[PATCH 1/2] perf vendor events amd: Update Zen 5 core events

[PATCH 1/2] perf vendor events amd: Update Zen 5 core events

[Sandipan Das]

Update definitions for the following events.
  * PMCx00A - Add missing unit masks
  * PMCx00B - Add missing unit masks and fix descriptions
  * PMCx00C - Add missing unit masks
  * PMCx00D - Add missing unit masks
  * PMCx025 - Add missing unit masks and fix descriptions

Fixes: 45c072f2537a ("perf vendor events amd: Add Zen 5 core events")
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
---
 .../arch/x86/amdzen5/floating-point.json      | 130 +++++++++++++++---
 .../arch/x86/amdzen5/load-store.json          |   8 +-
 2 files changed, 120 insertions(+), 18 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/amdzen5/floating-point.json b/tools/perf/pmu-events/arch/x86/amdzen5/floating-point.json
index 9204bfb1d69e..39bd720f9541 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen5/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen5/floating-point.json
@@ -179,6 +179,30 @@
     "BriefDescription": "Retired scalar floating-point blend ops.",
     "UMask": "0x09"
   },
+  {
+    "EventName": "fp_ops_retired_by_type.scalar_mov",
+    "EventCode": "0x0a",
+    "BriefDescription": "Retired scalar floating-point MOV ops.",
+    "UMask": "0x0a"
+  },
+  {
+    "EventName": "fp_ops_retired_by_type.scalar_shuffle",
+    "EventCode": "0x0a",
+    "BriefDescription": "Retired scalar floating-point shuffle ops (may include instructions not necessarily thought of as including shuffles e.g. horizontal add, dot product, and certain MOV instructions).",
+    "UMask": "0x0b"
+  },
+  {
+    "EventName": "fp_ops_retired_by_type.scalar_bfloat",
+    "EventCode": "0x0a",
+    "BriefDescription": "Retired scalar floating-point bfloat ops.",
+    "UMask": "0x0c"
+  },
+  {
+    "EventName": "fp_ops_retired_by_type.scalar_logical",
+    "EventCode": "0x0a",
+    "BriefDescription": "Retired scalar floating-point move ops.",
+    "UMask": "0x0d"
+  },
   {
     "EventName": "fp_ops_retired_by_type.scalar_other",
     "EventCode": "0x0a",
@@ -245,12 +269,24 @@
     "BriefDescription": "Retired vector floating-point blend ops.",
     "UMask": "0x90"
   },
+  {
+    "EventName": "fp_ops_retired_by_type.vector_mov",
+    "EventCode": "0x0a",
+    "BriefDescription": "Retired vector floating-point MOV ops.",
+    "UMask": "0xa0"
+  },
   {
     "EventName": "fp_ops_retired_by_type.vector_shuffle",
     "EventCode": "0x0a",
     "BriefDescription": "Retired vector floating-point shuffle ops (may include instructions not necessarily thought of as including shuffles e.g. horizontal add, dot product, and certain MOV instructions).",
     "UMask": "0xb0"
   },
+  {
+    "EventName": "fp_ops_retired_by_type.vector_bfloat",
+    "EventCode": "0x0a",
+    "BriefDescription": "Retired vector floating-point bfloat ops.",
+    "UMask": "0xc0"
+  },
   {
     "EventName": "fp_ops_retired_by_type.vector_logical",
     "EventCode": "0x0a",
@@ -278,7 +314,7 @@
   {
     "EventName": "sse_avx_ops_retired.mmx_add",
     "EventCode": "0x0b",
-    "BriefDescription": "Retired MMX integer add.",
+    "BriefDescription": "Retired MMX integer add ops.",
     "UMask": "0x01"
   },
   {
@@ -299,16 +335,34 @@
     "BriefDescription": "Retired MMX integer multiply-accumulate ops.",
     "UMask": "0x04"
   },
+  {
+    "EventName": "sse_avx_ops_retired.mmx_aes",
+    "EventCode": "0x0b",
+    "BriefDescription": "Retired MMX integer AES ops.",
+    "UMask": "0x05"
+  },
+  {
