diff options
author | Jin Yao <yao.jin@linux.intel.com> | 2021-08-09 05:53:48 +0300 |
---|---|---|
committer | Arnaldo Carvalho de Melo <acme@redhat.com> | 2021-08-10 21:19:12 +0300 |
commit | 2c72404e950a9e0cf39cedcee9bb34a29b19baf0 (patch) | |
tree | 239a1ec04cfb8c79701a658ccf2b86fbeb6532ec | |
parent | ed97cc6cbb1f440a0a3ab1483c93aff67ebe6f1d (diff) | |
download | linux-2c72404e950a9e0cf39cedcee9bb34a29b19baf0.tar.xz |
perf vendor events intel: Update core event list for SkyLake Server
Update JSON core events for SkyLake Server.
Based on JSON list v1.24:
https://download.01.org/perfmon/SKX/
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linux-kernel@vger.kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https //lore.kernel.org/r/20210810020508.31261-5-yao.jin@linux.intel.com
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
-rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/cache.json | 1648 | ||||
-rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/floating-point.json | 56 | ||||
-rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/frontend.json | 576 | ||||
-rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/memory.json | 1282 | ||||
-rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/other.json | 104 | ||||
-rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/pipeline.json | 1030 | ||||
-rw-r--r-- | tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json | 288 |
7 files changed, 2497 insertions, 2487 deletions
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json index e750a21976f1..9ff67206ade4 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json @@ -1,49 +1,123 @@ [ { - "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "L1D data line replacements", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0004", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "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": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", + "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xB0", - "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", - "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", - "SampleAfterValue": "100003", - "UMask": "0x4" + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.FB_FULL", + "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "BriefDescription": "Counts all demand code reads that have any response type.", + "BriefDescription": "L1D miss outstandings duration in cycles", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010004", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING", + "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle 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": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with L1D load Misses outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES", + "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "AnyThread": "1", + "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x48", + "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "L2 cache lines filling L2", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF1", + "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": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.NON_SILENT", + "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped.", + "SampleAfterValue": "200003", + "UMask": "0x2" + }, + { + "BriefDescription": "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 state. A non-threaded event.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.SILENT", + "SampleAfterValue": "200003", "UMask": "0x1" }, { - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", + "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.USELESS_HWPF", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Deprecated": "1", + "EventCode": "0xF2", + "EventName": "L2_LINES_OUT.USELESS_PREF", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "L2 code requests", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x24", - "EventName": "L2_RQSTS.PF_MISS", - "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", + "EventName": "L2_RQSTS.ALL_CODE_RD", + "PublicDescription": "Counts the total number of L2 code requests.", "SampleAfterValue": "200003", - "UMask": "0x38" + "UMask": "0xe4" + }, + { + "BriefDescription": "Demand Data Read requests", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", + "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", + "SampleAfterValue": "200003", + "UMask": "0xe1" }, { "BriefDescription": "Demand requests that miss L2 cache", @@ -56,157 +130,144 @@ "UMask": "0x27" }, { - "BriefDescription": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Demand requests to L2 cache", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0002", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", + "PublicDescription": "Demand requests to L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xe7" }, { - "BriefDescription": "Retired load instructions with L3 cache hits as data sources", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "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": "50021", - "UMask": "0x4" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.ALL_PF", + "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", + "SampleAfterValue": "200003", + "UMask": "0xf8" }, { - "BriefDescription": "L2 writebacks that access L2 cache", + "BriefDescription": "RFO requests to L2 cache", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xF0", - "EventName": "L2_TRANS.L2_WB", - "PublicDescription": "Counts L2 writebacks that access 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": "0x40" + "UMask": "0xe2" }, { - "BriefDescription": "L2 cache lines filling L2", + "BriefDescription": "L2 cache hits when fetching instructions, code reads.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xF1", - "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" + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_HIT", + "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", + "SampleAfterValue": "200003", + "UMask": "0xc4" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "L2 cache misses when fetching instructions", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0400", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.CODE_RD_MISS", + "PublicDescription": "Counts L2 cache misses when fetching instructions.", + "SampleAfterValue": "200003", + "UMask": "0x24" }, { - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Demand Data Read requests that hit L2 cache", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10003C0001", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "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": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.", + "BriefDescription": "Demand Data Read miss L2, no rejects", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0100", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", + "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", + "SampleAfterValue": "200003", + "UMask": "0x21" }, { - "BriefDescription": "Demand Data Read requests sent to uncore", + "BriefDescription": "All requests that miss L2 cache", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xB0", - "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" + "EventCode": "0x24", + "EventName": "L2_RQSTS.MISS", + "PublicDescription": "All requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x3f" }, { - "BriefDescription": "Retired load instructions missed L3 cache as data sources", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "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": "100007", - "UMask": "0x20" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.PF_HIT", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xd8" }, { - "BriefDescription": "All retired store instructions.", + "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD0", - "EventName": "MEM_INST_RETIRED.ALL_STORES", - "L1_Hit_Indication": "1", - "PEBS": "1", - "SampleAfterValue": "2000003", - "UMask": "0x82" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.PF_MISS", + "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x38" }, { - "BriefDescription": "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 state. A non-threaded event.", + "BriefDescription": "All L2 requests", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xF2", - "EventName": "L2_LINES_OUT.SILENT", + "EventCode": "0x24", + "EventName": "L2_RQSTS.REFERENCES", + "PublicDescription": "All L2 requests.", "SampleAfterValue": "200003", - "UMask": "0x1" + "UMask": "0xff" }, { - "BriefDescription": "Counts all prefetch data reads that hit in the L3.", + "BriefDescription": "RFO requests that hit L2 cache", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0490", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_HIT", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0xc2" }, { - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "RFO requests that miss L2 cache", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10003C0490", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x24", + "EventName": "L2_RQSTS.RFO_MISS", + "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x22" + }, + { + "BriefDescription": "L2 writebacks that access L2 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF0", + "EventName": "L2_TRANS.L2_WB", + "PublicDescription": "Counts L2 writebacks that access L2 cache.", + "SampleAfterValue": "200003", + "UMask": "0x40" }, { "BriefDescription": "Core-originated cacheable demand requests missed L3", @@ -220,223 +281,225 @@ "UMask": "0x41" }, { - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches", + "BriefDescription": "Core-originated cacheable demand requests that refer to L3", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.ALL_PF", - "PublicDescription": "Counts the total number of requests from the L2 hardware prefetchers.", - "SampleAfterValue": "200003", - "UMask": "0xf8" + "Errata": "SKL057", + "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 from L1 and L2. It does not include all accesses to the L3.", + "SampleAfterValue": "100003", + "UMask": "0x4f" }, { - "BriefDescription": "Retired load instructions whose data sources was remote HITM", + "BriefDescription": "All retired load instructions.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "Data_LA": "1", - "EventCode": "0xD3", - "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.ALL_LOADS", "PEBS": "1", - "PublicDescription": "Retired load instructions whose data sources was remote HITM.", - "SampleAfterValue": "100007", - "UMask": "0x4" + "SampleAfterValue": "2000003", + "UMask": "0x81" }, { - "BriefDescription": "Counts all prefetch data reads that have any response type.", + "BriefDescription": "All retired store instructions.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010490", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.ALL_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "SampleAfterValue": "2000003", + "UMask": "0x82" }, { - "BriefDescription": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Retired load instructions with locked access.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0122", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.LOCK_LOADS", + "PEBS": "1", + "SampleAfterValue": "100007", + "UMask": "0x21" }, { - "BriefDescription": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Retired load instructions that split across a cacheline boundary.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0100", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "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": "0x1" + "UMask": "0x41" }, { - "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "BriefDescription": "Retired store instructions that split across a cacheline boundary.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x60", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", - "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "UMask": "0x4" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.SPLIT_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "SampleAfterValue": "100003", + "UMask": "0x42" }, { - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Retired load instructions that miss the STLB.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10003C0491", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", + "PEBS": "1", "SampleAfterValue": "100003", - "UMask": "0x1" + "UMask": "0x11" }, { - "BriefDescription": "RFO requests that miss L2 cache", + "BriefDescription": "Retired store instructions that miss the STLB.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.RFO_MISS", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that miss L2 cache.", - "SampleAfterValue": "200003", - "UMask": "0x22" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD0", + "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", + "L1_Hit_Indication": "1", + "PEBS": "1", + "SampleAfterValue": "100003", + "UMask": "0x12" }, { - "BriefDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped", + "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xF2", - "EventName": "L2_LINES_OUT.NON_SILENT", - "PublicDescription": "Counts the number of lines that are evicted by L2 cache when triggered by an L2 cache fill. Those lines can be either in modified state or clean state. Modified lines may either be written back to L3 or directly written to memory and not allocated in L3. Clean lines may either be allocated in L3 or dropped.", - "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", + "SampleAfterValue": "20011", "UMask": "0x2" }, { - "BriefDescription": "Counts the number of lines that have been hardware prefetched but not used and now evicted by L2 cache", + "BriefDescription": "Retired load instructions which data sources were HitM responses from shared L3", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xF2", - "EventName": "L2_LINES_OUT.USELESS_HWPF", - "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", + "SampleAfterValue": "20011", "UMask": "0x4" }, { - "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.", + "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010002", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", + "PEBS": "1", + "SampleAfterValue": "20011", "UMask": "0x1" }, { - "BriefDescription": "All requests that miss L2 cache", + "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.MISS", - "PublicDescription": "All requests that miss L2 cache.", - "SampleAfterValue": "200003", - "UMask": "0x3f" + "CounterHTOff": "0,1,2,3", + "Data_LA": "1", + "EventCode": "0xD2", + "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", + "PEBS": "1", + "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", + "SampleAfterValue": "100003", + "UMask": "0x8" }, { - "BriefDescription": "L2 code requests", + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.ALL_CODE_RD", - "PublicDescription": "Counts the total number of L2 code requests.", - "SampleAfterValue": "200003", - "UMask": "0xe4" + "CounterHTOff": "0,1,2,3", + "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": "Retired load instructions whose data sources was forwarded from a remote cache", + "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from remote dram", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "Data_LA": "1", "EventCode": "0xD3", - "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_FWD", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", "PEBS": "1", - "PublicDescription": "Retired load instructions whose data sources was forwarded from a remote cache.", "SampleAfterValue": "100007", - "UMask": "0x8" + "UMask": "0x2" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Retired load instructions whose data sources was forwarded from a remote cache", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10003C0020", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "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": "Counts all demand & prefetch data reads that have any response type.", + "BriefDescription": "Retired load instructions whose data sources was remote HITM", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010491", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "Data_LA": "1", + "EventCode": "0xD3", + "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_HITM", + "PEBS": "1", + "PublicDescription": "Retired load instructions whose data sources was remote HITM.", + "SampleAfterValue": "100007", + "UMask": "0x4" }, { - "BriefDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache", + "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "Data_LA": "1", - "EventCode": "0xD2", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HIT", + "EventCode": "0xD4", + "EventName": "MEM_LOAD_MISC_RETIRED.UC", "PEBS": "1", - "PublicDescription": "Retired load instructions which data sources were L3 and cross-core snoop hits in on-pkg core cache.", - "SampleAfterValue": "20011", - "UMask": "0x2" + "SampleAfterValue": "100007", + "UMask": "0x4" }, { - "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from remote dram", + "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "Data_LA": "1", - "EventCode": "0xD3", - "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_DRAM", + "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": "0x2" + "UMask": "0x40" }, { - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Retired load instructions with L1 cache hits as data sources", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0122", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", + "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": "2000003", "UMask": "0x1" }, { @@ -452,104 +515,135 @@ "UMask": "0x8" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Retired load instructions with L2 cache hits as data sources", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0020", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L2_HIT", + "PEBS": "1", + "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", "SampleAfterValue": "100003", - "UMask": "0x1" + "UMask": "0x2" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Retired load instructions missed L2 cache as data sources", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10003C0400", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "Data_LA": "1", + "EventCode": "0xD1", + "EventName": "MEM_LOAD_RETIRED.L2_MISS", + "PEBS": "1", + "PublicDescription": "Retired load instructions missed L2 cache as data sources.", + "SampleAfterValue": "50021", + "UMask": "0x10" }, { - "BriefDescription": "L2 cache misses when fetching instructions", + "BriefDescription": "Retired load instructions with L3 cache hits as data sources", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.CODE_RD_MISS", - "PublicDescription": "Counts L2 cache misses when fetching instructions.", - "SampleAfterValue": "200003", - "UMask": "0x24" + "CounterHTOff": "0,1,2,3", + "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": "50021", + "UMask": "0x4" }, { - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Retired load instructions missed L3 cache as data sources", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0490", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "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": "100007", + "UMask": "0x20" + }, + { + "BriefDescription": "Demand and prefetch data reads", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_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": "0x1" + "UMask": "0x8" }, { - "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "BriefDescription": "Any memory transaction that reached the SQ.