[PATCH v2 13/32] perf vendor events: Update Intel icelake
From: Ian Rogers
Date: Mon Jul 25 2022 - 18:38:59 EST
Update to v1.14, the metrics are based on TMA 4.4 full.
Use script at:
https://github.com/intel/event-converter-for-linux-perf/blob/master/download_and_gen.py
to download and generate the latest events and metrics. Manually copy
the icelake files into perf and update mapfile.csv.
Tested on a non-icelake with 'perf test':
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
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
.../pmu-events/arch/x86/icelake/cache.json | 8 +-
.../arch/x86/icelake/floating-point.json | 2 +-
.../pmu-events/arch/x86/icelake/frontend.json | 2 +-
.../arch/x86/icelake/icl-metrics.json | 126 ++++++++++++------
.../arch/x86/icelake/uncore-other.json | 31 +++++
.../arch/x86/icelake/virtual-memory.json | 2 +-
tools/perf/pmu-events/arch/x86/mapfile.csv | 4 +-
7 files changed, 123 insertions(+), 52 deletions(-)
create mode 100644 tools/perf/pmu-events/arch/x86/icelake/uncore-other.json
diff --git a/tools/perf/pmu-events/arch/x86/icelake/cache.json b/tools/perf/pmu-events/arch/x86/icelake/cache.json
index 9989f3338f0a..b4f28f24ee63 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/cache.json
@@ -303,7 +303,7 @@
"UMask": "0x41"
},
{
- "BriefDescription": "All retired load instructions.",
+ "BriefDescription": "Retired load instructions.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"Data_LA": "1",
@@ -311,12 +311,12 @@
"EventName": "MEM_INST_RETIRED.ALL_LOADS",
"PEBS": "1",
"PEBScounters": "0,1,2,3",
- "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions for loads.",
+ "PublicDescription": "Counts all retired load instructions. This event accounts for SW prefetch instructions of PREFETCHNTA or PREFETCHT0/1/2 or PREFETCHW.",
"SampleAfterValue": "1000003",
"UMask": "0x81"
},
{
- "BriefDescription": "All retired store instructions.",
+ "BriefDescription": "Retired store instructions.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3",
"Data_LA": "1",
@@ -325,7 +325,7 @@
"L1_Hit_Indication": "1",
"PEBS": "1",
"PEBScounters": "0,1,2,3",
- "PublicDescription": "Counts all retired store instructions. This event account for SW prefetch instructions and PREFETCHW instruction for stores.",
+ "PublicDescription": "Counts all retired store instructions.",
"SampleAfterValue": "1000003",
"UMask": "0x82"
},
diff --git a/tools/perf/pmu-events/arch/x86/icelake/floating-point.json b/tools/perf/pmu-events/arch/x86/icelake/floating-point.json
index 4347e2d0d090..1925388969bb 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/floating-point.json
@@ -99,4 +99,4 @@
"SampleAfterValue": "100003",
"UMask": "0x2"
}
-]
\ No newline at end of file
+]
diff --git a/tools/perf/pmu-events/arch/x86/icelake/frontend.json b/tools/perf/pmu-events/arch/x86/icelake/frontend.json
index b510dd5d80da..739361d3f52f 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/frontend.json
@@ -494,4 +494,4 @@
"Speculative": "1",
"UMask": "0x1"
}
-]
\ No newline at end of file
+]
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 622c392f59be..f0356d66a927 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/icl-metrics.json
@@ -38,7 +38,7 @@
{
"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",
+ "MetricGroup": "SMT;TmaL1",
"MetricName": "Slots_Utilization"
},
{
@@ -61,24 +61,18 @@
"MetricName": "FLOPc"
},
{
- "BriefDescription": "Actual per-core usage of the Floating Point execution units (regardless of the vector width)",
+ "BriefDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or 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."
+ "PublicDescription": "Actual per-core usage of the Floating Point non-X87 execution units (regardless of precision or vector-width). Values > 1 are possible due to ([BDW+] Fused-Multiply Add (FMA) counting - common; [ADL+] use all of ADD/MUL/FMA in Scalar or 128/256-bit vectors - less common)."