+    "EventName": "sse_avx_ops_retired.mmx_sha",
+    "EventCode": "0x0b",
+    "BriefDescription": "Retired MMX integer SHA ops.",
+    "UMask": "0x06"
+  },
   {
     "EventName": "sse_avx_ops_retired.mmx_cmp",
     "EventCode": "0x0b",
     "BriefDescription": "Retired MMX integer compare ops.",
     "UMask": "0x07"
   },
+  {
+    "EventName": "sse_avx_ops_retired.mmx_cvt",
+    "EventCode": "0x0b",
+    "BriefDescription": "Retired MMX integer convert or pack ops.",
+    "UMask": "0x08"
+  },
   {
     "EventName": "sse_avx_ops_retired.mmx_shift",
     "EventCode": "0x0b",
-    "BriefDescription": "Retired MMX integer shift ops.",
+    "BriefDescription": "Retired MMX integer shift or rotate ops.",
     "UMask": "0x09"
   },
   {
@@ -324,9 +378,9 @@
     "UMask": "0x0b"
   },
   {
-    "EventName": "sse_avx_ops_retired.mmx_pack",
+    "EventName": "sse_avx_ops_retired.mmx_vnni",
     "EventCode": "0x0b",
-    "BriefDescription": "Retired MMX integer pack ops.",
+    "BriefDescription": "Retired MMX integer VNNI ops.",
     "UMask": "0x0c"
   },
   {
@@ -390,15 +444,15 @@
     "UMask": "0x70"
   },
   {
-    "EventName": "sse_avx_ops_retired.sse_avx_clm",
+    "EventName": "sse_avx_ops_retired.sse_avx_cvt",
     "EventCode": "0x0b",
-    "BriefDescription": "Retired SSE and AVX integer CLM ops.",
+    "BriefDescription": "Retired SSE and AVX integer convert or pack ops.",
     "UMask": "0x80"
   },
   {
     "EventName": "sse_avx_ops_retired.sse_avx_shift",
     "EventCode": "0x0b",
-    "BriefDescription": "Retired SSE and AVX integer shift ops.",
+    "BriefDescription": "Retired SSE and AVX integer shift or rotate ops.",
     "UMask": "0x90"
   },
   {
@@ -414,9 +468,9 @@
     "UMask": "0xb0"
   },
   {
-    "EventName": "sse_avx_ops_retired.sse_avx_pack",
+    "EventName": "sse_avx_ops_retired.sse_avx_vnni",
     "EventCode": "0x0b",
-    "BriefDescription": "Retired SSE and AVX integer pack ops.",
+    "BriefDescription": "Retired SSE and AVX integer VNNI ops.",
     "UMask": "0xc0"
   },
   {
@@ -497,12 +551,24 @@
     "BriefDescription": "Retired 128-bit packed floating-point blend ops.",
     "UMask": "0x09"
   },
+  {
+    "EventName": "fp_pack_ops_retired.fp128_mov",
+    "EventCode": "0x0c",
+    "BriefDescription": "Retired 128-bit packed floating-point MOV ops.",
+    "UMask": "0x0a"
+  },
   {
     "EventName": "fp_pack_ops_retired.fp128_shuffle",
     "EventCode": "0x0c",
     "BriefDescription": "Retired 128-bit packed floating-point shuffle ops (may include instructions not necessarily thought of as including shuffles e.g. horizontal add, dot product, and certain MOV instructions).",
     "UMask": "0x0b"
   },
+  {
+    "EventName": "fp_pack_ops_retired.fp128_bfloat",
+    "EventCode": "0x0c",
+    "BriefDescription": "Retired 128-bit packed floating-point bfloat ops.",
+    "UMask": "0x0c"
+  },
   {
     "EventName": "fp_pack_ops_retired.fp128_logical",
     "EventCode": "0x0c",
@@ -575,12 +641,24 @@
     "BriefDescription": "Retired 256-bit packed floating-point blend ops.",
     "UMask": "0x90"
   },
+  {
+    "EventName": "fp_pack_ops_retired.fp256_mov",
+    "EventCode": "0x0c",
+    "BriefDescription": "Retired 256-bit packed floating-point MOV ops.",
+    "UMask": "0xa0"
+  },
   {
     "EventName": "fp_pack_ops_retired.fp256_shuffle",
     "EventCode": "0x0c",
     "BriefDescription": "Retired 256-bit packed floating-point shuffle ops (may include instructions not necessarily thought of as including shuffles e.g. horizontal add, dot product, and certain MOV instructions).",