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x60", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", - "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", - "SampleAfterValue": "2000003", - "UMask": "0x1" + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", + "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", + "SampleAfterValue": "100003", + "UMask": "0x80" }, { - "BriefDescription": "Counts demand data reads that hit in the L3.", + "BriefDescription": "Cacheable and noncachaeble code read requests", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0001", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", + "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", "SampleAfterValue": "100003", - "UMask": "0x1" + "UMask": "0x2" }, { - "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Demand Data Read requests sent to uncore", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0120", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "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": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Demand RFO requests including regular RFOs, locks, ItoM", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0120", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.DEMAND_RFO", + "PublicDescription": "Counts the demand RFO (read for ownership) requests including regular RFOs, locks, ItoM.", "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB2", + "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", + "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", + "SampleAfterValue": "2000003", "UMask": "0x1" }, { + "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { "BriefDescription": "Cycles with offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", @@ -561,212 +655,257 @@ "UMask": "0x2" }, { - "BriefDescription": "Demand requests to L2 cache", + "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.ALL_DEMAND_REFERENCES", - "PublicDescription": "Demand requests to L2 cache.", - "SampleAfterValue": "200003", - "UMask": "0xe7" + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", + "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.", + "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", + "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD", + "PublicDescription": "Counts the number of offcore outstanding Demand Data Read transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor. See the corresponding Umask under OFFCORE_REQUESTS.Note: A prefetch promoted to Demand is counted from the promotion point.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore, every cycle", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_RFO", + "PublicDescription": "Counts the number of offcore outstanding RFO (store) transactions in the super queue (SQ) every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0080", - "Offcore": "1", + "EventName": "OFFCORE_RESPONSE", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Counts all demand & prefetch data reads that have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0491", + "MSRValue": "0x0000010491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010020", + "MSRValue": "0x3F803C0491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0122", + "MSRValue": "0x10003C0491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0001", + "MSRValue": "0x04003C0491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10003C0080", + "MSRValue": "0x01003C0491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "AnyThread": "1", - "BriefDescription": "Cycles with L1D load Misses outstanding from any thread on physical core.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x48", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES_ANY", - "SampleAfterValue": "2000003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0490", + "MSRValue": "0x08003C0491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Core-originated cacheable demand requests that refer to L3", + "BriefDescription": "Counts all prefetch data reads that have any response type.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "Errata": "SKL057", - "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 from L1 and L2. It does not include all accesses to the L3.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x4f" + "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.", + "BriefDescription": "Counts all prefetch data reads that hit in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010080", + "MSRValue": "0x3F803C0490", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0120", + "MSRValue": "0x10003C0490", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3.", + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0491", + "MSRValue": "0x04003C0490", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Retired load instructions that miss the STLB.", + "BriefDescription": "Counts all prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD0", - "EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS", - "PEBS": "1", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0490", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x11" + "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that have any response type.", + "BriefDescription": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010001", + "MSRValue": "0x08003C0490", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.", + "BriefDescription": "Counts prefetch RFOs that have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0020", + "MSRValue": "0x0000010120", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "L1D data line replacements", + "BriefDescription": "Counts prefetch RFOs that hit in the L3.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "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": "2000003", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { @@ -783,47 +922,43 @@ "UMask": "0x1" }, { - "BriefDescription": "Retired instructions with at least 1 uncacheable load or lock.", + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD4", - "EventName": "MEM_LOAD_MISC_RETIRED.UC", - "PEBS": "1", - "SampleAfterValue": "100007", - "UMask": "0x4" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "BriefDescription": "Retired load instructions which data sources were load missed L1 but hit FB due to preceding miss to the same cache line with data not ready", + "BriefDescription": "Counts prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "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": "This event is deprecated. Refer to new event L2_LINES_OUT.USELESS_HWPF", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "Deprecated": "1", - "EventCode": "0xF2", - "EventName": "L2_LINES_OUT.USELESS_PREF", - "SampleAfterValue": "200003", - "UMask": "0x4" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "BriefDescription": "Requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache", + "BriefDescription": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.PF_HIT", - "PublicDescription": "Counts requests from the L1/L2/L3 hardware prefetchers or Load software prefetches that hit L2 cache.", - "SampleAfterValue": "200003", - "UMask": "0xd8" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0120", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.", @@ -839,14 +974,17 @@ "UMask": "0x1" }, { - "BriefDescription": "Demand Data Read miss L2, no rejects", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.DEMAND_DATA_RD_MISS", - "PublicDescription": "Counts the number of demand Data Read requests that miss L2 cache. Only not rejected loads are counted.", - "SampleAfterValue": "200003", - "UMask": "0x21" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", @@ -862,293 +1000,247 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010100", + "MSRValue": "0x04003C0122", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Retired load instructions which data sources were hits in L3 without snoops required", + "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD2", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_NONE", - "PEBS": "1", - "PublicDescription": "Retired load instructions which data sources were hits in L3 without snoops required.", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x8" + "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0080", + "MSRValue": "0x08003C0122", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand code reads that have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0491", + "MSRValue": "0x0000010004", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "All retired load instructions.", + "BriefDescription": "Counts all demand code reads that hit in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD0", - "EventName": "MEM_INST_RETIRED.ALL_LOADS", - "PEBS": "1", - "SampleAfterValue": "2000003", - "UMask": "0x81" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "BriefDescription": "Retired load instructions which data sources were L3 hit and cross-core snoop missed in on-pkg core cache.", + "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD2", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_MISS", - "PEBS": "1", - "SampleAfterValue": "20011", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Demand Data Read requests", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.ALL_DEMAND_DATA_RD", - "PublicDescription": "Counts the number of demand Data Read requests (including requests from L1D hardware prefetchers). These loads may hit or miss L2 cache. Only non rejected loads are counted.", - "SampleAfterValue": "200003", - "UMask": "0xe1" - }, - { - "BriefDescription": "All L2 requests", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.REFERENCES", - "PublicDescription": "All L2 requests.", - "SampleAfterValue": "200003", - "UMask": "0xff" - }, - { - "BriefDescription": "Cycles with L1D load Misses outstanding.", + "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x48", - "EventName": "L1D_PEND_MISS.PENDING_CYCLES", - "PublicDescription": "Counts duration of L1D miss outstanding in cycles.", - "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Cycles with offcore outstanding demand rfo reads transactions in SuperQueue (SQ), queue to uncore.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x60", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_RFO", - "PublicDescription": "Counts the number of offcore outstanding demand rfo Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "UMask": "0x4" - }, - { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all demand code reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0100", + "MSRValue": "0x01003C0004", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of cache line split locks sent to uncore.", + "BriefDescription": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xF4", - "EventName": "SQ_MISC.SPLIT_LOCK", - "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x08003C0004", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x10" + "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.", + "BriefDescription": "Counts demand data reads that have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0002", + "MSRValue": "0x0000010001", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Counts demand data reads that hit in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0100", + "MSRValue": "0x3F803C0001", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "L2 cache hits when fetching instructions, code reads.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.CODE_RD_HIT", - "PublicDescription": "Counts L2 cache hits when fetching instructions, code reads.", - "SampleAfterValue": "200003", - "UMask": "0xc4" - }, - { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.", + "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0400", + "MSRValue": "0x10003C0001", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.", + "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010010", + "MSRValue": "0x04003C0001", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Retired load instructions with L2 cache hits as data sources", + "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD1", - "EventName": "MEM_LOAD_RETIRED.L2_HIT", - "PEBS": "1", - "PublicDescription": "Retired load instructions with L2 cache hits as data sources.", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0001", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x2" - }, - { - "BriefDescription": "RFO requests that hit L2 cache", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x24", - "EventName": "L2_RQSTS.RFO_HIT", - "PublicDescription": "Counts the RFO (Read-for-Ownership) requests that hit L2 cache.", - "SampleAfterValue": "200003", - "UMask": "0xc2" + "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0080", + "MSRValue": "0x08003C0001", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "L1D miss outstandings duration in cycles", + "BriefDescription": "Counts all demand data writes (RFOs) that have any response type.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x48", - "EventName": "L1D_PEND_MISS.PENDING", - "PublicDescription": "Counts duration of L1D miss outstanding, that is each cycle 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": "2000003", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0491", + "MSRValue": "0x3F803C0002", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Demand Data Read requests that hit L2 cache", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "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": "Retired load instructions which data sources were HitM responses from shared L3", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD2", - "EventName": "MEM_LOAD_L3_HIT_RETIRED.XSNP_HITM", - "PEBS": "1", - "PublicDescription": "Retired load instructions which data sources were HitM responses from shared L3.", - "SampleAfterValue": "20011", - "UMask": "0x4" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x10003C0002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0001", + "MSRValue": "0x04003C0002", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", @@ -1168,508 +1260,416 @@ "UMask": "0x1" }, { - "BriefDescription": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0080", + "MSRValue": "0x08003C0002", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0010", + "MSRValue": "0x0000010400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Retired store instructions that split across a cacheline boundary.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD0", - "EventName": "MEM_INST_RETIRED.SPLIT_STORES", - "L1_Hit_Indication": "1", - "PEBS": "1", - "PublicDescription": "Counts retired store instructions that split across a cacheline boundary.", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0400", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x42" + "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10003C0010", + "MSRValue": "0x10003C0400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Any memory transaction that reached the SQ.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xB0", - "EventName": "OFFCORE_REQUESTS.ALL_REQUESTS", - "PublicDescription": "Counts memory transactions reached the super queue including requests initiated by the core, all L3 prefetches, page walks, etc..", - "SampleAfterValue": "100003", - "UMask": "0x80" - }, - { - "BriefDescription": "Cacheable and noncachaeble code read requests", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xB0", - "EventName": "OFFCORE_REQUESTS.DEMAND_CODE_RD", - "PublicDescription": "Counts both cacheable and non-cacheable code read requests.", - "SampleAfterValue": "100003", - "UMask": "0x2" - }, - { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10003C0100", + "MSRValue": "0x04003C0400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0004", + "MSRValue": "0x01003C0400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Cycles when offcore outstanding Demand Data Read transactions are present in SuperQueue (SQ), queue to uncore", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x60", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD", - "PublicDescription": "Counts cycles when offcore outstanding Demand Data Read transactions are present in the super queue (SQ). A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation).", - "SampleAfterValue": "2000003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that have any response type.", + "BriefDescription": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.ANY_RESPONSE", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010400", + "MSRValue": "0x08003C0400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HITM_OTHER_CORE", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10003C0004", + "MSRValue": "0x0000010010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0004", + "MSRValue": "0x3F803C0010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times a request needed a FB entry but there was no entry available for it. That is the FB unavailability was dominant reason for blocking the request. A request includes cacheable/uncacheable demands that is load, store or SW prefetch.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x48", - "EventName": "L1D_PEND_MISS.FB_FULL", - "PublicDescription": "Number of times a request needed a FB (Fill Buffer) entry but there was no entry available for it. A request includes cacheable/uncacheable demands that are load, store or SW prefetch instructions.", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0020", + "MSRValue": "0x10003C0010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads that hit in the L3.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_HIT.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0004", + "MSRValue": "0x04003C0010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch RFOs that hit in the L3.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_HIT.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0120", + "MSRValue": "0x01003C0010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0020", + "MSRValue": "0x08003C0010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.SNOOP_HIT_WITH_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.ANY_RESPONSE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0400", + "MSRValue": "0x0000010020", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Retired load instructions with L1 cache hits as data sources", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "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": "2000003", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Cycles when offcore outstanding cacheable Core Data Read transactions are present in SuperQueue (SQ), queue to uncore.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x60", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DATA_RD", - "PublicDescription": "Counts cycles when offcore outstanding cacheable Core Data Read transactions are present in the super queue. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "UMask": "0x8" - }, - { - "BriefDescription": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0490", + "MSRValue": "0x10003C0020", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Retired load instructions with locked access.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD0", - "EventName": "MEM_INST_RETIRED.LOCK_LOADS", - "PEBS": "1", - "SampleAfterValue": "100007", - "UMask": "0x21" - }, - { - "BriefDescription": "Demand and prefetch data reads", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xB0", - "EventName": "OFFCORE_REQUESTS.ALL_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.", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x8" - }, - { - "BriefDescription": "Retired load instructions which data sources missed L3 but serviced from local dram", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "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": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.NO_SNOOP_NEEDED", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x01003C0020", + "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_HIT.NO_SNOOP_NEEDED", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0400", + "MSRValue": "0x08003C0020", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Retired load instructions that split across a cacheline boundary.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD0", - "EventName": "MEM_INST_RETIRED.SPLIT_LOADS", - "PEBS": "1", - "PublicDescription": "Counts retired load instructions that split across a cacheline boundary.", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x41" - }, - { - "BriefDescription": "Offcore requests buffer cannot take more entries for this thread core.