *brtype_stat) + const struct branch_type_stat *brtype_stat) { char str[256]; @@ -1447,11 +1462,14 @@ static int callchain_counts_printf(FILE *fp, char *bf, int bfsize, int callchain_list_counts__printf_value(struct callchain_list *clist, FILE *fp, char *bf, int bfsize) { + static const struct branch_type_stat empty_brtype_stat = {}; + const struct branch_type_stat *brtype_stat; u64 branch_count, predicted_count; u64 abort_count, cycles_count; u64 iter_count, iter_cycles; u64 from_count; + brtype_stat = clist->brtype_stat ?: &empty_brtype_stat; branch_count = clist->branch_count; predicted_count = clist->predicted_count; abort_count = clist->abort_count; @@ -1463,7 +1481,7 @@ int callchain_list_counts__printf_value(struct callchain_list *clist, return callchain_counts_printf(fp, bf, bfsize, branch_count, predicted_count, abort_count, cycles_count, iter_count, iter_cycles, - from_count, &clist->brtype_stat); + from_count, brtype_stat); } static void free_callchain_node(struct callchain_node *node) @@ -1474,15 +1492,15 @@ static void free_callchain_node(struct callchain_node *node) list_for_each_entry_safe(list, tmp, &node->parent_val, list) { list_del_init(&list->list); - map__zput(list->ms.map); - maps__zput(list->ms.maps); + map_symbol__exit(&list->ms); + zfree(&list->brtype_stat); free(list); } list_for_each_entry_safe(list, tmp, &node->val, list) { list_del_init(&list->list); - map__zput(list->ms.map); - maps__zput(list->ms.maps); + map_symbol__exit(&list->ms); + zfree(&list->brtype_stat); free(list); } @@ -1567,8 +1585,8 @@ int callchain_node__make_parent_list(struct callchain_node *node) out: list_for_each_entry_safe(chain, new, &head, list) { list_del_init(&chain->list); - map__zput(chain->ms.map); - maps__zput(chain->ms.maps); + map_symbol__exit(&chain->ms); + zfree(&chain->brtype_stat); free(chain); } return -ENOMEM; @@ -1651,10 +1669,8 @@ void callchain_cursor_reset(struct callchain_cursor *cursor) cursor->nr = 0; cursor->last = &cursor->first; - for (node = cursor->first; node != NULL; node = node->next) { - map__zput(node->ms.map); - maps__zput(node->ms.maps); - } + for (node = cursor->first; node != NULL; node = node->next) + map_symbol__exit(&node->ms); } void callchain_param_setup(u64 sample_type, const char *arch) diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index d2618a47deca..d5c66345ae31 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -116,22 +116,22 @@ extern struct callchain_param callchain_param; extern struct callchain_param callchain_param_default; struct callchain_list { + struct list_head list; u64 ip; struct map_symbol ms; - struct /* for TUI */ { - bool unfolded; - bool has_children; - }; + const char *srcline; u64 branch_count; u64 from_count; - u64 predicted_count; - u64 abort_count; u64 cycles_count; u64 iter_count; u64 iter_cycles; - struct branch_type_stat brtype_stat; - const char *srcline; - struct list_head list; + struct branch_type_stat *brtype_stat; + u64 predicted_count; + u64 abort_count; + struct /* for TUI */ { + bool unfolded; + bool has_children; + }; }; /* diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c index bfb13306d82c..fcb509058499 100644 --- a/tools/perf/util/cgroup.c +++ b/tools/perf/util/cgroup.c @@ -48,28 +48,36 @@ static int open_cgroup(const char *name) } #ifdef HAVE_FILE_HANDLE -int read_cgroup_id(struct cgroup *cgrp) +static u64 __read_cgroup_id(const char *path) { - char path[PATH_MAX + 1]; - char mnt[PATH_MAX + 1]; struct { struct file_handle fh; uint64_t cgroup_id; } handle; int mount_id; + handle.fh.handle_bytes = sizeof(handle.cgroup_id); + if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) + return -1ULL; + + return handle.cgroup_id; +} + +int read_cgroup_id(struct cgroup *cgrp) +{ + char path[PATH_MAX + 1]; + char mnt[PATH_MAX + 1]; + if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1, "perf_event")) return -1; scnprintf(path, PATH_MAX, "%s/%s", mnt, cgrp->name); - handle.fh.handle_bytes = sizeof(handle.cgroup_id); - if (name_to_handle_at(AT_FDCWD, path, &handle.fh, &mount_id, 0) < 0) - return -1; - - cgrp->id = handle.cgroup_id; + cgrp->id = __read_cgroup_id(path); return 0; } +#else +static inline u64 __read_cgroup_id(const char *path __maybe_unused) { return -1ULL; } #endif /* HAVE_FILE_HANDLE */ #ifndef CGROUP2_SUPER_MAGIC @@ -106,7 +114,7 @@ static struct cgroup *evlist__find_cgroup(struct evlist *evlist, const char *str return NULL; } -static struct cgroup *cgroup__new(const char *name, bool do_open) +struct cgroup *cgroup__new(const char *name, bool do_open) { struct cgroup *cgroup = zalloc(sizeof(*cgroup)); @@ -562,6 +570,11 @@ struct cgroup *cgroup__findnew(struct perf_env *env, uint64_t id, return cgrp; } +struct cgroup *__cgroup__find(struct rb_root *root, uint64_t id) +{ + return __cgroup__findnew(root, id, /*create=*/false, /*path=*/NULL); +} + struct cgroup *cgroup__find(struct perf_env *env, uint64_t id) { struct cgroup *cgrp; @@ -587,3 +600,35 @@ void perf_env__purge_cgroups(struct perf_env *env) } up_write(&env->cgroups.lock); } + +void read_all_cgroups(struct rb_root *root) +{ + char mnt[PATH_MAX]; + struct cgroup_name *cn; + int prefix_len; + + if (cgroupfs_find_mountpoint(mnt, sizeof(mnt), "perf_event")) + return; + + /* cgroup_name will have a full path, skip the root directory */ + prefix_len = strlen(mnt); + + /* collect all cgroups in the cgroup_list */ + if (nftw(mnt, add_cgroup_name, 20, 0) < 0) + return; + + list_for_each_entry(cn, &cgroup_list, list) { + const char *name; + u64 cgrp_id; + + /* cgroup_name might have a full path, skip the prefix */ + name = cn->name + prefix_len; + if (name[0] == '\0') + name = "/"; + + cgrp_id = __read_cgroup_id(cn->name); + __cgroup__findnew(root, cgrp_id, /*create=*/true, name); + } + + release_cgroup_list(); +} diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h index 12256b78608c..de8882d6e8d3 100644 --- a/tools/perf/util/cgroup.h +++ b/tools/perf/util/cgroup.h @@ -26,6 +26,7 @@ void cgroup__put(struct cgroup *cgroup); struct evlist; struct rblist; +struct cgroup *cgroup__new(const char *name, bool do_open); struct cgroup *evlist__findnew_cgroup(struct evlist *evlist, const char *name); int evlist__expand_cgroup(struct evlist *evlist, const char *cgroups, struct rblist *metric_events, bool open_cgroup); @@ -37,6 +38,7 @@ int parse_cgroups(const struct option *opt, const char *str, int unset); struct cgroup *cgroup__findnew(struct perf_env *env, uint64_t id, const char *path); struct cgroup *cgroup__find(struct perf_env *env, uint64_t id); +struct cgroup *__cgroup__find(struct rb_root *root, uint64_t id); void perf_env__purge_cgroups(struct perf_env *env); @@ -49,6 +51,9 @@ static inline int read_cgroup_id(struct cgroup *cgrp __maybe_unused) } #endif /* HAVE_FILE_HANDLE */ +/* read all cgroups in the system and save them in the rbtree */ +void read_all_cgroups(struct rb_root *root); + int cgroup_is_v2(const char *subsys); #endif /* __CGROUP_H__ */ diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c index 9729d006550d..a9873d14c632 100644 --- a/tools/perf/util/cs-etm.c +++ b/tools/perf/util/cs-etm.c @@ -283,22 +283,31 @@ static int cs_etm__metadata_set_trace_id(u8 trace_chan_id, u64 *cpu_metadata) } /* - * Get a metadata for a specific cpu from an array. + * Get a metadata index for a specific cpu from an array. * */ -static u64 *get_cpu_data(struct cs_etm_auxtrace *etm, int cpu) +static int get_cpu_data_idx(struct cs_etm_auxtrace *etm, int cpu) { int i; - u64 *metadata = NULL; for (i = 0; i < etm->num_cpu; i++) { if (etm->metadata[i][CS_ETM_CPU] == (u64)cpu) { - metadata = etm->metadata[i]; - break; + return i; } } - return metadata; + return -1; +} + +/* + * Get a metadata for a specific cpu from an array. + * + */ +static u64 *get_cpu_data(struct cs_etm_auxtrace *etm, int cpu) +{ + int idx = get_cpu_data_idx(etm, cpu); + + return (idx != -1) ? etm->metadata[idx] : NULL; } /* @@ -641,66 +650,80 @@ static void cs_etm__packet_dump(const char *pkt_string) } static void cs_etm__set_trace_param_etmv3(struct cs_etm_trace_params *t_params, - struct cs_etm_auxtrace *etm, int idx, - u32 etmidr) + struct cs_etm_auxtrace *etm, int t_idx, + int m_idx, u32 etmidr) { u64 **metadata = etm->metadata; - t_params[idx].protocol = cs_etm__get_v7_protocol_version(etmidr); - t_params[idx].etmv3.reg_ctrl = metadata[idx][CS_ETM_ETMCR]; - t_params[idx].etmv3.reg_trc_id = metadata[idx][CS_ETM_ETMTRACEIDR]; + t_params[t_idx].protocol = cs_etm__get_v7_protocol_version(etmidr); + t_params[t_idx].etmv3.reg_ctrl = metadata[m_idx][CS_ETM_ETMCR]; + t_params[t_idx].etmv3.reg_trc_id = metadata[m_idx][CS_ETM_ETMTRACEIDR]; } static void cs_etm__set_trace_param_etmv4(struct cs_etm_trace_params *t_params, - struct cs_etm_auxtrace *etm, int idx) + struct cs_etm_auxtrace *etm, int t_idx, + int m_idx) { u64 **metadata = etm->metadata; - t_params[idx].protocol = CS_ETM_PROTO_ETMV4i; - t_params[idx].etmv4.reg_idr0 = metadata[idx][CS_ETMV4_TRCIDR0]; - t_params[idx].etmv4.reg_idr1 = metadata[idx][CS_ETMV4_TRCIDR1]; - t_params[idx].etmv4.reg_idr2 = metadata[idx][CS_ETMV4_TRCIDR2]; - t_params[idx].etmv4.reg_idr8 = metadata[idx][CS_ETMV4_TRCIDR8]; - t_params[idx].etmv4.reg_configr = metadata[idx][CS_ETMV4_TRCCONFIGR]; - t_params[idx].etmv4.reg_traceidr = metadata[idx][CS_ETMV4_TRCTRACEIDR]; + t_params[t_idx].protocol = CS_ETM_PROTO_ETMV4i; + t_params[t_idx].etmv4.reg_idr0 = metadata[m_idx][CS_ETMV4_TRCIDR0]; + t_params[t_idx].etmv4.reg_idr1 = metadata[m_idx][CS_ETMV4_TRCIDR1]; + t_params[t_idx].etmv4.reg_idr2 = metadata[m_idx][CS_ETMV4_TRCIDR2]; + t_params[t_idx].etmv4.reg_idr8 = metadata[m_idx][CS_ETMV4_TRCIDR8]; + t_params[t_idx].etmv4.reg_configr = metadata[m_idx][CS_ETMV4_TRCCONFIGR]; + t_params[t_idx].etmv4.reg_traceidr = metadata[m_idx][CS_ETMV4_TRCTRACEIDR]; } static void cs_etm__set_trace_param_ete(struct cs_etm_trace_params *t_params, - struct cs_etm_auxtrace *etm, int idx) + struct cs_etm_auxtrace *etm, int t_idx, + int m_idx) { u64 **metadata = etm->metadata; - t_params[idx].protocol = CS_ETM_PROTO_ETE; - t_params[idx].ete.reg_idr0 = metadata[idx][CS_ETE_TRCIDR0]; - t_params[idx].ete.reg_idr1 = metadata[idx][CS_ETE_TRCIDR1]; - t_params[idx].ete.reg_idr2 = metadata[idx][CS_ETE_TRCIDR2]; - t_params[idx].ete.reg_idr8 = metadata[idx][CS_ETE_TRCIDR8]; - t_params[idx].ete.reg_configr = metadata[idx][CS_ETE_TRCCONFIGR]; - t_params[idx].ete.reg_traceidr = metadata[idx][CS_ETE_TRCTRACEIDR]; - t_params[idx].ete.reg_devarch = metadata[idx][CS_ETE_TRCDEVARCH]; + t_params[t_idx].protocol = CS_ETM_PROTO_ETE; + t_params[t_idx].ete.reg_idr0 = metadata[m_idx][CS_ETE_TRCIDR0]; + t_params[t_idx].ete.reg_idr1 = metadata[m_idx][CS_ETE_TRCIDR1]; + t_params[t_idx].ete.reg_idr2 = metadata[m_idx][CS_ETE_TRCIDR2]; + t_params[t_idx].ete.reg_idr8 = metadata[m_idx][CS_ETE_TRCIDR8]; + t_params[t_idx].ete.reg_configr = metadata[m_idx][CS_ETE_TRCCONFIGR]; + t_params[t_idx].ete.reg_traceidr = metadata[m_idx][CS_ETE_TRCTRACEIDR]; + t_params[t_idx].ete.reg_devarch = metadata[m_idx][CS_ETE_TRCDEVARCH]; } static int cs_etm__init_trace_params(struct cs_etm_trace_params *t_params, struct cs_etm_auxtrace *etm, + bool formatted, + int sample_cpu, int decoders) { - int i; + int t_idx, m_idx; u32 etmidr; u64 architecture; - for (i = 0; i < decoders; i++) { - architecture = etm->metadata[i][CS_ETM_MAGIC]; + for (t_idx = 0; t_idx < decoders; t_idx++) { + if (formatted) + m_idx = t_idx; + else { + m_idx = get_cpu_data_idx(etm, sample_cpu); + if (m_idx == -1) { + pr_warning("CS_ETM: unknown CPU, falling back to first metadata\n"); + m_idx = 0; + } + } + + architecture = etm->metadata[m_idx][CS_ETM_MAGIC]; switch (architecture) { case __perf_cs_etmv3_magic: - etmidr = etm->metadata[i][CS_ETM_ETMIDR]; - cs_etm__set_trace_param_etmv3(t_params, etm, i, etmidr); + etmidr = etm->metadata[m_idx][CS_ETM_ETMIDR]; + cs_etm__set_trace_param_etmv3(t_params, etm, t_idx, m_idx, etmidr); break; case __perf_cs_etmv4_magic: - cs_etm__set_trace_param_etmv4(t_params, etm, i); + cs_etm__set_trace_param_etmv4(t_params, etm, t_idx, m_idx); break; case __perf_cs_ete_magic: - cs_etm__set_trace_param_ete(t_params, etm, i); + cs_etm__set_trace_param_ete(t_params, etm, t_idx, m_idx); break; default: return -EINVAL; @@ -1016,7 +1039,7 @@ out: } static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm, - bool formatted) + bool formatted, int sample_cpu) { struct cs_etm_decoder_params d_params; struct cs_etm_trace_params *t_params = NULL; @@ -1041,7 +1064,7 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm, if (!t_params) goto out_free; - if (cs_etm__init_trace_params(t_params, etm, decoders)) + if (cs_etm__init_trace_params(t_params, etm, formatted, sample_cpu, decoders)) goto out_free; /* Set decoder parameters to decode trace packets */ @@ -1081,14 +1104,15 @@ out_free: static int cs_etm__setup_queue(struct cs_etm_auxtrace *etm, struct auxtrace_queue *queue, unsigned int queue_nr, - bool formatted) + bool formatted, + int sample_cpu) { struct cs_etm_queue *etmq = queue->priv; if (list_empty(&queue->head) || etmq) return 0; - etmq = cs_etm__alloc_queue(etm, formatted); + etmq = cs_etm__alloc_queue(etm, formatted, sample_cpu); if (!etmq) return -ENOMEM; @@ -2816,7 +2840,7 @@ static int cs_etm__process_auxtrace_event(struct perf_session *session, * formatted in piped mode (true). */ err = cs_etm__setup_queue(etm, &etm->queues.queue_array[idx], - idx, true); + idx, true, -1); if (err) return err; @@ -3022,7 +3046,7 @@ static int cs_etm__queue_aux_fragment(struct perf_session *session, off_t file_o idx = auxtrace_event->idx; formatted = !