[PATCH v1 4/4] perf vendor events intel: Update meteorlake events to v1.05
From: Ian Rogers
Date: Sat Sep 16 2023 - 01:16:01 EST
v1.05 was released in:
https://github.com/intel/perfmon/commit/405d3ee987d756b5b5d9a64d8a8fa77559822ecf
Update created using:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py
Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
tools/perf/pmu-events/arch/x86/mapfile.csv | 2 +-
.../pmu-events/arch/x86/meteorlake/cache.json | 30 ++++++++++
.../arch/x86/meteorlake/frontend.json | 29 ++++++++--
.../arch/x86/meteorlake/memory.json | 28 +++++++++
.../pmu-events/arch/x86/meteorlake/other.json | 40 +++++++++++++
.../arch/x86/meteorlake/pipeline.json | 57 +++++++++++++++++++
6 files changed, 181 insertions(+), 5 deletions(-)
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index a97f0734099a..e57fde489425 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -21,7 +21,7 @@ GenuineIntel-6-3E,v24,ivytown,core
GenuineIntel-6-2D,v24,jaketown,core
GenuineIntel-6-(57|85),v16,knightslanding,core
GenuineIntel-6-BD,v1.00,lunarlake,core
-GenuineIntel-6-A[AC],v1.04,meteorlake,core
+GenuineIntel-6-A[AC],v1.05,meteorlake,core
GenuineIntel-6-1[AEF],v4,nehalemep,core
GenuineIntel-6-2E,v4,nehalemex,core
GenuineIntel-6-A7,v1.01,rocketlake,core
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
index 1de0200b32f6..5fef87502d4b 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
@@ -966,6 +966,16 @@
"UMask": "0x3",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10003C0001",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"EventCode": "0x2A,0x2B",
@@ -976,6 +986,16 @@
"UMask": "0x1",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x8003C0001",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts demand data reads that resulted in a snoop hit in another cores caches which forwarded the unmodified data to the requesting core.",
"EventCode": "0x2A,0x2B",
@@ -986,6 +1006,16 @@
"UMask": "0x1",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
+ "EventCode": "0xB7",
+ "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10003C0002",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that resulted in a snoop hit in another cores caches, data forwarding is required as the data is modified.",
"EventCode": "0x2A,0x2B",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
index 8264419500a5..9da8689eda81 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
@@ -460,6 +460,27 @@
"UMask": "0x1",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+ "CounterMask": "6",
+ "EventCode": "0x9c",
+ "EventName": "IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE",
+ "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE]",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+ "CounterMask": "1",
+ "EventCode": "0x9c",
+ "EventName": "IDQ_BUBBLES.CYCLES_FE_WAS_OK",
+ "Invert": "1",
+ "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK]",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Uops not delivered by IDQ when backend of the machine is not stalled",
"EventCode": "0x9c",
@@ -470,22 +491,22 @@
"Unit": "cpu_core"
},
{
- "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled",
+ "BriefDescription": "Cycles when no uops are not delivered by the IDQ when backend of the machine is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
"CounterMask": "6",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE",
- "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
+ "PublicDescription": "Counts the number of cycles when no uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_0_UOPS_DELIV.CORE]",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
},
{
- "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled",
+ "BriefDescription": "Cycles when optimal number of uops was delivered to the back-end when the back-end is not stalled [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
"CounterMask": "1",
"EventCode": "0x9c",
"EventName": "IDQ_UOPS_NOT_DELIVERED.CYCLES_FE_WAS_OK",
"Invert": "1",
- "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle.",
+ "PublicDescription": "Counts the number of cycles when the optimal number of uops were delivered by the Instruction Decode Queue (IDQ) to the back-end of the pipeline when there was no back-end stalls. This event counts for one SMT thread in a given cycle. [This event is alias to IDQ_BUBBLES.CYCLES_FE_WAS_OK]",
"SampleAfterValue": "1000003",
"UMask": "0x1",
"Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
index 2605e1d0ba9f..1c1a2cf8d9ac 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
@@ -66,6 +66,14 @@
