perf vendor events: Update metrics for Icelake

Based on TMA_metrics-full.csv version 4.3 at 01.org:
    https://download.01.org/perfmon/
Events are updated to version 1.12:
    https://download.01.org/perfmon/ICL
Json files generated by the latest code at:
    https://github.com/intel/event-converter-for-linux-perf

Tested:

Not tested on an Icelake, on a SkylakeX:

  ...
    9: Parse perf pmu format                                           : Ok
   10: PMU events                                                      :
   10.1: PMU event table sanity                                        : Ok
   10.2: PMU event map aliases                                         : Ok
   10.3: Parsing of PMU event table metrics                            : Ok
   10.4: Parsing of PMU event table metrics with fake PMUs             : Ok
  ...

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Torgue <alexandre.torgue@foss.st.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.garry@huawei.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Zhengjun Xing <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20220201015858.1226914-16-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 259 insertions, 79 deletions

diff --git a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
index 432e45ac6814..4af23c04dc18 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
@@ -1,272 +1,452 @@
 [
     {
-        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "BriefDescription": "Total pipeline cost of branch related instructions (used for program control-flow including function calls)",
+        "MetricExpr": "100 * (( BR_INST_RETIRED.COND + 3 * BR_INST_RETIRED.NEAR_CALL + (BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) ) / TOPDOWN.SLOTS)",
+        "MetricGroup": "Ret",
+        "MetricName": "Branching_Overhead"
+    },
+    {
+        "BriefDescription": "Total pipeline cost of instruction fetch related bottlenecks by large code footprint programs (i-side cache; TLB and BTB misses)",
+        "MetricExpr": "100 * (( 5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING ) / TOPDOWN.SLOTS) * ( (ICACHE_64B.IFTAG_STALL / CPU_CLK_UNHALTED.THREAD) + (ICACHE_16B.IFDATA_STALL / CPU_CLK_UNHALTED.THREAD) + (10 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) ) / #(( 5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING ) / TOPDOWN.SLOTS)",
+        "MetricGroup": "BigFoot;Fed;Frontend;IcMiss;MemoryTLB",
+        "MetricName": "Big_Code"
+    },
+    {
         "BriefDescription": "Instructions Per Cycle (per Logical Processor)",
-        "MetricGroup": "Summary",
+        "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
+        "MetricGroup": "Ret;Summary",
         "MetricName": "IPC"
     },
     {
-        "MetricExpr": "UOPS_RETIRED.SLOTS / INST_RETIRED.ANY",
         "BriefDescription": "Uops Per Instruction",
-        "MetricGroup": "Pipeline;Retire",
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
+        "MetricGroup": "Pipeline;Ret;Retire",
         "MetricName": "UPI"
     },
     {
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
         "BriefDescription": "Instruction per taken branch",
-        "MetricGroup": "Branches;FetchBW;PGO",
-        "MetricName": "IpTB"
+        "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricGroup": "Branches;Fed;FetchBW",
+        "MetricName": "UpTB"
     },
     {
-        "MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
         "BriefDescription": "Cycles Per Instruction (per Logical Processor)",
-        "MetricGroup": "Pipeline",
+        "MetricExpr": "1 / (INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD)",
+        "MetricGroup": "Pipeline;Mem",
         "MetricName": "CPI"
     },
     {
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "BriefDescription": "Per-Logical Processor actual clocks when the Logical Processor is active.",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "Pipeline",
         "MetricName": "CLKS"
     },
     {
+        "BriefDescription": "Total issue-pipeline slots (per-Physical Core till ICL; per-Logical Processor ICL onward)",
+        "MetricExpr": "TOPDOWN.SLOTS",
+        "MetricGroup": "TmaL1",
+        "MetricName": "SLOTS"
+    },
+    {
+        "BriefDescription": "Fraction of Physical Core issue-slots utilized by this Logical Processor",
+        "MetricExpr": "TOPDOWN.SLOTS / ( TOPDOWN.SLOTS / 2 ) if #SMT_on else 1",
+        "MetricGroup": "SMT",
+        "MetricName": "Slots_Utilization"
+    },
+    {
+        "BriefDescription": "The ratio of Executed- by Issued-Uops",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / UOPS_ISSUED.ANY",
+        "MetricGroup": "Cor;Pipeline",
+        "MetricName": "Execute_per_Issue",
+        "PublicDescription": "The ratio of Executed- by Issued-Uops. Ratio > 1 suggests high rate of uop micro-fusions. Ratio < 1 suggest high rate of \"execute\" at rename stage."
