From ead81ee4f887c2e6205dacb83ab2e24367a003c1 Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 14 Sep 2017 13:02:28 -0700 Subject: [PATCH] perf vendor events: Update JSON metrics for Skylake Server Signed-off-by: Andi Kleen Link: http://lkml.kernel.org/r/20170914200748.GA13837@tassilo.jf.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- .../arch/x86/skylakex/skx-metrics.json | 42 ++++++------------- 1 file changed, 12 insertions(+), 30 deletions(-) diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json index 68f12a26c816..36c903faed0b 100644 --- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json +++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json @@ -13,19 +13,19 @@ }, { "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", - "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ((UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY) * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )", "MetricGroup": "Frontend", "MetricName": "IFetch_Line_Utilization" }, { - "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", "MetricGroup": "DSB; Frontend_Bandwidth", "MetricName": "DSB_Coverage" }, { "BriefDescription": "Cycles Per Instruction (threaded)", - "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricExpr": "1 / (INST_RETIRED.ANY / cycles)", "MetricGroup": "Pipeline;Summary", "MetricName": "CPI" }, @@ -36,8 +36,8 @@ "MetricName": "CLKS" }, { - "BriefDescription": "Total issue-pipeline slots (per-core)", - "MetricExpr": "4*cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )", + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*(( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "TopDownL1", "MetricName": "SLOTS" }, @@ -49,25 +49,25 @@ }, { "BriefDescription": "Instructions Per Cycle (per physical core)", - "MetricExpr": "INST_RETIRED.ANY / cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )", + "MetricExpr": "INST_RETIRED.ANY / (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", "MetricGroup": "SMT", "MetricName": "CoreIPC" }, { "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", - "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1", + "MetricExpr": "UOPS_EXECUTED.THREAD / (( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1)", "MetricGroup": "Pipeline;Ports_Utilization", "MetricName": "ILP" }, { "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", - "MetricExpr": "( RS_EVENTS.EMPTY_CYCLES - (ICACHE_16B.IFDATA_STALL +2* ICACHE_16B.IFDATA_STALL:c1:e1) - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END", + "MetricExpr": "2* (( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END)", "MetricGroup": "Unknown_Branches", "MetricName": "BAClear_Cost" }, { "BriefDescription": "Core actual clocks when any thread is active on the physical core", - "MetricExpr": "CPU_CLK_UNHALTED.THREAD if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if 1 else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", "MetricGroup": "SMT", "MetricName": "CORE_CLKS" }, @@ -79,34 +79,16 @@ }, { "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", - "MetricExpr": "L1D_PEND_MISS.PENDING / ( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES", + "MetricExpr": "L1D_PEND_MISS.PENDING / (( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES)", "MetricGroup": "Memory_Bound;Memory_BW", "MetricName": "MLP" }, { "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", - "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) )", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * (( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles) )", "MetricGroup": "TLB", "MetricName": "Page_Walks_Utilization" }, - { - "BriefDescription": "L1 cache miss per kilo instruction for demand loads", - "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS_PS / INST_RETIRED.ANY", - "MetricGroup": "Cache_Misses;", - "MetricName": "L1MPKI" - }, - { - "BriefDescription": "L2 cache miss per kilo instruction for demand loads", - "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS_PS / INST_RETIRED.ANY", - "MetricGroup": "Cache_Misses;", - "MetricName": "L2MPKI" - }, - { - "BriefDescription": "L3 cache miss per kilo instruction for demand loads", - "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS_PS / INST_RETIRED.ANY", - "MetricGroup": "Cache_Misses;", - "MetricName": "L3MPKI" - }, { "BriefDescription": "Average CPU Utilization", "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", @@ -115,7 +97,7 @@ }, { "BriefDescription": "Giga Floating Point Operations Per Second", - "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", + "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 )) / 1000000000 / duration_time", "MetricGroup": "FLOPS;Summary", "MetricName": "GFLOPs" },