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xB2", - "EventName": "OFFCORE_REQUESTS_BUFFER.SQ_FULL", - "PublicDescription": "Counts the number of cases when the offcore requests buffer cannot take more entries for the core. This can happen when the superqueue does not contain eligible entries, or when L1D writeback pending FIFO requests is full.Note: Writeback pending FIFO has six entries.", - "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Cycles with at least 6 offcore outstanding Demand Data Read transactions in uncore queue.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "6", - "EventCode": "0x60", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD_GE_6", - "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3F803C0080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Offcore outstanding Code Reads transactions in the SuperQueue (SQ), queue to uncore, every cycle.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x60", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_CODE_RD", - "PublicDescription": "Counts the number of offcore outstanding Code Reads transactions in the super queue every cycle. The 'Offcore outstanding' state of the transaction lasts from the L2 miss until the sending transaction completion to requestor (SQ deallocation). See the corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0002", + "MSRValue": "0x10003C0080", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3F803C0010", + "MSRValue": "0x04003C0080", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch RFOs that have any response type.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.ANY_RESPONSE", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0000010120", + "MSRValue": "0x01003C0080", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_HIT.HITM_OTHER_CORE", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x10003C0002", + "MSRValue": "0x08003C0080", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Retired store instructions that miss the STLB.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that have any response type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD0", - "EventName": "MEM_INST_RETIRED.STLB_MISS_STORES", - "L1_Hit_Indication": "1", - "PEBS": "1", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.ANY_RESPONSE", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0000010100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x12" - }, - { - "BriefDescription": "RFO requests to L2 cache", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "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" + "UMask": "0x1" }, { - "BriefDescription": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x08003C0010", + "MSRValue": "0x3F803C0100", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HITM_OTHER_CORE", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0010", + "MSRValue": "0x10003C0100", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Retired load instructions missed L2 cache as data sources", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "Data_LA": "1", - "EventCode": "0xD1", - "EventName": "MEM_LOAD_RETIRED.L2_MISS", - "PEBS": "1", - "PublicDescription": "Retired load instructions missed L2 cache as data sources.", - "SampleAfterValue": "50021", - "UMask": "0x10" + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x04003C0100", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that hit in the L3 and sibling core snoops are not needed as either the core-valid bit is not set or the shared line is present in multiple cores.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_HIT.NO_SNOOP_NEEDED", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.NO_SNOOP_NEEDED", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x01003C0001", + "MSRValue": "0x01003C0100", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Offcore outstanding cacheable Core Data Read transactions in SuperQueue (SQ), queue to uncore", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x60", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.ALL_DATA_RD", - "PublicDescription": "Counts the number of offcore outstanding cacheable Core Data Read transactions in the super queue every cycle. A transaction is considered to be in the Offcore outstanding state between L2 miss and transaction completion sent to requestor (SQ de-allocation). See corresponding Umask under OFFCORE_REQUESTS.", - "SampleAfterValue": "2000003", - "UMask": "0x8" - }, - { - "BriefDescription": "Counts all demand & prefetch RFOs that hit in the L3 and the snoop to one of the sibling cores hits the line in M state and the line is forwarded.", + "BriefDescription": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_HIT.HIT_OTHER_CORE_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_HIT.SNOOP_HIT_WITH_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x04003C0122", + "MSRValue": "0x08003C0100", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" + }, + { + "BriefDescription": "Number of cache line split locks sent to uncore.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xF4", + "EventName": "SQ_MISC.SPLIT_LOCK", + "PublicDescription": "Counts the number of cache line split locks sent to the uncore.", + "SampleAfterValue": "100003", + "UMask": "0x10" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json index e197cde15047..503737ed3a83 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/floating-point.json @@ -9,22 +9,13 @@ "UMask": "0x4" }, { - "BriefDescription": "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 RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC7", - "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", - "SampleAfterValue": "2000003", - "UMask": "0x40" - }, - { - "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar 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.", + "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.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0xC7", - "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", + "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", "SampleAfterValue": "2000003", - "UMask": "0x2" + "UMask": "0x8" }, { "BriefDescription": "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 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.", @@ -36,33 +27,31 @@ "UMask": "0x10" }, { - "BriefDescription": "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 RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 16 calculations per element.", + "BriefDescription": "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 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.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0xC7", - "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", + "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", "SampleAfterValue": "2000003", - "UMask": "0x80" + "UMask": "0x20" }, { - "BriefDescription": "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 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.", + "BriefDescription": "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 RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 8 calculations per element.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0xC7", - "EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE", "SampleAfterValue": "2000003", - "UMask": "0x20" + "UMask": "0x40" }, { - "BriefDescription": "Cycles with any input/output SSE or FP assist", + "BriefDescription": "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 RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 16 calculations per element.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0xCA", - "EventName": "FP_ASSIST.ANY", - "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", - "SampleAfterValue": "100003", - "UMask": "0x1e" + "EventCode": "0xC7", + "EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE", + "SampleAfterValue": "2000003", + "UMask": "0x80" }, { "BriefDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar double 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.", @@ -74,12 +63,23 @@ "UMask": "0x1" }, { - "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.", + "BriefDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computation. Applies to SSE* and AVX* scalar 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.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0xC7", - "EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE", + "EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE", "SampleAfterValue": "2000003", - "UMask": "0x8" + "UMask": "0x2" + }, + { + "BriefDescription": "Cycles with any input/output SSE or FP assist", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xCA", + "EventName": "FP_ASSIST.ANY", + "PublicDescription": "Counts cycles with any input and output SSE or x87 FP assist. If an input and output assist are detected on the same cycle the event increments by 1.", + "SampleAfterValue": "100003", + "UMask": "0x1e" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json index cdf95bd2a73d..078706a50091 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json @@ -1,13 +1,47 @@ [ { - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x80", - "EventName": "ICACHE_16B.IFDATA_STALL", - "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", + "EventCode": "0xE6", + "EventName": "BACLEARS.ANY", + "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This 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": "Decode Stream Buffer (DSB)-to-MITE switches", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.COUNT", + "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.", "SampleAfterValue": "2000003", - "UMask": "0x4" + "UMask": "0x1" + }, + { + "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xAB", + "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", + "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.DSB_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x11", + "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { "BriefDescription": "Retired Instructions who experienced iTLB true miss.", @@ -24,220 +58,246 @@ "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.", + "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "EventName": "FRONTEND_RETIRED.L1I_MISS", "MSRIndex": "0x3F7", - "MSRValue": "0x408006", + "MSRValue": "0x12", "PEBS": "1", "SampleAfterValue": "100007", "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x9C", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", - "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", - "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.L2_MISS", + "MSRIndex": "0x3F7", + "MSRValue": "0x13", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x79", - "EventName": "IDQ.DSB_CYCLES", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", - "SampleAfterValue": "2000003", - "UMask": "0x8" - }, - { - "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", + "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "3", - "EventCode": "0x9C", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", - "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", - "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xc6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", + "MSRIndex": "0x3F7", + "MSRValue": "0x400106", + "PEBS": "2", + "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", + "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Counts the total number when the front end is resteered, mainly when the BPU cannot provide a correct prediction and this is corrected by other branch handling mechanisms at the front end.", + "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.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xE6", - "EventName": "BACLEARS.ANY", - "PublicDescription": "Counts the number of times the front-end is resteered when it finds a branch instruction in a fetch line. This 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", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_128", + "MSRIndex": "0x3F7", + "MSRValue": "0x408006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Retired Instructions who experienced decode stream buffer (DSB - the decoded instruction-cache) miss.", + "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.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.DSB_MISS", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", "MSRIndex": "0x3F7", - "MSRValue": "0x11", + "MSRValue": "0x401006", "PEBS": "1", - "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.", + "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", "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "4", - "EventCode": "0x9C", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", - "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", - "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x400206", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", "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.", + "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.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_16", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", "MSRIndex": "0x3F7", - "MSRValue": "0x401006", + "MSRValue": "0x410006", "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", "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", + "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.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x79", - "EventName": "IDQ.MITE_UOPS", - "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", - "SampleAfterValue": "2000003", - "UMask": "0x4" + "CounterHTOff": "0,1,2,3", + "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", + "TakenAlone": "1", + "UMask": "0x1" }, { - "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "2", - "EventCode": "0x9C", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", - "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", - "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", + "MSRIndex": "0x3F7", + "MSRValue": "0x200206", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x79", - "EventName": "IDQ.MS_CYCLES", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", - "SampleAfterValue": "2000003", - "UMask": "0x30" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", + "MSRIndex": "0x3F7", + "MSRValue": "0x300206", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "BriefDescription": "Cycles MITE is delivering any Uop", + "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.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x79", - "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", - "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", - "SampleAfterValue": "2000003", - "UMask": "0x24" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", + "MSRIndex": "0x3F7", + "MSRValue": "0x402006", + "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", + "TakenAlone": "1", + "UMask": "0x1" }, { - "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "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.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x83", - "EventName": "ICACHE_64B.IFTAG_HIT", - "SampleAfterValue": "200003", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", + "MSRIndex": "0x3F7", + "MSRValue": "0x400406", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", + "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.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "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": "2000003", - "UMask": "0x30" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", + "MSRIndex": "0x3F7", + "MSRValue": "0x420006", + "PEBS": "1", + "SampleAfterValue": "100007", + "TakenAlone": "1", + "UMask": "0x1" }, { - "BriefDescription": "Retired Instructions who experienced Instruction L2 Cache true miss.", + "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.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.L2_MISS", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", "MSRIndex": "0x3F7", - "MSRValue": "0x13", + "MSRValue": "0x404006", "PEBS": "1", "SampleAfterValue": "100007", "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", + "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.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x79", - "EventName": "IDQ.MITE_CYCLES", - "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", - "SampleAfterValue": "2000003", - "UMask": "0x4" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC6", + "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", + "MSRIndex": "0x3F7", + "MSRValue": "0x400806", + "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", + "TakenAlone": "1", + "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.", + "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_64", + "EventName": "FRONTEND_RETIRED.STLB_MISS", "MSRIndex": "0x3F7", - "MSRValue": "0x404006", + "MSRValue": "0x15", "PEBS": "1", + "PublicDescription": "Counts retired Instructions that experienced STLB (2nd level TLB) true miss.", "SampleAfterValue": "100007", "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x9C", - "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", - "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", + "EventCode": "0x80", + "EventName": "ICACHE_16B.IFDATA_STALL", + "PublicDescription": "Cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Instruction fetch tag lookups that hit in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_HIT", + "SampleAfterValue": "200003", "UMask": "0x1" }, { - "BriefDescription": "Uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", + "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x79", - "EventName": "IDQ.MS_MITE_UOPS", - "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", - "SampleAfterValue": "2000003", - "UMask": "0x20" + "EventCode": "0x83", + "EventName": "ICACHE_64B.IFTAG_MISS", + "SampleAfterValue": "200003", + "UMask": "0x2" }, { "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", @@ -249,14 +309,15 @@ "UMask": "0x4" }, { - "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles.", + "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xAB", - "EventName": "DSB2MITE_SWITCHES.PENALTY_CYCLES", - "PublicDescription": "Counts Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles. These cycles do not include uops routed through because of the switch itself, for example, when Instruction Decode Queue (IDQ) pre-allocation is unavailable, or Instruction Decode Queue (IDQ) is full. SBD-to-MITE switch true penalty cycles happen after the merge mux (MM) receives Decode Stream Buffer (DSB) Sync-indication until receiving the first MITE uop. MM is placed before Instruction Decode Queue (IDQ) to merge uops being fed from the MITE and Decode Stream Buffer (DSB) paths. Decode Stream Buffer (DSB) inserts the Sync-indication whenever a Decode Stream Buffer (DSB)-to-MITE switch occurs.Penalty: A Decode Stream Buffer (DSB) hit followed by a Decode Stream Buffer (DSB) miss can cost up to six cycles in which no uops are delivered to the IDQ. Most often, such switches from the Decode Stream Buffer (DSB) to the legacy pipeline cost 02 cycles.", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "UMask": "0x2" + "UMask": "0x18" }, { "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering any Uop", @@ -270,106 +331,79 @@ "UMask": "0x18" }, { - "BriefDescription": "Retired Instructions who experienced STLB (2nd level TLB) true miss.", + "BriefDescription": "Cycles MITE is delivering 4 Uops", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "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", - "TakenAlone": "1", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x79", + "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", + "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x24" }, { - "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", + "BriefDescription": "Cycles MITE is delivering any Uop", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", "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. Counting includes uops that may 'bypass' the IDQ.", + "EventName": "IDQ.ALL_MITE_CYCLES_ANY_UOPS", + "PublicDescription": "Counts the number of cycles uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", "SampleAfterValue": "2000003", - "UMask": "0x8" + "UMask": "0x24" }, { - "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.