+    },
+    {
+        "BriefDescription": "Instructions Per Cycle across hyper-threads (per physical core)",
         "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.DISTRIBUTED",
-        "BriefDescription": "Instructions Per Cycle (per physical core)",
-        "MetricGroup": "SMT;TmaL1",
+        "MetricGroup": "Ret;SMT;TmaL1",
         "MetricName": "CoreIPC"
     },
     {
-        "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.DISTRIBUTED",
         "BriefDescription": "Floating Point Operations Per Cycle",
-        "MetricGroup": "Flops",
+        "MetricExpr": "( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / CPU_CLK_UNHALTED.DISTRIBUTED",
+        "MetricGroup": "Ret;Flops",
         "MetricName": "FLOPc"
     },
     {
-        "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 )",
+        "BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)",
+        "MetricExpr": "( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
+        "MetricGroup": "Cor;Flops;HPC",
+        "MetricName": "FP_Arith_Utilization",
+        "PublicDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width). Values > 1 are possible due to Fused-Multiply Add (FMA) counting."
+    },
+    {
         "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
-        "MetricGroup": "Pipeline;PortsUtil",
+        "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2 ) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)",
+        "MetricGroup": "Backend;Cor;Pipeline;PortsUtil",
         "MetricName": "ILP"
     },
     {
-        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
         "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
-        "MetricGroup": "BrMispredicts",
+        "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;BadSpec;BrMispredicts",
         "MetricName": "IpMispredict"
     },
     {
-        "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED",
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
+        "MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED",
         "MetricGroup": "SMT",
         "MetricName": "CORE_CLKS"
     },
     {
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
         "BriefDescription": "Instructions per Load (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_LOADS",
         "MetricGroup": "InsType",
         "MetricName": "IpLoad"
     },
     {
-        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
         "BriefDescription": "Instructions per Store (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / MEM_INST_RETIRED.ALL_STORES",
         "MetricGroup": "InsType",
         "MetricName": "IpStore"
     },
     {
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
         "BriefDescription": "Instructions per Branch (lower number means higher occurrence rate)",
-        "MetricGroup": "Branches;InsType",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Branches;Fed;InsType",
         "MetricName": "IpBranch"
     },
     {
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
         "BriefDescription": "Instructions per (near) call (lower number means higher occurrence rate)",
-        "MetricGroup": "Branches",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_CALL",
+        "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "IpCall"
     },
     {
-        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "BriefDescription": "Instruction per taken branch",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricGroup": "Branches;Fed;FetchBW;Frontend;PGO",
+        "MetricName": "IpTB"
+    },
+    {
         "BriefDescription": "Branch instructions per taken branch. ",
-        "MetricGroup": "Branches;PGO",
+        "MetricExpr": "BR_INST_RETIRED.ALL_BRANCHES / BR_INST_RETIRED.NEAR_TAKEN",
+        "MetricGroup": "Branches;Fed;PGO",
         "MetricName": "BpTkBranch"
     },
     {
-        "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
         "BriefDescription": "Instructions per Floating Point (FP) Operation (lower number means higher occurrence rate)",
-        "MetricGroup": "Flops;FpArith;InsType",
+        "MetricExpr": "INST_RETIRED.ANY / ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
+        "MetricGroup": "Flops;InsType",
         "MetricName": "IpFLOP"
     },
     {
+        "BriefDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / ( (FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE) + (FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) )",
+        "MetricGroup": "Flops;InsType",
+        "MetricName": "IpArith",
+        "PublicDescription": "Instructions per FP Arithmetic instruction (lower number means higher occurrence rate). May undercount due to FMA double counting. Approximated prior to BDW."
