All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	 Arnaldo Carvalho de Melo <acme@kernel.org>,
	Namhyung Kim <namhyung@kernel.org>,
	 Mark Rutland <mark.rutland@arm.com>,
	 Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@kernel.org>,  Ian Rogers <irogers@google.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	 Kan Liang <kan.liang@linux.intel.com>,
	James Clark <james.clark@linaro.org>,
	 Xu Yang <xu.yang_2@nxp.com>,
	linux-kernel@vger.kernel.org,  linux-perf-users@vger.kernel.org,
	John Garry <john.g.garry@oracle.com>,
	 Jing Zhang <renyu.zj@linux.alibaba.com>,
	Sandipan Das <sandipan.das@amd.com>,
	 Benjamin Gray <bgray@linux.ibm.com>,
	Perry Taylor <perry.taylor@intel.com>,
	 Samantha Alt <samantha.alt@intel.com>,
	Caleb Biggers <caleb.biggers@intel.com>,
	 Weilin Wang <weilin.wang@intel.com>,
	Edward Baker <edward.baker@intel.com>,
	 Thomas Falcon <thomas.falcon@intel.com>
Subject: [PATCH v5 11/22] perf jevents: Add load store breakdown metrics ldst for Intel
Date: Thu, 28 Aug 2025 21:10:52 -0700	[thread overview]
Message-ID: <20250829041104.4186320-12-irogers@google.com> (raw)
In-Reply-To: <20250829041104.4186320-1-irogers@google.com>

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@google.com>
---
 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 1bac424aca6a..03983107c5c0 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
@@ -522,6 +522,89 @@ def IntelSwpf() -> Optional[MetricGroup]:
   ], description="Software 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("lpm_ldst", [
+      MetricGroup("lpm_ldst_total", [
+          Metric("lpm_ldst_total_loads", "Load/store instructions total loads",
+                 ld_rate, "loads"),
+          Metric("lpm_ldst_total_stores", "Load/store instructions total stores",
+                 st_rate, "stores"),
+      ]),
+      MetricGroup("lpm_ldst_prcnt", [
+          Metric("lpm_ldst_prcnt_loads", "Percent of all instructions that are loads",
+                 d_ratio(LDST_LD, ins), "100%"),
+          Metric("lpm_ldst_prcnt_stores", "Percent of all instructions that are stores",
+                 d_ratio(LDST_ST, ins), "100%"),
+      ]),
+      MetricGroup("lpm_ldst_ret_lds", [
+          Metric("lpm_ldst_ret_lds_1", "Retired loads in 1 cycle",
+                 d_ratio(max(LDST_LDC1 - LDST_LDC2, 0), cyc), "100%",
+                 constraint = ldst_ret_constraint),
+          Metric("lpm_ldst_ret_lds_2", "Retired loads in 2 cycles",
+                 d_ratio(max(LDST_LDC2 - LDST_LDC3, 0), cyc), "100%",
+                 constraint = ldst_ret_constraint),
+          Metric("lpm_ldst_ret_lds_3", "Retired loads in 3 or more cycles",
+                 d_ratio(LDST_LDC3, cyc), "100%"),
+      ]),
+      MetricGroup("lpm_ldst_ret_sts", [
+          Metric("lpm_ldst_ret_sts_1", "Retired stores in 1 cycle",
+                 d_ratio(max(LDST_STC1 - LDST_STC2, 0), cyc), "100%",
+                 constraint = ldst_ret_constraint),
+          Metric("lpm_ldst_ret_sts_2", "Retired stores in 2 cycles",
+                 d_ratio(max(LDST_STC2 - LDST_STC3, 0), cyc), "100%",
+                 constraint = ldst_ret_constraint),
+          Metric("lpm_ldst_ret_sts_3", "Retired stores in 3 more cycles",
+                 d_ratio(LDST_STC3, cyc), "100%"),
+      ]),
+      Metric("lpm_ldst_ld_hit_swpf", "Load hit software prefetches per second",
+             pf_rate, "swpf/s") if pf_rate else None,
+      Metric("lpm_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
 
