Merge pull request #144 from captain5050/master

For Linux perf converter, add EBS_Mode back to CORE_CLKs

scripts/create_perf_json.py

@@ -335,9 +335,20 @@ def get(key: str) -> str:
                 self.unit = unit_fixups[self.unit]
             elif self.unit == "NCU" and self.event_name == "UNC_CLOCK.SOCKET":
                 self.unit = "CLOCK"
-            elif self.unit == "PCU" and self.umask:
-                # TODO: convert to right filter for occupancy
-                self.umask = None
+            elif self.event_name.startswith("UNC_P_POWER_STATE_OCCUPANCY"):
+                # Older uncore_pcu PMUs don't have a umask, fix to occ_sel.
+                assert self.unit == "PCU"
+                if shortname in ['SNB', 'IVB', 'HSW', 'BDW', 'BDW-DE', 'BDX',
+                                 'HSX', 'IVT', 'JKT']:
+                    self.umask = None
+                    assert not self.filter
+                    if self.event_name.endswith("C0"):
+                        self.filter = "occ_sel=1"
+                    elif self.event_name.endswith("C3"):
+                        self.filter = "occ_sel=2"
+                    else:
+                        assert self.event_name.endswith("C6")
+                        self.filter = "occ_sel=3"
         if jd.get('CounterType') == "FREERUN":
             self.unit = f"{self.unit.lower()}_free_running"
             m = re.search(r'_MC(\d+)_', self.event_name)
@@ -878,6 +889,12 @@ def is_topdown_row(key: str) -> bool:
             elif l[0].startswith('Info'):
                 metric_name = field('Level1')
                 form = find_form()
+                if metric_name == 'CORE_CLKS':
+                    if tma_cpu in ['CPX', 'CLX', 'KBLR/CFL/CML', 'SKX', 'SKL/KBL',
+                                'BDX', 'BDW', 'HSX', 'HSW', 'IVT', 'IVB',
+                                'JKT/SNB-EP', 'SNB']:
+                        # Substitute the #EBS mode formula as perf allows thread/process monitoring.
+                        form = "((CPU_CLK_UNHALTED.THREAD / 2) * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK)) if #EBS_Mode else (CPU_CLK_UNHALTED.THREAD_ANY / 2) if #SMT_on else CLKS"
                 if form:
                     tma_metric_name = f'tma_{l[0].lower().replace(".","_")}_{metric_name.lower()}'
                     mgroups = []

scripts/perf/broadwell/bdw-metrics.json

@@ -370,7 +370,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },

scripts/perf/broadwell/memory.json

@@ -2005,7 +2005,7 @@
         "BriefDescription": "Number of times RTM abort was triggered",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PEBS": "1",
+        "PEBS": "2",
         "PublicDescription": "Number of times RTM abort was triggered .",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"

scripts/perf/broadwellde/bdwde-metrics.json

@@ -362,7 +362,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },

scripts/perf/broadwellde/uncore-power.json

@@ -394,6 +394,7 @@
         "BriefDescription": "Number of cores in C-State; C0 and C1",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
@@ -402,6 +403,7 @@
         "BriefDescription": "Number of cores in C-State; C3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
@@ -410,6 +412,7 @@
         "BriefDescription": "Number of cores in C-State; C6 and C7",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"

scripts/perf/broadwellx/bdx-metrics.json

@@ -572,7 +572,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },

scripts/perf/broadwellx/uncore-power.json

@@ -394,6 +394,7 @@
         "BriefDescription": "Number of cores in C-State; C0 and C1",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
@@ -402,6 +403,7 @@
         "BriefDescription": "Number of cores in C-State; C3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
@@ -410,6 +412,7 @@
         "BriefDescription": "Number of cores in C-State; C6 and C7",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"

scripts/perf/cascadelakex/clx-metrics.json

@@ -836,7 +836,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },

scripts/perf/cascadelakex/uncore-power.json

@@ -144,6 +144,7 @@
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
+        "UMask": "0x40",
         "Unit": "PCU"
     },
     {
@@ -152,6 +153,7 @@
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
+        "UMask": "0x80",
         "Unit": "PCU"
     },
     {
@@ -160,6 +162,7 @@
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
+        "UMask": "0xc0",
         "Unit": "PCU"
     },
     {

scripts/perf/haswell/hsw-metrics.json

@@ -316,7 +316,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },

scripts/perf/haswell/memory.json

@@ -371,7 +371,7 @@
         "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PEBS": "1",
+        "PEBS": "2",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
     },

