linux-perf-users.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ian Rogers <irogers@google.com>
To: Adrian Hunter <adrian.hunter@intel.com>,
	 Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	 Arnaldo Carvalho de Melo <acme@kernel.org>,
	Benjamin Gray <bgray@linux.ibm.com>,
	 Caleb Biggers <caleb.biggers@intel.com>,
	Edward Baker <edward.baker@intel.com>,
	 Ian Rogers <irogers@google.com>, Ingo Molnar <mingo@redhat.com>,
	 James Clark <james.clark@linaro.org>,
	Jing Zhang <renyu.zj@linux.alibaba.com>,
	 Jiri Olsa <jolsa@kernel.org>,
	John Garry <john.g.garry@oracle.com>, Leo Yan <leo.yan@arm.com>,
	 Namhyung Kim <namhyung@kernel.org>,
	Perry Taylor <perry.taylor@intel.com>,
	 Peter Zijlstra <peterz@infradead.org>,
	Samantha Alt <samantha.alt@intel.com>,
	 Sandipan Das <sandipan.das@amd.com>,
	Thomas Falcon <thomas.falcon@intel.com>,
	 Weilin Wang <weilin.wang@intel.com>, Xu Yang <xu.yang_2@nxp.com>,
	linux-kernel@vger.kernel.org,  linux-perf-users@vger.kernel.org
Subject: [PATCH v9 37/48] perf jevents: Add FPU metrics for Intel
Date: Tue,  2 Dec 2025 09:50:32 -0800	[thread overview]
Message-ID: <20251202175043.623597-38-irogers@google.com> (raw)
In-Reply-To: <20251202175043.623597-1-irogers@google.com>

Metrics break down of floating point operations.

Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Thomas Falcon <thomas.falcon@intel.com>
---
 tools/perf/pmu-events/intel_metrics.py | 97 ++++++++++++++++++++++++++
 1 file changed, 97 insertions(+)

diff --git a/tools/perf/pmu-events/intel_metrics.py b/tools/perf/pmu-events/intel_metrics.py
index 9cf4bd8ac769..77b8e10194db 100755
--- a/tools/perf/pmu-events/intel_metrics.py
+++ b/tools/perf/pmu-events/intel_metrics.py
@@ -320,6 +320,102 @@ def IntelCtxSw() -> MetricGroup:
                                     "retired & core cycles between context switches"))
 
