[PATCH v3 14/30] perf vendor events: Update Intel ivybridge

From: Ian Rogers
Date: Wed Jul 27 2022 - 18:10:30 EST


Update to v22, 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 ivybridge files into perf and update mapfile.csv.

Tested on a non-ivybridge 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/ivybridge/cache.json | 2 +-
.../arch/x86/ivybridge/floating-point.json | 2 +-
.../arch/x86/ivybridge/frontend.json | 2 +-
.../arch/x86/ivybridge/ivb-metrics.json | 94 +++++++++++++------
.../pmu-events/arch/x86/ivybridge/memory.json | 2 +-
.../pmu-events/arch/x86/ivybridge/other.json | 2 +-
.../arch/x86/ivybridge/pipeline.json | 4 +-
.../arch/x86/ivybridge/uncore-other.json | 2 +-
.../arch/x86/ivybridge/virtual-memory.json | 2 +-
tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
10 files changed, 75 insertions(+), 39 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
index 62e9705daa19..8adb2e45e23d 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
@@ -1099,4 +1099,4 @@
"SampleAfterValue": "100003",
"UMask": "0x10"
}
-]
\ No newline at end of file
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json b/tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json
index db8b1c4fceb0..4c2ac010cf55 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/floating-point.json
@@ -166,4 +166,4 @@
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
-]
\ No newline at end of file
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json b/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json
index c956a0a51312..2b1a82dd86ab 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/frontend.json
@@ -312,4 +312,4 @@
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
-]
\ No newline at end of file
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
index 87670226f52d..3f48e75f8a86 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
@@ -130,17 +130,11 @@
"MetricName": "FLOPc_SMT"
},
{
- "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 / (( cpu@UOPS_EXECUTED.CORE\\,cmask\\=1@ / 2 ) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC)",
"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.THREAD / 2 ) * ( 1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK ) )",
@@ -196,6 +190,18 @@
"MetricGroup": "Summary;TmaL1",
"MetricName": "Instructions"
},
+ {
+ "BriefDescription": "Average number of Uops retired in cycles where at least one uop has retired.",
+ "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / cpu@UOPS_RETIRED.RETIRE_SLOTS\\,cmask\\=1@",
+ "MetricGroup": "Pipeline;Ret",
+ "MetricName": "Retire"
+ },
+ {
+ "BriefDescription": "",
+ "MetricExpr": "UOPS_EXECUTED.THREAD / cpu@UOPS_EXECUTED.THREAD\\,cmask\\=1@",
+ "MetricGroup": "Cor;Pipeline;PortsUtil;SMT",
+ "MetricName": "Execute"
+ },
{
"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 ) )",
@@ -203,11 +209,16 @@
"MetricName": "DSB_Coverage"
},
{
- "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load instructions (in core cycles)",
+ "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": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
"MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )",
"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)",
@@ -215,24 +226,6 @@
"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": "L1 cache true misses per kilo instruction for retired demand loads",
"MetricExpr": "1000 * MEM_LOAD_UOPS_RETIRED.L1_MISS / INST_RETIRED.ANY",
@@ -264,6 +257,48 @@
"MetricGroup": "Mem;MemoryTLB_SMT",
"MetricName": "Page_Walks_Utilization_SMT"
},
+ {
+ "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-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": "0",
+ "MetricGroup": "Mem;MemoryBW;Offcore",
+ "MetricName": "L3_Cache_Access_BW_1T"
+ },
{
"BriefDescription": "Average CPU Utilization",
"MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@",
@@ -280,7 +315,8 @@
"BriefDescription": "Giga Floating Point Operations Per Second",
"MetricExpr": "( ( 1 * ( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2 * FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4 * ( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8 * SIMD_FP_256.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/ivybridge/memory.json b/tools/perf/pmu-events/arch/x86/ivybridge/memory.json
index 5f98f7746cf7..30fc0af61eb3 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/memory.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/memory.json
@@ -233,4 +233,4 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
}
-]
\ No newline at end of file
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/other.json b/tools/perf/pmu-events/arch/x86/ivybridge/other.json
index 83fe8f79adc6..2d62521791d8 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/other.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/other.json
@@ -41,4 +41,4 @@
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
-]
\ No newline at end of file
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
index 2de31c56c2a5..d89d3f8db190 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/pipeline.json
@@ -676,7 +676,7 @@
"UMask": "0x3"
},
{
- "BriefDescription": "Number of occurences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc.)",
+ "BriefDescription": "Number of occurrences waiting for the checkpoints in Resource Allocation Table (RAT) to be recovered after Nuke due to all other cases except JEClear (e.g. whenever a ucode assist is needed like SSE exception, memory disambiguation, etc.)",
"Counter": "0,1,2,3",
"CounterHTOff": "0,1,2,3,4,5,6,7",
"CounterMask": "1",
@@ -1269,4 +1269,4 @@
"SampleAfterValue": "2000003",
"UMask": "0x1"
}
-]
\ No newline at end of file
+]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/uncore-other.json b/tools/perf/pmu-events/arch/x86/ivybridge/uncore-other.json
index 6278068908cf..88f1e326205f 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/uncore-other.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/uncore-other.json
@@ -82,10 +82,10 @@
{
"BriefDescription": "This 48-bit fixed counter counts the UCLK cycles.",
"Counter": "Fixed",
+ "EventCode": "0xff",
"EventName": "UNC_CLOCK.SOCKET",
"PerPkg": "1",
"PublicDescription": "This 48-bit fixed counter counts the UCLK cycles.",
- "UMask": "0x01",
"Unit": "ARB"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/virtual-memory.json b/tools/perf/pmu-events/arch/x86/ivybridge/virtual-memory.json
index 8cf1549797b0..a5e387bbb134 100644
--- a/tools/perf/pmu-events/arch/x86/ivybridge/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/ivybridge/virtual-memory.json
@@ -177,4 +177,4 @@
"SampleAfterValue": "100007",
"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 9a9593abd274..dbb1197805d3 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -12,7 +12,7 @@ GenuineIntel-6-(3C|45|46),v31,haswell,core
GenuineIntel-6-3F,v25,haswellx,core
GenuineIntel-6-(7D|7E|A7),v1.14,icelake,core
GenuineIntel-6-6[AC],v1.15,icelakex,core
-GenuineIntel-6-3A,v18,ivybridge,core
+GenuineIntel-6-3A,v22,ivybridge,core
GenuineIntel-6-3E,v19,ivytown,core
GenuineIntel-6-2D,v20,jaketown,core
GenuineIntel-6-57,v9,knightslanding,core
--
2.37.1.359.gd136c6c3e2-goog