     "UMask": "0xb0"
   },
+  {
+    "EventName": "fp_pack_ops_retired.fp256_bfloat",
+    "EventCode": "0x0c",
+    "BriefDescription": "Retired 256-bit packed floating-point bfloat ops.",
+    "UMask": "0xc0"
+  },
   {
     "EventName": "fp_pack_ops_retired.fp256_logical",
     "EventCode": "0x0c",
@@ -648,15 +726,15 @@
     "UMask": "0x07"
   },
   {
-    "EventName": "packed_int_op_type.int128_clm",
+    "EventName": "packed_int_op_type.int128_cvt",
     "EventCode": "0x0d",
-    "BriefDescription": "Retired 128-bit packed integer CLM ops.",
+    "BriefDescription": "Retired 128-bit packed integer convert or pack ops.",
     "UMask": "0x08"
   },
   {
     "EventName": "packed_int_op_type.int128_shift",
     "EventCode": "0x0d",
-    "BriefDescription": "Retired 128-bit packed integer shift ops.",
+    "BriefDescription": "Retired 128-bit packed integer shift or rotate ops.",
     "UMask": "0x09"
   },
   {
@@ -672,9 +750,9 @@
     "UMask": "0x0b"
   },
   {
-    "EventName": "packed_int_op_type.int128_pack",
+    "EventName": "packed_int_op_type.int128_vnni",
     "EventCode": "0x0d",
-    "BriefDescription": "Retired 128-bit packed integer pack ops.",
+    "BriefDescription": "Retired 128-bit packed integer VNNI ops.",
     "UMask": "0x0c"
   },
   {
@@ -719,16 +797,34 @@
     "BriefDescription": "Retired 256-bit packed integer multiply-accumulate ops.",
     "UMask": "0x40"
   },
+  {
+    "EventName": "packed_int_op_type.int256_aes",
+    "EventCode": "0x0d",
+    "BriefDescription": "Retired 256-bit packed integer AES ops.",
+    "UMask": "0x50"
+  },
+  {
+    "EventName": "packed_int_op_type.int256_sha",
+    "EventCode": "0x0d",
+    "BriefDescription": "Retired 256-bit packed integer SHA ops.",
+    "UMask": "0x60"
+  },
   {
     "EventName": "packed_int_op_type.int256_cmp",
     "EventCode": "0x0d",
     "BriefDescription": "Retired 256-bit packed integer compare ops.",
     "UMask": "0x70"
   },
+  {
+    "EventName": "packed_int_op_type.int256_cvt",
+    "EventCode": "0x0d",
+    "BriefDescription": "Retired 256-bit packed integer convert or pack ops.",
+    "UMask": "0x80"
+  },
   {
     "EventName": "packed_int_op_type.int256_shift",
     "EventCode": "0x0d",
-    "BriefDescription": "Retired 256-bit packed integer shift ops.",
+    "BriefDescription": "Retired 256-bit packed integer shift or rotate ops.",
     "UMask": "0x90"
   },
   {
@@ -744,9 +840,9 @@
     "UMask": "0xb0"
   },
   {
-    "EventName": "packed_int_op_type.int256_pack",
+    "EventName": "packed_int_op_type.int256_vnni",
     "EventCode": "0x0d",
-    "BriefDescription": "Retired 256-bit packed integer pack ops.",
+    "BriefDescription": "Retired 256-bit packed integer VNNI ops.",
     "UMask": "0xc0"
   },
   {
diff --git a/tools/perf/pmu-events/arch/x86/amdzen5/load-store.json b/tools/perf/pmu-events/arch/x86/amdzen5/load-store.json
index 06bbaea15925..b1994539ece8 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen5/load-store.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen5/load-store.json
@@ -8,9 +8,15 @@
   {
     "EventName": "ls_locks.bus_lock",
     "EventCode": "0x25",
-    "BriefDescription": "Retired Lock instructions which caused a bus lock.",
+    "BriefDescription": "Retired lock instructions which caused a bus lock.",
     "UMask": "0x01"
   },
+  {
+    "EventName": "ls_locks.all",
+    "EventCode": "0x25",
+    "BriefDescription": "Retired lock instructions of all types.",
+    "UMask": "0x1f"
+  },
   {
     "EventName": "ls_ret_cl_flush",
     "EventCode": "0x26",
-- 
2.53.0

