[PATCH 23/26] perf vendor events: Update Tigerlake
From: Ian Rogers
Date: Sat Jan 29 2022 - 03:15:08 EST
Events are updated to version 1.06:
https://download.01.org/perfmon/TGL
Json files generated by the latest code at:
https://github.com/intel/event-converter-for-linux-perf
Tested:
Not tested on a Tigerlake, on a SkylakeX:
...
9: Parse perf pmu format : Ok
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/tigerlake/cache.json | 44 +++++++++++++++++--
.../arch/x86/tigerlake/floating-point.json | 11 ++++-
.../arch/x86/tigerlake/frontend.json | 17 ++++++-
.../arch/x86/tigerlake/pipeline.json | 37 +++++++++++++++-
4 files changed, 100 insertions(+), 9 deletions(-)
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/cache.json b/tools/perf/pmu-events/arch/x86/tigerlake/cache.json
index 8d767b8932b0..543a3298f86f 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/cache.json
@@ -145,6 +145,17 @@
"SampleAfterValue": "200003",
"UMask": "0x24"
},
+ {
+ "BriefDescription": "Demand Data Read requests that hit L2 cache",
+ "CollectPEBSRecord": "2",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x24",
+ "EventName": "L2_RQSTS.DEMAND_DATA_RD_HIT",
+ "PEBScounters": "0,1,2,3",
+ "PublicDescription": "Counts the number of demand Data Read requests initiated by load instructions that hit L2 cache.",
+ "SampleAfterValue": "200003",
+ "UMask": "0xc1"
+ },
{
"BriefDescription": "All requests that miss L2 cache",
"CollectPEBSRecord": "2",
@@ -185,7 +196,7 @@
"EventCode": "0x24",
"EventName": "L2_RQSTS.SWPF_HIT",
"PEBScounters": "0,1,2,3",
- "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. This event accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions.",
+ "PublicDescription": "Counts Software prefetch requests that hit the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
"SampleAfterValue": "200003",
"UMask": "0xc8"
},
@@ -196,7 +207,7 @@
"EventCode": "0x24",
"EventName": "L2_RQSTS.SWPF_MISS",
"PEBScounters": "0,1,2,3",
- "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. This event accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions.",
+ "PublicDescription": "Counts Software prefetch requests that miss the L2 cache. Accounts for PREFETCHNTA and PREFETCHT0/1/2 instructions when FB is not full.",
"SampleAfterValue": "200003",
"UMask": "0x28"
},
@@ -222,6 +233,17 @@
"SampleAfterValue": "2000003",
"UMask": "0x2"
},
+ {
+ "BriefDescription": "Core-originated cacheable requests that missed L3 (Except hardware prefetches to the L3)",
+ "CollectPEBSRecord": "2",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0x2e",
+ "EventName": "LONGEST_LAT_CACHE.MISS",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "PublicDescription": "Counts core-originated cacheable requests that miss the L3 cache (Longest Latency cache). Requests include data and code reads, Reads-for-Ownership (RFOs), speculative accesses and hardware prefetches to the L1 and L2. It does not include hardware prefetches to the L3, and may not count other types of requests to the L3.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x41"
+ },
{
"BriefDescription": "All retired load instructions.",
"CollectPEBSRecord": "2",
@@ -249,6 +271,20 @@
"SampleAfterValue": "1000003",
"UMask": "0x82"
},
+ {
+ "BriefDescription": "All retired memory instructions.",
+ "CollectPEBSRecord": "2",
+ "Counter": "0,1,2,3",
+ "Data_LA": "1",
+ "EventCode": "0xd0",
+ "EventName": "MEM_INST_RETIRED.ANY",
+ "L1_Hit_Indication": "1",
+ "PEBS": "1",
+ "PEBScounters": "0,1,2,3",
+ "PublicDescription": "Counts all retired memory instructions - loads and stores.",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x83"
+ },
{
"BriefDescription": "Retired load instructions with locked access.",
"CollectPEBSRecord": "2",
@@ -298,7 +334,7 @@
"EventName": "MEM_INST_RETIRED.STLB_MISS_LOADS",
"PEBS": "1",
"PEBScounters": "0,1,2,3",
- "PublicDescription": "Counts retired load instructions that true miss the STLB.",
+ "PublicDescription": "Number of retired load instructions that (start a) miss in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x11"
},
@@ -312,7 +348,7 @@
"L1_Hit_Indication": "1",
"PEBS": "1",
"PEBScounters": "0,1,2,3",
- "PublicDescription": "Counts retired store instructions that true miss the STLB.",
+ "PublicDescription": "Number of retired store instructions that (start a) miss in the 2nd-level TLB (STLB).",
"SampleAfterValue": "100003",
"UMask": "0x12"
},
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json b/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json
index 402f01851313..de8eb2b34a3a 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/floating-point.json
@@ -17,6 +17,7 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
+ "PublicDescription": "Number of SSE/AVX computational 128-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 2 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x4"
},
@@ -27,7 +28,7 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
- "PublicDescription": "Counts number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+ "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x8"
},
@@ -38,6 +39,7 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
+ "PublicDescription": "Number of SSE/AVX computational 256-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 4 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x10"
},
@@ -48,6 +50,7 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
+ "PublicDescription": "Number of SSE/AVX computational 256-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT RSQRT RCP DPP FM(N)ADD/SUB. DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
@@ -58,16 +61,18 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
