perf vendor events intel: Update broadwell variant events/metrics

Update broadwell events to v28, broadwellde to v10, broadwellx to v21.
Including the new events FP_ARITH_INST_RETIRED.VECTOR, and
FP_ARITH_INST_RETIRED.4_FLOPS. Metrics are updated to make TMA info
metric names synchronized. Events and metrics were generated by:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py

Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230517173805.602113-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/pmu-events/arch/x86/broadwell/floating-point.json

@@ -31,6 +31,14 @@
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
+    {
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, 1 for each element.  Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x18"
+    },
     {
         "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "EventCode": "0xc7",
@@ -76,6 +84,13 @@
         "SampleAfterValue": "2000005",
         "UMask": "0x2a"
     },
+    {
+        "BriefDescription": "Number of any Vector retired FP arithmetic instructions",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
+        "SampleAfterValue": "2000003",
+        "UMask": "0xfc"
+    },
     {
         "BriefDescription": "Cycles with any input/output SSE or FP assist",
         "CounterMask": "1",

tools/perf/pmu-events/arch/x86/broadwellde/floating-point.json

@@ -31,6 +31,14 @@
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
+    {
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, 1 for each element.  Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x18"
+    },
     {
         "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "EventCode": "0xc7",
@@ -76,6 +84,13 @@
         "SampleAfterValue": "2000005",
         "UMask": "0x2a"
     },
+    {
+        "BriefDescription": "Number of any Vector retired FP arithmetic instructions",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
+        "SampleAfterValue": "2000003",
+        "UMask": "0xfc"
+    },
     {
         "BriefDescription": "Cycles with any input/output SSE or FP assist",
         "CounterMask": "1",

tools/perf/pmu-events/arch/x86/broadwellx/floating-point.json

@@ -31,6 +31,14 @@
         "SampleAfterValue": "2000003",
         "UMask": "0x20"
     },
+    {
+        "BriefDescription": "Number of SSE/AVX computational 128-bit packed single and 256-bit packed double precision FP instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, 1 for each element.  Applies to SSE* and AVX* packed single precision and packed double precision FP instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB count twice as they perform 2 calculations per element.",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.4_FLOPS",
+        "PublicDescription": "Number of SSE/AVX computational 128-bit packed single precision and 256-bit packed double precision  floating-point instructions retired; some instructions will count twice as noted below.  Each count represents 2 or/and 4 computation operations, one for each element.  Applies to SSE* and AVX* packed single precision floating-point and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX RCP14 RSQRT14 SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform 2 calculations per element. The DAZ and FTZ flags in the MXCSR register need to be set when using these events.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x18"
+    },
     {
         "BriefDescription": "Number of SSE/AVX computational double precision floating-point instructions retired; some instructions will count twice as noted below. Applies to SSE* and AVX* scalar and packed double precision floating-point instructions: ADD SUB HADD HSUB SUBADD MUL DIV MIN MAX SQRT DPP FM(N)ADD/SUB.  DPP and FM(N)ADD/SUB instructions count twice as they perform multiple calculations per element.",
         "EventCode": "0xc7",
@@ -76,6 +84,13 @@
         "SampleAfterValue": "2000005",
         "UMask": "0x2a"
     },
+    {
+        "BriefDescription": "Number of any Vector retired FP arithmetic instructions",
+        "EventCode": "0xc7",
+        "EventName": "FP_ARITH_INST_RETIRED.VECTOR",
+        "SampleAfterValue": "2000003",
+        "UMask": "0xfc"
+    },
     {
         "BriefDescription": "Cycles with any input/output SSE or FP assist",
         "CounterMask": "1",

tools/perf/pmu-events/arch/x86/mapfile.csv

@@ -2,9 +2,9 @@ Family-model,Version,Filename,EventType
 GenuineIntel-6-(97|9A|B7|BA|BF),v1.21,alderlake,core
 GenuineIntel-6-BE,v1.21,alderlaken,core
 GenuineIntel-6-(1C|26|27|35|36),v4,bonnell,core
-GenuineIntel-6-(3D|47),v27,broadwell,core
-GenuineIntel-6-56,v9,broadwellde,core
-GenuineIntel-6-4F,v20,broadwellx,core
+GenuineIntel-6-(3D|47),v28,broadwell,core
+GenuineIntel-6-56,v10,broadwellde,core
+GenuineIntel-6-4F,v21,broadwellx,core
 GenuineIntel-6-55-[56789ABCDEF],v1.17,cascadelakex,core
 GenuineIntel-6-9[6C],v1.03,elkhartlake,core
 GenuineIntel-6-5[CF],v13,goldmont,core