perf vendor events: Update Intel ivybridge

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@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexandre Torgue <alexandre.torgue@foss.st.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Caleb Biggers <caleb.biggers@intel.com>
Cc: James Clark <james.clark@arm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.garry@huawei.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kshipra Bopardikar <kshipra.bopardikar@intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Perry Taylor <perry.taylor@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sedat Dilek <sedat.dilek@gmail.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: http://lore.kernel.org/lkml/20220727220832.2865794-15-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/pmu-events/arch/x86/ivybridge/cache.json b/tools/perf/pmu-events/arch/x86/ivybridge/cache.json
index 62e9705daa193ab47b868fe5f949ad5eb6cd81c4..8adb2e45e23df7030b267c883e4a4a1883f00a8e 100644 (file)
--- 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 db8b1c4fceb04fd05eb47331a0693d65043ac340..4c2ac010cf55df92d4102a418b5abaddc5d23406 100644 (file)
--- 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 c956a0a51312c878c7533af6e6b1cbd52d78e074..2b1a82dd86abc04a50b4ce4b34684ff9c5a857b1 100644 (file)
--- 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 87670226f52d9c209f50b3f7955b07d638fc8432..3f48e75f8a86d9547a860f6cd734b1413e3bf6ca 100644 (file)
--- 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 5f98f7746cf76133b820fbddf59c5a6ac9736749..30fc0af61eb37d7721e02e71932fc87bfe96d6d7 100644 (file)
--- 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 83fe8f79adc64c1c974bcc07b349ad145fa548ca..2d62521791d8c4d5b094863a31e6cfb956be9571 100644 (file)
--- 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 2de31c56c2a5ae14003e9fe87e471b543a7c0875..d89d3f8db19056b2455b23b0c978d456247aadba 100644 (file)
--- 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 6278068908cf8f7a0b43890bb66055482eed0558..88f1e326205fa5426dc6e6f586f71aaab78d5516 100644 (file)
--- 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 8cf1549797b0ed9f73838190e682bc2d0dd3c47d..a5e387bbb13455bcc74c63d2ba665a1fa18b2b88 100644 (file)
--- 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 9a9593abd2740326adf0d3cb2f39b7c2a30d01bc..dbb1197805d334c3ac6d34561ac9a85e8c98aeab 100644 (file)
--- 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