[PATCH v1 2/3] perf vendor events intel: Update lunarlake events from 1.26 to 1.27
From: Chun-Tse Shao
Date: Wed Nov 18 2026 - 16:27:16 EST
The updated events were published in:
https://github.com/intel/perfmon/commit/99819cdd185adc5eb117eb78296bc29f15e9c5e7
Signed-off-by: Chun-Tse Shao <ctshao@xxxxxxxxxx>
Assisted-by: Gemini:gemini-4-carbon
---
.../pmu-events/arch/x86/lunarlake/cache.json | 2 +-
.../pmu-events/arch/x86/lunarlake/memory.json | 27 +++++++++++-
.../pmu-events/arch/x86/lunarlake/other.json | 19 ++++++++
.../arch/x86/lunarlake/pipeline.json | 44 +++++++++++++++++--
tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
5 files changed, 87 insertions(+), 7 deletions(-)
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
index c77040e87639..0789ce3db1a0 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
@@ -1652,7 +1652,7 @@
"EventCode": "0x2c",
"EventName": "SQ_MISC.BUS_LOCK",
"PublicDescription": "Counts the more expensive bus lock needed to enforce cache coherency for certain memory accesses that need to be done atomically. Can be created by issuing an atomic instruction (via the LOCK prefix) which causes a cache line split or accesses uncacheable memory.",
- "SampleAfterValue": "100003",
+ "SampleAfterValue": "503",
"UMask": "0x10",
"Unit": "cpu_core"
},
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
index caa387e10259..3c005420b7f1 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
@@ -141,7 +141,7 @@
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc3",
"EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
- "PublicDescription": "Counts the number of Machine Clears detected dye to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
+ "PublicDescription": "Counts the number of Machine Clears detected due to memory ordering. Memory Ordering Machine Clears may apply when a memory read may not conform to the memory ordering rules of the x86 architecture",
"SampleAfterValue": "100003",
"UMask": "0x2",
"Unit": "cpu_core"
@@ -155,6 +155,18 @@
"UMask": "0x82",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than any number of cycles.",
+ "Counter": "2,3,4,5,6,7,8,9",
+ "Data_LA": "1",
+ "EventCode": "0xcd",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY",
+ "MSRIndex": "0x3F6",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than any number of cycles. Reported latency may be longer than just the memory latency.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.",
"Counter": "2,3,4,5,6,7,8,9",
@@ -194,6 +206,19 @@
"UMask": "0x1",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2 cycles.",
+ "Counter": "2,3,4,5,6,7,8,9",
+ "Data_LA": "1",
+ "EventCode": "0xcd",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2",
+ "MSRIndex": "0x3F6",
+ "MSRValue": "0x2",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2 cycles. Reported latency may be longer than just the memory latency.",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.",
"Counter": "2,3,4,5,6,7,8,9",
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/other.json b/tools/perf/pmu-events/arch/x86/lunarlake/other.json
index 164374edf293..0475ba321e04 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/other.json
@@ -101,6 +101,25 @@
"UMask": "0x10",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. [This event is alias to MISC_RETIRED.LBR_INSERTS]",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xe4",
+ "EventName": "LBR_INSERTS.ANY",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "LBR record is inserted [This event is alias to MISC_RETIRED.LBR_INSERTS]",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xe4",
+ "EventName": "LBR_INSERTS.ANY",
+ "PublicDescription": "LBR record is inserted [This event is alias to MISC_RETIRED.LBR_INSERTS] Available PDIST counters: 0,1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts all requests that have any type of response.",
"Counter": "0,1,2,3,4,5,6,7",
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
index 5d8bd972d463..42c82b68a2f2 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
@@ -975,7 +975,7 @@
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xc0",
"EventName": "INST_RETIRED.REP_ITERATION",
- "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note: Since the number of iterations within a REP instruction can be significantly affected by fast strings, this event may vary run to run and not match the architectural number of iterations (specified by RCX) Available PDIST counters: 0,1",
+ "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note: Since the number of iterations within a REP instruction can be significantly affected by fast strings, this event may vary from run to run and not match the architectural number of iterations (specified by RCX). Available PDIST counters: 0,1",
"SampleAfterValue": "2000003",
"UMask": "0x8",
"Unit": "cpu_core"
@@ -1486,7 +1486,7 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL.",
+ "BriefDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL. [This event is alias to LBR_INSERTS.ANY]",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xe4",
"EventName": "MISC_RETIRED.LBR_INSERTS",
@@ -1495,11 +1495,11 @@
"Unit": "cpu_atom"
},
{
- "BriefDescription": "LBR record is inserted",
+ "BriefDescription": "LBR record is inserted [This event is alias to LBR_INSERTS.ANY]",
"Counter": "0,1,2,3,4,5,6,7,8,9",
"EventCode": "0xe4",
"EventName": "MISC_RETIRED.LBR_INSERTS",
- "PublicDescription": "LBR record is inserted Available PDIST counters: 0,1",
+ "PublicDescription": "LBR record is inserted [This event is alias to LBR_INSERTS.ANY] Available PDIST counters: 0,1",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
@@ -2299,5 +2299,41 @@
"SampleAfterValue": "2000003",
"UMask": "0x20",
"Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts number of vector uops dispatched on VEC0",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb4",
+ "EventName": "VEC_DISPATCHED.V0",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts number of vector uops dispatched on VEC1",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb4",
+ "EventName": "VEC_DISPATCHED.V1",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts number of vector uops dispatched on VEC2",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb4",
+ "EventName": "VEC_DISPATCHED.V2",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts number of vector uops dispatched on VEC3",
+ "Counter": "0,1,2,3,4,5,6,7,8,9",
+ "EventCode": "0xb4",
+ "EventName": "VEC_DISPATCHED.V3",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_core"
}
]
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 87fa8a7c2f8d..5e6bff382c23 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -23,7 +23,7 @@ GenuineIntel-6-3A,v24,ivybridge,core
GenuineIntel-6-3E,v24,ivytown,core
GenuineIntel-6-2D,v24,jaketown,core
GenuineIntel-6-(57|85),v16,knightslanding,core
-GenuineIntel-6-BD,v1.26,lunarlake,core
+GenuineIntel-6-BD,v1.27,lunarlake,core
GenuineIntel-6-(AA|AC|B5),v1.23,meteorlake,core
GenuineIntel-6-1[AEF],v4,nehalemep,core
GenuineIntel-6-2E,v4,nehalemex,core
--
2.56.1.708.g77570a6a1d-goog