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_512", - "MSRIndex": "0x3F7", - "MSRValue": "0x420006", - "PEBS": "1", - "SampleAfterValue": "100007", - "TakenAlone": "1", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.DSB_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "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.", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_8", - "MSRIndex": "0x3F7", - "MSRValue": "0x400806", - "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", - "TakenAlone": "1", - "UMask": "0x1" - }, - { - "BriefDescription": "Retired instructions after front-end starvation of at least 1 cycle", - "Counter": "0,1,2,3,4,5,6,7", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xc6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_1", - "MSRIndex": "0x3F7", - "MSRValue": "0x400106", - "PEBS": "2", - "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", - "TakenAlone": "1", - "UMask": "0x1" + "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. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end delivered no uops for a period of 2 cycles which was not interrupted by a back-end stall.", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2", - "MSRIndex": "0x3F7", - "MSRValue": "0x400206", - "PEBS": "1", - "SampleAfterValue": "100007", - "TakenAlone": "1", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x79", + "EventName": "IDQ.MITE_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ.", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "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.", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) from MITE path", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_4", - "MSRIndex": "0x3F7", - "MSRValue": "0x400406", - "PEBS": "1", - "SampleAfterValue": "100007", - "TakenAlone": "1", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x79", + "EventName": "IDQ.MITE_UOPS", + "PublicDescription": "Counts the number of uops delivered to Instruction Decode Queue (IDQ) from the MITE path. Counting includes uops that may 'bypass' the IDQ. This also means that uops are not being delivered from the Decode Stream Buffer (DSB).", + "SampleAfterValue": "2000003", + "UMask": "0x4" }, { - "BriefDescription": "Cycles MITE is delivering 4 Uops", + "BriefDescription": "Cycles when uops are being delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "4", + "CounterMask": "1", "EventCode": "0x79", - "EventName": "IDQ.ALL_MITE_CYCLES_4_UOPS", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. Counting includes uops that may 'bypass' the IDQ. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).", + "EventName": "IDQ.MS_CYCLES", + "PublicDescription": "Counts cycles during which uops are being delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ. Uops maybe initiated by Decode Stream Buffer (DSB) or MITE.", "SampleAfterValue": "2000003", - "UMask": "0x24" + "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", @@ -383,101 +417,56 @@ "UMask": "0x10" }, { - "BriefDescription": "Uops 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 Sequenser (MS) is busy", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x79", - "EventName": "IDQ.MS_UOPS", - "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", + "EventName": "IDQ.MS_MITE_UOPS", + "PublicDescription": "Counts the number of uops initiated by MITE and delivered to Instruction Decode Queue (IDQ) while the Microcode Sequencer (MS) is busy. Counting includes uops that may 'bypass' the IDQ.", "SampleAfterValue": "2000003", - "UMask": "0x30" - }, - { - "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.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_256", - "MSRIndex": "0x3F7", - "MSRValue": "0x410006", - "PEBS": "1", - "SampleAfterValue": "100007", - "TakenAlone": "1", - "UMask": "0x1" - }, - { - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 2 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_2", - "MSRIndex": "0x3F7", - "MSRValue": "0x200206", - "PEBS": "1", - "SampleAfterValue": "100007", - "TakenAlone": "1", - "UMask": "0x1" - }, - { - "BriefDescription": "Retired instructions that are fetched after an interval where the front-end had at least 3 bubble-slots for a period of 2 cycles which was not interrupted by a back-end stall.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_2_BUBBLES_GE_3", - "MSRIndex": "0x3F7", - "MSRValue": "0x300206", - "PEBS": "1", - "SampleAfterValue": "100007", - "TakenAlone": "1", - "UMask": "0x1" + "UMask": "0x20" }, { - "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.", + "BriefDescription": "Number of switches from DSB (Decode Stream Buffer) or MITE (legacy decode pipeline) to the Microcode Sequencer", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "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", - "TakenAlone": "1", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "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": "2000003", + "UMask": "0x30" }, { - "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops", + "BriefDescription": "Uops delivered to Instruction Decode Queue (IDQ) while Microcode Sequenser (MS) is busy", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "4", "EventCode": "0x79", - "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS", - "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ.", + "EventName": "IDQ.MS_UOPS", + "PublicDescription": "Counts the total number of uops delivered by the Microcode Sequencer (MS). Any instruction over 4 uops will be delivered by the MS. Some instructions such as transcendentals may additionally generate uops from the MS.", "SampleAfterValue": "2000003", - "UMask": "0x18" + "UMask": "0x30" }, { - "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches", + "BriefDescription": "Uops not delivered to Resource Allocation Table (RAT) per thread when backend of the machine is not stalled", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xAB", - "EventName": "DSB2MITE_SWITCHES.COUNT", - "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CORE", + "PublicDescription": "Counts the number of uops not delivered to Resource Allocation Table (RAT) per thread adding 4 x when Resource Allocation Table (RAT) is not stalled and Instruction Decode Queue (IDQ) delivers x uops to Resource Allocation Table (RAT) (where x belongs to {0,1,2,3}). Counting does not cover cases when: a. IDQ-Resource Allocation Table (RAT) pipe serves the other thread. b. Resource Allocation Table (RAT) is stalled for the thread (including uop drops and clear BE conditions). c. Instruction Decode Queue (IDQ) delivers four uops.", "SampleAfterValue": "2000003", "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.", + "BriefDescription": "Cycles per thread when 4 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.LATENCY_GE_32", - "MSRIndex": "0x3F7", - "MSRValue": "0x402006", - "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", - "TakenAlone": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "4", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE", + "PublicDescription": "Counts, on the per-thread basis, cycles when no uops are delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core =4.", + "SampleAfterValue": "2000003", "UMask": "0x1" }, { @@ -492,25 +481,36 @@ "UMask": "0x1" }, { - "BriefDescription": "Instruction fetch tag lookups that miss in the instruction cache (L1I). Counts at 64-byte cache-line granularity.", + "BriefDescription": "Cycles per thread when 3 or more uops are not delivered to Resource Allocation Table (RAT) when backend of the machine is not stalled", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x83", - "EventName": "ICACHE_64B.IFTAG_MISS", - "SampleAfterValue": "200003", - "UMask": "0x2" + "CounterMask": "3", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_1_UOP_DELIV.CORE", + "PublicDescription": "Counts, on the per-thread basis, cycles when less than 1 uop is delivered to Resource Allocation Table (RAT). IDQ_Uops_Not_Delivered.core >= 3.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "BriefDescription": "Retired Instructions who experienced Instruction L1 Cache true miss.", + "BriefDescription": "Cycles with less than 2 uops delivered by the front end.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xC6", - "EventName": "FRONTEND_RETIRED.L1I_MISS", - "MSRIndex": "0x3F7", - "MSRValue": "0x12", - "PEBS": "1", - "SampleAfterValue": "100007", - "TakenAlone": "1", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_2_UOP_DELIV.CORE", + "PublicDescription": "Cycles with less than 2 uops delivered by the front-end.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles with less than 3 uops delivered by the front end.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x9C", + "EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_LE_3_UOP_DELIV.CORE", + "PublicDescription": "Cycles with less than 3 uops delivered by the front-end.", + "SampleAfterValue": "2000003", "UMask": "0x1" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json index 6c3fd89d204d..6f29b02fa320 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/memory.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json @@ -1,31 +1,262 @@ [ { - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800122", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "2", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "6", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "SampleAfterValue": "2000003", + "UMask": "0x6" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED", + "PEBS": "1", + "PublicDescription": "Number of times HLE abort was triggered.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_MEM", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "UMask": "0x40" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of times an HLE execution successfully committed", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.COMMIT", + "PublicDescription": "Number of times HLE commit succeeded.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an HLE execution started.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC8", + "EventName": "HLE_RETIRED.START", + "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL089", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", + "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "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", + "TakenAlone": "1", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.", + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000122", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "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", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "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", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "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", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "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", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "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", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "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", + "TakenAlone": "1", + "UMask": "0x1" + }, + { + "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "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", + "TakenAlone": "1", "UMask": "0x1" }, { + "BriefDescription": "Demand Data Read requests who miss L3 cache", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xB0", + "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", + "PublicDescription": "Demand Data Read requests who miss L3 cache.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x60", + "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { "BriefDescription": "Cycles with at least 6 Demand Data Read requests that miss L3 cache in the superQ.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", @@ -36,146 +267,130 @@ "UMask": "0x10" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800020", + "MSRValue": "0x3FBC000491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000100", + "MSRValue": "0x103FC00491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00002", + "MSRValue": "0x083FC00491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an HLE execution aborted due to hardware timer expiration.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC8", - "EventName": "HLE_RETIRED.ABORTED_TIMER", - "SampleAfterValue": "2000003", - "UMask": "0x10" - }, - { - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800490", + "MSRValue": "0x063FC00491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC9", - "EventName": "RTM_RETIRED.ABORTED_MEM", - "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", - "SampleAfterValue": "2000003", - "UMask": "0x8" - }, - { - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800004", + "MSRValue": "0x0604000491", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", + "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC9", - "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", - "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", - "SampleAfterValue": "2000003", - "UMask": "0x40" + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800491", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.", + "BriefDescription": "Counts all prefetch data reads that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000002", + "MSRValue": "0x3FBC000490", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00120", + "MSRValue": "0x103FC00490", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch data reads that miss in the L3.", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000490", + "MSRValue": "0x083FC00490", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0604000120", + "MSRValue": "0x063FC00490", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", @@ -195,464 +410,312 @@ "UMask": "0x1" }, { - "BriefDescription": "Cycles while L3 cache miss demand load is outstanding.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "2", - "EventCode": "0xA3", - "EventName": "CYCLE_ACTIVITY.CYCLES_L3_MISS", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local dram.", + "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0604000491", + "MSRValue": "0x063B800490", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts prefetch RFOs that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00004", + "MSRValue": "0x3FBC000120", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00004", + "MSRValue": "0x103FC00120", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 32 cycles.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "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", - "TakenAlone": "1", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00020", + "MSRValue": "0x083FC00120", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00490", + "MSRValue": "0x063FC00120", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000020", + "MSRValue": "0x0604000120", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x54", - "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", - "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", - "SampleAfterValue": "2000003", - "UMask": "0x4" - }, - { - "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x54", - "EventName": "TX_MEM.ABORT_CONFLICT", - "PublicDescription": "Number of times a TSX line had a cache conflict.", - "SampleAfterValue": "2000003", - "UMask": "0x1" - }, - { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.", + "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000400", + "MSRValue": "0x063B800120", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 64 cycles.", + "BriefDescription": "Counts all demand & prefetch RFOs that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "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", - "TakenAlone": "1", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000122", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00002", + "MSRValue": "0x103FC00122", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an HLE execution aborted due to various memory events (e.g., read/write capacity and conflicts).", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC8", - "EventName": "HLE_RETIRED.ABORTED_MEM", - "SampleAfterValue": "2000003", - "UMask": "0x8" - }, - { - "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x54", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", - "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", - "SampleAfterValue": "2000003", - "UMask": "0x8" - }, - { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00080", + "MSRValue": "0x083FC00122", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x5d", - "EventName": "TX_EXEC.MISC5", - "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", - "SampleAfterValue": "2000003", - "UMask": "0x10" - }, - { - "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x5d", - "EventName": "TX_EXEC.MISC4", - "PublicDescription": "RTM region detected inside HLE.", - "SampleAfterValue": "2000003", - "UMask": "0x8" - }, - { - "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x5d", - "EventName": "TX_EXEC.MISC3", - "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", - "SampleAfterValue": "2000003", - "UMask": "0x4" - }, - { - "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x5d", - "EventName": "TX_EXEC.MISC2", - "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x5d", - "EventName": "TX_EXEC.MISC1", - "SampleAfterValue": "2000003", - "UMask": "0x1" - }, - { - "BriefDescription": "Number of times an RTM execution successfully committed", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC9", - "EventName": "RTM_RETIRED.COMMIT", - "PublicDescription": "Number of times RTM commit succeeded.", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Counts prefetch RFOs that miss in the L3.", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000120", + "MSRValue": "0x063FC00122", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts number of Offcore outstanding Demand Data Read requests that miss L3 cache in the superQ every cycle.