[PATCH v1 06/21] perf vendor events intel: Update emeraldrapids events from 1.24 to 1.25
From: Ian Rogers
Date: Thu Sep 24 2026 - 01:40:19 EST
The updated events were published in:
https://github.com/intel/perfmon/commit/0929815a4859319c27d2aa9099d39440829c5d7a
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
.../arch/x86/emeraldrapids/cache.json | 2 +-
.../arch/x86/emeraldrapids/memory.json | 35 ++++++++++++
.../arch/x86/emeraldrapids/other.json | 9 ++++
.../arch/x86/emeraldrapids/pipeline.json | 10 ++--
.../arch/x86/emeraldrapids/uncore-io.json | 53 ++++++++++++++++++-
tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
6 files changed, 103 insertions(+), 8 deletions(-)
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json
index a44e1f027c1d..fc1be5b2bff2 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/cache.json
@@ -1201,7 +1201,7 @@
"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"
},
{
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
index 5e6c1f05c981..93effd1d69a2 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
@@ -55,6 +55,17 @@
"SampleAfterValue": "1000003",
"UMask": "0x9"
},
+ {
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than any number of cycles.",
+ "Counter": "1,2,3,4,5,6,7",
+ "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"
+ },
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 1024 cycles.",
"Counter": "1,2,3,4,5,6,7",
@@ -91,6 +102,30 @@
"SampleAfterValue": "20011",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2 cycles.",
+ "Counter": "1,2,3,4,5,6,7",
+ "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"
+ },
+ {
+ "BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles.",
+ "Counter": "1,2,3,4,5,6,7",
+ "Data_LA": "1",
+ "EventCode": "0xcd",
+ "EventName": "MEM_TRANS_RETIRED.LOAD_LATENCY_GT_2048",
+ "MSRIndex": "0x3F6",
+ "MSRValue": "0x800",
+ "PublicDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 2048 cycles. Reported latency may be longer than just the memory latency.",
+ "SampleAfterValue": "23",
+ "UMask": "0x1"
+ },
{
"BriefDescription": "Counts randomly selected loads when the latency from first dispatch to completion is greater than 256 cycles.",
"Counter": "1,2,3,4,5,6,7",
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json
index 21f49f609ed4..4ded9b0499c3 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/other.json
@@ -32,6 +32,15 @@
"SampleAfterValue": "203",
"UMask": "0x1"
},
+ {
+ "BriefDescription": "Increments whenever there is an update to the LBR array. [This event is alias to MISC_RETIRED.LBR_INSERTS]",
+ "Counter": "0,1,2,3,4,5,6,7",
+ "EventCode": "0xcc",
+ "EventName": "LBR_INSERTS.ANY",
+ "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. [This event is alias to MISC_RETIRED.LBR_INSERTS]",
+ "SampleAfterValue": "100003",
+ "UMask": "0x20"
+ },
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"Counter": "0,1,2,3",
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
index 1fa7957956df..035c01540cf7 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
@@ -200,11 +200,11 @@
"UMask": "0x20"
},
{
- "BriefDescription": "This event counts the number of mispredicted ret instructions retired. Non PEBS",
+ "BriefDescription": "This event counts the number of mispredicted ret instructions retired.",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xc5",
"EventName": "BR_MISP_RETIRED.RET",
- "PublicDescription": "This is a non-precise version (that is, does not use PEBS) of the event that counts mispredicted return instructions retired. Available PDIST counters: 0",
+ "PublicDescription": "This event counts the number of mispredicted ret instructions retired. Available PDIST counters: 0",
"SampleAfterValue": "100007",
"UMask": "0x8"
},
@@ -502,7 +502,7 @@
"Counter": "0,1,2,3,4,5,6,7",
"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 the number of iterations is implementation-dependent.",
+ "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).",
"SampleAfterValue": "2000003",
"UMask": "0x8"
},
@@ -723,11 +723,11 @@
"UMask": "0x20"
},
{