},
{
- "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)",
+ "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is execution) per-core",
"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"
},
- {
- "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear)",
- "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
- "MetricGroup": "Bad;BadSpec;BrMispredicts",
- "MetricName": "IpMispredict"
- },
{
"BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
"MetricExpr": "CPU_CLK_UNHALTED.DISTRIBUTED",
@@ -169,12 +163,24 @@
"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": "Instructions per Software prefetch instruction (of any type: NTA/T0/T1/T2/Prefetch) (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / cpu@SW_PREFETCH_ACCESS.T0\\,umask\\=0xF@",
+ "MetricGroup": "Prefetches",
+ "MetricName": "IpSWPF"
+ },
{
"BriefDescription": "Total number of retired Instructions, Sample with: INST_RETIRED.PREC_DIST",
"MetricExpr": "INST_RETIRED.ANY",
"MetricGroup": "Summary;TmaL1",
"MetricName": "Instructions"
},
+ {
+ "BriefDescription": "",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+ "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
+ "MetricName": "Execute"
+ },
{
"BriefDescription": "Average number of Uops issued by front-end when it issued something",
"MetricExpr": "UOPS_ISSUED.ANY / cpu@UOPS_ISSUED.ANY\\,cmask\\=1@",
@@ -194,11 +200,23 @@
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Number of Instructions per non-speculative DSB miss",
+ "BriefDescription": "Average number of cycles of a switch from the DSB fetch-unit to MITE fetch unit - see DSB_Switches tree node for details.",
+ "MetricExpr": "DSB2MITE_SWITCHES.PENALTY_CYCLES / cpu@DSB2MITE_SWITCHES.PENALTY_CYCLES\\,cmask\\=1\\,edge@",
+ "MetricGroup": "DSBmiss",
+ "MetricName": "DSB_Switch_Cost"
+ },
+ {
+ "BriefDescription": "Number of Instructions per non-speculative DSB miss (lower number means higher occurrence rate)",
"MetricExpr": "INST_RETIRED.ANY / FRONTEND_RETIRED.ANY_DSB_MISS",
"MetricGroup": "DSBmiss;Fed",
"MetricName": "IpDSB_Miss_Ret"
},
+ {
+ "BriefDescription": "Number of Instructions per non-speculative Branch Misprediction (JEClear) (lower number means higher occurrence rate)",
+ "MetricExpr": "INST_RETIRED.ANY / BR_MISP_RETIRED.ALL_BRANCHES",
+ "MetricGroup": "Bad;BadSpec;BrMispredicts",
+ "MetricName": "IpMispredict"
+ },
{
"BriefDescription": "Fraction of branches that are non-taken conditionals",
"MetricExpr": "BR_INST_RETIRED.COND_NTAKEN / BR_INST_RETIRED.ALL_BRANCHES",
@@ -230,11 +248,10 @@
"MetricName": "Other_Branches"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
+ "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )",
"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."
+ "MetricName": "Load_Miss_Real_Latency"
},
{
"BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least one such miss. Per-Logical Processor)",
@@ -242,30 +259,6 @@
"MetricGroup": "Mem;MemoryBound;MemoryBW",
"MetricName": "MLP"
},
- {
- "BriefDescription": "Average data fill bandwidth to the L1 data cache [GB / sec]",
- "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
- "MetricGroup": "Mem;MemoryBW",
- "MetricName": "L1D_Cache_Fill_BW"
- },
- {
- "BriefDescription": "Average data fill bandwidth to the L2 cache [GB / sec]",
- "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
- "MetricGroup": "Mem;MemoryBW",
- "MetricName": "L2_Cache_Fill_BW"
- },
- {
- "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
- "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
- "MetricGroup": "Mem;MemoryBW",
- "MetricName": "L3_Cache_Fill_BW"
- },
- {
- "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
- "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
- "MetricGroup": "Mem;MemoryBW;Offcore",
- "MetricName": "L3_Cache_Access_BW"
- },
{
"BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS / INST_RETIRED.ANY",
@@ -285,13 +278,13 @@
"MetricName": "L2MPKI"
},
{
- "BriefDescription": "L2 cache misses per kilo instruction for all request types (including speculative)",
+ "BriefDescription": "L2 cache ([RKL+] true) misses per kilo instruction for all request types (including speculative)",
"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"
},
{
- "BriefDescription": "L2 cache misses per kilo instruction for all demand loads (including speculative)",
+ "BriefDescription": "L2 cache ([RKL+] true) 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"
@@ -309,7 +302,7 @@
"MetricName": "L3MPKI"
},
{
- "BriefDescription": "Fill Buffer (FB) true hits per kilo instructions for retired demand loads",
+ "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
"MetricExpr": "1000 * MEM_LOAD_RETIRED.FB_HIT / INST_RETIRED.ANY",