@@ -551,6 +634,7 @@ def main() -> None:
       Tsx(),
       IntelBr(),
       IntelL2(),
+      IntelLdSt(),
       IntelPorts(),
       IntelSwpf(),
   ])
-- 
2.51.0.318.gd7df087d1a-goog


  parent reply	other threads:[~2025-08-29  4:11 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-08-29  4:10 [PATCH v5 00/22] Python generated Intel metrics Ian Rogers
2025-08-29  4:10 ` [PATCH v5 01/22] perf jevents: Add RAPL metrics for all Intel models Ian Rogers
2025-08-29  4:10 ` [PATCH v5 02/22] perf jevents: Add idle metric for " Ian Rogers
2025-08-29  4:10 ` [PATCH v5 03/22] perf jevents: Add CheckPmu to see if a PMU is in loaded json events Ian Rogers
2025-08-29  4:10 ` [PATCH v5 04/22] perf jevents: Add smi metric group for Intel models Ian Rogers
2025-08-29  4:10 ` [PATCH v5 05/22] perf jevents: Mark metrics with experimental events as experimental Ian Rogers
2025-08-29  4:10 ` [PATCH v5 06/22] perf jevents: Add tsx metric group for Intel models Ian Rogers
2025-08-29  4:10 ` [PATCH v5 07/22] perf jevents: Add br metric group for branch statistics on Intel Ian Rogers
2025-08-29  4:10 ` [PATCH v5 08/22] perf jevents: Add software prefetch (swpf) metric group for Intel Ian Rogers
2025-08-29  4:10 ` [PATCH v5 09/22] perf jevents: Add ports metric group giving utilization on Intel Ian Rogers
2025-08-29  4:10 ` [PATCH v5 10/22] perf jevents: Add L2 metrics for Intel Ian Rogers
2025-08-29  4:10 ` Ian Rogers [this message]
2025-08-29  4:10 ` [PATCH v5 12/22] perf jevents: Add ILP " Ian Rogers
2025-08-29  4:10 ` [PATCH v5 13/22] perf jevents: Add context switch " Ian Rogers
2025-08-29  4:10 ` [PATCH v5 14/22] perf jevents: Add FPU " Ian Rogers
2025-08-29  4:10 ` [PATCH v5 15/22] perf jevents: Add Miss Level Parallelism (MLP) metric " Ian Rogers
2025-08-29  4:10 ` [PATCH v5 16/22] perf jevents: Add mem_bw " Ian Rogers
2025-08-29  4:10 ` [PATCH v5 17/22] perf jevents: Add local/remote "mem" breakdown metrics " Ian Rogers
2025-08-29  4:10 ` [PATCH v5 18/22] perf jevents: Add dir " Ian Rogers
2025-08-29  4:11 ` [PATCH v5 19/22] perf jevents: Add C-State metrics from the PCU PMU " Ian Rogers
2025-08-29  4:11 ` [PATCH v5 20/22] perf jevents: Add local/remote miss latency metrics " Ian Rogers
2025-08-29  4:11 ` [PATCH v5 21/22] perf jevents: Add upi_bw metric " Ian Rogers
2025-08-29  4:11 ` [PATCH v5 22/22] perf jevents: Add mesh bandwidth saturation " Ian Rogers

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250829041104.4186320-12-irogers@google.com \
    --to=irogers@google.com \
    --cc=acme@kernel.org \
    --cc=adrian.hunter@intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=bgray@linux.ibm.com \
    --cc=caleb.biggers@intel.com \
    --cc=edward.baker@intel.com \
    --cc=james.clark@linaro.org \
    --cc=john.g.garry@oracle.com \
    --cc=jolsa@kernel.org \
    --cc=kan.liang@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=perry.taylor@intel.com \
    --cc=peterz@infradead.org \
    --cc=renyu.zj@linux.alibaba.com \
    --cc=samantha.alt@intel.com \
    --cc=sandipan.das@amd.com \
    --cc=thomas.falcon@intel.com \
    --cc=weilin.wang@intel.com \
    --cc=xu.yang_2@nxp.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.