 
+def IntelFpu() -> Optional[MetricGroup]:
+    cyc = Event("cycles")
+    try:
+        s_64 = Event("FP_ARITH_INST_RETIRED.SCALAR_SINGLE",
+                     "SIMD_INST_RETIRED.SCALAR_SINGLE")
+    except:
+        return None
+    d_64 = Event("FP_ARITH_INST_RETIRED.SCALAR_DOUBLE",
+                 "SIMD_INST_RETIRED.SCALAR_DOUBLE")
+    s_128 = Event("FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE",
+                  "SIMD_INST_RETIRED.PACKED_SINGLE")
+
+    flop = s_64 + d_64 + 4 * s_128
+
+    d_128 = None
+    s_256 = None
+    d_256 = None
+    s_512 = None
+    d_512 = None
+    try:
+        d_128 = Event("FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE")
+        flop += 2 * d_128
+        s_256 = Event("FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE")
+        flop += 8 * s_256
+        d_256 = Event("FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE")
+        flop += 4 * d_256
+        s_512 = Event("FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE")
+        flop += 16 * s_512
+        d_512 = Event("FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE")
+        flop += 8 * d_512
+    except:
+        pass
+
+    f_assist = Event("ASSISTS.FP", "FP_ASSIST.ANY", "FP_ASSIST.S")
+    if f_assist in [
+        "ASSISTS.FP",
+        "FP_ASSIST.S",
+    ]:
+        f_assist += "/cmask=1/"
+
+    flop_r = d_ratio(flop, interval_sec)
+    flop_c = d_ratio(flop, cyc)
+    nmi_constraint = MetricConstraint.GROUPED_EVENTS
+    if f_assist.name == "ASSISTS.FP":  # Icelake+
+        nmi_constraint = MetricConstraint.NO_GROUP_EVENTS_NMI
+
+    def FpuMetrics(group: str, fl: Optional[Event], mult: int, desc: str) -> Optional[MetricGroup]:
+        if not fl:
+            return None
+
+        f = fl * mult
+        fl_r = d_ratio(f, interval_sec)
+        r_s = d_ratio(fl, interval_sec)
+        return MetricGroup(group, [
+            Metric(f"{group}_of_total", desc + " floating point operations per second",
+                   d_ratio(f, flop), "100%"),
+            Metric(f"{group}_flops", desc + " floating point operations per second",
+                   fl_r, "flops/s"),
+            Metric(f"{group}_ops", desc + " operations per second",
+                   r_s, "ops/s"),
+        ])
+
+    return MetricGroup("lpm_fpu", [
+        MetricGroup("lpm_fpu_total", [
+            Metric("lpm_fpu_total_flops", "Floating point operations per second",
+                   flop_r, "flops/s"),
+            Metric("lpm_fpu_total_flopc", "Floating point operations per cycle",
+                   flop_c, "flops/cycle", constraint=nmi_constraint),
+        ]),
+        MetricGroup("lpm_fpu_64", [
+            FpuMetrics("lpm_fpu_64_single", s_64, 1, "64-bit single"),
+            FpuMetrics("lpm_fpu_64_double", d_64, 1, "64-bit double"),
+        ]),
+        MetricGroup("lpm_fpu_128", [
+            FpuMetrics("lpm_fpu_128_single", s_128,
+                       4, "128-bit packed single"),
+            FpuMetrics("lpm_fpu_128_double", d_128,
+                       2, "128-bit packed double"),
+        ]),
+        MetricGroup("lpm_fpu_256", [
+            FpuMetrics("lpm_fpu_256_single", s_256,
+                       8, "128-bit packed single"),
+            FpuMetrics("lpm_fpu_256_double", d_256,
+                       4, "128-bit packed double"),
+        ]),
+        MetricGroup("lpm_fpu_512", [
+            FpuMetrics("lpm_fpu_512_single", s_512,
+                       16, "128-bit packed single"),
+            FpuMetrics("lpm_fpu_512_double", d_512,
+                       8, "128-bit packed double"),
+        ]),
+        Metric("lpm_fpu_assists", "FP assists as a percentage of cycles",
+               d_ratio(f_assist, cyc), "100%"),
+    ])
+
+
 def IntelIlp() -> MetricGroup:
     tsc = Event("msr/tsc/")
     c0 = Event("msr/mperf/")
@@ -736,6 +832,7 @@ def main() -> None:
         Tsx(),
         IntelBr(),
         IntelCtxSw(),
+        IntelFpu(),
         IntelIlp(),
         IntelL2(),
         IntelLdSt(),
-- 
2.52.0.158.g65b55ccf14-goog