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x60", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "UMask": "0x10" - }, - { - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800491", + "MSRValue": "0x0604000122", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800080", + "MSRValue": "0x063B800122", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts all demand code reads that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00490", + "MSRValue": "0x3FBC000004", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.", + "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0604000010", + "MSRValue": "0x103FC00004", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC9", - "EventName": "RTM_RETIRED.ABORTED_TIMER", - "SampleAfterValue": "2000003", - "UMask": "0x10" - }, - { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts all demand code reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00020", + "MSRValue": "0x083FC00004", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00002", + "MSRValue": "0x063FC00004", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch data reads that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00490", + "MSRValue": "0x0604000004", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800100", + "MSRValue": "0x063B800004", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts demand data reads that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00010", + "MSRValue": "0x3FBC000001", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00010", + "MSRValue": "0x103FC00001", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an HLE execution aborted due to HLE-unfriendly instructions and certain unfriendly events (such as AD assists etc.).", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC8", - "EventName": "HLE_RETIRED.ABORTED_UNFRIENDLY", - "SampleAfterValue": "2000003", - "UMask": "0x20" - }, - { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800400", + "MSRValue": "0x083FC00001", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00122", + "MSRValue": "0x063FC00001", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00122", + "MSRValue": "0x0604000001", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", @@ -672,541 +735,442 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local dram.", + "BriefDescription": "Counts all demand data writes (RFOs) that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0604000001", + "MSRValue": "0x3FBC000002", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an HLE execution successfully committed", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC8", - "EventName": "HLE_RETIRED.COMMIT", - "PublicDescription": "Number of times HLE commit succeeded.", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x54", - "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", - "PublicDescription": "Number of times we could not allocate Lock Buffer.", - "SampleAfterValue": "2000003", - "UMask": "0x40" - }, - { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00100", + "MSRValue": "0x103FC00002", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00001", + "MSRValue": "0x083FC00002", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0604000020", + "MSRValue": "0x063FC00002", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00080", + "MSRValue": "0x0604000002", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Demand Data Read requests who miss L3 cache", + "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xB0", - "EventName": "OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD", - "PublicDescription": "Demand Data Read requests who miss L3 cache.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800002", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x10" + "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00080", + "MSRValue": "0x3FBC000400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that miss in the L3.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000001", + "MSRValue": "0x103FC00400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC9", - "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", - "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", - "SampleAfterValue": "2000003", - "UMask": "0x20" - }, - { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00010", + "MSRValue": "0x083FC00400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00120", + "MSRValue": "0x063FC00400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00004", + "MSRValue": "0x0604000400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00100", + "MSRValue": "0x063B800400", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "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", - "TakenAlone": "1", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x3FBC000010", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00122", + "MSRValue": "0x103FC00010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00001", + "MSRValue": "0x083FC00010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00020", + "MSRValue": "0x063FC00010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800002", + "MSRValue": "0x0604000010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00491", + "MSRValue": "0x063B800010", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC9", - "EventName": "RTM_RETIRED.ABORTED", - "PEBS": "1", - "PublicDescription": "Number of times RTM abort was triggered.", - "SampleAfterValue": "2000003", - "UMask": "0x4" - }, - { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00400", + "MSRValue": "0x3FBC000020", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an HLE execution aborted due to any reasons (multiple categories may count as one).", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC8", - "EventName": "HLE_RETIRED.ABORTED", - "PEBS": "1", - "PublicDescription": "Number of times HLE abort was triggered.", - "SampleAfterValue": "2000003", - "UMask": "0x4" - }, - { - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 16 cycles.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "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", - "TakenAlone": "1", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HITM", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x103FC00020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x54", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", - "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", - "SampleAfterValue": "2000003", - "UMask": "0x20" - }, - { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00400", + "MSRValue": "0x083FC00020", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800010", + "MSRValue": "0x063FC00020", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Cycles with at least 1 Demand Data Read requests who miss L3 cache in the superQ.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x60", - "EventName": "OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_L3_MISS_DEMAND_DATA_RD", - "SampleAfterValue": "2000003", - "UMask": "0x10" - }, - { - "BriefDescription": "Counts all demand data writes (RFOs) that miss the L3 and the data is returned from local dram.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0604000002", + "MSRValue": "0x0604000020", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 512 cycles.", + "BriefDescription": "Counts all prefetch (that bring data to L2) RFOs that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", - "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", - "TakenAlone": "1", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L2_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800020", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS.REMOTE_HITM", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00400", + "MSRValue": "0x3FBC000080", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts prefetch (that bring data to L2) data reads that miss in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L2_DATA_RD.L3_MISS.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000010", + "MSRValue": "0x103FC00080", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand code reads that miss the L3 and the data is returned from local dram.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0604000004", + "MSRValue": "0x083FC00080", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x54", - "EventName": "TX_MEM.ABORT_CAPACITY", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the data is returned from remote dram.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063B800120", + "MSRValue": "0x063FC00080", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Number of times an HLE execution aborted due to incompatible memory type", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC8", - "EventName": "HLE_RETIRED.ABORTED_MEMTYPE", - "PublicDescription": "Number of times an HLE execution aborted due to incompatible memory type.", - "SampleAfterValue": "2000003", - "UMask": "0x40" - }, - { - "BriefDescription": "Number of times an RTM execution started.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC9", - "EventName": "RTM_RETIRED.START", - "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", - "SampleAfterValue": "2000003", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x0604000080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts the number of machine clears due to memory order conflicts.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "Errata": "SKL089", - "EventCode": "0xC3", - "EventName": "MACHINE_CLEARS.MEMORY_ORDERING", - "PublicDescription": "Counts the number of memory ordering Machine Clears detected. Memory Ordering Machine Clears can result from one of the following:a. memory disambiguation,b. external snoop, orc. cross SMT-HW-thread snoop (stores) hitting load buffer.", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xB7, 0xBB", + "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", + "MSRIndex": "0x1a6,0x1a7", + "MSRValue": "0x063B800080", + "Offcore": "1", + "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", - "UMask": "0x2" - }, - { - "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x54", - "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", - "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", - "SampleAfterValue": "2000003", - "UMask": "0x10" + "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss in the L3.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.ANY_SNOOP", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00491", + "MSRValue": "0x3FBC000100", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all demand & prefetch data reads that miss in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the modified data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HITM", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000491", + "MSRValue": "0x103FC00100", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts demand data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and clean or shared data is transferred from remote cache.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.REMOTE_HIT_FORWARD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00001", + "MSRValue": "0x083FC00100", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss in the L3.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS.ANY_SNOOP", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000080", + "MSRValue": "0x063FC00100", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", @@ -1226,19 +1190,30 @@ "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) data reads that miss the L3 and the data is returned from local dram.", + "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from remote dram.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3", "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_DATA_RD.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", + "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS_REMOTE_DRAM.SNOOP_MISS_OR_NO_FWD", "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0604000080", + "MSRValue": "0x063B800100", "Offcore": "1", "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", "SampleAfterValue": "100003", "UMask": "0x1" }, { + "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED", + "PEBS": "1", + "PublicDescription": "Number of times RTM abort was triggered.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { "BriefDescription": "Number of times an RTM execution aborted due to none of the previous 4 categories (e.g. interrupt)", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", @@ -1249,155 +1224,180 @@ "UMask": "0x80" }, { - "BriefDescription": "Number of times an HLE execution started.", + "BriefDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts)", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC8", - "EventName": "HLE_RETIRED.START", - "PublicDescription": "Number of times we entered an HLE region. Does not count nested transactions.", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_MEM", + "PublicDescription": "Number of times an RTM execution aborted due to various memory events (e.g. read/write capacity and conflicts).", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0x8" }, { - "BriefDescription": "Counts all demand code reads that miss in the L3.", + "BriefDescription": "Number of times an RTM execution aborted due to incompatible memory type", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.DEMAND_CODE_RD.L3_MISS.ANY_SNOOP", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x3FBC000004", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_MEMTYPE", + "PublicDescription": "Number of times an RTM execution aborted due to incompatible memory type.", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 128 cycles.", + "BriefDescription": "Number of times an RTM execution aborted due to uncommon conditions.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "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", - "TakenAlone": "1", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_TIMER", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "BriefDescription": "Counts all demand & prefetch data reads that miss the L3 and clean or shared data is transferred from remote cache.", + "BriefDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_DATA_RD.L3_MISS.REMOTE_HIT_FORWARD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x083FC00491", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.ABORTED_UNFRIENDLY", + "PublicDescription": "Number of times an RTM execution aborted due to HLE-unfriendly instructions.", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "BriefDescription": "Counts prefetch RFOs that miss the L3 and the modified data is transferred from remote cache.", + "BriefDescription": "Number of times an RTM execution successfully committed", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_PF_RFO.L3_MISS.REMOTE_HITM", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x103FC00120", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.COMMIT", + "PublicDescription": "Number of times RTM commit succeeded.", + "SampleAfterValue": "2000003", + "UMask": "0x2" + }, + { + "BriefDescription": "Number of times an RTM execution started.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC9", + "EventName": "RTM_RETIRED.START", + "PublicDescription": "Number of times we entered an RTM region. Does not count nested transactions.", + "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Counts all prefetch (that bring data to LLC only) RFOs that miss the L3 and the data is returned from local or remote dram.", + "BriefDescription": "Counts the number of times a class of instructions that may cause a transactional abort was executed. Since this is the count of execution, it may not always cause a transactional abort.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L3_RFO.L3_MISS.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x063FC00100", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC1", + "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Execution stalls while L3 cache miss demand load is outstanding.", + "BriefDescription": "Counts the number of times a class of instructions (e.g., vzeroupper) that may cause a transactional abort was executed inside a transactional region", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "6", - "EventCode": "0xA3", - "EventName": "CYCLE_ACTIVITY.STALLS_L3_MISS", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC2", + "PublicDescription": "Unfriendly TSX abort triggered by a vzeroupper instruction.", "SampleAfterValue": "2000003", - "UMask": "0x6" + "UMask": "0x2" }, { - "BriefDescription": "Number of times an HLE execution aborted due to unfriendly events (such as interrupts).", + "BriefDescription": "Counts the number of times an instruction execution caused the transactional nest count supported to be exceeded", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC8", - "EventName": "HLE_RETIRED.ABORTED_EVENTS", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC3", + "PublicDescription": "Unfriendly TSX abort triggered by a nest count that is too deep.", "SampleAfterValue": "2000003", - "UMask": "0x80" + "UMask": "0x4" }, { - "BriefDescription": "Counts all demand & prefetch RFOs that miss the L3 and the data is returned from local dram.", + "BriefDescription": "Counts the number of times a XBEGIN instruction was executed inside an HLE transactional region.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.ALL_RFO.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0604000122", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC4", + "PublicDescription": "RTM region detected inside HLE.", + "SampleAfterValue": "2000003", + "UMask": "0x8" }, { - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 4 cycles.", + "BriefDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "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", - "TakenAlone": "1", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x5d", + "EventName": "TX_EXEC.MISC5", + "PublicDescription": "Counts the number of times an HLE XACQUIRE instruction was executed inside an RTM transactional region.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 8 cycles.", + "BriefDescription": "Number of times a transactional abort was signaled due to a data capacity limitation for transactional reads or writes.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "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", - "TakenAlone": "1", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CAPACITY", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "BriefDescription": "Counts L1 data cache hardware prefetch requests and software prefetch requests that miss the L3 and the data is returned from local dram.", + "BriefDescription": "Number of times a transactional abort was signaled due to a data conflict on a transactionally accessed address", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xB7, 0xBB", - "EventName": "OFFCORE_RESPONSE.PF_L1D_AND_SW.L3_MISS_LOCAL_DRAM.SNOOP_MISS_OR_NO_FWD", - "MSRIndex": "0x1a6,0x1a7", - "MSRValue": "0x0604000400", - "Offcore": "1", - "PublicDescription": "Offcore response can be programmed only with a specific pair of event select and counter MSR, and with specific event codes and predefine mask bit value in a dedicated MSR to specify attributes of the offcore transaction.", - "SampleAfterValue": "100003", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_CONFLICT", + "PublicDescription": "Number of times a TSX line had a cache conflict.", + "SampleAfterValue": "2000003", "UMask": "0x1" + }, + { + "BriefDescription": "Number of times an HLE transactional execution aborted due to XRELEASE lock not satisfying the address and value requirements in the elision buffer", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_MISMATCH", + "PublicDescription": "Number of times a TSX Abort was triggered due to release/commit but data and address mismatch.", + "SampleAfterValue": "2000003", + "UMask": "0x10" + }, + { + "BriefDescription": "Number of times an HLE transactional execution aborted due to NoAllocatedElisionBuffer being non-zero.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_NOT_EMPTY", + "PublicDescription": "Number of times a TSX Abort was triggered due to commit but Lock Buffer not empty.", + "SampleAfterValue": "2000003", + "UMask": "0x8" + }, + { + "BriefDescription": "Number of times an HLE transactional execution aborted due to an unsupported read alignment from the elision buffer.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_ELISION_BUFFER_UNSUPPORTED_ALIGNMENT", + "PublicDescription": "Number of times a TSX Abort was triggered due to attempting an unsupported alignment from Lock Buffer.", + "SampleAfterValue": "2000003", + "UMask": "0x20" + }, + { + "BriefDescription": "Number of times a HLE transactional region aborted due to a non XRELEASE prefixed instruction writing to an elided lock in the elision buffer", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.ABORT_HLE_STORE_TO_ELIDED_LOCK", + "PublicDescription": "Number of times a TSX Abort was triggered due to a non-release/commit store to lock.", + "SampleAfterValue": "2000003", + "UMask": "0x4" + }, + { + "BriefDescription": "Number of times HLE lock could not be elided due to ElisionBufferAvailable being zero.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x54", + "EventName": "TX_MEM.HLE_ELISION_BUFFER_FULL", + "PublicDescription": "Number of times we could not allocate Lock Buffer.", + "SampleAfterValue": "2000003", + "UMask": "0x40" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json index f6b147ba8ef6..8b344259176f 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/other.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json @@ -1,34 +1,5 @@ [ { - "BriefDescription": "Core cycles the core was throttled due to a pending power level request.