+    },
+    {
+        "BriefDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+        "MetricGroup": "Flops;FpScalar;InsType",
+        "MetricName": "IpArith_Scalar_SP",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Single-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
+    },
+    {
+        "BriefDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+        "MetricGroup": "Flops;FpScalar;InsType",
+        "MetricName": "IpArith_Scalar_DP",
+        "PublicDescription": "Instructions per FP Arithmetic Scalar Double-Precision instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
+    },
+    {
+        "BriefDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE )",
+        "MetricGroup": "Flops;FpVector;InsType",
+        "MetricName": "IpArith_AVX128",
+        "PublicDescription": "Instructions per FP Arithmetic AVX/SSE 128-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
+    },
+    {
+        "BriefDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE )",
+        "MetricGroup": "Flops;FpVector;InsType",
+        "MetricName": "IpArith_AVX256",
+        "PublicDescription": "Instructions per FP Arithmetic AVX* 256-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
+    },
+    {
+        "BriefDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate)",
+        "MetricExpr": "INST_RETIRED.ANY / ( FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE + FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE )",
+        "MetricGroup": "Flops;FpVector;InsType",
+        "MetricName": "IpArith_AVX512",
+        "PublicDescription": "Instructions per FP Arithmetic AVX 512-bit instruction (lower number means higher occurrence rate). May undercount due to FMA double counting."
+    },
+    {
+        "BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
         "MetricExpr": "INST_RETIRED.ANY",
-        "BriefDescription": "Total number of retired Instructions",
         "MetricGroup": "Summary;TmaL1",
         "MetricName": "Instructions"
     },
     {
-        "MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
+        "BriefDescription": "Average number of Uops issued by front-end when it issued something",
+        "MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
+        "MetricGroup": "Fed;FetchBW",
+        "MetricName": "Fetch_UpC"
+    },
+    {
         "BriefDescription": "Fraction of Uops delivered by the LSD (Loop Stream Detector; aka Loop Cache)",
-        "MetricGroup": "LSD",
+        "MetricExpr": "LSD.UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
+        "MetricGroup": "Fed;LSD",
         "MetricName": "LSD_Coverage"
     },
     {
-        "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
         "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)",
-        "MetricGroup": "DSB;FetchBW",
+        "MetricExpr": "IDQ.DSB_UOPS / (IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS)",
+        "MetricGroup": "DSB;Fed;FetchBW",
         "MetricName": "DSB_Coverage"
     },
     {
+        "BriefDescription": "Number of Instructions per non-speculative DSB miss",
+        "MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
+        "MetricGroup": "DSBmiss;Fed",
+        "MetricName": "IpDSB_Miss_Ret"
+    },
+    {
+        "BriefDescription": "Fraction of branches that are non-taken conditionals",
+        "MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;Branches;CodeGen;PGO",
+        "MetricName": "Cond_NT"
+    },
+    {
+        "BriefDescription": "Fraction of branches that are taken conditionals",
+        "MetricExpr": "BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;Branches;CodeGen;PGO",
+        "MetricName": "Cond_TK"
+    },
+    {
+        "BriefDescription": "Fraction of branches that are CALL or RET",
+        "MetricExpr": "( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;Branches",
+        "MetricName": "CallRet"
+    },
+    {
+        "BriefDescription": "Fraction of branches that are unconditional (direct or indirect) jumps",
+        "MetricExpr": "(BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES",
+        "MetricGroup": "Bad;Branches",
+        "MetricName": "Jump"
+    },
+    {
+        "BriefDescription": "Fraction of branches of other types (not individually covered by other metrics in Info.Branches group)",
+        "MetricExpr": "1 - ( (BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (BR_INST_RETIRED.COND_TAKEN / BR_INST_RETIRED.ALL_BRANCHES) + (( BR_INST_RETIRED.NEAR_CALL + BR_INST_RETIRED.NEAR_RETURN ) / BR_INST_RETIRED.ALL_BRANCHES) + ((BR_INST_RETIRED.NEAR_TAKEN - BR_INST_RETIRED.COND_TAKEN - 2 * BR_INST_RETIRED.NEAR_CALL) / BR_INST_RETIRED.ALL_BRANCHES) )",
+        "MetricGroup": "Bad;Branches",
+        "MetricName": "Other_Branches"
+    },
+    {
+        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
         "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
-        "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads (in core cycles)",
-        "MetricGroup": "MemoryBound;MemoryLat",
-        "MetricName": "Load_Miss_Real_Latency"
+        "MetricGroup": "Mem;MemoryBound;MemoryLat",
+        "MetricName": "Load_Miss_Real_Latency",
+        "PublicDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles). Latency may be overestimated for multi-load instructions - e.g. repeat strings."