(aux_event->flags & PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW); return cs_etm__setup_queue(etm, &etm->queues.queue_array[idx], - idx, formatted); + idx, formatted, sample->cpu); } /* Wasn't inside this buffer, but there were no parse errors. 1 == 'not found' */ diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h index 7cca37887917..4696267a32f0 100644 --- a/tools/perf/util/cs-etm.h +++ b/tools/perf/util/cs-etm.h @@ -242,7 +242,7 @@ struct cs_etm_packet_queue { int cs_etm__process_auxtrace_info(union perf_event *event, struct perf_session *session); -struct perf_event_attr *cs_etm_get_default_config(struct perf_pmu *pmu); +void cs_etm_get_default_config(const struct perf_pmu *pmu, struct perf_event_attr *attr); enum cs_etm_pid_fmt { CS_ETM_PIDFMT_NONE, diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index fc16299c915f..c29d8a382b19 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -17,6 +17,7 @@ #include "util.h" // rm_rf_perf_data() #include "debug.h" #include "header.h" +#include "rlimit.h" #include <internal/lib.h> static void close_dir(struct perf_data_file *files, int nr) @@ -35,6 +36,7 @@ void perf_data__close_dir(struct perf_data *data) int perf_data__create_dir(struct perf_data *data, int nr) { + enum rlimit_action set_rlimit = NO_CHANGE; struct perf_data_file *files = NULL; int i, ret; @@ -54,11 +56,21 @@ int perf_data__create_dir(struct perf_data *data, int nr) goto out_err; } +retry_open: ret = open(file->path, O_RDWR|O_CREAT|O_TRUNC, S_IRUSR|S_IWUSR); if (ret < 0) { + /* + * If using parallel threads to collect data, + * perf record needs at least 6 fds per CPU. + * When we run out of them try to increase the limits. + */ + if (errno == EMFILE && rlimit__increase_nofile(&set_rlimit)) + goto retry_open; + ret = -errno; goto out_err; } + set_rlimit = NO_CHANGE; file->fd = ret; } diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index 4a1dc21b0450..908e16813722 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -52,8 +52,10 @@ static void al_to_d_al(struct addr_location *al, struct perf_dlfilter_al *d_al) d_al->sym_end = sym->end; if (al->addr < sym->end) d_al->symoff = al->addr - sym->start; - else + else if (al->map) d_al->symoff = al->addr - map__start(al->map) - sym->start; + else + d_al->symoff = 0; d_al->sym_binding = sym->binding; } else { d_al->sym = NULL; diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c index bdfead36b83a..1f629b6fb7cf 100644 --- a/tools/perf/util/dso.c +++ b/tools/perf/util/dso.c @@ -477,6 +477,7 @@ void dso__set_module_info(struct dso *dso, struct kmod_path *m, dso->comp = m->comp; } + dso->is_kmod = 1; dso__set_short_name(dso, strdup(m->name), true); } @@ -1338,6 +1339,7 @@ struct dso *dso__new_id(const char *name, struct dso_id *id) dso->has_srcline = 1; dso->a2l_fails = 1; dso->kernel = DSO_SPACE__USER; + dso->is_kmod = 0; dso->needs_swap = DSO_SWAP__UNSET; dso->comp = COMP_ID__NONE; RB_CLEAR_NODE(&dso->rb_node); diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h index b41c9782c754..3759de8c2267 100644 --- a/tools/perf/util/dso.h +++ b/tools/perf/util/dso.h @@ -162,6 +162,7 @@ struct dso { char *symsrc_filename; unsigned int a2l_fails; enum dso_space_type kernel; + bool is_kmod; enum dso_swap_type needs_swap; enum dso_binary_type symtab_type; enum dso_binary_type binary_type; @@ -181,6 +182,7 @@ struct dso { u8 rel; struct build_id bid; u64 text_offset; + u64 text_end; const char *short_name; const char *long_name; u16 long_name_len; diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c index a164164001fb..44140b7f596a 100644 --- a/tools/perf/util/env.c +++ b/tools/perf/util/env.c @@ -457,7 +457,7 @@ const char *perf_env__cpuid(struct perf_env *env) { int status; - if (!env || !env->cpuid) { /* Assume local operation */ + if (!env->cpuid) { /* Assume local operation */ status = perf_env__read_cpuid(env); if (status) return NULL; @@ -470,7 +470,7 @@ int perf_env__nr_pmu_mappings(struct perf_env *env) { int status; - if (!env || !env->nr_pmu_mappings) { /* Assume local operation */ + if (!env->nr_pmu_mappings) { /* Assume local operation */ status = perf_env__read_pmu_mappings(env); if (status) return 0; @@ -483,7 +483,7 @@ const char *perf_env__pmu_mappings(struct perf_env *env) { int status; - if (!env || !env->pmu_mappings) { /* Assume local operation */ + if (!env->pmu_mappings) { /* Assume local operation */ status = perf_env__read_pmu_mappings(env); if (status) return NULL; diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 7ef43f72098e..e36da58522ef 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -251,6 +251,9 @@ static struct evsel *evlist__dummy_event(struct evlist *evlist) .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_DUMMY, .size = sizeof(attr), /* to capture ABI version */ + /* Avoid frequency mode for dummy events to avoid associated timers. */ + .freq = 0, + .sample_period = 1, }; return evsel__new_idx(&attr, evlist->core.nr_entries); @@ -277,8 +280,6 @@ struct evsel *evlist__add_aux_dummy(struct evlist *evlist, bool system_wide) evsel->core.attr.exclude_kernel = 1; evsel->core.attr.exclude_guest = 1; evsel->core.attr.exclude_hv = 1; - evsel->core.attr.freq = 0; - evsel->core.attr.sample_period = 1; evsel->core.system_wide = system_wide; evsel->no_aux_samples = true; evsel->name = strdup("dummy:u"); @@ -1694,6 +1695,24 @@ void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_ev tracking_evsel->tracking = true; } +struct evsel *evlist__findnew_tracking_event(struct evlist *evlist, bool system_wide) +{ + struct evsel *evsel; + + evsel = evlist__get_tracking_event(evlist); + if (!evsel__is_dummy_event(evsel)) { + evsel = evlist__add_aux_dummy(evlist, system_wide); + if (!evsel) + return NULL; + + evlist__set_tracking_event(evlist, evsel); + } else if (system_wide) { + perf_evlist__go_system_wide(&evlist->core, &evsel->core); + } + + return evsel; +} + struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str) { struct evsel *evsel; diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 664c6bf7b3e0..98e7ddb2bd30 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -387,6 +387,7 @@ bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr); struct evsel *evlist__get_tracking_event(struct evlist *evlist); void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel); +struct evsel *evlist__findnew_tracking_event(struct evlist *evlist, bool system_wide); struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a8a5ff87cc1f..72a5dfc38d38 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -49,6 +49,7 @@ #include "off_cpu.h" #include "pmu.h" #include "pmus.h" +#include "rlimit.h" #include "../perf-sys.h" #include "util/parse-branch-options.h" #include "util/bpf-filter.h" @@ -1989,33 +1990,6 @@ bool evsel__detect_missing_features(struct evsel *evsel) } } -bool evsel__increase_rlimit(enum rlimit_action *set_rlimit) -{ - int old_errno; - struct rlimit l; - - if (*set_rlimit < INCREASED_MAX) { - old_errno = errno; - - if (getrlimit(RLIMIT_NOFILE, &l) == 0) { - if (*set_rlimit == NO_CHANGE) { - l.rlim_cur = l.rlim_max; - } else { - l.rlim_cur = l.rlim_max + 1000; - l.rlim_max = l.rlim_cur; - } - if (setrlimit(RLIMIT_NOFILE, &l) == 0) { - (*set_rlimit) += 1; - errno = old_errno; - return true; - } - } - errno = old_errno; - } - - return false; -} - static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads, int start_cpu_map_idx, int end_cpu_map_idx) @@ -2143,7 +2117,7 @@ try_fallback: * perf stat needs between 5 and 22 fds per CPU. When we run out * of them try to increase the limits. */ - if (err == -EMFILE && evsel__increase_rlimit(&set_rlimit)) + if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit)) goto retry_open; if (err != -EINVAL || idx > 0 || thread > 0) @@ -2766,6 +2740,11 @@ struct tep_format_field *evsel__field(struct evsel *evsel, const char *name) return tep_find_field(evsel->tp_format, name); } +struct tep_format_field *evsel__common_field(struct evsel *evsel, const char *name) +{ + return tep_find_common_field(evsel->tp_format, name); +} + void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name) { struct tep_format_field *field = evsel__field(evsel, name); @@ -2831,6 +2810,14 @@ u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *n return field ? format_field__intval(field, sample, evsel->needs_swap) : 0; } + +u64 evsel__intval_common(struct evsel *evsel, struct perf_sample *sample, const char *name) +{ + struct tep_format_field *field = evsel__common_field(evsel, name); + + return field ? format_field__intval(field, sample, evsel->needs_swap) : 0; +} + #endif bool evsel__fallback(struct evsel *evsel, int err, char *msg, size_t msgsize) diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 848534ec74fa..d791316a1792 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -330,9 +330,6 @@ int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads); bool evsel__detect_missing_features(struct evsel *evsel); -enum rlimit_action { NO_CHANGE, SET_TO_MAX, INCREASED_MAX }; -bool evsel__increase_rlimit(enum rlimit_action *set_rlimit); - bool evsel__precise_ip_fallback(struct evsel *evsel); struct perf_sample; @@ -340,6 +337,7 @@ struct perf_sample; #ifdef HAVE_LIBTRACEEVENT void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name); u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name); +u64 evsel__intval_common(struct evsel *evsel, struct perf_sample *sample, const char *name); static inline char *evsel__strval(struct evsel *evsel, struct perf_sample *sample, const char *name) { @@ -352,6 +350,7 @@ struct tep_format_field; u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap); struct tep_format_field *evsel__field(struct evsel *evsel, const char *name); +struct tep_format_field *evsel__common_field(struct evsel *evsel, const char *name); static inline bool __evsel__match(const struct evsel *evsel, u32 type, u64 config) { diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c index 4488f306de78..7be23b3ac082 100644 --- a/tools/perf/util/expr.c +++ b/tools/perf/util/expr.c @@ -509,7 +509,7 @@ double expr__strcmp_cpuid_str(const struct expr_parse_ctx *ctx __maybe_unused, bool compute_ids __maybe_unused, const char *test_id) { double ret; - struct perf_pmu *pmu = pmu__find_core_pmu(); + struct perf_pmu *pmu = perf_pmus__find_core_pmu(); char *cpuid = perf_pmu__getcpuid(pmu); if (!cpuid) diff --git a/tools/perf/util/expr.y b/tools/perf/util/expr.y index 6c93b358cc2d..e364790babb5 100644 --- a/tools/perf/util/expr.y +++ b/tools/perf/util/expr.y @@ -1,6 +1,8 @@ /* Simple expression parser */ %{ +#ifndef NDEBUG #define YYDEBUG 1 +#endif #include <assert.h> #include <math.h> #include <stdlib.h> diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d812e1e371a7..e86b9439ffee 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -2573,7 +2573,7 @@ error: static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) { u32 nr, i; - char *str; + char *str = NULL; struct strbuf sb; int cpu_nr = ff->ph->env.nr_cpus_avail; u64 size = 0; @@ -2601,7 +2601,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) if (strbuf_add(&sb, str, strlen(str) + 1) < 0) goto error; size += string_size(str); - free(str); + zfree(&str); } ph->env.sibling_cores = strbuf_detach(&sb, NULL); @@ -2620,7 +2620,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) if (strbuf_add(&sb, str, strlen(str) + 1) < 0) goto error; size += string_size(str); - free(str); + zfree(&str); } ph->env.sibling_threads = strbuf_detach(&sb, NULL); @@ -2684,7 +2684,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) if (strbuf_add(&sb, str, strlen(str) + 1) < 0) goto error; size += string_size(str); - free(str); + zfree(&str); } ph->env.sibling_dies = strbuf_detach(&sb, NULL); @@ -2699,6 +2699,7 @@ static int process_cpu_topology(struct feat_fd *ff, void *data __maybe_unused) error: strbuf_release(&sb); + zfree(&str); free_cpu: zfree(&ph->env.cpu); return -1; @@ -2736,10 +2737,9 @@ static int process_numa_topology(struct feat_fd *ff, void *data __maybe_unused) goto error; n->map = perf_cpu_map__new(str); + free(str); if (!n->map) goto error; - - free(str); } ff->ph->env.nr_numa_nodes = nr; ff->ph->env.numa_nodes = nodes; @@ -2913,10 +2913,10 @@ static int process_cache(struct feat_fd *ff, void *data __maybe_unused) return -1; for (i = 0; i < cnt; i++) { - struct cpu_cache_level c; + struct cpu_cache_level *c = &caches[i]; #define _R(v) \ - if (do_read_u32(ff, &c.v))\ + if (do_read_u32(ff, &c->v)) \ goto out_free_caches; \ _R(level) @@ -2926,22 +2926,25 @@ static int process_cache(struct feat_fd *ff, void *data __maybe_unused) #undef _R #define _R(v) \ - c.v = do_read_string(ff); \ - if (!c.v) \ - goto out_free_caches; + c->v = do_read_string(ff); \ + if (!c->v) \ + goto out_free_caches; \ _R(type) _R(size) _R(map) #undef _R - - caches[i] = c; } ff->ph->env.caches = caches; ff->ph->env.caches_cnt = cnt; return 0; out_free_caches: + for (i = 0; i < cnt; i++) { + free(caches[i].type); + free(caches[i].size); + free(caches[i].map); + } free(caches); return -1; } @@ -3585,18 +3588,16 @@ static int perf_header__adds_write(struct perf_header *header, struct feat_copier *fc) { int nr_sections; - struct feat_fd ff; + struct feat_fd ff = { + .fd = fd, + .ph = header, + }; struct perf_file_section *feat_sec, *p; int sec_size; u64 sec_start; int feat; int err; - ff = (struct feat_fd){ - .fd = fd, - .ph = header, - }; - nr_sections = bitmap_weight(header->adds_features, HEADER_FEAT_BITS); if (!nr_sections) return 0; @@ -3623,6 +3624,7 @@ static int perf_header__adds_write(struct perf_header *header, err = do_write(&ff, feat_sec, sec_size); if (err < 0) pr_debug("failed to write feature section\n"); + free(ff.buf); /* TODO: added to silence clang-tidy. */ free(feat_sec); return err; } @@ -3630,11 +3632,11 @@ static int perf_header__adds_write(struct perf_header *header, int perf_header__write_pipe(int fd) { struct perf_pipe_file_header f_header; - struct feat_fd ff; + struct feat_fd ff = { + .fd = fd, + }; int err; - ff = (struct feat_fd){ .fd = fd }; - f_header = (struct perf_pipe_file_header){ .magic = PERF_MAGIC, .size = sizeof(f_header), @@ -3645,7 +3647,7 @@ int perf_header__write_pipe(int fd) pr_debug("failed to write perf pipe header\n"); return err; } - + free(ff.buf); return 0; } @@ -3658,11 +3660,12 @@ static int perf_session__do_write_header(struct perf_session *session, struct perf_file_attr f_attr; struct perf_header *header = &session->header; struct evsel *evsel; - struct feat_fd ff; + struct feat_fd ff = { + .fd = fd, + }; u64 attr_offset; int err; - ff = (struct feat_fd){ .fd = fd}; lseek(fd, sizeof(f_header), SEEK_SET); evlist__for_each_entry(session->evlist, evsel) { @@ -3670,6 +3673,7 @@ static int perf_session__do_write_header(struct perf_session *session, err = do_write(&ff, evsel->core.id, evsel->core.ids * sizeof(u64)); if (err < 0) { pr_debug("failed to write perf header\n"); + free(ff.buf); return err; } } @@ -3695,6 +3699,7 @@ static int perf_session__do_write_header(struct perf_session *session, err = do_write(&ff, &f_attr, sizeof(f_attr)); if (err < 0) { pr_debug("failed to write perf header attribute\n"); + free(ff.buf); return err; } } @@ -3705,8 +3710,10 @@ static int perf_session__do_write_header(struct perf_session *session, if (at_exit) { err = perf_header__adds_write(header, evlist, fd, fc); - if (err < 0) + if (err < 0) { + free(ff.buf); return err; + } } f_header = (struct perf_file_header){ @@ -3728,6 +3735,7 @@ static int perf_session__do_write_header(struct perf_session *session, lseek(fd, 0, SEEK_SET); err = do_write(&ff, &f_header, sizeof(f_header)); + free(ff.buf); if (err < 0) { pr_debug("failed to write perf header\n"); return err; diff --git a/tools/perf/util/hisi-ptt.c b/tools/perf/util/hisi-ptt.c index 45b614bb73bf..43bd1ca62d58 100644 --- a/tools/perf/util/hisi-ptt.c +++ b/tools/perf/util/hisi-ptt.c @@ -108,8 +108,10 @@ static int hisi_ptt_process_auxtrace_event(struct perf_session *session, data_offset = 0; } else { data_offset = lseek(fd, 0, SEEK_CUR); - if (data_offset == -1) + if (data_offset == -1) { + free(data); return -errno; + } } err = readn(fd, data, size); diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c index 3dc8a4968beb..0888b7163b7c 100644 --- a/tools/perf/util/hist.c +++ b/tools/perf/util/hist.c @@ -515,17 +515,16 @@ err_rawdata: err_infos: if (he->branch_info) { - map__put(he->branch_info->from.ms.map); - map__put(he->branch_info->to.ms.map); + map_symbol__exit(&he->branch_info->from.ms); + map_symbol__exit(&he->branch_info->to.ms); zfree(&he->branch_info); } if (he->mem_info) { - map__put(he->mem_info->iaddr.ms.map); - map__put(he->mem_info->daddr.ms.map); + map_symbol__exit(&he->mem_info->iaddr.ms); + map_symbol__exit(&he->mem_info->daddr.ms); } err: - maps__zput(he->ms.maps); - map__zput(he->ms.map); + map_symbol__exit(&he->ms); zfree(&he->stat_acc); return -ENOMEM; } @@ -1317,20 +1316,19 @@ void hist_entry__delete(struct hist_entry *he) struct hist_entry_ops *ops = he->ops; thread__zput(he->thread); - maps__zput(he->ms.maps); - map__zput(he->ms.map); + map_symbol__exit(&he->ms); if (he->branch_info) { - map__zput(he->branch_info->from.ms.map); - map__zput(he->branch_info->to.ms.map); + map_symbol__exit(&he->branch_info->from.ms); + map_symbol__exit(&he->branch_info->to.ms); zfree_srcline(&he->branch_info->srcline_from); zfree_srcline(&he->branch_info->srcline_to); zfree(&he->branch_info); } if (he->mem_info) { - map__zput(he->mem_info->iaddr.ms.map); - map__zput(he->mem_info->daddr.ms.map); + map_symbol__exit(&he->mem_info->iaddr.ms); + map_symbol__exit(&he->mem_info->daddr.ms); mem_info__zput(he->mem_info); } @@ -2142,7 +2140,7 @@ static bool hists__filter_entry_by_thread(struct hists *hists, struct hist_entry *he) { if (hists->thread_filter != NULL && - RC_CHK_ACCESS(he->thread) != RC_CHK_ACCESS(hists->thread_filter)) { + !RC_CHK_EQUAL(he->thread, hists->thread_filter)) { he->filtered |= (1 << HIST_FILTER__THREAD); return true; } @@ -2676,8 +2674,6 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, /* If we have branch cycles always annotate them. */ if (bs && bs->nr && entries[0].flags.cycles) { - int i; - bi = sample__resolve_bstack(sample, al); if (bi) { struct addr_map_symbol *prev = NULL; @@ -2692,7 +2688,7 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, * Note that perf stores branches reversed from * program order! */ - for (i = bs->nr - 1; i >= 0; i--) { + for (int i = bs->nr - 1; i >= 0; i--) { addr_map_symbol__account_cycles(&bi[i].from, nonany_branch_mode ? NULL : prev, bi[i].flags.cycles); @@ -2701,6 +2697,10 @@ void hist__account_cycles(struct branch_stack *bs, struct addr_location *al, if (total_cycles) *total_cycles += bi[i].flags.cycles; } + for (unsigned int i = 0; i < bs->nr; i++) { + map_symbol__exit(&bi[i].to.ms); + map_symbol__exit(&bi[i].from.ms); + } free(bi); } } diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c index af9710622a1f..bccb988a7a44 100644 --- a/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c +++ b/tools/perf/util/intel-pt-decoder/intel-pt-pkt-decoder.c @@ -8,7 +8,9 @@ #include <string.h> #include <endian.h> #include <byteswap.h> +#include <linux/kernel.h> #include <linux/compiler.h> +#include <asm-generic/unaligned.h> #include "intel-pt-pkt-decoder.h" @@ -17,17 +19,11 @@ #define BIT63 ((uint64_t)1 << 63) #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ -#define le16_to_cpu bswap_16 -#define le32_to_cpu bswap_32 -#define le64_to_cpu bswap_64 #define memcpy_le64(d, s, n) do { \ memcpy((d), (s), (n)); \ *(d) = le64_to_cpu(*(d)); \ } while (0) #else -#define le16_to_cpu -#define le32_to_cpu -#define le64_to_cpu #define memcpy_le64 memcpy #endif @@ -83,7 +79,7 @@ static int intel_pt_get_long_tnt(const unsigned char *buf, size_t len, if (len < 8) return INTEL_PT_NEED_MORE_BYTES; - payload = le64_to_cpu(*(uint64_t *)buf); + payload = get_unaligned_le64(buf); for (count = 47; count; count--) { if (payload & BIT63) @@ -124,26 +120,21 @@ static int intel_pt_get_cbr(const unsigned char *buf, size_t len, if (len < 4) return INTEL_PT_NEED_MORE_BYTES; packet->type = INTEL_PT_CBR; - packet->payload = le16_to_cpu(*(uint16_t *)(buf + 2)); + packet->payload = get_unaligned_le16(buf + 2); return 4; } static int intel_pt_get_vmcs(const unsigned char *buf, size_t len, struct intel_pt_pkt *packet) { - unsigned int count = (52 - 5) >> 3; - - if (count < 1 || count > 7) - return INTEL_PT_BAD_PACKET; - - if (len < count + 2) + if (len < 7) return INTEL_PT_NEED_MORE_BYTES; packet->type = INTEL_PT_VMCS; - packet->count = count; - memcpy_le64(&packet->payload, buf + 2, count); + packet->count = 5; + memcpy_le64(&packet->payload, buf + 2, 5); - return count + 2; + return 7; } static int intel_pt_get_ovf(struct intel_pt_pkt *packet) @@ -199,7 +190,7 @@ static int intel_pt_get_mnt(const unsigned char *buf, size_t len, if (len < 11) return INTEL_PT_NEED_MORE_BYTES; packet->type = INTEL_PT_MNT; - memcpy_le64(&packet->payload, buf + 3, 8); + packet->payload = get_unaligned_le64(buf + 3); return 11; } @@ -228,12 +219,12 @@ static int intel_pt_get_ptwrite(const unsigned char *buf, size_t len, case 0: if (len < 6) return INTEL_PT_NEED_MORE_BYTES; - packet->payload = le32_to_cpu(*(uint32_t *)(buf + 2)); + packet->payload = get_unaligned_le32(buf + 2); return 6; case 1: if (len < 10) return INTEL_PT_NEED_MORE_BYTES; - packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2)); + packet->payload = get_unaligned_le64(buf + 2); return 10; default: return INTEL_PT_BAD_PACKET; @@ -258,7 +249,7 @@ static int intel_pt_get_mwait(const unsigned char *buf, size_t len, if (len < 10) return INTEL_PT_NEED_MORE_BYTES; packet->type = INTEL_PT_MWAIT; - packet->payload = le64_to_cpu(*(uint64_t *)(buf + 2)); + packet->payload = get_unaligned_le64(buf + 2); return 10; } @@ -311,7 +302,7 @@ static int intel_pt_get_bip_8(const unsigned char *buf, size_t len, return INTEL_PT_NEED_MORE_BYTES; packet->type = INTEL_PT_BIP; packet->count = buf[0] >> 3; - memcpy_le64(&packet->payload, buf + 1, 8); + packet->payload = get_unaligned_le64(buf + 1); return 9; } @@ -350,7 +341,7 @@ static int intel_pt_get_evd(const unsigned char *buf, size_t len, packet->type = INTEL_PT_EVD; packet->count = buf[2] & 0x3f; packet->payload = buf[3]; - memcpy_le64(&packet->payload, buf + 3, 8); + packet->payload = get_unaligned_le64(buf + 3); return 11; } @@ -465,13 +456,13 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte, if (len < 3) return INTEL_PT_NEED_MORE_BYTES; ip_len = 2; - packet->payload = le16_to_cpu(*(uint16_t *)(buf + 1)); + packet->payload = get_unaligned_le16(buf + 1); break; case 2: if (len < 5) return INTEL_PT_NEED_MORE_BYTES; ip_len = 4; - packet->payload = le32_to_cpu(*(uint32_t *)(buf + 1)); + packet->payload = get_unaligned_le32(buf + 1); break; case 3: case 4: @@ -484,7 +475,7 @@ static int intel_pt_get_ip(enum intel_pt_pkt_type type, unsigned int byte, if (len < 9) return INTEL_PT_NEED_MORE_BYTES; ip_len = 8; - packet->payload = le64_to_cpu(*(uint64_t *)(buf + 1)); + packet->payload = get_unaligned_le64(buf + 1); break; default: return INTEL_PT_BAD_PACKET; diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c index dbf0bc71a63b..f38893e0b036 100644 --- a/tools/perf/util/intel-pt.c +++ b/tools/perf/util/intel-pt.c @@ -1512,9 +1512,11 @@ static void intel_pt_sample_flags(struct intel_pt_queue *ptq) } else if (ptq->state->flags & INTEL_PT_ASYNC) { if (!ptq->state->to_ip) ptq->flags = PERF_IP_FLAG_BRANCH | + PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_TRACE_END; else if (ptq->state->from_nr && !ptq->state->to_nr) ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | + PERF_IP_FLAG_ASYNC | PERF_IP_FLAG_VMEXIT; else ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | diff --git a/tools/perf/util/intel-pt.h b/tools/perf/util/intel-pt.h index c7d6068e3a6b..18fd0be52e6c 100644 --- a/tools/perf/util/intel-pt.h +++ b/tools/perf/util/intel-pt.h @@ -42,6 +42,7 @@ struct auxtrace_record *intel_pt_recording_init(int *err); int intel_pt_process_auxtrace_info(union perf_event *event, struct perf_session *session); -struct perf_event_attr *intel_pt_pmu_default_config(struct perf_pmu *pmu); +void intel_pt_pmu_default_config(const struct perf_pmu *intel_pt_pmu, + struct perf_event_attr *attr); #endif diff --git a/tools/perf/util/jitdump.c b/tools/perf/util/jitdump.c index 6b2b96c16ccd..1f657ef8975f 100644 --- a/tools/perf/util/jitdump.c +++ b/tools/perf/util/jitdump.c @@ -675,6 +675,7 @@ jit_repipe_unwinding_info(struct jit_buf_desc *jd, union jr_entry *jr) jd->eh_frame_hdr_size = jr->unwinding.eh_frame_hdr_size; jd->unwinding_size = jr->unwinding.unwinding_size; jd->unwinding_mapped_size = jr->unwinding.mapped_size; + free(jd->unwinding_data); jd->unwinding_data = unwinding_data; return 0; diff --git a/tools/perf/util/kwork.h b/tools/perf/util/kwork.h index 53b7327550b8..76fe2a821bcf 100644 --- a/tools/perf/util/kwork.h +++ b/tools/perf/util/kwork.h @@ -16,6 +16,7 @@ enum kwork_class_type { KWORK_CLASS_IRQ, KWORK_CLASS_SOFTIRQ, KWORK_CLASS_WORKQUEUE, + KWORK_CLASS_SCHED, KWORK_CLASS_MAX, }; @@ -23,6 +24,7 @@ enum kwork_report_type { KWORK_REPORT_RUNTIME, KWORK_REPORT_LATENCY, KWORK_REPORT_TIMEHIST, + KWORK_REPORT_TOP, }; enum kwork_trace_type { @@ -91,6 +93,7 @@ struct kwork_atom_page { DECLARE_BITMAP(bitmap, NR_ATOM_PER_PAGE); }; +struct perf_kwork; struct kwork_class; struct kwork_work { /* @@ -127,6 +130,13 @@ struct kwork_work { u64 max_latency_start; u64 max_latency_end; u64 total_latency; + + /* + * top report + */ + u32 cpu_usage; + u32 tgid; + bool is_kthread; }; struct kwork_class { @@ -142,8 +152,10 @@ struct kwork_class { int (*class_init)(struct kwork_class *class, struct perf_session *session); - void (*work_init)(struct kwork_class *class, + void (*work_init)(struct perf_kwork *kwork, + struct kwork_class *class, struct kwork_work *work, + enum kwork_trace_type src_type, struct evsel *evsel, struct perf_sample *sample, struct machine *machine); @@ -152,7 +164,6 @@ struct kwork_class { char *buf, int len); }; -struct perf_kwork; struct trace_kwork_handler { int (*raise_event)(struct perf_kwork *kwork, struct kwork_class *class, struct evsel *evsel, @@ -165,6 +176,23 @@ struct trace_kwork_handler { int (*exit_event)(struct perf_kwork *kwork, struct kwork_class *class, struct evsel *evsel, struct perf_sample *sample, struct machine *machine); + + int (*sched_switch_event)(struct perf_kwork *kwork, + struct kwork_class *class, struct evsel *evsel, + struct perf_sample *sample, struct machine *machine); +}; + +struct __top_cpus_runtime { + u64 load; + u64 idle; + u64 irq; + u64 softirq; + u64 total; +}; + +struct kwork_top_stat { + DECLARE_BITMAP(all_cpus_bitmap, MAX_NR_CPUS); + struct __top_cpus_runtime *cpus_runtime; }; struct perf_kwork { @@ -218,6 +246,11 @@ struct perf_kwork { u64 all_runtime; u64 all_count; u64 nr_skipped_events[KWORK_TRACE_MAX + 1]; + + /* + * perf kwork top data + */ + struct kwork_top_stat top_stat; }; struct kwork_work *perf_kwork_add_work(struct perf_kwork *kwork, @@ -233,6 +266,13 @@ void perf_kwork__report_cleanup_bpf(void); void perf_kwork__trace_start(void); void perf_kwork__trace_finish(void); +int perf_kwork__top_prepare_bpf(struct perf_kwork *kwork); +int perf_kwork__top_read_bpf(struct perf_kwork *kwork); +void perf_kwork__top_cleanup_bpf(void); + +void perf_kwork__top_start(void); +void perf_kwork__top_finish(void); + #else /* !HAVE_BPF_SKEL */ static inline int @@ -252,6 +292,23 @@ static inline void perf_kwork__report_cleanup_bpf(void) {} static inline void perf_kwork__trace_start(void) {} static inline void perf_kwork__trace_finish(void) {} +static inline int +perf_kwork__top_prepare_bpf(struct perf_kwork *kwork __maybe_unused) +{ + return -1; +} + +static inline int +perf_kwork__top_read_bpf(struct perf_kwork *kwork __maybe_unused) +{ + return -1; +} + +static inline void perf_kwork__top_cleanup_bpf(void) {} + +static inline void perf_kwork__top_start(void) {} +static inline void perf_kwork__top_finish(void) {} + #endif /* HAVE_BPF_SKEL */ #endif /* PERF_UTIL_KWORK_H */ diff --git a/tools/perf/util/lock-contention.h b/tools/perf/util/lock-contention.h index fa16532c971c..1a7248ff3889 100644 --- a/tools/perf/util/lock-contention.h +++ b/tools/perf/util/lock-contention.h @@ -9,9 +9,11 @@ struct lock_filter { int nr_types; int nr_addrs; int nr_syms; + int nr_cgrps; unsigned int *types; unsigned long *addrs; char **syms; + u64 *cgrps; }; struct lock_stat { @@ -136,6 +138,7 @@ struct lock_contention { struct hlist_head *result; struct lock_filter *filters; struct lock_contention_fails fails; + struct rb_root cgroups; unsigned long map_nr_entries; int max_stack; int stack_skip; @@ -151,7 +154,7 @@ int lock_contention_prepare(struct lock_contention *con); int lock_contention_start(void); int lock_contention_stop(void); int lock_contention_read(struct lock_contention *con); -int lock_contention_finish(void); +int lock_contention_finish(struct lock_contention *con); #else /* !HAVE_BPF_SKEL */ @@ -162,7 +165,10 @@ static inline int lock_contention_prepare(struct lock_contention *con __maybe_un static inline int lock_contention_start(void) { return 0; } static inline int lock_contention_stop(void) { return 0; } -static inline int lock_contention_finish(void) { return 0; } +static inline int lock_contention_finish(struct lock_contention *con __maybe_unused) +{ + return 0; +} static inline int lock_contention_read(struct lock_contention *con __maybe_unused) { diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index 88f31b3a63ac..90c750150b19 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -67,7 +67,6 @@ static void machine__threads_init(struct machine *machine) threads->entries = RB_ROOT_CACHED; init_rwsem(&threads->lock); threads->nr = 0; - INIT_LIST_HEAD(&threads->dead); threads->last_match = NULL; } } @@ -969,7 +968,7 @@ static int machine__process_ksymbol_unregister(struct machine *machine, if (!map) return 0; - if (RC_CHK_ACCESS(map) != RC_CHK_ACCESS(machine->vmlinux_map)) + if (!RC_CHK_EQUAL(map, machine->vmlinux_map)) maps__remove(machine__kernel_maps(machine), map); else { struct dso *dso = map__dso(map); @@ -2058,7 +2057,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread_rb_n if (!nd) nd = thread_rb_node__find(th, &threads->entries.rb_root); - if (threads->last_match && RC_CHK_ACCESS(threads->last_match) == RC_CHK_ACCESS(th)) + if (threads->last_match && RC_CHK_EQUAL(threads->last_match, th)) threads__set_last_match(threads, NULL); if (lock) @@ -2213,9 +2212,7 @@ int machine__process_event(struct machine *machine, union perf_event *event, static bool symbol__match_regex(struct symbol *sym, regex_t *regex) { - if (!regexec(regex, sym->name, 0, NULL, 0)) - return true; - return false; + return regexec(regex, sym->name, 0, NULL, 0) == 0; } static void ip__resolve_ams(struct thread *thread, @@ -2392,8 +2389,7 @@ static int add_callchain_ip(struct thread *thread, iter_cycles, branch_from, srcline); out: addr_location__exit(&al); - maps__put(ms.maps); - map__put(ms.map); + map_symbol__exit(&ms); return err; } @@ -2624,16 +2620,18 @@ static int lbr_callchain_add_lbr_ip(struct thread *thread, save_lbr_cursor_node(thread, cursor, i); } - /* Add LBR ip from first entries.to */ - ip = entries[0].to; - flags = &entries[0].flags; - *branch_from = entries[0].from; - err = add_callchain_ip(thread, cursor, parent, - root_al, &cpumode, ip, - true, flags, NULL, - *branch_from); - if (err) - return err; + if (lbr_nr > 0) { + /* Add LBR ip from first entries.to */ + ip = entries[0].to; + flags = &entries[0].flags; + *branch_from = entries[0].from; + err = add_callchain_ip(thread, cursor, parent, + root_al, &cpumode, ip, + true, flags, NULL, + *branch_from); + if (err) + return err; + } return 0; } @@ -3117,8 +3115,7 @@ static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms if (ret != 0) return ret; } - map__put(ilist_ms.map); - maps__put(ilist_ms.maps); + map_symbol__exit(&ilist_ms); return ret; } diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h index d034ecaf89c1..1279acda6a8a 100644 --- a/tools/perf/util/machine.h +++ b/tools/perf/util/machine.h @@ -35,7 +35,6 @@ struct threads { struct rb_root_cached entries; struct rw_semaphore lock; unsigned int nr; - struct list_head dead; struct thread *last_match; }; diff --git a/tools/perf/util/map_symbol.c b/tools/perf/util/map_symbol.c new file mode 100644 index 000000000000..bef5079f2403 --- /dev/null +++ b/tools/perf/util/map_symbol.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "map_symbol.h" +#include "maps.h" +#include "map.h" + +void map_symbol__exit(struct map_symbol *ms) +{ + maps__zput(ms->maps); + map__zput(ms->map); +} + +void addr_map_symbol__exit(struct addr_map_symbol *ams) +{ + map_symbol__exit(&ams->ms); +} diff --git a/tools/perf/util/map_symbol.h b/tools/perf/util/map_symbol.h index e08817b0c30f..72d5ed938ed6 100644 --- a/tools/perf/util/map_symbol.h +++ b/tools/perf/util/map_symbol.h @@ -22,4 +22,8 @@ struct addr_map_symbol { u64 phys_addr; u64 data_page_size; }; + +void map_symbol__exit(struct map_symbol *ms); +void addr_map_symbol__exit(struct addr_map_symbol *ams); + #endif // __PERF_MAP_SYMBOL diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 39ffe8ceb380..954b235e12e5 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -185,7 +185,6 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, { int i = *argv_nr, k = 0; struct perf_mem_event *e; - struct perf_pmu *pmu; for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) { e = perf_mem_events__ptr(j); @@ -202,6 +201,8 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, rec_argv[i++] = "-e"; rec_argv[i++] = perf_mem_events__name(j, NULL); } else { + struct perf_pmu *pmu = NULL; + if (!e->supported) { perf_mem_events__print_unsupport_hybrid(e, j); return -1; diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c index 6231044a491e..0484736d9fe4 100644 --- a/tools/perf/util/metricgroup.c +++ b/tools/perf/util/metricgroup.c @@ -498,7 +498,7 @@ static int metricgroup__sys_event_iter(const struct pmu_metric *pm, while ((pmu = perf_pmus__scan(pmu))) { - if (!pmu->id || strcmp(pmu->id, pm->compat)) + if (!pmu->id || !pmu_uncore_identifier_match(pm->compat, pmu->id)) continue; return d->fn(pm, table, d->data); diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 65608a3cba81..aa2f5c6fc7fc 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -34,8 +34,9 @@ #ifdef PARSER_DEBUG extern int parse_events_debug; #endif -static int get_config_terms(struct list_head *head_config, - struct list_head *head_terms __maybe_unused); +static int get_config_terms(struct parse_events_terms *head_config, struct list_head *head_terms); +static int parse_events_terms__copy(const struct parse_events_terms *src, + struct parse_events_terms *dest); struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = { @@ -153,26 +154,27 @@ const char *event_type(int type) return "unknown"; } -static char *get_config_str(struct list_head *head_terms, enum parse_events__term_type type_term) +static char *get_config_str(struct parse_events_terms *head_terms, + enum parse_events__term_type type_term) { struct parse_events_term *term; if (!head_terms) return NULL; - list_for_each_entry(term, head_terms, list) + list_for_each_entry(term, &head_terms->terms, list) if (term->type_term == type_term) return term->val.str; return NULL; } -static char *get_config_metric_id(struct list_head *head_terms) +static char *get_config_metric_id(struct parse_events_terms *head_terms) { return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_METRIC_ID); } -static char *get_config_name(struct list_head *head_terms) +static char *get_config_name(struct parse_events_terms *head_terms) { return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_NAME); } @@ -188,11 +190,11 @@ static char *get_config_name(struct list_head *head_terms) * @config_terms: the list of terms that may contain a raw term. * @pmu: the PMU to scan for events from. */ -static void fix_raw(struct list_head *config_terms, struct perf_pmu *pmu) +static void fix_raw(struct parse_events_terms *config_terms, struct perf_pmu *pmu) { struct parse_events_term *term; - list_for_each_entry(term, config_terms, list) { + list_for_each_entry(term, &config_terms->terms, list) { u64 num; if (term->type_term != PARSE_EVENTS__TERM_TYPE_RAW) @@ -356,7 +358,7 @@ static int config_term_common(struct perf_event_attr *attr, struct parse_events_term *term, struct parse_events_error *err); static int config_attr(struct perf_event_attr *attr, - struct list_head *head, + struct parse_events_terms *head, struct parse_events_error *err, config_term_func_t config_term); @@ -442,7 +444,7 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state, int parse_events_add_cache(struct list_head *list, int *idx, const char *name, struct parse_events_state *parse_state, - struct list_head *head_config) + struct parse_events_terms *head_config) { struct perf_pmu *pmu = NULL; bool found_supported = false; @@ -520,7 +522,7 @@ static void tracepoint_error(struct parse_events_error *e, int err, static int add_tracepoint(struct list_head *list, int *idx, const char *sys_name, const char *evt_name, struct parse_events_error *err, - struct list_head *head_config, void *loc_) + struct parse_events_terms *head_config, void *loc_) { YYLTYPE *loc = loc_; struct evsel *evsel = evsel__newtp_idx(sys_name, evt_name, (*idx)++); @@ -545,7 +547,7 @@ static int add_tracepoint(struct list_head *list, int *idx, static int add_tracepoint_multi_event(struct list_head *list, int *idx, const char *sys_name, const char *evt_name, struct parse_events_error *err, - struct list_head *head_config, YYLTYPE *loc) + struct parse_events_terms *head_config, YYLTYPE *loc) { char *evt_path; struct dirent *evt_ent; @@ -593,7 +595,7 @@ static int add_tracepoint_multi_event(struct list_head *list, int *idx, static int add_tracepoint_event(struct list_head *list, int *idx, const char *sys_name, const char *evt_name, struct parse_events_error *err, - struct list_head *head_config, YYLTYPE *loc) + struct parse_events_terms *head_config, YYLTYPE *loc) { return strpbrk(evt_name, "*?") ? add_tracepoint_multi_event(list, idx, sys_name, evt_name, @@ -605,7 +607,7 @@ static int add_tracepoint_event(struct list_head *list, int *idx, static int add_tracepoint_multi_sys(struct list_head *list, int *idx, const char *sys_name, const char *evt_name, struct parse_events_error *err, - struct list_head *head_config, YYLTYPE *loc) + struct parse_events_terms *head_config, YYLTYPE *loc) { struct dirent *events_ent; DIR *events_dir; @@ -680,7 +682,7 @@ do { \ int parse_events_add_breakpoint(struct parse_events_state *parse_state, struct list_head *list, u64 addr, char *type, u64 len, - struct list_head *head_config __maybe_unused) + struct parse_events_terms *head_config) { struct perf_event_attr attr; LIST_HEAD(config_terms); @@ -1066,21 +1068,20 @@ static int config_term_tracepoint(struct perf_event_attr *attr, #endif static int config_attr(struct perf_event_attr *attr, - struct list_head *head, + struct parse_events_terms *head, struct parse_events_error *err, config_term_func_t config_term) { struct parse_events_term *term; - list_for_each_entry(term, head, list) + list_for_each_entry(term, &head->terms, list) if (config_term(attr, term, err)) return -EINVAL; return 0; } -static int get_config_terms(struct list_head *head_config, - struct list_head *head_terms __maybe_unused) +static int get_config_terms(struct parse_events_terms *head_config, struct list_head *head_terms) { #define ADD_CONFIG_TERM(__type, __weak) \ struct evsel_config_term *__t; \ @@ -1113,7 +1114,7 @@ do { \ struct parse_events_term *term; - list_for_each_entry(term, head_config, list) { + list_for_each_entry(term, &head_config->terms, list) { switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_SAMPLE_PERIOD: ADD_CONFIG_TERM_VAL(PERIOD, period, term->val.num, term->weak); @@ -1194,14 +1195,14 @@ do { \ * Add EVSEL__CONFIG_TERM_CFG_CHG where cfg_chg will have a bit set for * each bit of attr->config that the user has changed. */ -static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config, +static int get_config_chgs(struct perf_pmu *pmu, struct parse_events_terms *head_config, struct list_head *head_terms) { struct parse_events_term *term; u64 bits = 0; int type; - list_for_each_entry(term, head_config, list) { + list_for_each_entry(term, &head_config->terms, list) { switch (term->type_term) { case PARSE_EVENTS__TERM_TYPE_USER: type = perf_pmu__format_type(pmu, term->config); @@ -1251,7 +1252,7 @@ static int get_config_chgs(struct perf_pmu *pmu, struct list_head *head_config, int parse_events_add_tracepoint(struct list_head *list, int *idx, const char *sys, const char *event, struct parse_events_error *err, - struct list_head *head_config, void *loc_) + struct parse_events_terms *head_config, void *loc_) { YYLTYPE *loc = loc_; #ifdef HAVE_LIBTRACEEVENT @@ -1284,7 +1285,7 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx, static int __parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, struct perf_pmu *pmu, u32 type, u32 extended_type, - u64 config, struct list_head *head_config) + u64 config, struct parse_events_terms *head_config) { struct perf_event_attr attr; LIST_HEAD(config_terms); @@ -1320,7 +1321,7 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state, int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, - struct list_head *head_config, + struct parse_events_terms *head_config, bool wildcard) { struct perf_pmu *pmu = NULL; @@ -1369,7 +1370,7 @@ static bool config_term_percore(struct list_head *config_terms) int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, const char *name, - struct list_head *head_config, + const struct parse_events_terms *const_parsed_terms, bool auto_merge_stats, void *loc_) { struct perf_event_attr attr; @@ -1379,6 +1380,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, struct parse_events_error *err = parse_state->error; YYLTYPE *loc = loc_; LIST_HEAD(config_terms); + struct parse_events_terms parsed_terms; pmu = parse_state->fake_pmu ?: perf_pmus__find(name); @@ -1392,32 +1394,37 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, return -EINVAL; } + parse_events_terms__init(&parsed_terms); + if (const_parsed_terms) { + int ret = parse_events_terms__copy(const_parsed_terms, &parsed_terms); + + if (ret) + return ret; + } + if (verbose > 1) { struct strbuf sb; strbuf_init(&sb, /*hint=*/ 0); - if (pmu->selectable && !head_config) { + if (pmu->selectable && list_empty(&parsed_terms.terms)) { strbuf_addf(&sb, "%s//", name); } else { strbuf_addf(&sb, "%s/", name); - parse_events_term__to_strbuf(head_config, &sb); + parse_events_terms__to_strbuf(&parsed_terms, &sb); strbuf_addch(&sb, '/'); } fprintf(stderr, "Attempt to add: %s\n", sb.buf); strbuf_release(&sb); } - if (head_config) - fix_raw(head_config, pmu); + fix_raw(&parsed_terms, pmu); + + memset(&attr, 0, sizeof(attr)); + if (pmu->perf_event_attr_init_default) + pmu->perf_event_attr_init_default(pmu, &attr); - if (pmu->default_config) { - memcpy(&attr, pmu->default_config, - sizeof(struct perf_event_attr)); - } else { - memset(&attr, 0, sizeof(attr)); - } attr.type = pmu->type; - if (!head_config) { + if (list_empty(&parsed_terms.terms)) { evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true, /*name=*/NULL, /*metric_id=*/NULL, pmu, @@ -1426,14 +1433,16 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, return evsel ? 0 : -ENOMEM; } - if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, head_config, &info, err)) + if (!parse_state->fake_pmu && perf_pmu__check_alias(pmu, &parsed_terms, &info, err)) { + parse_events_terms__exit(&parsed_terms); return -EINVAL; + } if (verbose > 1) { struct strbuf sb; strbuf_init(&sb, /*hint=*/ 0); - parse_events_term__to_strbuf(head_config, &sb); + parse_events_terms__to_strbuf(&parsed_terms, &sb); fprintf(stderr, "..after resolving event: %s/%s/\n", name, sb.buf); strbuf_release(&sb); } @@ -1442,39 +1451,53 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, * Configure hardcoded terms first, no need to check * return value when called with fail == 0 ;) */ - if (config_attr(&attr, head_config, parse_state->error, config_term_pmu)) + if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) { + parse_events_terms__exit(&parsed_terms); return -EINVAL; + } - if (get_config_terms(head_config, &config_terms)) + if (get_config_terms(&parsed_terms, &config_terms)) { + parse_events_terms__exit(&parsed_terms); return -ENOMEM; + } /* * When using default config, record which bits of attr->config were * changed by the user. */ - if (pmu->default_config && get_config_chgs(pmu, head_config, &config_terms)) + if (pmu->perf_event_attr_init_default && + get_config_chgs(pmu, &parsed_terms, &config_terms)) { + parse_events_terms__exit(&parsed_terms); return -ENOMEM; + } - if (!parse_state->fake_pmu && perf_pmu__config(pmu, &attr, head_config, parse_state->error)) { + if (!parse_state->fake_pmu && + perf_pmu__config(pmu, &attr, &parsed_terms, parse_state->error)) { free_config_terms(&config_terms); + parse_events_terms__exit(&parsed_terms); return -EINVAL; } evsel = __add_event(list, &parse_state->idx, &attr, /*init_attr=*/true, - get_config_name(head_config), - get_config_metric_id(head_config), pmu, + get_config_name(&parsed_terms), + get_config_metric_id(&parsed_terms), pmu, &config_terms, auto_merge_stats, /*cpu_list=*/NULL); - if (!evsel) + if (!evsel) { + parse_events_terms__exit(&parsed_terms); return -ENOMEM; + } if (evsel->name) evsel->use_config_name = true; evsel->percore = config_term_percore(&evsel->config_terms); - if (parse_state->fake_pmu) + if (parse_state->fake_pmu) { + parse_events_terms__exit(&parsed_terms); return 0; + } + parse_events_terms__exit(&parsed_terms); free((char *)evsel->unit); evsel->unit = strdup(info.unit); evsel->scale = info.scale; @@ -1484,27 +1507,29 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, } int parse_events_multi_pmu_add(struct parse_events_state *parse_state, - char *str, struct list_head *head, + const char *event_name, + const struct parse_events_terms *const_parsed_terms, struct list_head **listp, void *loc_) { struct parse_events_term *term; struct list_head *list = NULL; - struct list_head *orig_head = NULL; struct perf_pmu *pmu = NULL; YYLTYPE *loc = loc_; int ok = 0; const char *config; + struct parse_events_terms parsed_terms; *listp = NULL; - if (!head) { - head = malloc(sizeof(struct list_head)); - if (!head) - goto out_err; + parse_events_terms__init(&parsed_terms); + if (const_parsed_terms) { + int ret = parse_events_terms__copy(const_parsed_terms, &parsed_terms); - INIT_LIST_HEAD(head); + if (ret) + return ret; } - config = strdup(str); + + config = strdup(event_name); if (!config) goto out_err; @@ -1515,7 +1540,7 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, zfree(&config); goto out_err; } - list_add_tail(&term->list, head); + list_add_tail(&term->list, &parsed_terms.terms); /* Add it for all PMUs that support the alias */ list = malloc(sizeof(struct list_head)); @@ -1530,44 +1555,42 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state, if (parse_events__filter_pmu(parse_state, pmu)) continue; - if (!perf_pmu__have_event(pmu, str)) + if (!perf_pmu__have_event(pmu, event_name)) continue; auto_merge_stats = perf_pmu__auto_merge_stats(pmu); - parse_events_copy_term_list(head, &orig_head); if (!parse_events_add_pmu(parse_state, list, pmu->name, - orig_head, auto_merge_stats, loc)) { + &parsed_terms, auto_merge_stats, loc)) { struct strbuf sb; strbuf_init(&sb, /*hint=*/ 0); - parse_events_term__to_strbuf(orig_head, &sb); - pr_debug("%s -> %s/%s/\n", str, pmu->name, sb.buf); + parse_events_terms__to_strbuf(&parsed_terms, &sb); + pr_debug("%s -> %s/%s/\n", event_name, pmu->name, sb.buf); strbuf_release(&sb); ok++; } - parse_events_terms__delete(orig_head); } if (parse_state->fake_pmu) { - if (!parse_events_add_pmu(parse_state, list, str, head, + if (!parse_events_add_pmu(parse_state, list, event_name, &parsed_terms, /*auto_merge_stats=*/true, loc)) { struct strbuf sb; strbuf_init(&sb, /*hint=*/ 0); - parse_events_term__to_strbuf(head, &sb); - pr_debug("%s -> %s/%s/\n", str, "fake_pmu", sb.buf); + parse_events_terms__to_strbuf(&parsed_terms, &sb); + pr_debug("%s -> %s/%s/\n", event_name, "fake_pmu", sb.buf); strbuf_release(&sb); ok++; } } out_err: + parse_events_terms__exit(&parsed_terms); if (ok) *listp = list; else free(list); - parse_events_terms__delete(head); return ok ? 0 : -1; } @@ -1832,7 +1855,7 @@ static int parse_events__scanner(const char *str, /* * parse event config string, return a list of event terms. */ -int parse_events_terms(struct list_head *terms, const char *str, FILE *input) +int parse_events_terms(struct parse_events_terms *terms, const char *str, FILE *input) { struct parse_events_state parse_state = { .terms = NULL, @@ -1841,14 +1864,10 @@ int parse_events_terms(struct list_head *terms, const char *str, FILE *input) int ret; ret = parse_events__scanner(str, input, &parse_state); + if (!ret) + list_splice(&parse_state.terms->terms, &terms->terms); - if (!ret) { - list_splice(parse_state.terms, terms); - zfree(&parse_state.terms); - return 0; - } - - parse_events_terms__delete(parse_state.terms); + zfree(&parse_state.terms); return ret; } @@ -2530,8 +2549,10 @@ int parse_events_term__clone(struct parse_events_term **new, return new_term(new, &temp, /*str=*/NULL, term->val.num); str = strdup(term->val.str); - if (!str) + if (!str) { + zfree(&temp.config); return -ENOMEM; + } return new_term(new, &temp, str, /*num=*/0); } @@ -2544,58 +2565,56 @@ void parse_events_term__delete(struct parse_events_term *term) free(term); } -int parse_events_copy_term_list(struct list_head *old, - struct list_head **new) +static int parse_events_terms__copy(const struct parse_events_terms *src, + struct parse_events_terms *dest) { - struct parse_events_term *term, *n; - int ret; - - if (!old) { - *new = NULL; - return 0; - } + struct parse_events_term *term; - *new = malloc(sizeof(struct list_head)); - if (!*new) - return -ENOMEM; - INIT_LIST_HEAD(*new); + list_for_each_entry (term, &src->terms, list) { + struct parse_events_term *n; + int ret; - list_for_each_entry (term, old, list) { ret = parse_events_term__clone(&n, term); if (ret) return ret; - list_add_tail(&n->list, *new); + + list_add_tail(&n->list, &dest->terms); } return 0; } -void parse_events_terms__purge(struct list_head *terms) +void parse_events_terms__init(struct parse_events_terms *terms) +{ + INIT_LIST_HEAD(&terms->terms); +} + +void parse_events_terms__exit(struct parse_events_terms *terms) { struct parse_events_term *term, *h; - list_for_each_entry_safe(term, h, terms, list) { + list_for_each_entry_safe(term, h, &terms->terms, list) { list_del_init(&term->list); parse_events_term__delete(term); } } -void parse_events_terms__delete(struct list_head *terms) +void parse_events_terms__delete(struct parse_events_terms *terms) { if (!terms) return; - parse_events_terms__purge(terms); + parse_events_terms__exit(terms); free(terms); } -int parse_events_term__to_strbuf(struct list_head *term_list, struct strbuf *sb) +int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct strbuf *sb) { struct parse_events_term *term; bool first = true; - if (!term_list) + if (!terms) return 0; - list_for_each_entry(term, term_list, list) { + list_for_each_entry(term, &terms->terms, list) { int ret; if (!first) { diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 594e5d2dc67f..63c0a36a4bf1 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -44,7 +44,6 @@ static inline int parse_events(struct evlist *evlist, const char *str, int parse_event(struct evlist *evlist, const char *str); -int parse_events_terms(struct list_head *terms, const char *str, FILE *input); int parse_filter(const struct option *opt, const char *str, int unset); int exclude_perf(const struct option *opt, const char *arg, int unset); @@ -140,6 +139,11 @@ struct parse_events_error { char *first_help; }; +/* A wrapper around a list of terms for the sake of better type safety. */ +struct parse_events_terms { + struct list_head terms; +}; + struct parse_events_state { /* The list parsed events are placed on. */ struct list_head list; @@ -148,7 +152,7 @@ struct parse_events_state { /* Error information. */ struct parse_events_error *error; /* Holds returned terms for term parsing. */ - struct list_head *terms; + struct parse_events_terms *terms; /* Start token. */ int stoken; /* Special fake PMU marker for testing. */ @@ -181,35 +185,38 @@ int parse_events_term__term(struct parse_events_term **term, int parse_events_term__clone(struct