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x28", - "EventName": "CORE_POWER.THROTTLE", - "PublicDescription": "Core cycles the out-of-order engine was throttled due to a pending power level request.", - "SampleAfterValue": "200003", - "UMask": "0x40" - }, - { - "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xFE", - "EventName": "IDI_MISC.WB_DOWNGRADE", - "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", - "SampleAfterValue": "100003", - "UMask": "0x4" - }, - { - "BriefDescription": "Number of PREFETCHW instructions executed.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x32", - "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", - "SampleAfterValue": "2000003", - "UMask": "0x8" - }, - { "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the Non-AVX turbo schedule.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", @@ -49,13 +20,24 @@ "UMask": "0x18" }, { - "BriefDescription": "Number of PREFETCHT0 instructions executed.", + "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x32", - "EventName": "SW_PREFETCH_ACCESS.T0", - "SampleAfterValue": "2000003", - "UMask": "0x2" + "EventCode": "0x28", + "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", + "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture). This includes high current AVX 512-bit instructions.", + "SampleAfterValue": "200003", + "UMask": "0x20" + }, + { + "BriefDescription": "Core cycles the core was throttled due to a pending power level request.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x28", + "EventName": "CORE_POWER.THROTTLE", + "PublicDescription": "Core cycles the out-of-order engine was throttled due to a pending power level request.", + "SampleAfterValue": "200003", + "UMask": "0x40" }, { "BriefDescription": "Number of hardware interrupts received by the processor.", @@ -68,14 +50,32 @@ "UMask": "0x1" }, { - "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.", + "BriefDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x28", - "EventName": "CORE_POWER.LVL2_TURBO_LICENSE", - "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture). This includes high current AVX 512-bit instructions.", - "SampleAfterValue": "200003", - "UMask": "0x20" + "EventCode": "0xFE", + "EventName": "IDI_MISC.WB_DOWNGRADE", + "PublicDescription": "Counts number of cache lines that are dropped and not written back to L3 as they are deemed to be less likely to be reused shortly.", + "SampleAfterValue": "100003", + "UMask": "0x4" + }, + { + "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xFE", + "EventName": "IDI_MISC.WB_UPGRADE", + "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.", + "SampleAfterValue": "100003", + "UMask": "0x2" + }, + { + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x09", + "EventName": "MEMORY_DISAMBIGUATION.HISTORY_RESET", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { "BriefDescription": "Number of PREFETCHNTA instructions executed.", @@ -87,30 +87,30 @@ "UMask": "0x1" }, { - "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", + "BriefDescription": "Number of PREFETCHW instructions executed.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x32", - "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "EventName": "SW_PREFETCH_ACCESS.PREFETCHW", "SampleAfterValue": "2000003", - "UMask": "0x4" + "UMask": "0x8" }, { + "BriefDescription": "Number of PREFETCHT0 instructions executed.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x09", - "EventName": "MEMORY_DISAMBIGUATION.HISTORY_RESET", + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.T0", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0x2" }, { - "BriefDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly", + "BriefDescription": "Number of PREFETCHT1 or PREFETCHT2 instructions executed.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xFE", - "EventName": "IDI_MISC.WB_UPGRADE", - "PublicDescription": "Counts number of cache lines that are allocated and written back to L3 with the intention that they are more likely to be reused shortly.", - "SampleAfterValue": "100003", - "UMask": "0x2" + "EventCode": "0x32", + "EventName": "SW_PREFETCH_ACCESS.T1_T2", + "SampleAfterValue": "2000003", + "UMask": "0x4" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json index 3bfc6943ddf9..ca5748120666 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json @@ -1,55 +1,58 @@ [ { - "BriefDescription": "Number of instructions retired. General Counter - architectural event", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "Errata": "SKL091, SKL044", - "EventCode": "0xC0", - "EventName": "INST_RETIRED.ANY_P", - "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", - "SampleAfterValue": "2000003" - }, - { - "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", + "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.STALL_CYCLES", - "Invert": "1", - "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "EventCode": "0x14", + "EventName": "ARITH.DIVIDER_ACTIVE", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", + "BriefDescription": "All (macro) branch instructions retired.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "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" + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES", + "PublicDescription": "Counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009" }, { - "BriefDescription": "Cycles when divide unit is busy executing divide or square root operations. Accounts for integer and floating-point operations.", + "BriefDescription": "All (macro) branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x4" + }, + { + "BriefDescription": "Conditional branch instructions retired.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x14", - "EventName": "ARITH.DIVIDER_ACTIVE", - "SampleAfterValue": "2000003", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.CONDITIONAL", + "PEBS": "1", + "PublicDescription": "This event counts conditional branch instructions retired.", + "SampleAfterValue": "400009", "UMask": "0x1" }, { - "BriefDescription": "False dependencies in MOB due to partial compare on address.", + "BriefDescription": "Not taken branch instructions retired.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x07", - "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", - "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.", - "SampleAfterValue": "100003", - "UMask": "0x1" + "Errata": "SKL091", + "EventCode": "0xc4", + "EventName": "BR_INST_RETIRED.COND_NTAKEN", + "PublicDescription": "This event counts not taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x10" }, { "BriefDescription": "Far branch instructions retired.", @@ -64,23 +67,81 @@ "UMask": "0x40" }, { - "BriefDescription": "Counts the number of x87 uops dispatched.", + "BriefDescription": "Direct and indirect near call instructions retired.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.X87", - "PublicDescription": "Counts the number of x87 uops executed.", - "SampleAfterValue": "2000003", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_CALL", + "PEBS": "1", + "PublicDescription": "This event counts both direct and indirect near call instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x2" + }, + { + "BriefDescription": "Return instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_RETURN", + "PEBS": "1", + "PublicDescription": "This event counts return instructions retired.", + "SampleAfterValue": "100007", + "UMask": "0x8" + }, + { + "BriefDescription": "Taken branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "PublicDescription": "This event counts taken branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x20" + }, + { + "BriefDescription": "Not taken branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091", + "EventCode": "0xC4", + "EventName": "BR_INST_RETIRED.NOT_TAKEN", + "PublicDescription": "This event counts not taken branch instructions retired.", + "SampleAfterValue": "400009", "UMask": "0x10" }, { - "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", + "BriefDescription": "All mispredicted macro branch instructions retired.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x4C", - "EventName": "LOAD_HIT_PRE.SW_PF", - "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", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", + "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 macro branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", + "PEBS": "2", + "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", + "SampleAfterValue": "400009", + "UMask": "0x4" + }, + { + "BriefDescription": "Mispredicted conditional branch instructions retired.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.CONDITIONAL", + "PEBS": "1", + "PublicDescription": "This event counts mispredicted conditional branch instructions retired.", + "SampleAfterValue": "400009", "UMask": "0x1" }, { @@ -95,85 +156,99 @@ "UMask": "0x2" }, { - "BriefDescription": "Total execution stalls.", + "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "4", - "EventCode": "0xA3", - "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", - "SampleAfterValue": "2000003", - "UMask": "0x4" + "EventCode": "0xC5", + "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", + "PEBS": "1", + "SampleAfterValue": "400009", + "UMask": "0x20" }, { - "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "5", - "EventCode": "0xA3", - "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", - "SampleAfterValue": "2000003", - "UMask": "0x5" + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "UMask": "0x2" }, { - "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x0E", - "EventName": "UOPS_ISSUED.SLOW_LEA", - "SampleAfterValue": "2000003", - "UMask": "0x20" + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "BriefDescription": "Cycles with less than 10 actually retired uops.", + "AnyThread": "1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "10", - "EventCode": "0xC2", - "EventName": "UOPS_RETIRED.TOTAL_CYCLES", - "Invert": "1", - "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", - "SampleAfterValue": "2000003", - "UMask": "0x2" + "EventCode": "0x3C", + "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", + "SampleAfterValue": "25003", + "UMask": "0x1" }, { - "BriefDescription": "Thread cycles when thread is not in halt state", + "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "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" + "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", + "SampleAfterValue": "25003", + "UMask": "0x2" }, { - "BriefDescription": "Cycles where at least 2 uops were executed per-thread", + "BriefDescription": "Reference cycles when the core is not in halt state.", + "Counter": "Fixed counter 2", + "CounterHTOff": "Fixed counter 2", + "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. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. 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": "0x3" + }, + { + "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "2", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", - "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", - "SampleAfterValue": "2000003", + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK", + "SampleAfterValue": "25003", "UMask": "0x1" }, { - "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "AnyThread": "1", + "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x3C", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK", + "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", "SampleAfterValue": "25003", "UMask": "0x1" }, { - "BriefDescription": "Number of machine clears (nukes) of any type.", + "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", "EdgeDetect": "1", - "EventCode": "0xC3", - "EventName": "MACHINE_CLEARS.COUNT", - "SampleAfterValue": "100003", - "UMask": "0x1" + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", + "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", + "SampleAfterValue": "100007" + }, + { + "BriefDescription": "Core cycles when the thread is not in halt state", + "Counter": "Fixed counter 1", + "CounterHTOff": "Fixed counter 1", + "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 four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { "AnyThread": "1", @@ -185,177 +260,182 @@ "UMask": "0x2" }, { - "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", + "BriefDescription": "Thread cycles when thread is not in halt state", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.THREAD", - "PublicDescription": "Number of uops to be executed per-thread each cycle.", - "SampleAfterValue": "2000003", - "UMask": "0x1" + "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 where at least 3 uops were executed per-thread", + "AnyThread": "1", + "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "3", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", - "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", - "SampleAfterValue": "2000003", - "UMask": "0x1" + "EventCode": "0x3C", + "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", + "SampleAfterValue": "2000003" }, { - "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", + "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", - "Invert": "1", + "CounterMask": "8", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", "SampleAfterValue": "2000003", - "UMask": "0x2" + "UMask": "0x8" }, { - "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", + "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA6", - "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", + "CounterMask": "1", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", "SampleAfterValue": "2000003", - "UMask": "0x40" + "UMask": "0x1" }, { - "BriefDescription": "Cycles while L1 cache miss demand load is outstanding.", + "BriefDescription": "Cycles while memory subsystem has an outstanding load.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "8", + "CounterMask": "16", "EventCode": "0xA3", - "EventName": "CYCLE_ACTIVITY.CYCLES_L1D_MISS", + "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", "SampleAfterValue": "2000003", - "UMask": "0x8" + "UMask": "0x10" }, { - "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", + "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "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).", + "CounterMask": "12", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0xc" }, { - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", + "BriefDescription": "Execution stalls while L2 cache miss demand load is outstanding.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x0D", - "EventName": "INT_MISC.RECOVERY_CYCLES", - "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", + "CounterMask": "5", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_L2_MISS", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0x5" }, { - "BriefDescription": "Core crystal clock cycles when the thread is unhalted.", + "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x3C", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK", - "SampleAfterValue": "25003", - "UMask": "0x1" + "CounterHTOff": "0,1,2,3", + "CounterMask": "20", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", + "SampleAfterValue": "2000003", + "UMask": "0x14" }, { - "BriefDescription": "Cycles per thread when uops are executed in port 0", + "BriefDescription": "Total execution stalls.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_0", - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", + "CounterMask": "4", + "EventCode": "0xA3", + "EventName": "CYCLE_ACTIVITY.STALLS_TOTAL", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0x4" }, { - "BriefDescription": "Cycles per thread when uops are executed in port 1", + "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_1", - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", + "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 per thread when uops are executed in port 2", + "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_2", - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.", + "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 per thread when uops are executed in port 3", + "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_3", - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.", + "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 per thread when uops are executed in port 4", + "BriefDescription": "Cycles total of 4 uops are executed on all ports and Reservation Station was not empty.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_4", - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.", + "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": "Cycles per thread when uops are executed in port 5", + "BriefDescription": "Cycles where the Store Buffer was full and no outstanding load.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_5", - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.BOUND_ON_STORES", "SampleAfterValue": "2000003", - "UMask": "0x20" + "UMask": "0x40" }, { - "BriefDescription": "Cycles per thread when uops are executed in port 6", + "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_6", - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", + "EventCode": "0xA6", + "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", + "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", "SampleAfterValue": "2000003", - "UMask": "0x40" + "UMask": "0x1" }, { - "BriefDescription": "Cycles per thread when uops are executed in port 7", + "BriefDescription": "Stalls caused by changing prefix length of the instruction.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA1", - "EventName": "UOPS_DISPATCHED_PORT.PORT_7", - "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.", + "EventCode": "0x87", + "EventName": "ILD_STALL.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": "2000003", - "UMask": "0x80" + "UMask": "0x1" }, { - "AnyThread": "1", - "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x0D", - "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", + "BriefDescription": "Instructions retired from execution.", + "Counter": "Fixed counter 0", + "CounterHTOff": "Fixed counter 0", + "EventName": "INST_RETIRED.ANY", + "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", "SampleAfterValue": "2000003", "UMask": "0x1" }, { + "BriefDescription": "Number of instructions retired. General Counter - architectural event", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.ANY_P", + "PublicDescription": "Counts the number of instructions (EOMs) retired. Counting covers macro-fused instructions individually (that is, increments by two).", + "SampleAfterValue": "2000003" + }, + { "BriefDescription": "Precise instruction retired event with HW to reduce effect of PEBS shadow in IP distribution", "Counter": "1", "CounterHTOff": "1", @@ -368,24 +448,56 @@ "UMask": "0x1" }, { - "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", + "BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.", + "Counter": "0,2,3", + "CounterHTOff": "0,2,3", + "CounterMask": "10", + "Errata": "SKL091, SKL044", + "EventCode": "0xC0", + "EventName": "INST_RETIRED.TOTAL_CYCLES_PS", + "Invert": "1", + "PEBS": "2", + "PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)", + "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "4", - "EventCode": "0xA8", - "EventName": "LSD.CYCLES_4_UOPS", - "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", + "EventCode": "0x0D", + "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "SampleAfterValue": "2000003", + "UMask": "0x80" + }, + { + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for this thread (e.g. misprediction or memory nuke)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES", + "PublicDescription": "Core cycles the Resource allocator was stalled due to recovery from an earlier branch misprediction or machine clear event.", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Cycles total of 3 uops are executed on all ports and Reservation Station was not empty.", + "AnyThread": "1", + "BriefDescription": "Core cycles the allocator was stalled due to recovery from earlier clear event for any thread running on the physical core (e.g. misprediction or memory nuke).", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "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.", + "EventCode": "0x0D", + "EventName": "INT_MISC.RECOVERY_CYCLES_ANY", "SampleAfterValue": "2000003", + "UMask": "0x1" + }, + { + "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x03", + "EventName": "LD_BLOCKS.NO_SR", + "PublicDescription": "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": "0x8" }, { @@ -399,108 +511,77 @@ "UMask": "0x2" }, { - "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "BriefDescription": "False dependencies in MOB due to partial compare on address.