[PATCH 2/2] perf vendor events amd: Update Zen 6 core events

[Sandipan Das]

Update definitions for the following events.
  * PMCx00A - Fix descriptions
  * PMCx00C - Add missing unit masks
  * PMCx00D - Add missing unit masks and fix descriptions
  * PMCx013 - Fix incorrect unit masks

Fixes: 2f42fb0661d9 ("perf vendor events amd: Add Zen 6 core events")
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
---
 .../arch/x86/amdzen6/floating-point.json      | 34 ++++++++++++++++---
 1 file changed, 29 insertions(+), 5 deletions(-)

diff --git a/tools/perf/pmu-events/arch/x86/amdzen6/floating-point.json b/tools/perf/pmu-events/arch/x86/amdzen6/floating-point.json
index 03cb039434de..71b883776f37 100644
--- a/tools/perf/pmu-events/arch/x86/amdzen6/floating-point.json
+++ b/tools/perf/pmu-events/arch/x86/amdzen6/floating-point.json
@@ -212,7 +212,7 @@
   {
     "EventName": "fp_ops_ret_by_type.scalar_logical",
     "EventCode": "0x0a",
-    "BriefDescription": "Retired scalar floating-point move uops.",
+    "BriefDescription": "Retired scalar floating-point logical uops.",
     "UMask": "0x0d"
   },
   {
@@ -665,6 +665,12 @@
     "BriefDescription": "Retired 256-bit packed floating-point shuffle uops (may include instructions not necessarily thought of as including shuffles e.g. horizontal add, dot product, and certain MOV instructions).",
     "UMask": "0xb0"
   },
+  {
+    "EventName": "fp_pack_ops_ret.fp256_bfloat",
+    "EventCode": "0x0c",
+    "BriefDescription": "Retired 256-bit packed floating-point bfloat uops.",
+    "UMask": "0xc0"
+  },
   {
     "EventName": "fp_pack_ops_ret.fp256_logical",
     "EventCode": "0x0c",
@@ -758,7 +764,7 @@
   {
     "EventName": "fp_pack_int_ops_ret.int128_vnni",
     "EventCode": "0x0d",
-    "BriefDescription": "Retired 128-bit packed integer VNNI ops.",
+    "BriefDescription": "Retired 128-bit packed integer VNNI uops.",
     "UMask": "0x0c"
   },
   {
@@ -803,12 +809,30 @@
     "BriefDescription": "Retired 256-bit packed integer multiply-accumulate uops.",
     "UMask": "0x40"
   },
+  {
+    "EventName": "fp_pack_int_ops_ret.int256_aes",
+    "EventCode": "0x0d",
+    "BriefDescription": "Retired 256-bit packed integer AES uops.",
+    "UMask": "0x50"
+  },
+  {
+    "EventName": "fp_pack_int_ops_ret.int256_sha",
+    "EventCode": "0x0d",
+    "BriefDescription": "Retired 256-bit packed integer SHA uops.",
+    "UMask": "0x60"
+  },
   {
     "EventName": "fp_pack_int_ops_ret.int256_cmp",
     "EventCode": "0x0d",
     "BriefDescription": "Retired 256-bit packed integer compare uops.",
     "UMask": "0x70"
   },
+  {
+    "EventName": "fp_pack_int_ops_ret.int256_cvt",
+    "EventCode": "0x0d",
+    "BriefDescription": "Retired 256-bit packed integer convert or pack uops.",
+    "UMask": "0x80"
+  },
   {
     "EventName": "fp_pack_int_ops_ret.int256_shift",
     "EventCode": "0x0d",
@@ -1083,19 +1107,19 @@
     "EventName": "fp_nsq_read_stalls.fp_prf",
     "EventCode": "0x13",
     "BriefDescription": "Cycles when reads of the NSQ and writes to the floating-point or SIMD schedulers are stalled due to insufficient free physical register file (FP-PRF) entries.",
-    "UMask": "0x0e"
+    "UMask": "0x02"
   },
   {
     "EventName": "fp_nsq_read_stalls.k_prf",
     "EventCode": "0x13",
     "BriefDescription": "Cycles when reads of the NSQ and writes to the floating-point or SIMD schedulers are stalled due to insufficient free mask physical register file (K-PRF) entries.",
-    "UMask": "0x0e"
+    "UMask": "0x04"
   },
   {
     "EventName": "fp_nsq_read_stalls.fp_sq",
     "EventCode": "0x13",
     "BriefDescription": "Cycles when reads of the NSQ and writes to the floating-point or SIMD schedulers are stalled due to insufficient free scheduler entries.",
-    "UMask": "0x0e"
+    "UMask": "0x08"
   },
   {
     "EventName": "fp_nsq_read_stalls.all",
-- 
2.53.0

