[tip:perf/core] perf vendor events: Add JSON metrics for Skylake server

From: tip-bot for Andi Kleen
Date: Fri Sep 22 2017 - 12:43:15 EST


Commit-ID: 56de5b63ffaff859f75c19aff057ee10f20c6c07
Gitweb: http://git.kernel.org/tip/56de5b63ffaff859f75c19aff057ee10f20c6c07
Author: Andi Kleen <ak@xxxxxxxxxxxxxxx>
AuthorDate: Tue, 5 Sep 2017 16:26:13 -0700
Committer: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Wed, 13 Sep 2017 09:49:18 -0300

perf vendor events: Add JSON metrics for Skylake server

Add JSON metrics for Skylake server

Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/20170908180133.GA20128@xxxxxxxxxxxxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
.../skl-metrics.json => skylakex/skx-metrics.json} | 36 ++++++++++++++++------
1 file changed, 27 insertions(+), 9 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
similarity index 74%
copy from tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
copy to tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 411f941..68f12a2 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -18,7 +18,7 @@
"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"
@@ -36,8 +36,8 @@
"MetricName": "CLKS"
},
{
- "BriefDescription": "Total issue-pipeline slots",
- "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+ "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 )",
"MetricGroup": "TopDownL1",
"MetricName": "SLOTS"
},
@@ -49,7 +49,7 @@
},
{
"BriefDescription": "Instructions Per Cycle (per physical core)",
- "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles",
+ "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 )",
"MetricGroup": "SMT",
"MetricName": "CoreIPC"
},
@@ -61,19 +61,19 @@
},
{
"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",
+ "MetricExpr": "( RS_EVENTS.EMPTY_CYCLES - (ICACHE_16B.IFDATA_STALL +2* ICACHE_16B.IFDATA_STALL:c1:e1) - 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",
+ "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 )",
"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 )",
+ "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )",
"MetricGroup": "Memory_Bound;Memory_Lat",
"MetricName": "Load_Miss_Real_Latency"
},
@@ -85,11 +85,29 @@
},
{
"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 )",
+ "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 ) )",
"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@",
"MetricGroup": "Summary",
@@ -97,7 +115,7 @@
},
{
"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 ) / 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 + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16* FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1000000000 / duration_time",
"MetricGroup": "FLOPS;Summary",
"MetricName": "GFLOPs"
},