     },
     {
-        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
         "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
-        "MetricGroup": "MemoryBound;MemoryBW",
+        "MetricExpr": "L1D_PEND_MISS.PENDING / L1D_PEND_MISS.PENDING_CYCLES",
+        "MetricGroup": "Mem;MemoryBound;MemoryBW",
         "MetricName": "MLP"
     },
     {
-        "MetricConstraint": "NO_NMI_WATCHDOG",
-        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
-        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
-        "MetricGroup": "MemoryTLB",
-        "MetricName": "Page_Walks_Utilization"
-    },
-    {
-        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
         "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
-        "MetricGroup": "MemoryBW",
+        "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+        "MetricGroup": "Mem;MemoryBW",
         "MetricName": "L1D_Cache_Fill_BW"
     },
     {
-        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
         "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
-        "MetricGroup": "MemoryBW",
+        "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+        "MetricGroup": "Mem;MemoryBW",
         "MetricName": "L2_Cache_Fill_BW"
     },
     {
-        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
         "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
-        "MetricGroup": "MemoryBW",
+        "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+        "MetricGroup": "Mem;MemoryBW",
         "MetricName": "L3_Cache_Fill_BW"
     },
     {
-        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
         "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
-        "MetricGroup": "MemoryBW;Offcore",
+        "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+        "MetricGroup": "Mem;MemoryBW;Offcore",
         "MetricName": "L3_Cache_Access_BW"
     },
     {
-        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
         "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
-        "MetricGroup": "CacheMisses",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
         "MetricName": "L1MPKI"
     },
     {
-        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L1 cache true misses per kilo instruction for all demand loads (including speculative)",
+        "MetricExpr": "1000 * L2_RQSTS.ALL_DEMAND_DATA_RD / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "L1MPKI_Load"
+    },
+    {
         "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
-        "MetricGroup": "CacheMisses",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;Backend;CacheMisses",
         "MetricName": "L2MPKI"
     },
     {
-        "MetricExpr": "1000 * ( ( OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD ) + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS ) / INST_RETIRED.ANY",
         "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
-        "MetricGroup": "CacheMisses;Offcore",
+        "MetricExpr": "1000 * ( ( OFFCORE_REQUESTS.ALL_DATA_RD - OFFCORE_REQUESTS.DEMAND_DATA_RD ) + L2_RQSTS.ALL_DEMAND_MISS + L2_RQSTS.SWPF_MISS ) / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses;Offcore",
         "MetricName": "L2MPKI_All"
     },
     {
-        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "BriefDescription": "L2 cache misses per kilo instruction for all demand loads  (including speculative)",
+        "MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_MISS / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "L2MPKI_Load"
+    },
+    {
+        "BriefDescription": "L2 cache hits per kilo instruction for all demand loads  (including speculative)",
+        "MetricExpr": "1000 * L2_RQSTS.DEMAND_DATA_RD_HIT / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "L2HPKI_Load"
+    },
+    {
         "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
-        "MetricGroup": "CacheMisses",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
         "MetricName": "L3MPKI"
     },
     {
-        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
+        "BriefDescription": "Fill Buffer (FB) true hits per kilo instructions for retired demand loads",
+        "MetricExpr": "1000 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
+        "MetricGroup": "Mem;CacheMisses",
+        "MetricName": "FB_HPKI"
+    },
+    {
+        "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
+        "MetricConstraint": "NO_NMI_WATCHDOG",
+        "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING ) / ( 2 * CPU_CLK_UNHALTED.DISTRIBUTED )",
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "Page_Walks_Utilization"
+    },
+    {
         "BriefDescription": "Average CPU Utilization",
+        "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
         "MetricGroup": "HPC;Summary",
         "MetricName": "CPU_Utilization"
     },
     {
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
         "BriefDescription": "Measured Average Frequency for unhalted processors [GHz]",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC) * msr@tsc@ / 1000000000 / duration_time",
         "MetricGroup": "Summary;Power",
         "MetricName": "Average_Frequency"
     },
     {
-        "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
         "BriefDescription": "Giga Floating Point Operations Per Second",
-        "MetricGroup": "Flops;HPC",
+        "MetricExpr": "( ( 1 * ( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2 * FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4 * ( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8 * ( FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16 * FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE ) / 1000000000 ) / duration_time",
+        "MetricGroup": "Cor;Flops;HPC",
         "MetricName": "GFLOPs"
     },
     {
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
         "BriefDescription": "Average Frequency Utilization relative nominal frequency",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
         "MetricGroup": "Power",
         "MetricName": "Turbo_Utilization"
     },
     {
-        "MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED",
+        "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0",
+        "MetricExpr": "CORE_POWER.LVL0_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
+        "MetricGroup": "Power",
+        "MetricName": "Power_License0_Utilization",
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for baseline license level 0.  This includes non-AVX codes, SSE, AVX 128-bit, and low-current AVX 256-bit codes."