scripts/perf/haswellx/hsx-metrics.json

@@ -518,7 +518,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },

scripts/perf/haswellx/uncore-power.json

@@ -426,6 +426,7 @@
         "BriefDescription": "Number of cores in C-State; C0 and C1",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
@@ -434,6 +435,7 @@
         "BriefDescription": "Number of cores in C-State; C3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
@@ -442,6 +444,7 @@
         "BriefDescription": "Number of cores in C-State; C6 and C7",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"

scripts/perf/icelake/memory.json

@@ -259,6 +259,7 @@
         "BriefDescription": "Number of times an RTM execution aborted.",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
+        "PEBS": "1",
         "PublicDescription": "Counts the number of times RTM abort was triggered.",
         "SampleAfterValue": "100003",
         "UMask": "0x4"

scripts/perf/icelake/other.json

@@ -19,7 +19,7 @@
         "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LVL2_TURBO_LICENSE",
-        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchtecture).  This includes high current AVX 512-bit instructions.",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchitecture).  This includes high current AVX 512-bit instructions.",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },

scripts/perf/icelake/pipeline.json

@@ -529,7 +529,7 @@
         "BriefDescription": "Cycles when Reservation Station (RS) is empty for the thread",
         "EventCode": "0x5e",
         "EventName": "RS_EVENTS.EMPTY_CYCLES",
-        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into stravation periods (e.g. branch mispredictions or i-cache misses)",
+        "PublicDescription": "Counts cycles during which the reservation station (RS) is empty for this logical processor. This is usually caused when the front-end pipeline runs into starvation periods (e.g. branch mispredictions or i-cache misses)",
         "SampleAfterValue": "1000003",
         "UMask": "0x1"
     },
@@ -552,14 +552,6 @@
         "SampleAfterValue": "10000003",
         "UMask": "0x2"
     },
-    {
-        "BriefDescription": "TMA slots wasted due to incorrect speculation by branch mispredictions",
-        "EventCode": "0xa4",
-        "EventName": "TOPDOWN.BR_MISPREDICT_SLOTS",
-        "PublicDescription": "Number of TMA slots that were wasted due to incorrect speculation by branch mispredictions. This event estimates number of operations that were issued but not retired from the speculative path as well as the out-of-order engine recovery past a branch misprediction.",
-        "SampleAfterValue": "10000003",
-        "UMask": "0x8"
-    },
     {
         "BriefDescription": "TMA slots available for an unhalted logical processor. Fixed counter - architectural event",
         "EventName": "TOPDOWN.SLOTS",

scripts/perf/icelakex/uncore-power.json

@@ -151,6 +151,7 @@
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
         "PerPkg": "1",
         "PublicDescription": "Number of cores in C-State : C0 and C1 : This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
+        "UMask": "0x40",
         "Unit": "PCU"
     },
     {
@@ -159,6 +160,7 @@
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
         "PerPkg": "1",
         "PublicDescription": "Number of cores in C-State : C3 : This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
+        "UMask": "0x80",
         "Unit": "PCU"
     },
     {
@@ -167,6 +169,7 @@
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
         "PerPkg": "1",
         "PublicDescription": "Number of cores in C-State : C6 and C7 : This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
+        "UMask": "0xc0",
         "Unit": "PCU"
     },
     {

scripts/perf/ivybridge/ivb-metrics.json

@@ -361,7 +361,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },

scripts/perf/ivytown/ivt-metrics.json

@@ -361,7 +361,7 @@
     },
     {
         "BriefDescription": "Core actual clocks when any Logical Processor is active on the Physical Core",
-        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks)",
+        "MetricExpr": "(CPU_CLK_UNHALTED.THREAD / 2 * (1 + CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK) if #core_wide < 1 else (CPU_CLK_UNHALTED.THREAD_ANY / 2 if #SMT_on else tma_info_thread_clks))",
         "MetricGroup": "SMT",
         "MetricName": "tma_info_core_core_clks"
     },

scripts/perf/ivytown/uncore-power.json

@@ -514,6 +514,7 @@
         "BriefDescription": "Number of cores in C-State; C0 and C1",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C0",
+        "Filter": "occ_sel=1",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
@@ -522,6 +523,7 @@
         "BriefDescription": "Number of cores in C-State; C3",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C3",
+        "Filter": "occ_sel=2",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"
@@ -530,6 +532,7 @@
         "BriefDescription": "Number of cores in C-State; C6 and C7",
         "EventCode": "0x80",
         "EventName": "UNC_P_POWER_STATE_OCCUPANCY.CORES_C6",
+        "Filter": "occ_sel=3",
         "PerPkg": "1",
         "PublicDescription": "This is an occupancy event that tracks the number of cores that are in the chosen C-State.  It can be used by itself to get the average number of cores in that C-state with thresholding to generate histograms, or with other PCU events and occupancy triggering to capture other details.",
         "Unit": "PCU"