"MetricGroup": "Mem;CacheMisses",
"MetricName": "FB_HPKI"
@@ -321,6 +314,54 @@
"MetricGroup": "Mem;MemoryTLB",
"MetricName": "Page_Walks_Utilization"
},
+ {
+ "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricExpr": "64 * L1D.REPLACEMENT / 1000000000 / duration_time",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "L1D_Cache_Fill_BW"
+ },
+ {
+ "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricExpr": "64 * L2_LINES_IN.ALL / 1000000000 / duration_time",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "L2_Cache_Fill_BW"
+ },
+ {
+ "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "L3_Cache_Fill_BW"
+ },
+ {
+ "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
+ "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time",
+ "MetricGroup": "Mem;MemoryBW;Offcore",
+ "MetricName": "L3_Cache_Access_BW"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L1 data cache [GB / sec]",
+ "MetricExpr": "(64 * L1D.REPLACEMENT / 1000000000 / duration_time)",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "L1D_Cache_Fill_BW_1T"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L2 cache [GB / sec]",
+ "MetricExpr": "(64 * L2_LINES_IN.ALL / 1000000000 / duration_time)",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "L2_Cache_Fill_BW_1T"
+ },
+ {
+ "BriefDescription": "Average per-thread data fill bandwidth to the L3 cache [GB / sec]",
+ "MetricExpr": "(64 * LONGEST_LAT_CACHE.MISS / 1000000000 / duration_time)",
+ "MetricGroup": "Mem;MemoryBW",
+ "MetricName": "L3_Cache_Fill_BW_1T"
+ },
+ {
+ "BriefDescription": "Average per-thread data access bandwidth to the L3 cache [GB / sec]",
+ "MetricExpr": "(64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1000000000 / duration_time)",
+ "MetricGroup": "Mem;MemoryBW;Offcore",
+ "MetricName": "L3_Cache_Access_BW_1T"
+ },
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
@@ -337,7 +378,8 @@
"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",
"MetricGroup": "Cor;Flops;HPC",
- "MetricName": "GFLOPs"
+ "MetricName": "GFLOPs",
+ "PublicDescription": "Giga Floating Point Operations Per Second. Aggregate across all supported options of: FP precisions, scalar and vector instructions, vector-width and AMX engine."
},
{
"BriefDescription": "Average Frequency Utilization relative nominal frequency",
diff --git a/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json b/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json
new file mode 100644
index 000000000000..e007b976547d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/x86/icelake/uncore-other.json
@@ -0,0 +1,31 @@
+[
+ {
+ "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, etc.",
+ "Counter": "1",
+ "EventCode": "0x84",
+ "EventName": "UNC_ARB_COH_TRK_REQUESTS.ALL",
+ "PerPkg": "1",
+ "PublicDescription": "Number of entries allocated. Account for Any type: e.g. Snoop, etc.",
+ "UMask": "0x01",
+ "Unit": "ARB"
+ },
+ {
+ "BriefDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+ "Counter": "1",
+ "EventCode": "0x81",
+ "EventName": "UNC_ARB_TRK_REQUESTS.ALL",
+ "PerPkg": "1",
+ "PublicDescription": "Total number of all outgoing entries allocated. Accounts for Coherent and non-coherent traffic.",
+ "UMask": "0x01",
+ "Unit": "ARB"
+ },
+ {
+ "BriefDescription": "UNC_CLOCK.SOCKET",
+ "Counter": "FIXED",
+ "EventCode": "0xff",
+ "EventName": "UNC_CLOCK.SOCKET",
+ "PerPkg": "1",
+ "PublicDescription": "UNC_CLOCK.SOCKET",
+ "Unit": "CLOCK"
+ }
+]
diff --git a/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json b/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json
index a006fd7f7b18..58809e16bf98 100644
--- a/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/icelake/virtual-memory.json
@@ -242,4 +242,4 @@
"Speculative": "1",
"UMask": "0x20"
}
-]
\ No newline at end of file
+]
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 41c0c694211a..aae90ece2013 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -10,6 +10,7 @@ GenuineIntel-6-5[CF],v13,goldmont,core
GenuineIntel-6-7A,v1.01,goldmontplus,core
GenuineIntel-6-(3C|45|46),v31,haswell,core
GenuineIntel-6-3F,v25,haswellx,core
+GenuineIntel-6-(7D|7E|A7),v1.14,icelake,core
GenuineIntel-6-3A,v18,ivybridge,core
GenuineIntel-6-3E,v19,ivytown,core
GenuineIntel-6-2D,v20,jaketown,core
@@ -29,10 +30,7 @@ GenuineIntel-6-2C,v2,westmereep-dp,core
GenuineIntel-6-25,v2,westmereep-sp,core
GenuineIntel-6-2F,v2,westmereex,core
GenuineIntel-6-55-[01234],v1,skylakex,core
-GenuineIntel-6-7D,v1,icelake,core
-GenuineIntel-6-7E,v1,icelake,core
GenuineIntel-6-8[CD],v1,tigerlake,core
-GenuineIntel-6-A7,v1,icelake,core
GenuineIntel-6-6A,v1,icelakex,core
GenuineIntel-6-6C,v1,icelakex,core
GenuineIntel-6-86,v1,tremontx,core
--
2.37.1.359.gd136c6c3e2-goog