parse_events_term **new, struct parse_events_term *term); void parse_events_term__delete(struct parse_events_term *term); -void parse_events_terms__delete(struct list_head *terms); -void parse_events_terms__purge(struct list_head *terms); -int parse_events_term__to_strbuf(struct list_head *term_list, struct strbuf *sb); + +void parse_events_terms__delete(struct parse_events_terms *terms); +void parse_events_terms__init(struct parse_events_terms *terms); +void parse_events_terms__exit(struct parse_events_terms *terms); +int parse_events_terms(struct parse_events_terms *terms, const char *str, FILE *input); +int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct strbuf *sb); int parse_events__modifier_event(struct list_head *list, char *str, bool add); int parse_events__modifier_group(struct list_head *list, char *event_mod); int parse_events_name(struct list_head *list, const char *name); int parse_events_add_tracepoint(struct list_head *list, int *idx, const char *sys, const char *event, struct parse_events_error *error, - struct list_head *head_config, void *loc); + struct parse_events_terms *head_config, void *loc); int parse_events_add_numeric(struct parse_events_state *parse_state, struct list_head *list, u32 type, u64 config, - struct list_head *head_config, + struct parse_events_terms *head_config, bool wildcard); int parse_events_add_tool(struct parse_events_state *parse_state, struct list_head *list, int tool_event); int parse_events_add_cache(struct list_head *list, int *idx, const char *name, struct parse_events_state *parse_state, - struct list_head *head_config); + struct parse_events_terms *head_config); int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config); int parse_events_add_breakpoint(struct parse_events_state *parse_state, struct list_head *list, u64 addr, char *type, u64 len, - struct list_head *head_config); + struct parse_events_terms *head_config); int parse_events_add_pmu(struct parse_events_state *parse_state, struct list_head *list, const char *name, - struct list_head *head_config, + const struct parse_events_terms *const_parsed_terms, bool auto_merge_stats, void *loc); struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, @@ -217,13 +224,10 @@ struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr, struct perf_pmu *pmu); int parse_events_multi_pmu_add(struct parse_events_state *parse_state, - char *str, - struct list_head *head_config, + const char *event_name, + const struct parse_events_terms *const_parsed_terms, struct list_head **listp, void *loc); -int parse_events_copy_term_list(struct list_head *old, - struct list_head **new); - void parse_events__set_leader(char *name, struct list_head *list); void parse_events_update_lists(struct list_head *list_event, struct list_head *list_all); diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index 4ef4b6f171a0..e86c45675e1d 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -120,7 +120,7 @@ static int term(yyscan_t scanner, enum parse_events__term_type type) { YYSTYPE *yylval = parse_events_get_lval(scanner); - yylval->num = type; + yylval->term_type = type; return PE_TERM; } @@ -156,8 +156,8 @@ event_pmu [^,{}/]+[/][^/]*[/][^,{}/]* event [^,{}/]+ num_dec [0-9]+ -num_hex 0x[a-fA-F0-9]+ -num_raw_hex [a-fA-F0-9]+ +num_hex 0x[a-fA-F0-9]{1,16} +num_raw_hex [a-fA-F0-9]{1,16} name [a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]!\-]* name_tag [\'][a-zA-Z_*?\[\]][a-zA-Z0-9_*?\-,\.\[\]:=]*[\'] name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y index 21bfe7e0d944..de098caf0c1c 100644 --- a/tools/perf/util/parse-events.y +++ b/tools/perf/util/parse-events.y @@ -6,14 +6,13 @@ %{ +#ifndef NDEBUG #define YYDEBUG 1 +#endif #include <errno.h> -#include <fnmatch.h> -#include <stdio.h> #include <linux/compiler.h> #include <linux/types.h> -#include <linux/zalloc.h> #include "pmu.h" #include "pmus.h" #include "evsel.h" @@ -70,7 +69,7 @@ static void free_list_evsel(struct list_head* list_evsel) %type <num> PE_VALUE_SYM_HW %type <num> PE_VALUE_SYM_SW %type <num> PE_VALUE_SYM_TOOL -%type <num> PE_TERM +%type <term_type> PE_TERM %type <num> value_sym %type <str> PE_RAW %type <str> PE_NAME @@ -79,7 +78,7 @@ static void free_list_evsel(struct list_head* list_evsel) %type <str> PE_MODIFIER_BP %type <str> PE_EVENT_NAME %type <str> PE_DRV_CFG_TERM -%type <str> name_or_raw name_or_legacy +%type <str> name_or_raw %destructor { free ($$); } <str> %type <term> event_term %destructor { parse_events_term__delete ($$); } <term> @@ -104,6 +103,7 @@ static void free_list_evsel(struct list_head* list_evsel) %type <list_evsel> groups %destructor { free_list_evsel ($$); } <list_evsel> %type <tracepoint_name> tracepoint_name +%destructor { free ($$.sys); free ($$.event); } <tracepoint_name> %type <hardware_term> PE_TERM_HW %destructor { free ($$.str); } <hardware_term> @@ -111,8 +111,9 @@ static void free_list_evsel(struct list_head* list_evsel) { char *str; u64 num; + enum parse_events__term_type term_type; struct list_head *list_evsel; - struct list_head *list_terms; + struct parse_events_terms *list_terms; struct parse_events_term *term; struct tracepoint_name { char *sys; @@ -273,23 +274,18 @@ event_pmu: PE_NAME opt_pmu_config { struct parse_events_state *parse_state = _parse_state; - struct list_head *list = NULL, *orig_terms = NULL, *terms= NULL; + /* List of created evsels. */ + struct list_head *list = NULL; char *pattern = NULL; #define CLEANUP \ do { \ parse_events_terms__delete($2); \ - parse_events_terms__delete(orig_terms); \ free(list); \ free($1); \ free(pattern); \ } while(0) - if (parse_events_copy_term_list($2, &orig_terms)) { - CLEANUP; - YYNOMEM; - } - list = alloc_list(); if (!list) { CLEANUP; @@ -319,16 +315,11 @@ PE_NAME opt_pmu_config !perf_pmu__match(pattern, pmu->alias_name, $1)) { bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu); - if (parse_events_copy_term_list(orig_terms, &terms)) { - CLEANUP; - YYNOMEM; - } - if (!parse_events_add_pmu(parse_state, list, pmu->name, terms, + if (!parse_events_add_pmu(parse_state, list, pmu->name, $2, auto_merge_stats, &@1)) { ok++; parse_state->wild_card_pmus = true; } - parse_events_terms__delete(terms); } } @@ -336,7 +327,6 @@ PE_NAME opt_pmu_config /* Failure to add, assume $1 is an event name. */ zfree(&list); ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list, &@1); - $2 = NULL; } if (!ok) { struct parse_events_error *error = parse_state->error; @@ -654,33 +644,31 @@ start_terms: event_config event_config: event_config ',' event_term { - struct list_head *head = $1; + struct parse_events_terms *head = $1; struct parse_events_term *term = $3; if (!head) { parse_events_term__delete(term); YYABORT; } - list_add_tail(&term->list, head); + list_add_tail(&term->list, &head->terms); $$ = $1; } | event_term { - struct list_head *head = malloc(sizeof(*head)); + struct parse_events_terms *head = malloc(sizeof(*head)); struct parse_events_term *term = $1; if (!head) YYNOMEM; - INIT_LIST_HEAD(head); - list_add_tail(&term->list, head); + parse_events_terms__init(head); + list_add_tail(&term->list, &head->terms); $$ = head; } name_or_raw: PE_RAW | PE_NAME | PE_LEGACY_CACHE -name_or_legacy: PE_NAME | PE_LEGACY_CACHE - event_term: PE_RAW { @@ -695,7 +683,7 @@ PE_RAW $$ = term; } | -name_or_raw '=' name_or_legacy +name_or_raw '=' name_or_raw { struct parse_events_term *term; int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER, $1, $3, &@1, &@3); @@ -775,11 +763,10 @@ PE_TERM_HW $$ = term; } | -PE_TERM '=' name_or_legacy +PE_TERM '=' name_or_raw { struct parse_events_term *term; - int err = parse_events_term__str(&term, (enum parse_events__term_type)$1, - /*config=*/NULL, $3, &@1, &@3); + int err = parse_events_term__str(&term, $1, /*config=*/NULL, $3, &@1, &@3); if (err) { free($3); @@ -791,8 +778,7 @@ PE_TERM '=' name_or_legacy PE_TERM '=' PE_TERM_HW { struct parse_events_term *term; - int err = parse_events_term__str(&term, (enum parse_events__term_type)$1, - /*config=*/NULL, $3.str, &@1, &@3); + int err = parse_events_term__str(&term, $1, /*config=*/NULL, $3.str, &@1, &@3); if (err) { free($3.str); @@ -804,10 +790,7 @@ PE_TERM '=' PE_TERM_HW PE_TERM '=' PE_TERM { struct parse_events_term *term; - int err = parse_events_term__term(&term, - (enum parse_events__term_type)$1, - (enum parse_events__term_type)$3, - &@1, &@3); + int err = parse_events_term__term(&term, $1, $3, &@1, &@3); if (err) PE_ABORT(err); @@ -818,8 +801,9 @@ PE_TERM '=' PE_TERM PE_TERM '=' PE_VALUE { struct parse_events_term *term; - int err = parse_events_term__num(&term, (enum parse_events__term_type)$1, - /*config=*/NULL, $3, /*novalue=*/false, &@1, &@3); + int err = parse_events_term__num(&term, $1, + /*config=*/NULL, $3, /*novalue=*/false, + &@1, &@3); if (err) PE_ABORT(err); @@ -830,9 +814,9 @@ PE_TERM '=' PE_VALUE PE_TERM { struct parse_events_term *term; - int err = parse_events_term__num(&term, (enum parse_events__term_type)$1, - /*config=*/NULL, /*num=*/1, /*novalue=*/true, - &@1, /*loc_val=*/NULL); + int err = parse_events_term__num(&term, $1, + /*config=*/NULL, /*num=*/1, /*novalue=*/true, + &@1, /*loc_val=*/NULL); if (err) PE_ABORT(err); diff --git a/tools/perf/util/pfm.c b/tools/perf/util/pfm.c index 862e4a689868..5ccfe4b64cdf 100644 --- a/tools/perf/util/pfm.c +++ b/tools/perf/util/pfm.c @@ -145,7 +145,20 @@ static bool is_libpfm_event_supported(const char *name, struct perf_cpu_map *cpu evsel->is_libpfm_event = true; - if (evsel__open(evsel, cpus, threads) < 0) + ret = evsel__open(evsel, cpus, threads); + if (ret == -EACCES) { + /* + * This happens if the paranoid value + * /proc/sys/kernel/perf_event_paranoid is set to 2 + * Re-run with exclude_kernel set; we don't do that + * by default as some ARM machines do not support it. + * + */ + evsel->core.attr.exclude_kernel = 1; + ret = evsel__open(evsel, cpus, threads); + + } + if (ret < 0) result = false; evsel__close(evsel); diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index d515ba8a0e16..d3c9aa4326be 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -28,6 +28,7 @@ #include "strbuf.h" #include "fncache.h" #include "util/evsel_config.h" +#include <regex.h> struct perf_pmu perf_pmu__fake = { .name = "fake", @@ -52,7 +53,7 @@ struct perf_pmu_alias { */ char *topic; /** @terms: Owned list of the original parsed parameters. */ - struct list_head terms; + struct parse_events_terms terms; /** @list: List element of struct perf_pmu aliases. */ struct list_head list; /** @@ -155,7 +156,7 @@ static void __perf_pmu_format__load(struct perf_pmu_format *format, FILE *file) format->loaded = true; } -static void perf_pmu_format__load(struct perf_pmu *pmu, struct perf_pmu_format *format) +static void perf_pmu_format__load(const struct perf_pmu *pmu, struct perf_pmu_format *format) { char path[PATH_MAX]; FILE *file = NULL; @@ -404,7 +405,7 @@ static void perf_pmu_free_alias(struct perf_pmu_alias *newalias) zfree(&newalias->long_desc); zfree(&newalias->topic); zfree(&newalias->pmu_name); - parse_events_terms__purge(&newalias->terms); + parse_events_terms__exit(&newalias->terms); free(newalias); } @@ -484,7 +485,7 @@ static int update_alias(const struct pmu_event *pe, assign_str(pe->name, "topic", &data->alias->topic, pe->topic); data->alias->per_pkg = pe->perpkg; if (pe->event) { - parse_events_terms__purge(&data->alias->terms); + parse_events_terms__exit(&data->alias->terms); ret = parse_events_terms(&data->alias->terms, pe->event, /*input=*/NULL); } if (!ret && pe->unit) { @@ -524,7 +525,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, if (!alias) return -ENOMEM; - INIT_LIST_HEAD(&alias->terms); + parse_events_terms__init(&alias->terms); alias->scale = 1.0; alias->unit[0] = '\0'; alias->per_pkg = perpkg; @@ -574,7 +575,7 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name, return 0; } -static inline bool pmu_alias_info_file(char *name) +static inline bool pmu_alias_info_file(const char *name) { size_t len; @@ -656,17 +657,17 @@ static int pmu_aliases_parse(struct perf_pmu *pmu) return 0; } -static int pmu_alias_terms(struct perf_pmu_alias *alias, - struct list_head *terms) +static int pmu_alias_terms(struct perf_pmu_alias *alias, struct list_head *terms) { struct parse_events_term *term, *cloned; - LIST_HEAD(list); - int ret; + struct parse_events_terms clone_terms; + + parse_events_terms__init(&clone_terms); + list_for_each_entry(term, &alias->terms.terms, list) { + int ret = parse_events_term__clone(&cloned, term); - list_for_each_entry(term, &alias->terms, list) { - ret = parse_events_term__clone(&cloned, term); if (ret) { - parse_events_terms__purge(&list); + parse_events_terms__exit(&clone_terms); return ret; } /* @@ -674,9 +675,10 @@ static int pmu_alias_terms(struct perf_pmu_alias *alias, * which we don't want for implicit terms in aliases. */ cloned->weak = true; - list_add_tail(&cloned->list, &list); + list_add_tail(&cloned->list, &clone_terms.terms); } - list_splice(&list, terms); + list_splice_init(&clone_terms.terms, terms); + parse_events_terms__exit(&clone_terms); return 0; } @@ -775,11 +777,6 @@ char *perf_pmu__getcpuid(struct perf_pmu *pmu) return cpuid; } -__weak const struct pmu_events_table *pmu_events_table__find(void) -{ - return perf_pmu__find_events_table(NULL); -} - __weak