[PATCH v3 10/20] perf jevents: Add load store breakdown metrics ldst for Intel

[Ian Rogers]

Give breakdown of number of instructions. Use the counter mask (cmask)
to show the number of cycles taken to retire the instructions.

Signed-off-by: Ian Rogers <irogers@xxxxxxxxxx>
---
 tools/perf/pmu-events/intel_metrics.py | 86 +++++++++++++++++++++++++-
 1 file changed, 85 insertions(+), 1 deletion(-)

diff --git a/tools/perf/pmu-events/intel_metrics.py b/tools/perf/pmu-events/intel_metrics.py
index 9ef30e5d3e25..4ac419212b3d 100755
--- a/tools/perf/pmu-events/intel_metrics.py
+++ b/tools/perf/pmu-events/intel_metrics.py
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 from metric import (d_ratio, has_event, max, CheckPmu, Event, JsonEncodeMetric,
                     JsonEncodeMetricGroupDescriptions, Literal, LoadEvents,
-                    Metric, MetricGroup, MetricRef, Select)
+                    Metric, MetricConstraint, MetricGroup, MetricRef, Select)
 import argparse
 import json
 import math
@@ -508,6 +508,89 @@ def IntelSwpf() -> Optional[MetricGroup]:
   ], description="Sofware prefetch instruction breakdown")
 
 
+def IntelLdSt() -> Optional[MetricGroup]:
+  if _args.model in [
+      "bonnell",
+      "nehalemep",
+      "nehalemex",
+      "westmereep-dp",
+      "westmereep-sp",
+      "westmereex",
+  ]:
+    return None
+  LDST_LD = Event("MEM_INST_RETIRED.ALL_LOADS", "MEM_UOPS_RETIRED.ALL_LOADS")
+  LDST_ST = Event("MEM_INST_RETIRED.ALL_STORES", "MEM_UOPS_RETIRED.ALL_STORES")
+  LDST_LDC1 = Event(f"{LDST_LD.name}/cmask=1/")
+  LDST_STC1 = Event(f"{LDST_ST.name}/cmask=1/")
+  LDST_LDC2 = Event(f"{LDST_LD.name}/cmask=2/")
+  LDST_STC2 = Event(f"{LDST_ST.name}/cmask=2/")
+  LDST_LDC3 = Event(f"{LDST_LD.name}/cmask=3/")
+  LDST_STC3 = Event(f"{LDST_ST.name}/cmask=3/")
+  ins = Event("instructions")
+  LDST_CYC = Event("CPU_CLK_UNHALTED.THREAD",
+                   "CPU_CLK_UNHALTED.CORE_P",
+                   "CPU_CLK_UNHALTED.THREAD_P")
+  LDST_PRE = None
+  try:
+    LDST_PRE = Event("LOAD_HIT_PREFETCH.SWPF", "LOAD_HIT_PRE.SW_PF")
+  except:
+    pass
+  LDST_AT = None
+  try:
+    LDST_AT = Event("MEM_INST_RETIRED.LOCK_LOADS")
+  except:
+    pass
+  cyc  = LDST_CYC
+
+  ld_rate = d_ratio(LDST_LD, interval_sec)
+  st_rate = d_ratio(LDST_ST, interval_sec)
+  pf_rate = d_ratio(LDST_PRE, interval_sec) if LDST_PRE else None
+  at_rate = d_ratio(LDST_AT, interval_sec) if LDST_AT else None
+
+  ldst_ret_constraint = MetricConstraint.GROUPED_EVENTS
+  if LDST_LD.name == "MEM_UOPS_RETIRED.ALL_LOADS":
+    ldst_ret_constraint = MetricConstraint.NO_GROUP_EVENTS_NMI
+
+  return MetricGroup("ldst", [
+      MetricGroup("ldst_total", [
+          Metric("ldst_total_loads", "Load/store instructions total loads",
+                 ld_rate, "loads"),
+          Metric("ldst_total_stores", "Load/store instructions total stores",
+                 st_rate, "stores"),
+      ]),
+      MetricGroup("ldst_prcnt", [
+          Metric("ldst_prcnt_loads", "Percent of all instructions that are loads",
+                 d_ratio(LDST_LD, ins), "100%"),
+          Metric("ldst_prcnt_stores", "Percent of all instructions that are stores",
+                 d_ratio(LDST_ST, ins), "100%"),
+      ]),
+      MetricGroup("ldst_ret_lds", [
+          Metric("ldst_ret_lds_1", "Retired loads in 1 cycle",
+                 d_ratio(max(LDST_LDC1 - LDST_LDC2, 0), cyc), "100%",
+                 constraint = ldst_ret_constraint),
+          Metric("ldst_ret_lds_2", "Retired loads in 2 cycles",
+                 d_ratio(max(LDST_LDC2 - LDST_LDC3, 0), cyc), "100%",
+                 constraint = ldst_ret_constraint),
+          Metric("ldst_ret_lds_3", "Retired loads in 3 or more cycles",
+                 d_ratio(LDST_LDC3, cyc), "100%"),
+      ]),
+      MetricGroup("ldst_ret_sts", [
+          Metric("ldst_ret_sts_1", "Retired stores in 1 cycle",
+                 d_ratio(max(LDST_STC1 - LDST_STC2, 0), cyc), "100%",
+                 constraint = ldst_ret_constraint),
+          Metric("ldst_ret_sts_2", "Retired stores in 2 cycles",
+                 d_ratio(max(LDST_STC2 - LDST_STC3, 0), cyc), "100%",
+                 constraint = ldst_ret_constraint),
+          Metric("ldst_ret_sts_3", "Retired stores in 3 more cycles",
+                 d_ratio(LDST_STC3, cyc), "100%"),
+      ]),
+      Metric("ldst_ld_hit_swpf", "Load hit software prefetches per second",
+             pf_rate, "swpf/s") if pf_rate else None,
+      Metric("ldst_atomic_lds", "Atomic loads per second",
+             at_rate, "loads/s") if at_rate else None,
+  ], description = "Breakdown of load/store instructions")
+
+
 def main() -> None:
   global _args
 
@@ -537,6 +620,7 @@ def main() -> None:
       Tsx(),
       IntelBr(),
       IntelL2(),
+      IntelLdSt(),
       IntelPorts(),
       IntelSwpf(),
   ])
-- 
2.44.0.278.ge034bb2e1d-goog