+ "PublicDescription": "Number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 8 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x40"
},
{
- "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
+ "BriefDescription": "Counts number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element.",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
+ "PublicDescription": "Number of SSE/AVX computational 512-bit packed single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 16 computation operations, one for each element. Applies to SSE* and AVX* packed single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT14 RCP14 FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
@@ -78,6 +83,7 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
+ "PublicDescription": "Number of SSE/AVX computational scalar double precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar double precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x1"
},
@@ -88,6 +94,7 @@
"EventCode": "0xc7",
"EventName": "FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
"PEBScounters": "0,1,2,3,4,5,6,7",
+ "PublicDescription": "Number of SSE/AVX computational scalar single precision floating-point instructions retired; some instructions will count twice as noted below. Each count represents 1 computational operation. Applies to SSE* and AVX* scalar single precision floating-point instructions: ADD SUB MUL DIV MIN MAX SQRT RSQRT RCP FM(N)ADD/SUB. FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
"SampleAfterValue": "100003",
"UMask": "0x2"
}
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json b/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json
index 24c736ac8f8e..2eaa33cc574e 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/frontend.json
@@ -39,12 +39,27 @@
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc6",
+ "EventName": "FRONTEND_RETIRED.ANY_DSB_MISS",
+ "MSRIndex": "0x3F7",
+ "MSRValue": "0x1",
+ "PEBS": "1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+ "SampleAfterValue": "100007",
+ "TakenAlone": "1",
+ "UMask": "0x1"
+ },
+ {
+ "BriefDescription": "Retired Instructions who experienced a critical DSB miss.",
+ "CollectPEBSRecord": "2",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc6",
"EventName": "FRONTEND_RETIRED.DSB_MISS",
"MSRIndex": "0x3F7",
"MSRValue": "0x11",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
- "PublicDescription": "Counts retired Instructions that experienced DSB (Decode stream buffer i.e. the decoded instruction-cache) miss.",
+ "PublicDescription": "Number of retired Instructions that experienced a critical DSB (Decode stream buffer i.e. the decoded instruction-cache) miss. Critical means stalls were exposed to the back-end as a result of the DSB miss.",
"SampleAfterValue": "100007",
"TakenAlone": "1",
"UMask": "0x1"
diff --git a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json
index d0d8a09bc470..4dc3a16e3da4 100644
--- a/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/tigerlake/pipeline.json
@@ -71,14 +71,14 @@
"UMask": "0x40"
},
{
- "BriefDescription": "All indirect branch instructions retired (excluding RETs. TSX aborts are considered indirect branch).",
+ "BriefDescription": "Indirect near branch instructions retired (excluding returns)",
"CollectPEBSRecord": "2",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc4",
"EventName": "BR_INST_RETIRED.INDIRECT",
"PEBS": "1",
"PEBScounters": "0,1,2,3,4,5,6,7",
- "PublicDescription": "Counts all indirect branch instructions retired (excluding RETs. TSX aborts is considered indirect branch).",
+ "PublicDescription": "Counts near indirect branch instructions retired excluding returns. TSX abort is an indirect branch.",
"SampleAfterValue": "100003",
"UMask": "0x80"
},
@@ -442,6 +442,17 @@
"SampleAfterValue": "500009",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Instruction decoders utilized in a cycle",
+ "CollectPEBSRecord": "2",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x55",
+ "EventName": "INST_DECODED.DECODERS",
+ "PEBScounters": "0,1,2,3",
+ "PublicDescription": "Number of decoders utilized in a cycle when the MITE (legacy decode pipeline) fetches instructions.",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Number of instructions retired. Fixed Counter - architectural event",
"CollectPEBSRecord": "2",
@@ -464,6 +475,17 @@
"PublicDescription": "Counts the number of X86 instructions retired - an Architectural PerfMon event. Counting continues during hardware interrupts, traps, and inside interrupt handlers. Notes: INST_RETIRED.ANY is counted by a designated fixed counter freeing up programmable counters to count other events. INST_RETIRED.ANY_P is counted by a programmable counter.",
"SampleAfterValue": "2000003"
},
+ {
+ "BriefDescription": "Number of all retired NOP instructions.",
+ "CollectPEBSRecord": "2",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xc0",
+ "EventName": "INST_RETIRED.NOP",
+ "PEBS": "1",
+ "PEBScounters": "0,1,2,3,4,5,6,7",
+ "SampleAfterValue": "2000003",
+ "UMask": "0x2"
+ },
{
"BriefDescription": "Precise instruction retired event with a reduced effect of PEBS shadow in IP distribution",
"CollectPEBSRecord": "2",
@@ -689,6 +711,17 @@
"SampleAfterValue": "100003",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Number of uops decoded out of instructions exclusively fetched by decoder 0",
+ "CollectPEBSRecord": "2",
+ "Counter": "0,1,2,3",
+ "EventCode": "0x56",
+ "EventName": "UOPS_DECODED.DEC0",
+ "PEBScounters": "0,1,2,3",
+ "PublicDescription": "Uops exclusively fetched by decoder 0",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Number of uops executed on port 0",
"CollectPEBSRecord": "2",
--
2.35.0.rc2.247.g8bbb082509-goog