From 663655c91ce195f912957157d7aaa3e8c06e8b14 Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Fri, 23 Jun 2023 08:10:12 -0700 Subject: perf vendor events intel: Update icelakex to 1.21 Updates were released in: https://github.com/intel/perfmon/commit/78d47cbbae48a0297a507ae4fea234ff37ff9960 Adds the events ICACHE_DATA.STALLS, ICACHE_TAG.STALLS and DECODE.LCP. Descriptions are also updated. Signed-off-by: Ian Rogers Cc: Mark Rutland Cc: Eduard Zingerman Cc: Sohom Datta Cc: Peter Zijlstra Cc: Adrian Hunter Cc: Caleb Biggers Cc: Edward Baker Cc: Perry Taylor Cc: Samantha Alt Cc: Weilin Wang Cc: Arnaldo Carvalho de Melo Cc: Andrii Nakryiko Cc: Jiri Olsa Cc: Jing Zhang Cc: Kajol Jain Cc: Alexander Shishkin Cc: Kan Liang Cc: Zhengjun Xing Cc: John Garry Cc: Ingo Molnar Link: https://lore.kernel.org/r/20230623151016.4193660-9-irogers@google.com Signed-off-by: Namhyung Kim --- .../pmu-events/arch/x86/icelakex/frontend.json | 32 +++++++++++++++++++--- .../pmu-events/arch/x86/icelakex/pipeline.json | 4 +-- .../arch/x86/icelakex/uncore-interconnect.json | 2 +- tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +- 4 files changed, 32 insertions(+), 8 deletions(-) (limited to 'tools/perf/pmu-events') diff --git a/tools/perf/pmu-events/arch/x86/icelakex/frontend.json b/tools/perf/pmu-events/arch/x86/icelakex/frontend.json index 71498044f1cb..f6edc4222f42 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/frontend.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/frontend.json @@ -7,6 +7,14 @@ "SampleAfterValue": "100003", "UMask": "0x1" }, + { + "BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to ILD_STALL.LCP]", + "EventCode": "0x87", + "EventName": "DECODE.LCP", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to ILD_STALL.LCP]", + "SampleAfterValue": "500009", + "UMask": "0x1" + }, { "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE transitions count.", "CounterMask": "1", @@ -213,10 +221,10 @@ "UMask": "0x1" }, { - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss.", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_DATA.STALLS]", "EventCode": "0x80", "EventName": "ICACHE_16B.IFDATA_STALL", - "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity.", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_DATA.STALLS]", "SampleAfterValue": "500009", "UMask": "0x4" }, @@ -237,10 +245,26 @@ "UMask": "0x2" }, { - "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]", "EventCode": "0x83", "EventName": "ICACHE_64B.IFTAG_STALL", - "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss.", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_TAG.STALLS]", + "SampleAfterValue": "200003", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache miss. [This event is alias to ICACHE_16B.IFDATA_STALL]", + "EventCode": "0x80", + "EventName": "ICACHE_DATA.STALLS", + "PublicDescription": "Counts cycles where a code line fetch is stalled due to an L1 instruction cache miss. The legacy decode pipeline works at a 16 Byte granularity. [This event is alias to ICACHE_16B.IFDATA_STALL]", + "SampleAfterValue": "500009", + "UMask": "0x4" + }, + { + "BriefDescription": "Cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]", + "EventCode": "0x83", + "EventName": "ICACHE_TAG.STALLS", + "PublicDescription": "Counts cycles where a code fetch is stalled due to L1 instruction cache tag miss. [This event is alias to ICACHE_64B.IFTAG_STALL]", "SampleAfterValue": "200003", "UMask": "0x4" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json b/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json index 442a4c7539dd..176e5ef2a24a 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/pipeline.json @@ -318,10 +318,10 @@ "UMask": "0x40" }, { - "BriefDescription": "Stalls caused by changing prefix length of the instruction.", + "BriefDescription": "Stalls caused by changing prefix length of the instruction. [This event is alias to DECODE.LCP]", "EventCode": "0x87", "EventName": "ILD_STALL.LCP", - "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk.", + "PublicDescription": "Counts cycles that the Instruction Length decoder (ILD) stalls occurred due to dynamically changing prefix length of the decoded instruction (by operand size prefix instruction 0x66, address size prefix instruction 0x67 or REX.W for Intel64). Count is proportional to the number of prefixes in a 16B-line. This may result in a three-cycle penalty for each LCP (Length changing prefix) in a 16-byte chunk. [This event is alias to DECODE.LCP]", "SampleAfterValue": "500009", "UMask": "0x1" }, diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json index 8ac5907762e1..f87ea3f66d1b 100644 --- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json +++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json @@ -9311,7 +9311,7 @@ "EventCode": "0x50", "EventName": "UNC_M3UPI_RxC_HELD.PARALLEL_SUCCESS", "PerPkg": "1", - "PublicDescription": "Message Held : Parallel Success : ad and bl messages were actually slotted into the same flit in paralle", + "PublicDescription": "Message Held : Parallel Success : ad and bl messages were actually slotted into the same flit in parallel", "UMask": "0x8", "Unit": "M3UPI" }, diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv index d63c9df8f65d..98828c3a9cde 100644 --- a/tools/perf/pmu-events/arch/x86/mapfile.csv +++ b/tools/perf/pmu-events/arch/x86/mapfile.csv @@ -14,7 +14,7 @@ GenuineIntel-6-A[DE],v1.01,graniterapids,core GenuineIntel-6-(3C|45|46),v33,haswell,core GenuineIntel-6-3F,v27,haswellx,core GenuineIntel-6-7[DE],v1.19,icelake,core -GenuineIntel-6-6[AC],v1.20,icelakex,core +GenuineIntel-6-6[AC],v1.21,icelakex,core GenuineIntel-6-3A,v24,ivybridge,core GenuineIntel-6-3E,v23,ivytown,core GenuineIntel-6-2D,v23,jaketown,core -- cgit v1.2.3