"UMask": "0x84",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of machine clears due to memory ordering caused by a snoop from an external agent. Does not count internally generated machine clears such as those due to memory disambiguation.",
+ "EventCode": "0xc3",
+ "EventName": "MACHINE_CLEARS.MEMORY_ORDERING",
+ "SampleAfterValue": "20003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Number of machine clears due to memory ordering conflicts.",
"EventCode": "0xc3",
@@ -279,6 +287,26 @@
"UMask": "0x4",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x3FBFC00001",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_RFO.L3_MISS",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x3FBFC00002",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
{
"BriefDescription": "Counts demand data read requests that miss the L3 cache.",
"EventCode": "0x21",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json
index f4c603599df4..d55e792c0c43 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json
@@ -7,6 +7,46 @@
"UMask": "0x8",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts demand data reads that have any type of response.",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10001",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x184000001",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+ "EventCode": "0x2A,0x2B",
+ "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10002",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_core"
+ },
+ {
+ "BriefDescription": "Counts streaming stores that have any type of response.",
+ "EventCode": "0xB7",
+ "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
+ "MSRIndex": "0x1a6,0x1a7",
+ "MSRValue": "0x10800",
+ "SampleAfterValue": "100003",
+ "UMask": "0x1",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts streaming stores that have any type of response.",
"EventCode": "0x2A,0x2B",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
index 352c5efafc06..85a92baa004a 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
@@ -217,6 +217,15 @@
"UMask": "0x50",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the number of mispredicted taken JCC (Jump on Conditional Code) branch instructions retired.",
+ "EventCode": "0xc5",
+ "EventName": "BR_MISP_RETIRED.COND_TAKEN",
+ "PEBS": "1",
+ "SampleAfterValue": "200003",
+ "UMask": "0xfe",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "number of branch instructions retired that were mispredicted and taken.",
"EventCode": "0xc5",
@@ -1045,6 +1054,14 @@
"UMask": "0x3",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to Branch Mispredict",
+ "EventCode": "0x73",
+ "EventName": "TOPDOWN_BAD_SPECULATION.MISPREDICT",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x4",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to a machine clear (nuke).",
"EventCode": "0x73",
@@ -1068,6 +1085,22 @@
"UMask": "0x1",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop). This could be caused by RSV full or load/store buffer block.",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x2",
+ "Unit": "cpu_atom"
+ },
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to IEC and FPC RAT stalls - which can be due to the FIQ and IEC reservation station stall (integer, FP and SIMD scheduler not being able to accept another uop. )",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.NON_MEM_SCHEDULER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x8",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to mrbl stall. A 'marble' refers to a physical register file entry, also known as the physical destination (PDST).",
"EventCode": "0x74",
@@ -1076,6 +1109,14 @@
"UMask": "0x20",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to ROB full",
+ "EventCode": "0x74",
+ "EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x40",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to iq/jeu scoreboards or ms scb",
"EventCode": "0x74",
@@ -1156,6 +1197,14 @@
"UMask": "0x10",
"Unit": "cpu_atom"
},
+ {
+ "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend that do not categorize into any other common frontend stall",
+ "EventCode": "0x71",
+ "EventName": "TOPDOWN_FE_BOUND.OTHER",
+ "SampleAfterValue": "1000003",
+ "UMask": "0x80",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to predecode wrong",
"EventCode": "0x71",
@@ -1398,6 +1447,14 @@
"UMask": "0x1",
"Unit": "cpu_core"
},
+ {
+ "BriefDescription": "Counts the total number of uops retired.",
+ "EventCode": "0xc2",
+ "EventName": "UOPS_RETIRED.ALL",
+ "PEBS": "1",
+ "SampleAfterValue": "2000003",
+ "Unit": "cpu_atom"
+ },
{
"BriefDescription": "Cycles with retired uop(s).",
"CounterMask": "1",
--
2.42.0.459.ge4e396fd5e-goog