Re: [PATCH 1/2] perf vendor events amd: Update Zen 5 core events

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Low] Incorrect description for the newly added `fp_ops_retired_by_type.scalar_logical` PMU event.
--

commit ec579a038d59c44007350888149b4dd94c5079db
Author: Sandipan Das <sandipan.das@amd.com>

perf vendor events amd: Update Zen 5 core events

This commit updates the definitions for Zen 5 core events by adding missing
unit masks and fixing descriptions for several PMCx events.

> diff --git a/tools/perf/pmu-events/arch/x86/amdzen5/floating-point.json b/tools/perf/pmu-events/arch/x86/amdzen5/floating-point.json
> index 9204bfb1d69e0..39bd720f95414 100644
> --- a/tools/perf/pmu-events/arch/x86/amdzen5/floating-point.json
> +++ b/tools/perf/pmu-events/arch/x86/amdzen5/floating-point.json
[ ... ]
> @@ -179,6 +179,30 @@
>      "BriefDescription": "Retired scalar floating-point blend ops.",
>      "UMask": "0x09"
>    },
> +  {
> +    "EventName": "fp_ops_retired_by_type.scalar_mov",
> +    "EventCode": "0x0a",
> +    "BriefDescription": "Retired scalar floating-point MOV ops.",
> +    "UMask": "0x0a"
> +  },
> +  {
> +    "EventName": "fp_ops_retired_by_type.scalar_shuffle",
> +    "EventCode": "0x0a",
> +    "BriefDescription": "Retired scalar floating-point shuffle ops (may include instructions not necessarily thought of as including shuffles e.g. horizontal add, dot product, and certain MOV instructions).",
> +    "UMask": "0x0b"
> +  },
> +  {
> +    "EventName": "fp_ops_retired_by_type.scalar_bfloat",
> +    "EventCode": "0x0a",
> +    "BriefDescription": "Retired scalar floating-point bfloat ops.",
> +    "UMask": "0x0c"
> +  },
> +  {
> +    "EventName": "fp_ops_retired_by_type.scalar_logical",
> +    "EventCode": "0x0a",
> +    "BriefDescription": "Retired scalar floating-point move ops.",

[Severity: Low]
This isn't a bug, but there is a typo in the description for the
scalar_logical event. It currently reads "move ops", duplicating the
description from the scalar_mov event. Should this be "logical ops"?

A subsequent patch in the series (commit "perf vendor events amd: Update Zen
6 core events") fixes this identical typo for Zen 6 architectures, but it
appears to remain unaddressed here for Zen 5.

> +    "UMask": "0x0d"
> +  },

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/f16d1391366762dee0d49f00697f5e6ea913e2c1.1780330378.git.sandipan.das@amd.com?part=1