const struct pmu_metrics_table *pmu_metrics_table__find(void) { return perf_pmu__find_metrics_table(NULL); @@ -874,6 +871,28 @@ out: return res; } +bool pmu_uncore_identifier_match(const char *compat, const char *id) +{ + regex_t re; + regmatch_t pmatch[1]; + int match; + + if (regcomp(&re, compat, REG_EXTENDED) != 0) { + /* Warn unable to generate match particular string. */ + pr_info("Invalid regular expression %s\n", compat); + return false; + } + + match = !regexec(&re, id, 1, pmatch, 0); + if (match) { + /* Ensure a full match. */ + match = pmatch[0].rm_so == 0 && (size_t)pmatch[0].rm_eo == strlen(id); + } + regfree(&re); + + return match; +} + static int pmu_add_cpu_aliases_map_callback(const struct pmu_event *pe, const struct pmu_events_table *table __maybe_unused, void *vdata) @@ -914,8 +933,8 @@ static int pmu_add_sys_aliases_iter_fn(const struct pmu_event *pe, if (!pe->compat || !pe->pmu) return 0; - if (!strcmp(pmu->id, pe->compat) && - pmu_uncore_alias_match(pe->pmu, pmu->name)) { + if (pmu_uncore_alias_match(pe->pmu, pmu->name) && + pmu_uncore_identifier_match(pe->compat, pmu->id)) { perf_pmu__new_alias(pmu, pe->name, pe->desc, @@ -935,22 +954,27 @@ void pmu_add_sys_aliases(struct perf_pmu *pmu) pmu_for_each_sys_event(pmu_add_sys_aliases_iter_fn, pmu); } -struct perf_event_attr * __weak -perf_pmu__get_default_config(struct perf_pmu *pmu __maybe_unused) +static char *pmu_find_alias_name(struct perf_pmu *pmu, int dirfd) { - return NULL; -} + FILE *file = perf_pmu__open_file_at(pmu, dirfd, "alias"); + char *line = NULL; + size_t line_len = 0; + ssize_t ret; -const char * __weak -pmu_find_real_name(const char *name) -{ - return name; -} + if (!file) + return NULL; -const char * __weak -pmu_find_alias_name(const char *name __maybe_unused) -{ - return NULL; + ret = getline(&line, &line_len, file); + if (ret < 0) { + fclose(file); + return NULL; + } + /* Remove trailing newline. */ + if (ret > 0 && line[ret - 1] == '\n') + line[--ret] = '\0'; + + fclose(file); + return line; } static int pmu_max_precise(int dirfd, struct perf_pmu *pmu) @@ -961,12 +985,15 @@ static int pmu_max_precise(int dirfd, struct perf_pmu *pmu) return max_precise; } -struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name) +void __weak +perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused) +{ +} + +struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *name) { struct perf_pmu *pmu; __u32 type; - const char *name = pmu_find_real_name(lookup_name); - const char *alias_name; pmu = zalloc(sizeof(*pmu)); if (!pmu) @@ -999,23 +1026,17 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char pmu->is_core = is_pmu_core(name); pmu->cpus = pmu_cpumask(dirfd, name, pmu->is_core); - alias_name = pmu_find_alias_name(name); - if (alias_name) { - pmu->alias_name = strdup(alias_name); - if (!pmu->alias_name) - goto err; - } - pmu->type = type; pmu->is_uncore = pmu_is_uncore(dirfd, name); if (pmu->is_uncore) pmu->id = pmu_id(name); pmu->max_precise = pmu_max_precise(dirfd, pmu); + pmu->alias_name = pmu_find_alias_name(pmu, dirfd); pmu->events_table = perf_pmu__find_events_table(pmu); pmu_add_sys_aliases(pmu); list_add_tail(&pmu->list, pmus); - pmu->default_config = perf_pmu__get_default_config(pmu); + perf_pmu__arch_init(pmu); return pmu; err: @@ -1110,7 +1131,7 @@ void evsel__set_config_if_unset(struct perf_pmu *pmu, struct evsel *evsel, } static struct perf_pmu_format * -pmu_find_format(struct list_head *formats, const char *name) +pmu_find_format(const struct list_head *formats, const char *name) { struct perf_pmu_format *format; @@ -1188,12 +1209,12 @@ static __u64 pmu_format_max_value(const unsigned long *format) * in a config string) later on in the term list. */ static int pmu_resolve_param_term(struct parse_events_term *term, - struct list_head *head_terms, + struct parse_events_terms *head_terms, __u64 *value) { struct parse_events_term *t; - list_for_each_entry(t, head_terms, list) { + list_for_each_entry(t, &head_terms->terms, list) { if (t->type_val == PARSE_EVENTS__TERM_TYPE_NUM && t->config && !strcmp(t->config, term->config)) { t->used = true; @@ -1208,7 +1229,7 @@ static int pmu_resolve_param_term(struct parse_events_term *term, return -1; } -static char *pmu_formats_string(struct list_head *formats) +static char *pmu_formats_string(const struct list_head *formats) { struct perf_pmu_format *format; char *str = NULL; @@ -1234,10 +1255,10 @@ error: * Setup one of config[12] attr members based on the * user input data - term parameter. */ -static int pmu_config_term(struct perf_pmu *pmu, +static int pmu_config_term(const struct perf_pmu *pmu, struct perf_event_attr *attr, struct parse_events_term *term, - struct list_head *head_terms, + struct parse_events_terms *head_terms, bool zero, struct parse_events_error *err) { struct perf_pmu_format *format; @@ -1357,15 +1378,15 @@ static int pmu_config_term(struct perf_pmu *pmu, return 0; } -int perf_pmu__config_terms(struct perf_pmu *pmu, +int perf_pmu__config_terms(const struct perf_pmu *pmu, struct perf_event_attr *attr, - struct list_head *head_terms, + struct parse_events_terms *terms, bool zero, struct parse_events_error *err) { struct parse_events_term *term; - list_for_each_entry(term, head_terms, list) { - if (pmu_config_term(pmu, attr, term, head_terms, zero, err)) + list_for_each_entry(term, &terms->terms, list) { + if (pmu_config_term(pmu, attr, term, terms, zero, err)) return -EINVAL; } @@ -1378,10 +1399,10 @@ int perf_pmu__config_terms(struct perf_pmu *pmu, * 2) pmu format definitions - specified by pmu parameter */ int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, - struct list_head *head_terms, + struct parse_events_terms *head_terms, struct parse_events_error *err) { - bool zero = !!pmu->default_config; + bool zero = !!pmu->perf_event_attr_init_default; return perf_pmu__config_terms(pmu, attr, head_terms, zero, err); } @@ -1472,7 +1493,7 @@ static int check_info_data(struct perf_pmu *pmu, * Find alias in the terms list and replace it with the terms * defined for the alias */ -int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, +int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms, struct perf_pmu_info *info, struct parse_events_error *err) { struct parse_events_term *term, *h; @@ -1489,7 +1510,7 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, info->scale = 0.0; info->snapshot = false; - list_for_each_entry_safe(term, h, head_terms, list) { + list_for_each_entry_safe(term, h, &head_terms->terms, list) { alias = pmu_find_alias(pmu, term); if (!alias) continue; @@ -1634,7 +1655,7 @@ static char *format_alias(char *buf, int len, const struct perf_pmu *pmu, : (int)strlen(pmu->name); int used = snprintf(buf, len, "%.*s/%s", pmu_name_len, pmu->name, alias->name); - list_for_each_entry(term, &alias->terms, list) { + list_for_each_entry(term, &alias->terms.terms, list) { if (term->type_val == PARSE_EVENTS__TERM_TYPE_STR) used += snprintf(buf + used, sub_non_neg(len, used), ",%s=%s", term->config, @@ -1693,7 +1714,7 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus, info.desc = event->desc; info.long_desc = event->long_desc; info.encoding_desc = buf + buf_used; - parse_events_term__to_strbuf(&event->terms, &sb); + parse_events_terms__to_strbuf(&event->terms, &sb); buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used, "%s/%s/", info.pmu_name, sb.buf) + 1; info.topic = event->topic; @@ -1749,7 +1770,7 @@ bool perf_pmu__is_software(const struct perf_pmu *pmu) return !strcmp(pmu->name, "kprobe") || !strcmp(pmu->name, "uprobe"); } -FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) +FILE *perf_pmu__open_file(const struct perf_pmu *pmu, const char *name) { char path[PATH_MAX]; @@ -1760,7 +1781,7 @@ FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name) return fopen(path, "r"); } -FILE *perf_pmu__open_file_at(struct perf_pmu *pmu, int dirfd, const char *name) +FILE *perf_pmu__open_file_at(const struct perf_pmu *pmu, int dirfd, const char *name) { int fd; @@ -1771,7 +1792,7 @@ FILE *perf_pmu__open_file_at(struct perf_pmu *pmu, int dirfd, const char *name) return fdopen(fd, "r"); } -int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, +int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char *fmt, ...) { va_list args; @@ -1788,7 +1809,7 @@ int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, return ret; } -int perf_pmu__scan_file_at(struct perf_pmu *pmu, int dirfd, const char *name, +int perf_pmu__scan_file_at(const struct perf_pmu *pmu, int dirfd, const char *name, const char *fmt, ...) { va_list args; @@ -1805,7 +1826,7 @@ int perf_pmu__scan_file_at(struct perf_pmu *pmu, int dirfd, const char *name, return ret; } -bool perf_pmu__file_exists(struct perf_pmu *pmu, const char *name) +bool perf_pmu__file_exists(const struct perf_pmu *pmu, const char *name) { char path[PATH_MAX]; @@ -2043,26 +2064,8 @@ void perf_pmu__delete(struct perf_pmu *pmu) perf_cpu_map__put(pmu->cpus); - zfree(&pmu->default_config); zfree(&pmu->name); zfree(&pmu->alias_name); zfree(&pmu->id); free(pmu); } - -struct perf_pmu *pmu__find_core_pmu(void) -{ - struct perf_pmu *pmu = NULL; - - while ((pmu = perf_pmus__scan_core(pmu))) { - /* - * The cpumap should cover all CPUs. Otherwise, some CPUs may - * not support some events or have different event IDs. - */ - if (RC_CHK_ACCESS(pmu->cpus)->nr != cpu__max_cpu().cpu) - return NULL; - - return pmu; - } - return NULL; -} diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 6a4e170c61d6..d2895d415f08 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -92,10 +92,11 @@ struct perf_pmu { */ int max_precise; /** - * @default_config: Optional default perf_event_attr determined in - * architecture specific code. + * @perf_event_attr_init_default: Optional function to default + * initialize PMU specific parts of the perf_event_attr. */ - struct perf_event_attr *default_config; + void (*perf_event_attr_init_default)(const struct perf_pmu *pmu, + struct perf_event_attr *attr); /** * @cpus: Empty or the contents of either of: * <sysfs>/bus/event_source/devices/<name>/cpumask. @@ -191,15 +192,15 @@ typedef int (*pmu_event_callback)(void *state, struct pmu_event_info *info); void pmu_add_sys_aliases(struct perf_pmu *pmu); int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, - struct list_head *head_terms, + struct parse_events_terms *head_terms, struct parse_events_error *error); -int perf_pmu__config_terms(struct perf_pmu *pmu, +int perf_pmu__config_terms(const struct perf_pmu *pmu, struct perf_event_attr *attr, - struct list_head *head_terms, + struct parse_events_terms *terms, bool zero, struct parse_events_error *error); __u64 perf_pmu__format_bits(struct perf_pmu *pmu, const char *name); int perf_pmu__format_type(struct perf_pmu *pmu, const char *name); -int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms, +int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_terms, struct perf_pmu_info *info, struct parse_events_error *err); int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, pmu_event_callback cb); @@ -222,24 +223,25 @@ bool pmu__name_match(const struct perf_pmu *pmu, const char *pmu_name); */ bool perf_pmu__is_software(const struct perf_pmu *pmu); -FILE *perf_pmu__open_file(struct perf_pmu *pmu, const char *name); -FILE *perf_pmu__open_file_at(struct perf_pmu *pmu, int dirfd, const char *name); +FILE *perf_pmu__open_file(const struct perf_pmu *pmu, const char *name); +FILE *perf_pmu__open_file_at(const struct perf_pmu *pmu, int dirfd, const char *name); -int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) __scanf(3, 4); -int perf_pmu__scan_file_at(struct perf_pmu *pmu, int dirfd, const char *name, +int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char *fmt, ...) + __scanf(3, 4); +int perf_pmu__scan_file_at(const struct perf_pmu *pmu, int dirfd, const char *name, const char *fmt, ...) __scanf(4, 5); -bool perf_pmu__file_exists(struct perf_pmu *pmu, const char *name); +bool perf_pmu__file_exists(const struct perf_pmu *pmu, const char *name); int perf_pmu__test(void); -struct perf_event_attr *perf_pmu__get_default_config(struct perf_pmu *pmu); +void perf_pmu__arch_init(struct perf_pmu *pmu); void pmu_add_cpu_aliases_table(struct perf_pmu *pmu, const struct pmu_events_table *table); char *perf_pmu__getcpuid(struct perf_pmu *pmu); -const struct pmu_events_table *pmu_events_table__find(void); const struct pmu_metrics_table *pmu_metrics_table__find(void); +bool pmu_uncore_identifier_match(const char *compat, const char *id); int perf_pmu__convert_scale(const char *scale, char **end, double *sval); @@ -252,8 +254,6 @@ void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu); int perf_pmu__match(const char *pattern, const char *name, const char *tok); -const char *pmu_find_real_name(const char *name); -const char *pmu_find_alias_name(const char *name); double perf_pmu__cpu_slots_per_cycle(void); int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size); int perf_pmu__pathname_scnprintf(char *buf, size_t size, @@ -264,6 +264,6 @@ int perf_pmu__pathname_fd(int dirfd, const char *pmu_name, const char *filename, struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char *lookup_name); struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus); void