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EdgeDetect": "1", - "EventCode": "0x5E", - "EventName": "RS_EVENTS.EMPTY_END", - "Invert": "1", - "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.", - "SampleAfterValue": "2000003", + "EventCode": "0x07", + "EventName": "LD_BLOCKS_PARTIAL.ADDRESS_ALIAS", + "PublicDescription": "Counts false dependencies in MOB when the partial comparison upon loose net check and dependency was resolved by the Enhanced Loose net mechanism. This may not result in high performance penalties. Loose net checks can fail when loads and stores are 4k aliased.", + "SampleAfterValue": "100003", "UMask": "0x1" }, { - "AnyThread": "1", - "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", + "BriefDescription": "Demand load dispatches that hit L1D fill buffer (FB) allocated for software prefetch.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x3C", - "EventName": "CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "25003", + "EventCode": "0x4C", + "EventName": "LOAD_HIT_PRE.SW_PF", + "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 where the pipeline is stalled due to serializing operations.", + "BriefDescription": "Cycles 4 Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x59", - "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", - "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", + "CounterMask": "4", + "EventCode": "0xA8", + "EventName": "LSD.CYCLES_4_UOPS", + "PublicDescription": "Counts the cycles when 4 uops are delivered by the LSD (Loop-stream detector).", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", + "BriefDescription": "Cycles Uops delivered by the LSD, but didn't come from the decoder.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "EventCode": "0x0E", - "EventName": "UOPS_ISSUED.STALL_CYCLES", - "Invert": "1", - "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", + "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": "Not taken branch instructions retired.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "Errata": "SKL091", - "EventCode": "0xc4", - "EventName": "BR_INST_RETIRED.COND_NTAKEN", - "PublicDescription": "This event counts not taken branch instructions retired.", - "SampleAfterValue": "400009", - "UMask": "0x10" - }, - { - "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", + "BriefDescription": "Number of Uops delivered by the LSD.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "3", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "EventCode": "0xA8", + "EventName": "LSD.UOPS", + "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).", "SampleAfterValue": "2000003", - "UMask": "0x2" + "UMask": "0x1" }, { - "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "BriefDescription": "Number of machine clears (nukes) of any type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "4", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Reference cycles when the core is not in halt state.", - "Counter": "Fixed counter 2", - "CounterHTOff": "Fixed counter 2", - "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. This event has a constant ratio with the CPU_CLK_UNHALTED.REF_XCLK event. 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": "0x3" + "EdgeDetect": "1", + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.COUNT", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "BriefDescription": "All mispredicted macro branch instructions retired.", + "BriefDescription": "Self-modifying code (SMC) detected.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC5", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES", - "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" + "EventCode": "0xC3", + "EventName": "MACHINE_CLEARS.SMC", + "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", + "SampleAfterValue": "100003", + "UMask": "0x4" }, { "BriefDescription": "Number of times a microcode assist is invoked by HW other than FP-assist. Examples include AD (page Access Dirty) and AVX* related assists.", @@ -512,448 +593,377 @@ "UMask": "0x3f" }, { - "BriefDescription": "Cycles without actually retired uops.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0xC2", - "EventName": "UOPS_RETIRED.STALL_CYCLES", - "Invert": "1", - "PublicDescription": "This event counts cycles without actually retired uops.", - "SampleAfterValue": "2000003", - "UMask": "0x2" - }, - { - "BriefDescription": "Number of Uops delivered by the LSD.", + "BriefDescription": "Cycles where the pipeline is stalled due to serializing operations.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA8", - "EventName": "LSD.UOPS", - "PublicDescription": "Number of uops delivered to the back-end by the LSD(Loop Stream Detector).", + "EventCode": "0x59", + "EventName": "PARTIAL_RAT_STALLS.SCOREBOARD", + "PublicDescription": "This event counts cycles during which the microcode scoreboard stalls happen.", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x3C", - "EventName": "CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE", - "SampleAfterValue": "25003", - "UMask": "0x2" - }, - { - "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "BriefDescription": "Resource-related stall cycles", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x87", - "EventName": "ILD_STALL.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.", + "EventCode": "0xa2", + "EventName": "RESOURCE_STALLS.ANY", + "PublicDescription": "Counts resource-related stall cycles.", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Cycles while memory subsystem has an outstanding load.", + "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "16", - "EventCode": "0xA3", - "EventName": "CYCLE_ACTIVITY.CYCLES_MEM_ANY", + "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": "2000003", - "UMask": "0x10" + "UMask": "0x8" }, { - "BriefDescription": "Taken branch instructions retired.", + "BriefDescription": "Increments whenever there is an update to the LBR array.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "Errata": "SKL091", - "EventCode": "0xC4", - "EventName": "BR_INST_RETIRED.NEAR_TAKEN", - "PEBS": "1", - "PublicDescription": "This event counts taken branch instructions retired.", - "SampleAfterValue": "400009", + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.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": "2000003", "UMask": "0x20" }, { - "BriefDescription": "The number of times that split load operations are temporarily blocked because all resources for handling the split accesses are in use", + "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x03", - "EventName": "LD_BLOCKS.NO_SR", - "PublicDescription": "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": "0x8" + "EventCode": "0xCC", + "EventName": "ROB_MISC_EVENTS.PAUSE_INST", + "SampleAfterValue": "2000003", + "UMask": "0x40" }, { - "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", + "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x0E", - "EventName": "UOPS_ISSUED.ANY", - "PublicDescription": "Counts the number of uops that the Resource Allocation Table (RAT) issues to the Reservation Station (RS).", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_CYCLES", + "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Core cycles when the thread is not in halt state", - "Counter": "Fixed counter 1", - "CounterHTOff": "Fixed counter 1", - "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 four (eight when Hyperthreading is disabled) programmable counters available for other events.", + "BriefDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate Frontend Latency Bound issues.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EdgeDetect": "1", + "EventCode": "0x5E", + "EventName": "RS_EVENTS.EMPTY_END", + "Invert": "1", + "PublicDescription": "Counts end of periods where the Reservation Station (RS) was empty. Could be useful to precisely locate front-end Latency Bound issues.", "SampleAfterValue": "2000003", - "UMask": "0x2" + "UMask": "0x1" }, { - "AnyThread": "1", - "BriefDescription": "Core crystal clock cycles when at least one thread on the physical core is unhalted.", + "BriefDescription": "Cycles per thread when uops are executed in port 0", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x3C", - "EventName": "CPU_CLK_UNHALTED.REF_XCLK_ANY", - "SampleAfterValue": "25003", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_0", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 0.", + "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Direct and indirect near call instructions retired.", + "BriefDescription": "Cycles per thread when uops are executed in port 1", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "Errata": "SKL091", - "EventCode": "0xC4", - "EventName": "BR_INST_RETIRED.NEAR_CALL", - "PEBS": "1", - "PublicDescription": "This event counts both direct and indirect near call instructions retired.", - "SampleAfterValue": "100007", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_1", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 1.", + "SampleAfterValue": "2000003", "UMask": "0x2" }, { - "BriefDescription": "Number of retired PAUSE instructions (that do not end up with a VMExit to the VMM; TSX aborted Instructions may be counted). This event is not supported on first SKL and KBL products.", + "BriefDescription": "Cycles per thread when uops are executed in port 2", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xCC", - "EventName": "ROB_MISC_EVENTS.PAUSE_INST", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_2", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 2.", "SampleAfterValue": "2000003", - "UMask": "0x40" + "UMask": "0x4" }, { - "BriefDescription": "Resource-related stall cycles", + "BriefDescription": "Cycles per thread when uops are executed in port 3", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xa2", - "EventName": "RESOURCE_STALLS.ANY", - "PublicDescription": "Counts resource-related stall cycles.", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_3", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 3.", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0x8" }, { - "BriefDescription": "Self-modifying code (SMC) detected.", + "BriefDescription": "Cycles per thread when uops are executed in port 4", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC3", - "EventName": "MACHINE_CLEARS.SMC", - "PublicDescription": "Counts self-modifying code (SMC) detected, which causes a machine clear.", - "SampleAfterValue": "100003", - "UMask": "0x4" + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_4", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 4.", + "SampleAfterValue": "2000003", + "UMask": "0x10" }, { - "BriefDescription": "Core crystal clock cycles when this thread is unhalted and the other thread is halted.", + "BriefDescription": "Cycles per thread when uops are executed in port 5", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x3C", - "EventName": "CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE", - "SampleAfterValue": "25003", - "UMask": "0x2" + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_5", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 5.", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "BriefDescription": "Cycles where at least 4 uops were executed per-thread", + "BriefDescription": "Cycles per thread when uops are executed in port 6", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "4", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", - "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_6", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 6.", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0x40" }, { - "BriefDescription": "Number of near branch instructions retired that were mispredicted and taken.", + "BriefDescription": "Cycles per thread when uops are executed in port 7", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC5", - "EventName": "BR_MISP_RETIRED.NEAR_TAKEN", - "PEBS": "1", - "SampleAfterValue": "400009", - "UMask": "0x20" - }, - { - "BriefDescription": "Execution stalls while memory subsystem has an outstanding load.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "CounterMask": "20", - "EventCode": "0xA3", - "EventName": "CYCLE_ACTIVITY.STALLS_MEM_ANY", + "EventCode": "0xA1", + "EventName": "UOPS_DISPATCHED_PORT.PORT_7", + "PublicDescription": "Counts, on the per-thread basis, cycles during which at least one uop is dispatched from the Reservation Station (RS) to port 7.", "SampleAfterValue": "2000003", - "UMask": "0x14" + "UMask": "0x80" }, { - "BriefDescription": "Cycles where no uops were executed, the Reservation Station was not empty, the Store Buffer was full and there was no outstanding load.", + "BriefDescription": "Number of uops executed on the core.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xA6", - "EventName": "EXE_ACTIVITY.EXE_BOUND_0_PORTS", - "PublicDescription": "Counts cycles during which no uops were executed on all ports and Reservation Station (RS) was not empty.", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE", + "PublicDescription": "Number of uops executed from any thread.", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0x2" }, { - "BriefDescription": "Number of cycles using always true condition applied to PEBS instructions retired event.", - "Counter": "0,2,3", - "CounterHTOff": "0,2,3", - "CounterMask": "10", - "Errata": "SKL091, SKL044", - "EventCode": "0xC0", - "EventName": "INST_RETIRED.TOTAL_CYCLES_PS", - "Invert": "1", - "PEBS": "2", - "PublicDescription": "Number of cycles using an always true condition applied to PEBS instructions retired event. (inst_ret< 16)", + "BriefDescription": "Cycles at least 1 micro-op is executed from any thread on physical core.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_1", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0x2" }, { - "BriefDescription": "Retirement slots used.", + "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC2", - "EventName": "UOPS_RETIRED.RETIRE_SLOTS", - "PublicDescription": "Counts the retirement slots used.", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", "SampleAfterValue": "2000003", "UMask": "0x2" }, { - "AnyThread": "1", - "BriefDescription": "Core cycles when at least one thread on the physical core is not in halt state.", + "BriefDescription": "Cycles at least 3 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x3C", - "EventName": "CPU_CLK_UNHALTED.THREAD_P_ANY", - "SampleAfterValue": "2000003" + "CounterMask": "3", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_3", + "SampleAfterValue": "2000003", + "UMask": "0x2" }, { - "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", + "BriefDescription": "Cycles at least 4 micro-op is executed from any thread on physical core.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x0E", - "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", - "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_4", "SampleAfterValue": "2000003", "UMask": "0x2" }, { - "BriefDescription": "Increments whenever there is an update to the LBR array.", + "BriefDescription": "Cycles with no micro-ops executed from any thread on physical core.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xCC", - "EventName": "ROB_MISC_EVENTS.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.", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CORE_CYCLES_NONE", + "Invert": "1", "SampleAfterValue": "2000003", - "UMask": "0x20" + "UMask": "0x2" }, { - "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread", + "BriefDescription": "Cycles where at least 1 uop was executed per-thread", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x5E", - "EventName": "RS_EVENTS.EMPTY_CYCLES", - "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for the thread.; Note: In ST-mode, not active thread should drive 0. This is usually caused by severely costly branch mispredictions, or allocator/FE issues.", + "CounterMask": "1", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Return instructions retired.", + "BriefDescription": "Cycles where at least 2 uops were executed per-thread", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "Errata": "SKL091", - "EventCode": "0xC4", - "EventName": "BR_INST_RETIRED.NEAR_RETURN", - "PEBS": "1", - "PublicDescription": "This event counts return instructions retired.", - "SampleAfterValue": "100007", - "UMask": "0x8" - }, - { - "BriefDescription": "Instructions retired from execution.", - "Counter": "Fixed counter 0", - "CounterHTOff": "Fixed counter 0", - "EventName": "INST_RETIRED.ANY", - "PublicDescription": "Counts the number of instructions retired from execution. For instructions that consist of multiple micro-ops, Counts the retirement of the last micro-op of the instruction. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter, leaving the four (eight when Hyperthreading is disabled) programmable counters available for other events. INST_RETIRED.ANY_P is counted by a programmable counter and it is an architectural performance event. Counting: Faulting executions of GETSEC/VM entry/VM Exit/MWait will not count as retired instructions.", + "CounterMask": "2", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_2_UOPS_EXEC", + "PublicDescription": "Cycles where at least 2 uops were executed per-thread.", "SampleAfterValue": "2000003", "UMask": "0x1" }, { - "BriefDescription": "Cycles at least 2 micro-op is executed from any thread on physical core.", + "BriefDescription": "Cycles where at least 3 uops were executed per-thread", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "2", + "CounterMask": "3", "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.CORE_CYCLES_GE_2", + "EventName": "UOPS_EXECUTED.CYCLES_GE_3_UOPS_EXEC", + "PublicDescription": "Cycles where at least 3 uops were executed per-thread.", "SampleAfterValue": "2000003", - "UMask": "0x2" + "UMask": "0x1" }, { - "BriefDescription": "Cycles stalled due to no store buffers available. (not including draining form sync).", + "BriefDescription": "Cycles where at least 4 uops were executed per-thread", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "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.", + "CounterMask": "4", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.CYCLES_GE_4_UOPS_EXEC", + "PublicDescription": "Cycles where at least 4 uops were executed per-thread.", "SampleAfterValue": "2000003", - "UMask": "0x8" + "UMask": "0x1" }, { - "BriefDescription": "Counts when there is a transition from ring 1, 2 or 3 to ring 0.", + "BriefDescription": "Counts number of cycles no uops were dispatched to be executed on this thread.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "EdgeDetect": "1", - "EventCode": "0x3C", - "EventName": "CPU_CLK_UNHALTED.RING0_TRANS", - "PublicDescription": "Counts when the Current Privilege Level (CPL) transitions from ring 1, 2 or 3 to ring 0 (Kernel).", - "SampleAfterValue": "100007" - }, - { - "BriefDescription": "All (macro) branch instructions retired.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "Errata": "SKL091", - "EventCode": "0xC4", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES_PEBS", - "PEBS": "2", - "PublicDescription": "This is a precise version of BR_INST_RETIRED.ALL_BRANCHES that counts all (macro) branch instructions retired.", - "SampleAfterValue": "400009", - "UMask": "0x4" - }, - { - "BriefDescription": "Mispredicted macro branch instructions retired.