mirror of
https://github.com/torvalds/linux.git
synced 2024-11-18 18:11:56 +00:00
perf vendor events: Add JSON metrics for Skylake
Add JSON metrics for Skylake. Committer testing: # grep "model name" /proc/cpuinfo | head -1 model name : Intel(R) Core(TM) i5-7500 CPU @ 3.40GHz # uname -a Linux seventh 4.12.0-rc6+ #1 SMP Fri Jun 30 16:40:55 -03 2017 x86_64 x86_64 x86_64 GNU/Linux # perf stat --metric-only -M Summary -a sleep 1 Performance counter stats for 'system wide': Instructions CPI CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 34021097.0 0.0 119424171.0 0.0 0.0 0.0 0.0 1.001001793 seconds time elapsed # perf list metricgroup List of pre-defined events (to be used in -e): Metric Groups: DSB FLOPS Frontend Frontend_Bandwidth Memory_BW Memory_Bound Memory_Lat Pipeline Ports_Utilization Power SMT Summary TLB TopDownL1 Unknown_Branches # perf stat --metric-only -M Ports_Utilization -a sleep 1 Performance counter stats for 'system wide': ILP 1475828.0 1.000688547 seconds time elapsed # perf stat -v --metric-only -M Ports_Utilization -a sleep 1 Using CPUID GenuineIntel-6-9E metric expr uops_executed.thread / ( uops_executed.core_cycles_ge_1 / 2) if #smt_on else uops_executed.core_cycles_ge_1 for ILP found event uops_executed.thread found event uops_executed.core_cycles_ge_1 adding {uops_executed.thread,uops_executed.core_cycles_ge_1}:W uops_executed.thread -> cpu/umask=0x1,period=2000003,event=0xb1/ uops_executed.core_cycles_ge_1 -> cpu/umask=0x2,period=2000003,cmask=1,event=0xb1/ uops_executed.thread: 8115271 4002547654 4002547654 uops_executed.core_cycles_ge_1: 3282969 4002547654 4002547654 Performance counter stats for 'system wide': ILP 3282969.0 1.000719870 seconds time elapsed # Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20170905195235.GW2482@two.firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Andi Kleen
Arnaldo Carvalho de Melo
parent
cf97962308
commit
2e006a2412
164
tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
Normal file
164
tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
Normal file
@ -0,0 +1,164 @@
|
||||
[
|
||||
{
|
||||
"BriefDescription": "Instructions Per Cycle (per logical thread)",
|
||||
"MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD",
|
||||
"MetricGroup": "TopDownL1",
|
||||
"MetricName": "IPC"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Uops Per Instruction",
|
||||
"MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY",
|
||||
"MetricGroup": "Pipeline",
|
||||
"MetricName": "UPI"
|
||||
},
|
||||
{
|
||||
"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) )",
|
||||
"MetricGroup": "Frontend",
|
||||
"MetricName": "IFetch_Line_Utilization"
|
||||
},
|
||||
{
|
||||
"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",
|
||||
"MetricGroup": "Pipeline;Summary",
|
||||
"MetricName": "CPI"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.",
|
||||
"MetricExpr": "CPU_CLK_UNHALTED.THREAD",
|
||||
"MetricGroup": "Summary",
|
||||
"MetricName": "CLKS"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Total issue-pipeline slots",
|
||||
"MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
|
||||
"MetricGroup": "TopDownL1",
|
||||
"MetricName": "SLOTS"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Total number of retired Instructions",
|
||||
"MetricExpr": "INST_RETIRED.ANY",
|
||||
"MetricGroup": "Summary",
|
||||
"MetricName": "Instructions"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Instructions Per Cycle (per physical core)",
|
||||
"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",
|
||||
"MetricGroup": "Pipeline;Ports_Utilization",
|
||||
"MetricName": "ILP"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)",
|
||||
"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_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD",
|
||||
"MetricGroup": "SMT",
|
||||
"MetricName": "CORE_CLKS"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads",
|
||||
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
|
||||
"MetricGroup": "Memory_Bound;Memory_Lat",
|
||||
"MetricName": "Load_Miss_Real_Latency"
|
||||
},
|
||||
{
|
||||
"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",
|
||||
"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 * ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles )",
|
||||
"MetricGroup": "TLB",
|
||||
"MetricName": "Page_Walks_Utilization"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Average CPU Utilization",
|
||||
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
|
||||
"MetricGroup": "Summary",
|
||||
"MetricName": "CPU_Utilization"
|
||||
},
|
||||
{
|
||||
"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 ) / 1000000000 / duration_time",
|
||||
"MetricGroup": "FLOPS;Summary",
|
||||
"MetricName": "GFLOPs"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
|
||||
"MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC",
|
||||
"MetricGroup": "Power",
|
||||
"MetricName": "Turbo_Utilization"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Fraction of cycles where both hardware threads were active",
|
||||
"MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0",
|
||||
"MetricGroup": "SMT;Summary",
|
||||
"MetricName": "SMT_2T_Utilization"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "Fraction of cycles spent in Kernel mode",
|
||||
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC",
|
||||
"MetricGroup": "Summary",
|
||||
"MetricName": "Kernel_Utilization"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "C3 residency percent per core",
|
||||
"MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100",
|
||||
"MetricGroup": "Power",
|
||||
"MetricName": "C3_Core_Residency"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "C6 residency percent per core",
|
||||
"MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100",
|
||||
"MetricGroup": "Power",
|
||||
"MetricName": "C6_Core_Residency"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "C7 residency percent per core",
|
||||
"MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100",
|
||||
"MetricGroup": "Power",
|
||||
"MetricName": "C7_Core_Residency"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "C2 residency percent per package",
|
||||
"MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100",
|
||||
"MetricGroup": "Power",
|
||||
"MetricName": "C2_Pkg_Residency"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "C3 residency percent per package",
|
||||
"MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100",
|
||||
"MetricGroup": "Power",
|
||||
"MetricName": "C3_Pkg_Residency"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "C6 residency percent per package",
|
||||
"MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100",
|
||||
"MetricGroup": "Power",
|
||||
"MetricName": "C6_Pkg_Residency"
|
||||
},
|
||||
{
|
||||
"BriefDescription": "C7 residency percent per package",
|
||||
"MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100",
|
||||
"MetricGroup": "Power",
|
||||
"MetricName": "C7_Pkg_Residency"
|
||||
}
|
||||
]
|
||||
Loading…
Reference in New Issue
Block a user