perf_pmu__delete(struct perf_pmu *pmu); -struct perf_pmu *pmu__find_core_pmu(void); +struct perf_pmu *perf_pmus__find_core_pmu(void); #endif /* __PMU_H */ diff --git a/tools/perf/util/pmu.y b/tools/perf/util/pmu.y index 600c8c158c8e..198907a8a48a 100644 --- a/tools/perf/util/pmu.y +++ b/tools/perf/util/pmu.y @@ -5,6 +5,10 @@ %{ +#ifndef NDEBUG +#define YYDEBUG 1 +#endif + #include <linux/compiler.h> #include <linux/list.h> #include <linux/bitmap.h> diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c index 6631367c756f..ce4931461741 100644 --- a/tools/perf/util/pmus.c +++ b/tools/perf/util/pmus.c @@ -10,6 +10,7 @@ #include <pthread.h> #include <string.h> #include <unistd.h> +#include "cpumap.h" #include "debug.h" #include "evsel.h" #include "pmus.h" @@ -36,6 +37,8 @@ static LIST_HEAD(other_pmus); static bool read_sysfs_core_pmus; static bool read_sysfs_all_pmus; +static void pmu_read_sysfs(bool core_only); + int pmu_name_len_no_suffix(const char *str, unsigned long *num) { int orig_len, len; @@ -123,6 +126,14 @@ struct perf_pmu *perf_pmus__find(const char *name) pmu = perf_pmu__lookup(core_pmu ? &core_pmus : &other_pmus, dirfd, name); close(dirfd); + if (!pmu) { + /* + * Looking up an inidividual PMU failed. This may mean name is + * an alias, so read the PMUs from sysfs and try to find again. + */ + pmu_read_sysfs(core_pmu); + pmu = pmu_find(name); + } return pmu; } @@ -268,7 +279,7 @@ struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu) { if (!pmu) { pmu_read_sysfs(/*core_only=*/true); - pmu = list_prepare_entry(pmu, &core_pmus, list); + return list_first_entry_or_null(&core_pmus, typeof(*pmu), list); } list_for_each_entry_continue(pmu, &core_pmus, list) return pmu; @@ -592,3 +603,8 @@ struct perf_pmu *evsel__find_pmu(const struct evsel *evsel) } return pmu; } + +struct perf_pmu *perf_pmus__find_core_pmu(void) +{ + return perf_pmus__scan_core(NULL); +} diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c index a7566edc86a3..b0fc48be623f 100644 --- a/tools/perf/util/print-events.c +++ b/tools/perf/util/print-events.c @@ -395,6 +395,8 @@ void print_symbol_events(const struct print_callbacks *print_cb, void *print_sta */ void print_events(const struct print_callbacks *print_cb, void *print_state) { + char *tmp; + print_symbol_events(print_cb, print_state, PERF_TYPE_HARDWARE, event_symbols_hw, PERF_COUNT_HW_MAX); print_symbol_events(print_cb, print_state, PERF_TYPE_SOFTWARE, @@ -418,17 +420,21 @@ void print_events(const struct print_callbacks *print_cb, void *print_state) /*long_desc=*/NULL, /*encoding_desc=*/NULL); - print_cb->print_event(print_state, - /*topic=*/NULL, - /*pmu_name=*/NULL, - "cpu/t1=v1[,t2=v2,t3 ...]/modifier", - /*event_alias=*/NULL, - /*scale_unit=*/NULL, - /*deprecated=*/false, - event_type_descriptors[PERF_TYPE_RAW], - "(see 'man perf-list' on how to encode it)", - /*long_desc=*/NULL, - /*encoding_desc=*/NULL); + if (asprintf(&tmp, "%s/t1=v1[,t2=v2,t3 ...]/modifier", + perf_pmus__scan_core(/*pmu=*/NULL)->name) > 0) { + print_cb->print_event(print_state, + /*topic=*/NULL, + /*pmu_name=*/NULL, + tmp, + /*event_alias=*/NULL, + /*scale_unit=*/NULL, + /*deprecated=*/false, + event_type_descriptors[PERF_TYPE_RAW], + "(see 'man perf-list' on how to encode it)", + /*long_desc=*/NULL, + /*encoding_desc=*/NULL); + free(tmp); + } print_cb->print_event(print_state, /*topic=*/NULL, diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources index 26e1c8d973ea..593b660ec75e 100644 --- a/tools/perf/util/python-ext-sources +++ b/tools/perf/util/python-ext-sources @@ -40,6 +40,7 @@ util/rwsem.c util/hashmap.c util/perf_regs.c util/fncache.c +util/rlimit.c util/perf-regs-arch/perf_regs_aarch64.c util/perf-regs-arch/perf_regs_arm.c util/perf-regs-arch/perf_regs_csky.c diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c index c29f5f0bb552..8761f51b5c7c 100644 --- a/tools/perf/util/python.c +++ b/tools/perf/util/python.c @@ -98,7 +98,7 @@ struct perf_pmu *evsel__find_pmu(const struct evsel *evsel __maybe_unused) return NULL; } -int perf_pmu__scan_file(struct perf_pmu *pmu, const char *name, const char *fmt, ...) +int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char *fmt, ...) { return EOF; } diff --git a/tools/perf/util/rlimit.c b/tools/perf/util/rlimit.c index 13521d392a22..f857405fe1aa 100644 --- a/tools/perf/util/rlimit.c +++ b/tools/perf/util/rlimit.c @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1 */ +#include <errno.h> #include "util/debug.h" #include "util/rlimit.h" #include <sys/time.h> @@ -27,3 +28,30 @@ void rlimit__bump_memlock(void) } } } + +bool rlimit__increase_nofile(enum rlimit_action *set_rlimit) +{ + int old_errno; + struct rlimit l; + + if (*set_rlimit < INCREASED_MAX) { + old_errno = errno; + + if (getrlimit(RLIMIT_NOFILE, &l) == 0) { + if (*set_rlimit == NO_CHANGE) { + l.rlim_cur = l.rlim_max; + } else { + l.rlim_cur = l.rlim_max + 1000; + l.rlim_max = l.rlim_cur; + } + if (setrlimit(RLIMIT_NOFILE, &l) == 0) { + (*set_rlimit) += 1; + errno = old_errno; + return true; + } + } + errno = old_errno; + } + + return false; +} diff --git a/tools/perf/util/rlimit.h b/tools/perf/util/rlimit.h index 9f59d8e710a3..19050d7fb9d7 100644 --- a/tools/perf/util/rlimit.h +++ b/tools/perf/util/rlimit.h @@ -1,6 +1,15 @@ +/* SPDX-License-Identifier: LGPL-2.1 */ #ifndef __PERF_RLIMIT_H_ #define __PERF_RLIMIT_H_ -/* SPDX-License-Identifier: LGPL-2.1 */ + +enum rlimit_action { + NO_CHANGE, + SET_TO_MAX, + INCREASED_MAX +}; void rlimit__bump_memlock(void); + +bool rlimit__increase_nofile(enum rlimit_action *set_rlimit); + #endif // __PERF_RLIMIT_H_ diff --git a/tools/perf/util/rwsem.c b/tools/perf/util/rwsem.c index f3d29d8ddc99..5109167f27f7 100644 --- a/tools/perf/util/rwsem.c +++ b/tools/perf/util/rwsem.c @@ -2,32 +2,66 @@ #include "util.h" #include "rwsem.h" +#if RWS_ERRORCHECK +#include "mutex.h" +#endif + int init_rwsem(struct rw_semaphore *sem) { +#if RWS_ERRORCHECK + mutex_init(&sem->mtx); + return 0; +#else return pthread_rwlock_init(&sem->lock, NULL); +#endif } int exit_rwsem(struct rw_semaphore *sem) { +#if RWS_ERRORCHECK + mutex_destroy(&sem->mtx); + return 0; +#else return pthread_rwlock_destroy(&sem->lock); +#endif } int down_read(struct rw_semaphore *sem) { +#if RWS_ERRORCHECK + mutex_lock(&sem->mtx); + return 0; +#else return perf_singlethreaded ? 0 : pthread_rwlock_rdlock(&sem->lock); +#endif } int up_read(struct rw_semaphore *sem) { +#if RWS_ERRORCHECK + mutex_unlock(&sem->mtx); + return 0; +#else return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock); +#endif } int down_write(struct rw_semaphore *sem) { +#if RWS_ERRORCHECK + mutex_lock(&sem->mtx); + return 0; +#else return perf_singlethreaded ? 0 : pthread_rwlock_wrlock(&sem->lock); +#endif } int up_write(struct rw_semaphore *sem) { +#if RWS_ERRORCHECK + mutex_unlock(&sem->mtx); + return 0; +#else return perf_singlethreaded ? 0 : pthread_rwlock_unlock(&sem->lock); +#endif } diff --git a/tools/perf/util/rwsem.h b/tools/perf/util/rwsem.h index 94565ad4d494..ef5cbc31d967 100644 --- a/tools/perf/util/rwsem.h +++ b/tools/perf/util/rwsem.h @@ -2,9 +2,20 @@ #define _PERF_RWSEM_H #include <pthread.h> +#include "mutex.h" + +/* + * Mutexes have additional error checking. Enable to use a mutex rather than a + * rwlock for debugging. + */ +#define RWS_ERRORCHECK 0 struct rw_semaphore { +#if RWS_ERRORCHECK + struct mutex mtx; +#else pthread_rwlock_t lock; +#endif }; int init_rwsem(struct rw_semaphore *sem); diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c index 6aa1c7f2b444..80e4f6132740 100644 --- a/tools/perf/util/sort.c +++ b/tools/perf/util/sort.c @@ -128,7 +128,7 @@ static int hist_entry__thread_filter(struct hist_entry *he, int type, const void if (type != HIST_FILTER__THREAD) return -1; - return th && RC_CHK_ACCESS(he->thread) != RC_CHK_ACCESS(th); + return th && !RC_CHK_EQUAL(he->thread, th); } struct sort_entry sort_thread = { diff --git a/tools/perf/util/string.c b/tools/perf/util/string.c index cf05b0b56c57..116a642ad99d 100644 --- a/tools/perf/util/string.c +++ b/tools/perf/util/string.c @@ -301,3 +301,51 @@ unsigned int hex(char c) return c - 'a' + 10; return c - 'A' + 10; } + +/* + * Replace all occurrences of character 'needle' in string 'haystack' with + * string 'replace' + * + * The new string could be longer so a new string is returned which must be + * freed. + */ +char *strreplace_chars(char needle, const char *haystack, const char *replace) +{ + int replace_len = strlen(replace); + char *new_s, *to; + const char *loc = strchr(haystack, needle); + const char *from = haystack; + int num = 0; + + /* Count occurrences */ + while (loc) { + loc = strchr(loc + 1, needle); + num++; + } + + /* Allocate enough space for replacements and reset first location */ + new_s = malloc(strlen(haystack) + (num * (replace_len - 1) + 1)); + if (!new_s) + return NULL; + loc = strchr(haystack, needle); + to = new_s; + + while (loc) { + /* Copy original string up to found char and update positions */ + memcpy(to, from, 1 + loc - from); + to += loc - from; + from = loc + 1; + + /* Copy replacement string and update positions */ + memcpy(to, replace, replace_len); + to += replace_len; + + /* needle next occurrence or end of string */ + loc = strchr(from, needle); + } + + /* Copy any remaining chars + null */ + strcpy(to, from); + + return new_s; +} diff --git a/tools/perf/util/string2.h b/tools/perf/util/string2.h index 56c30fef9682..52cb8ba057c7 100644 --- a/tools/perf/util/string2.h +++ b/tools/perf/util/string2.h @@ -39,5 +39,6 @@ char *strpbrk_esc(char *str, const char *stopset); char *strdup_esc(const char *str); unsigned int hex(char c); +char *strreplace_chars(char needle, const char *haystack, const char *replace); #endif /* PERF_STRING_H */ diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c index 0e4dc31c6c9c..1892e9b6aa7f 100644 --- a/tools/perf/util/svghelper.c +++ b/tools/perf/util/svghelper.c @@ -754,6 +754,7 @@ int svg_build_topology_map(struct perf_env *env) int i, nr_cpus; struct topology t; char *sib_core, *sib_thr; + int ret = -1; nr_cpus = min(env->nr_cpus_online, MAX_NR_CPUS); @@ -799,11 +800,11 @@ int svg_build_topology_map(struct perf_env *env) scan_core_topology(topology_map, &t, nr_cpus); - return 0; + ret = 0; exit: zfree(&t.sib_core); zfree(&t.sib_thr); - return -1; + return ret; } diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 95e99c332d7e..9e7eeaf616b8 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1514,8 +1514,10 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, } if (elf_section_by_name(runtime_ss->elf, &runtime_ss->ehdr, &tshdr, - ".text", NULL)) + ".text", NULL)) { dso->text_offset = tshdr.sh_addr - tshdr.sh_offset; + dso->text_end = tshdr.sh_offset + tshdr.sh_size; + } if (runtime_ss->opdsec) opddata = elf_rawdata(runtime_ss->opdsec, NULL); diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 3f36675b7c8f..82cc74b9358e 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -202,11 +202,10 @@ void symbols__fixup_duplicate(struct rb_root_cached *symbols) curr = rb_entry(nd, struct symbol, rb_node); again: nd = rb_next(&curr->rb_node); - next = rb_entry(nd, struct symbol, rb_node); - if (!nd) break; + next = rb_entry(nd, struct symbol, rb_node); if (curr->start != next->start) continue; @@ -719,6 +718,7 @@ static bool symbol__is_idle(const char *name) "cpu_startup_entry", "idle_cpu", "intel_idle", + "intel_idle_ibrs", "default_idle", "native_safe_halt", "enter_idle", @@ -877,7 +877,7 @@ static int maps__split_kallsyms(struct maps *kmaps, struct dso *dso, u64 delta, *module++ = '\0'; curr_map_dso = map__dso(curr_map); if (strcmp(curr_map_dso->short_name, module)) { - if (RC_CHK_ACCESS(curr_map) != RC_CHK_ACCESS(initial_map) && + if (!RC_CHK_EQUAL(curr_map, initial_map) && dso->kernel == DSO_SPACE__KERNEL_GUEST && machine__is_default_guest(machine)) { /* @@ -1469,7 +1469,7 @@ static int dso__load_kcore(struct dso *dso, struct map *map, list_del_init(&new_node->node); - if (RC_CHK_ACCESS(new_map) == RC_CHK_ACCESS(replacement_map)) { + if (RC_CHK_EQUAL(new_map, replacement_map)) { struct map *map_ref; map__set_start(map, map__start(new_map)); @@ -1733,8 +1733,10 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) /* PE symbols can only have 4 bytes, so use .text high bits */ dso->text_offset = section->vma - (u32)section->vma; dso->text_offset += (u32)bfd_asymbol_value(symbols[i]); + dso->text_end = (section->vma - dso->text_offset) + section->size; } else { dso->text_offset = section->vma - section->filepos; + dso->text_end = section->filepos + section->size; } } @@ -2789,8 +2791,11 @@ struct mem_info *mem_info__get(struct mem_info *mi) void mem_info__put(struct mem_info *mi) { - if (mi && refcount_dec_and_test(&mi->refcnt)) + if (mi && refcount_dec_and_test(&mi->refcnt)) { + addr_map_symbol__exit(&mi->iaddr); + addr_map_symbol__exit(&mi->daddr); free(mi); + } } struct mem_info *mem_info__new(void) diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index 319ccf09a435..c8755679281e 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -313,7 +313,8 @@ static int record_event_files(struct tracepoint_path *tps) } err = 0; out: - closedir(dir); + if (dir) + closedir(dir); put_tracing_file(path); return err; |