+    },
+    {
+        "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1",
+        "MetricExpr": "CORE_POWER.LVL1_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
+        "MetricGroup": "Power",
+        "MetricName": "Power_License1_Utilization",
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 1.  This includes high current AVX 256-bit instructions as well as low current AVX 512-bit instructions."
+    },
+    {
+        "BriefDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX)",
+        "MetricExpr": "CORE_POWER.LVL2_TURBO_LICENSE / CPU_CLK_UNHALTED.DISTRIBUTED",
+        "MetricGroup": "Power",
+        "MetricName": "Power_License2_Utilization",
+        "PublicDescription": "Fraction of Core cycles where the core was running with power-delivery for license level 2 (introduced in SKX).  This includes high current AVX 512-bit instructions."
+    },
+    {
         "BriefDescription": "Fraction of cycles where both hardware Logical Processors were active",
+        "MetricExpr": "1 - CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_DISTRIBUTED if #SMT_on else 0",
         "MetricGroup": "SMT",
         "MetricName": "SMT_2T_Utilization"
     },
     {
-        "MetricExpr": "CPU_CLK_UNHALTED.THREAD:k / CPU_CLK_UNHALTED.THREAD",
         "BriefDescription": "Fraction of cycles spent in the Operating System (OS) Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / CPU_CLK_UNHALTED.THREAD",
         "MetricGroup": "OS",
         "MetricName": "Kernel_Utilization"
     },
     {
-        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "BriefDescription": "Cycles Per Instruction for the Operating System (OS) Kernel mode",
+        "MetricExpr": "CPU_CLK_UNHALTED.THREAD_P:k / INST_RETIRED.ANY_P:k",
+        "MetricGroup": "OS",
+        "MetricName": "Kernel_CPI"
+    },
+    {
         "BriefDescription": "Average external Memory Bandwidth Use for reads and writes [GB / sec]",
-        "MetricGroup": "HPC;MemoryBW;SoC",
+        "MetricExpr": "64 * ( arb@event\\=0x81\\,umask\\=0x1@ + arb@event\\=0x84\\,umask\\=0x1@ ) / 1000000 / duration_time / 1000",
+        "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "DRAM_BW_Use"
     },
     {
-        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "BriefDescription": "Instructions per Far Branch ( Far Branches apply upon transition from application to operating system, handling interrupts, exceptions) [lower number means higher occurrence rate]",
+        "MetricExpr": "INST_RETIRED.ANY / BR_INST_RETIRED.FAR_BRANCH:u",
         "MetricGroup": "Branches;OS",
         "MetricName": "IpFarBranch"
     },
     {
-        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "BriefDescription": "C3 residency percent per core",
+        "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
         "MetricName": "C3_Core_Residency"
     },
     {
-        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "BriefDescription": "C6 residency percent per core",
+        "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
         "MetricName": "C6_Core_Residency"
     },
     {
-        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "BriefDescription": "C7 residency percent per core",
+        "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
         "MetricName": "C7_Core_Residency"
     },
     {
-        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "BriefDescription": "C2 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
         "MetricName": "C2_Pkg_Residency"
     },
     {
-        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "BriefDescription": "C3 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
         "MetricName": "C3_Pkg_Residency"
     },
     {
-        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "BriefDescription": "C6 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
         "MetricName": "C6_Pkg_Residency"
     },
     {
-        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "BriefDescription": "C7 residency percent per package",
+        "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
         "MetricGroup": "Power",
         "MetricName": "C7_Pkg_Residency"
     }