  parent reply	other threads:[~2025-12-02 17:54 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-12-02 17:49 [PATCH v9 00/48] AMD, ARM, Intel metric generation with Python Ian Rogers
2025-12-02 17:49 ` [PATCH v9 01/48] perf python: Correct copying of metric_leader in an evsel Ian Rogers
2025-12-02 17:49 ` [PATCH v9 02/48] perf ilist: Be tolerant of reading a metric on the wrong CPU Ian Rogers
2025-12-02 17:49 ` [PATCH v9 03/48] perf jevents: Allow multiple metricgroups.json files Ian Rogers
2025-12-02 17:49 ` [PATCH v9 04/48] perf jevents: Update metric constraint support Ian Rogers
2025-12-02 17:50 ` [PATCH v9 05/48] perf jevents: Add descriptions to metricgroup abstraction Ian Rogers
2025-12-02 17:50 ` [PATCH v9 06/48] perf jevents: Allow metric groups not to be named Ian Rogers
2025-12-02 17:50 ` [PATCH v9 07/48] perf jevents: Support parsing negative exponents Ian Rogers
2025-12-02 17:50 ` [PATCH v9 08/48] perf jevents: Term list fix in event parsing Ian Rogers
2025-12-02 17:50 ` [PATCH v9 09/48] perf jevents: Add threshold expressions to Metric Ian Rogers
2025-12-02 17:50 ` [PATCH v9 10/48] perf jevents: Move json encoding to its own functions Ian Rogers
2025-12-02 17:50 ` [PATCH v9 11/48] perf jevents: Drop duplicate pending metrics Ian Rogers
2025-12-02 17:50 ` [PATCH v9 12/48] perf jevents: Skip optional metrics in metric group list Ian Rogers
2025-12-02 17:50 ` [PATCH v9 13/48] perf jevents: Build support for generating metrics from python Ian Rogers
2025-12-02 17:50 ` [PATCH v9 14/48] perf jevents: Add load event json to verify and allow fallbacks Ian Rogers
2025-12-02 17:50 ` [PATCH v9 15/48] perf jevents: Add RAPL event metric for AMD zen models Ian Rogers
2025-12-02 17:50 ` [PATCH v9 16/48] perf jevents: Add idle " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 17/48] perf jevents: Add upc metric for uops per cycle for AMD Ian Rogers
2025-12-08  9:46   ` Sandipan Das
2025-12-02 17:50 ` [PATCH v9 18/48] perf jevents: Add br metric group for branch statistics on AMD Ian Rogers
2025-12-08 12:42   ` Sandipan Das
2025-12-02 17:50 ` [PATCH v9 19/48] perf jevents: Add itlb metric group for AMD Ian Rogers
2025-12-02 17:50 ` [PATCH v9 20/48] perf jevents: Add dtlb " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 21/48] perf jevents: Add uncore l3 " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 22/48] perf jevents: Add load store breakdown metrics ldst " Ian Rogers
2025-12-08  9:21   ` Sandipan Das
2025-12-02 17:50 ` [PATCH v9 23/48] perf jevents: Add context switch metrics " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 24/48] perf jevents: Add RAPL metrics for all Intel models Ian Rogers
2025-12-02 17:50 ` [PATCH v9 25/48] perf jevents: Add idle metric for " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 26/48] perf jevents: Add CheckPmu to see if a PMU is in loaded json events Ian Rogers
2025-12-02 17:50 ` [PATCH v9 27/48] perf jevents: Add smi metric group for Intel models Ian Rogers
2025-12-02 17:50 ` [PATCH v9 28/48] perf jevents: Mark metrics with experimental events as experimental Ian Rogers
2025-12-02 17:50 ` [PATCH v9 29/48] perf jevents: Add tsx metric group for Intel models Ian Rogers
2025-12-02 17:50 ` [PATCH v9 30/48] perf jevents: Add br metric group for branch statistics on Intel Ian Rogers
2025-12-02 17:50 ` [PATCH v9 31/48] perf jevents: Add software prefetch (swpf) metric group for Intel Ian Rogers
2025-12-02 17:50 ` [PATCH v9 32/48] perf jevents: Add ports metric group giving utilization on Intel Ian Rogers
2025-12-02 17:50 ` [PATCH v9 33/48] perf jevents: Add L2 metrics for Intel Ian Rogers
2025-12-02 17:50 ` [PATCH v9 34/48] perf jevents: Add load store breakdown metrics ldst " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 35/48] perf jevents: Add ILP metrics " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 36/48] perf jevents: Add context switch " Ian Rogers
2025-12-02 17:50 ` Ian Rogers [this message]
2025-12-02 17:50 ` [PATCH v9 38/48] perf jevents: Add Miss Level Parallelism (MLP) metric " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 39/48] perf jevents: Add mem_bw " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 40/48] perf jevents: Add local/remote "mem" breakdown metrics " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 41/48] perf jevents: Add dir " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 42/48] perf jevents: Add C-State metrics from the PCU PMU " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 43/48] perf jevents: Add local/remote miss latency metrics " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 44/48] perf jevents: Add upi_bw metric " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 45/48] perf jevents: Add mesh bandwidth saturation " Ian Rogers
2025-12-02 17:50 ` [PATCH v9 46/48] perf jevents: Add collection of topdown like metrics for arm64 Ian Rogers
2025-12-09 11:31   ` James Clark
2025-12-09 21:23     ` Ian Rogers
2025-12-02 17:50 ` [PATCH v9 47/48] perf jevents: Add cycles breakdown metric for arm64/AMD/Intel Ian Rogers
2025-12-02 17:50 ` [PATCH v9 48/48] perf jevents: Validate that all names given an Event Ian Rogers
2025-12-03 17:59 ` [PATCH v9 00/48] AMD, ARM, Intel metric generation with Python Namhyung Kim

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=20251202175043.623597-38-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=leo.yan@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-perf-users@vger.kernel.org \
    --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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).