- "BriefDescription": "Increments whenever there is an update to the LBR array.",
+ "BriefDescription": "Increments whenever there is an update to the LBR array. [This event is alias to LBR_INSERTS.ANY]",
"Counter": "0,1,2,3,4,5,6,7",
"EventCode": "0xcc",
"EventName": "MISC_RETIRED.LBR_INSERTS",
- "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT.",
+ "PublicDescription": "Increments when an entry is added to the Last Branch Record (LBR) array (or removed from the array in case of RETURNs in call stack mode). The event requires LBR enable via IA32_DEBUGCTL MSR and branch type selection via MSR_LBR_SELECT. [This event is alias to LBR_INSERTS.ANY]",
"SampleAfterValue": "100003",
"UMask": "0x20"
},
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json
index ddb0f65307f4..d7a6ae230e61 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-io.json
@@ -573,6 +573,19 @@
"UMask": "0x1",
"Unit": "IIO"
},
+ {
+ "BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to this IIO unit",
+ "Counter": "2,3",
+ "EventCode": "0xc0",
+ "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_READ.ALL_PARTS",
+ "Experimental": "1",
+ "FCMask": "0x07",
+ "PerPkg": "1",
+ "PortMask": "0x00FF",
+ "PublicDescription": "Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
+ "UMask": "0x8",
+ "Unit": "IIO"
+ },
{
"BriefDescription": "Peer to peer read request for 4 bytes made by a different IIO unit to IIO Part0",
"Counter": "2,3",
@@ -677,6 +690,19 @@
"UMask": "0x8",
"Unit": "IIO"
},
+ {
+ "BriefDescription": "Peer to peer write request of 4 bytes made to this IIO by a different IIO unit",
+ "Counter": "2,3",
+ "EventCode": "0xc0",
+ "EventName": "UNC_IIO_DATA_REQ_BY_CPU.PEER_WRITE.ALL_PARTS",
+ "Experimental": "1",
+ "FCMask": "0x07",
+ "PerPkg": "1",
+ "PortMask": "0x00FF",
+ "PublicDescription": "Number of DWs (4 bytes) requested by the main die. Includes all requests initiated by the main die, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
+ "UMask": "0x2",
+ "Unit": "IIO"
+ },
{
"BriefDescription": "Peer to peer write request of 4 bytes made to IIO Part0 by a different IIO unit",
"Counter": "2,3",
@@ -1104,6 +1130,32 @@
"UMask": "0x1",
"Unit": "IIO"
},
+ {
+ "BriefDescription": "Peer to peer read request for 4 bytes made by IIO any part to an IIO target",
+ "Counter": "0,1",
+ "EventCode": "0x83",
+ "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_READ.ALL_PARTS",
+ "Experimental": "1",
+ "FCMask": "0x07",
+ "PerPkg": "1",
+ "PortMask": "0x00FF",
+ "PublicDescription": "Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
+ "UMask": "0x8",
+ "Unit": "IIO"
+ },
+ {
+ "BriefDescription": "Peer to peer write request of 4 bytes made by any IIO part to an IIO target",
+ "Counter": "0,1",
+ "EventCode": "0x83",
+ "EventName": "UNC_IIO_DATA_REQ_OF_CPU.PEER_WRITE.ALL_PARTS",
+ "Experimental": "1",
+ "FCMask": "0x07",
+ "PerPkg": "1",
+ "PortMask": "0x00FF",
+ "PublicDescription": "Number of DWs (4 bytes) the card requests of the main die. Includes all requests initiated by the Card, including reads and writes. : x16 card plugged in to stack, Or x8 card plugged in to Lane 0/1, Or x4 card is plugged in to slot 0",
+ "UMask": "0x2",
+ "Unit": "IIO"
+ },
{
"BriefDescription": "Peer to peer write request of 4 bytes made by IIO Part0 to an IIO target",
"Counter": "0,1",
@@ -1827,7 +1879,6 @@
"Counter": "0,1,2,3",
"EventCode": "0x8e",
"EventName": "UNC_IIO_NUM_REQ_OF_CPU_BY_TGT.UBOX_POSTED",
- "Experimental": "1",
"FCMask": "0x01",
"PerPkg": "1",
"PortMask": "0x00FF",
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 27eaf934b925..3753ff64835e 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -9,7 +9,7 @@ GenuineIntel-6-4F,v23,broadwellx,core
GenuineIntel-6-55-[56789ABCDEF],v1.25,cascadelakex,core
GenuineIntel-6-DD,v1.04,clearwaterforest,core
GenuineIntel-6-9[6C],v1.05,elkhartlake,core
-GenuineIntel-6-CF,v1.24,emeraldrapids,core
+GenuineIntel-6-CF,v1.25,emeraldrapids,core
GenuineIntel-6-5[CF],v13,goldmont,core
GenuineIntel-6-7A,v1.01,goldmontplus,core
GenuineIntel-6-B6,v1.13,grandridge,core
--
2.56.0.rc1.310.g51773c2048-goog