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3", - "EventCode": "0xC5", - "EventName": "BR_MISP_RETIRED.ALL_BRANCHES_PEBS", - "PEBS": "2", - "PublicDescription": "This is a precise version of BR_MISP_RETIRED.ALL_BRANCHES that counts all mispredicted macro branch instructions retired.", - "SampleAfterValue": "400009", - "UMask": "0x4" + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which no uops were dispatched from the Reservation Station (RS) per thread.", + "SampleAfterValue": "2000003", + "UMask": "0x1" }, { - "BriefDescription": "Cycles total of 1 uop is executed on all ports and Reservation Station was not empty.", + "BriefDescription": "Counts the number of uops to be executed per-thread each cycle.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "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.", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.THREAD", + "PublicDescription": "Number of uops to be executed per-thread each cycle.", "SampleAfterValue": "2000003", - "UMask": "0x2" + "UMask": "0x1" }, { - "BriefDescription": "Not taken branch instructions retired.", + "BriefDescription": "Counts the number of x87 uops dispatched.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "Errata": "SKL091", - "EventCode": "0xC4", - "EventName": "BR_INST_RETIRED.NOT_TAKEN", - "PublicDescription": "This event counts not taken branch instructions retired.", - "SampleAfterValue": "400009", + "EventCode": "0xB1", + "EventName": "UOPS_EXECUTED.X87", + "PublicDescription": "Counts the number of x87 uops executed.", + "SampleAfterValue": "2000003", "UMask": "0x10" }, { - "BriefDescription": "Conditional branch instructions retired.", + "BriefDescription": "Uops that Resource Allocation Table (RAT) issues to Reservation Station (RS)", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "Errata": "SKL091", - "EventCode": "0xC4", - "EventName": "BR_INST_RETIRED.CONDITIONAL", - "PEBS": "1", - "PublicDescription": "This event counts conditional branch instructions retired.", - "SampleAfterValue": "400009", + "EventCode": "0x0E", + "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": "Mispredicted conditional branch instructions retired.", + "BriefDescription": "Number of slow LEA uops being allocated. A uop is generally considered SlowLea if it has 3 sources (e.g. 2 sources + immediate) regardless if as a result of LEA instruction or not.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xC5", - "EventName": "BR_MISP_RETIRED.CONDITIONAL", - "PEBS": "1", - "PublicDescription": "This event counts mispredicted conditional branch instructions retired.", - "SampleAfterValue": "400009", - "UMask": "0x1" + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.SLOW_LEA", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "BriefDescription": "Number of uops executed on the core.", + "BriefDescription": "Cycles when Resource Allocation Table (RAT) does not issue Uops to Reservation Station (RS) for the thread", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.CORE", - "PublicDescription": "Number of uops executed from any thread.", + "CounterMask": "1", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "Counts cycles during which the Resource Allocation Table (RAT) does not issue any Uops to the reservation station (RS) for the current thread.", "SampleAfterValue": "2000003", - "UMask": "0x2" + "UMask": "0x1" }, { - "BriefDescription": "Execution stalls while L1 cache miss demand load is outstanding.", + "BriefDescription": "Uops inserted at issue-stage in order to preserve upper bits of vector registers.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "12", - "EventCode": "0xA3", - "EventName": "CYCLE_ACTIVITY.STALLS_L1D_MISS", + "EventCode": "0x0E", + "EventName": "UOPS_ISSUED.VECTOR_WIDTH_MISMATCH", + "PublicDescription": "Counts the number of Blend Uops issued by the Resource Allocation Table (RAT) to the reservation station (RS) in order to preserve upper bits of vector registers. Starting with the Skylake microarchitecture, these Blend uops are needed since every Intel SSE instruction executed in Dirty Upper State needs to preserve bits 128-255 of the destination register. For more information, refer to Mixing Intel AVX and Intel SSE Code section of the Optimization Guide.", "SampleAfterValue": "2000003", - "UMask": "0xc" + "UMask": "0x2" }, { - "BriefDescription": "Cycles total of 2 uops are executed on all ports and Reservation Station was not empty.", + "BriefDescription": "Number of macro-fused uops retired. (non precise)", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "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.", + "EventCode": "0xc2", + "EventName": "UOPS_RETIRED.MACRO_FUSED", + "PublicDescription": "Counts the number of macro-fused uops retired. (non precise)", "SampleAfterValue": "2000003", "UMask": "0x4" }, { - "BriefDescription": "Cycles the issue-stage is waiting for front-end to fetch from resteered path following branch misprediction or machine clear events.", + "BriefDescription": "Retirement slots used.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x0D", - "EventName": "INT_MISC.CLEAR_RESTEER_CYCLES", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.RETIRE_SLOTS", + "PublicDescription": "Counts the retirement slots used.", "SampleAfterValue": "2000003", - "UMask": "0x80" - }, - { - "BriefDescription": "All (macro) branch instructions retired.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "Errata": "SKL091", - "EventCode": "0xC4", - "EventName": "BR_INST_RETIRED.ALL_BRANCHES", - "PublicDescription": "Counts all (macro) branch instructions retired.", - "SampleAfterValue": "400009" + "UMask": "0x2" }, { - "BriefDescription": "Cycles where at least 1 uop was executed per-thread", + "BriefDescription": "Cycles without actually retired uops.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "CounterMask": "1", - "EventCode": "0xB1", - "EventName": "UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", - "PublicDescription": "Cycles where at least 1 uop was executed per-thread.", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.STALL_CYCLES", + "Invert": "1", + "PublicDescription": "This event counts cycles without actually retired uops.", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0x2" }, { - "BriefDescription": "Cycles while L2 cache miss demand load is outstanding.", + "BriefDescription": "Cycles with less than 10 actually retired uops.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0xA3", - "EventName": "CYCLE_ACTIVITY.CYCLES_L2_MISS", + "CounterMask": "10", + "EventCode": "0xC2", + "EventName": "UOPS_RETIRED.TOTAL_CYCLES", + "Invert": "1", + "PublicDescription": "Number of cycles using always true condition (uops_ret < 16) applied to non PEBS uops retired event.", "SampleAfterValue": "2000003", - "UMask": "0x1" + "UMask": "0x2" } ]
\ No newline at end of file diff --git a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json index bbeee1058096..792ca39f013a 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json @@ -1,103 +1,74 @@ [ { - "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x85", - "EventName": "ITLB_MISSES.STLB_HIT", - "SampleAfterValue": "100003", - "UMask": "0x20" - }, - { - "BriefDescription": "Store misses in all DTLB levels that cause page walks", + "BriefDescription": "Load misses in all DTLB levels that cause page walks", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x49", - "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", - "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", "SampleAfterValue": "100003", "UMask": "0x1" }, { - "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page", + "BriefDescription": "Loads that miss the DTLB and hit the STLB.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x49", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", - "SampleAfterValue": "100003", - "UMask": "0x4" + "EventCode": "0x08", + "EventName": "DTLB_LOAD_MISSES.STLB_HIT", + "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "SampleAfterValue": "2000003", + "UMask": "0x20" }, { - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x85", - "EventName": "ITLB_MISSES.WALK_PENDING", - "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", + "CounterMask": "1", + "EventCode": "0x08", + "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 load.", "SampleAfterValue": "100003", "UMask": "0x10" }, { - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x85", - "EventName": "ITLB_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts completed page walks (4K page size) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", - "SampleAfterValue": "100003", - "UMask": "0x2" - }, - { - "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xAE", - "EventName": "ITLB.ITLB_FLUSH", - "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", - "SampleAfterValue": "100007", - "UMask": "0x1" - }, - { - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", + "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x85", - "EventName": "ITLB_MISSES.WALK_ACTIVE", - "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", + "EventCode": "0x08", + "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": "0x10" + "UMask": "0xe" }, { - "BriefDescription": "Loads that miss the DTLB and hit the STLB.", + "BriefDescription": "Page walk completed due to a demand data load to a 1G page", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x08", - "EventName": "DTLB_LOAD_MISSES.STLB_HIT", - "PublicDescription": "Counts loads that miss the DTLB (Data TLB) and hit the STLB (Second level TLB).", + "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": "2000003", - "UMask": "0x20" + "UMask": "0x8" }, { - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", + "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x49", - "EventName": "DTLB_STORE_MISSES.WALK_PENDING", - "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.", + "EventCode": "0x08", + "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": "2000003", - "UMask": "0x10" + "UMask": "0x4" }, { - "BriefDescription": "DTLB flush attempts of the thread-specific entries", + "BriefDescription": "Page walk completed due to a demand data load to a 4K page", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xBD", - "EventName": "TLB_FLUSH.DTLB_THREAD", - "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", - "SampleAfterValue": "100007", - "UMask": "0x1" + "EventCode": "0x08", + "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": "2000003", + "UMask": "0x2" }, { "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", @@ -110,23 +81,12 @@ "UMask": "0x10" }, { - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", + "BriefDescription": "Store misses in all DTLB levels that cause page walks", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", "EventCode": "0x49", - "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": "Misses at all ITLB levels that cause page walks", - "Counter": "0,1,2,3", - "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x85", - "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", - "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", + "EventName": "DTLB_STORE_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts demand data stores that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", "SampleAfterValue": "100003", "UMask": "0x1" }, @@ -141,125 +101,135 @@ "UMask": "0x20" }, { - "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", + "CounterMask": "1", "EventCode": "0x49", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts demand data stores that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "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": "0xe" + "UMask": "0x10" }, { - "BriefDescription": "Load miss in all TLB levels causes a page walk that completes. (All page sizes)", + "BriefDescription": "Store misses in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x08", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts demand data loads that caused a completed page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels. The page walk can end with or without a fault.", + "EventCode": "0x49", + "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 walk completed due to a demand data store to a 4K page", + "BriefDescription": "Page walk completed due to a demand data store to a 1G page", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x49", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "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": "0x2" + "UMask": "0x8" }, { - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)", + "BriefDescription": "Page walk completed due to a demand data store to a 2M/4M page", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x85", - "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts store misses in all DTLB levels that cause a completed page walk (1G page size). The page walk can end with or without a fault.", + "EventCode": "0x49", + "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": "0x8" + "UMask": "0x4" }, { - "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", + "BriefDescription": "Page walk completed due to a demand data store to a 4K page", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x85", - "EventName": "ITLB_MISSES.WALK_COMPLETED", - "PublicDescription": "Counts completed page walks (2M and 4M page sizes) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB. The page walk can end with or without a fault.", + "EventCode": "0x49", + "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": "0xe" + "UMask": "0x2" }, { - "BriefDescription": "Page walk completed due to a demand data load to a 4K page", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x08", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_4K", - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", + "EventCode": "0x49", + "EventName": "DTLB_STORE_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for a store. EPT page walk duration are excluded in Skylake microarchitecture.", "SampleAfterValue": "2000003", - "UMask": "0x2" + "UMask": "0x10" }, { - "BriefDescription": "Page walk completed due to a demand data load to a 2M/4M page", + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x08", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 2M/4M pages. The page walks can end with or without a page fault.", + "EventCode": "0x4f", + "EventName": "EPT.WALK_PENDING", + "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", "SampleAfterValue": "2000003", - "UMask": "0x4" + "UMask": "0x10" }, { - "BriefDescription": "Load misses in all DTLB levels that cause page walks", + "BriefDescription": "Flushing of the Instruction TLB (ITLB) pages, includes 4k/2M/4M pages.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x08", - "EventName": "DTLB_LOAD_MISSES.MISS_CAUSES_A_WALK", - "PublicDescription": "Counts demand data loads that caused a page walk of any page size (4K/2M/4M/1G). This implies it missed in all TLB levels, but the walk need not have completed.", - "SampleAfterValue": "100003", + "EventCode": "0xAE", + "EventName": "ITLB.ITLB_FLUSH", + "PublicDescription": "Counts the number of flushes of the big or small ITLB pages. Counting include both TLB Flush (covering all sets) and TLB Set Clear (set-specific).", + "SampleAfterValue": "100007", "UMask": "0x1" }, { - "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a EPT (Extended Page Table) walk for any request type.", + "BriefDescription": "Misses at all ITLB levels that cause page walks", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x4F", - "EventName": "EPT.WALK_PENDING", - "PublicDescription": "Counts cycles for each PMH (Page Miss Handler) that is busy with an EPT (Extended Page Table) walk for any request type.", - "SampleAfterValue": "2000003", - "UMask": "0x10" + "EventCode": "0x85", + "EventName": "ITLB_MISSES.MISS_CAUSES_A_WALK", + "PublicDescription": "Counts page walks of any page size (4K/2M/4M/1G) caused by a code fetch. This implies it missed in the ITLB and further levels of TLB, but the walk need not have completed.", + "SampleAfterValue": "100003", + "UMask": "0x1" }, { - "BriefDescription": "STLB flush attempts", + "BriefDescription": "Instruction fetch requests that miss the ITLB and hit the STLB.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0xBD", - "EventName": "TLB_FLUSH.STLB_ANY", - "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", - "SampleAfterValue": "100007", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.STLB_HIT", + "SampleAfterValue": "100003", "UMask": "0x20" }, { - "BriefDescription": "Page walk completed due to a demand data load to a 1G page", + "BriefDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake.", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x08", - "EventName": "DTLB_LOAD_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts page walks completed due to demand data loads whose address translations missed in the TLB and were mapped to 4K pages. The page walks can end with or without a page fault.", - "SampleAfterValue": "2000003", - "UMask": "0x8" + "CounterMask": "1", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_ACTIVE", + "PublicDescription": "Cycles when at least one PMH is busy with a page walk for code (instruction fetch) request. EPT page walk duration are excluded in Skylake microarchitecture.", + "SampleAfterValue": "100003", + "UMask": "0x10" }, { - "BriefDescription": "Cycles when at least one PMH is busy with a page walk for a load. EPT page walk duration are excluded in Skylake.", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (All page sizes)", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "CounterMask": "1", - "EventCode": "0x08", - "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 load.", + "EventCode": "0x85", + "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": "0x10" + "UMask": "0xe" + }, + { + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (1G)", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_COMPLETED_1G", + "PublicDescription": "Counts completed page walks (1G 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": "0x8" }, { "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (2M/4M)", @@ -267,18 +237,48 @@ "CounterHTOff": "0,1,2,3,4,5,6,7", "EventCode": "0x85", "EventName": "ITLB_MISSES.WALK_COMPLETED_2M_4M", - "PublicDescription": "Counts code misses in all ITLB levels that caused a completed page walk (2M and 4M page sizes). The page walk can end with or without a fault.", + "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": "Page walk completed due to a demand data store to a 1G page", + "BriefDescription": "Code miss in all TLB levels causes a page walk that completes. (4K)", "Counter": "0,1,2,3", "CounterHTOff": "0,1,2,3,4,5,6,7", - "EventCode": "0x49", - "EventName": "DTLB_STORE_MISSES.WALK_COMPLETED_1G", - "PublicDescription": "Counts page walks completed due to demand data stores whose address translations missed in the TLB and were mapped to 1G pages. The page walks can end with or without a page fault.", + "EventCode": "0x85", + "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": "0x8" + "UMask": "0x2" + }, + { + "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0x85", + "EventName": "ITLB_MISSES.WALK_PENDING", + "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.", + "SampleAfterValue": "100003", + "UMask": "0x10" + }, + { + "BriefDescription": "DTLB flush attempts of the thread-specific entries", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.DTLB_THREAD", + "PublicDescription": "Counts the number of DTLB flush attempts of the thread-specific entries.", + "SampleAfterValue": "100007", + "UMask": "0x1" + }, + { + "BriefDescription": "STLB flush attempts", + "Counter": "0,1,2,3", + "CounterHTOff": "0,1,2,3,4,5,6,7", + "EventCode": "0xBD", + "EventName": "TLB_FLUSH.STLB_ANY", + "PublicDescription": "Counts the number of any STLB flush attempts (such as entire, VPID, PCID, InvPage, CR3 write, etc.).", + "SampleAfterValue": "100007", + "UMask": "0x20" } ]
\ No newline at end of file |