Skip to contentSkip to conversation

Python generated Intel metrics

PATCH Superseded Ian Rogers 3 participants 39 messages Feb 29, 2024 – Mar 1, 2024 perf events

v1 of 7 Superseded Latest is v7 →

lore
Share & tools
lore

Ian Rogers

author reviewer
#0 lore raw

cover Python generated Intel metrics

Generate twenty sets of additional metrics for Intel. Rapl and Idle metrics aren't specific to Intel but are placed here for ease and convenience. Smi and tsx metrics are added so they can be dropped from the per model json files. There are four uncore sets of metrics and twelve core metrics.

The cstate metrics require the event encoding fix of:
https://lore.kernel.org/lkml/[email protected]/

The patches should be applied on top of:
https://lore.kernel.org/lkml/[email protected]/

Ian Rogers (20):
perf jevents: Add RAPL metrics for all Intel models perf jevents: Add idle metric for Intel models
perf jevents: Add smi metric group for Intel models perf jevents: Add tsx metric group for Intel models perf jevents: Add br metric group for branch statistics on Intel perf jevents: Add software prefetch (swpf) metric group for Intel perf jevents: Add ports metric group giving utilization on Intel perf jevents: Add L2 metrics for Intel
perf jevents: Add load store breakdown metrics ldst for Intel perf jevents: Add ILP metrics for Intel
perf jevents: Add context switch metrics for Intel perf jevents: Add FPU metrics for Intel
perf jevents: Add cycles breakdown metric for Intel perf jevents: Add Miss Level Parallelism (MLP) metric for Intel perf jevents: Add mem_bw metric for Intel
perf jevents: Add local/remote "mem" breakdown metrics for Intel perf jevents: Add dir breakdown metrics for Intel
perf jevents: Add C-State metrics from the PCU PMU for Intel perf jevents: Add local/remote miss latency metrics for Intel perf jevents: Add upi_bw metric for Intel

 tools/perf/pmu-events/intel_metrics.py | 1040 +++++++++++++++++++++++-
 1 file changed, 1037 insertions(+), 3 deletions(-)
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#1 lore raw

PATCH 1/20 perf jevents: Add RAPL metrics for all Intel models

Add a 'cpu_power' metric group that computes the power consumption from RAPL events if they are present.

---
 tools/perf/pmu-events/intel_metrics.py | 45 ++++++++++++++++++++++++--
 1 file changed, 42 insertions(+), 3 deletions(-)
tools/perf/pmu-events/intel_metrics.py +42 -3
index 4fbb31c9eccd..5827f555005f 100755
@@ -1,9 +1,10 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-from metric import (JsonEncodeMetric, JsonEncodeMetricGroupDescriptions, LoadEvents,
-                    MetricGroup)
+from metric import (d_ratio, has_event, Event, JsonEncodeMetric, JsonEncodeMetricGroupDescriptions,
+                    LoadEvents, Metric, MetricGroup, Select)
 import argparse
 import json
+import math
 import os
 
 parser = argparse.ArgumentParser(description="Intel perf json generator")
@@ -14,7 +15,45 @@ args = parser.parse_args()
 directory = f"{os.path.dirname(os.path.realpath(__file__))}/arch/x86/{args.model}/"
 LoadEvents(directory)
 
-all_metrics = MetricGroup("",[])
+interval_sec = Event("duration_time")
+
+def Rapl() -> MetricGroup:
+  """Processor socket power consumption estimate.
+
+  Use events from the running average power limit (RAPL) driver.
+  """
+  # Watts = joules/second
+  pkg = Event("power/energy\-pkg/")
+  cond_pkg = Select(pkg, has_event(pkg), math.nan)
+  cores = Event("power/energy\-cores/")
+  cond_cores = Select(cores, has_event(cores), math.nan)
+  ram = Event("power/energy\-ram/")
+  cond_ram = Select(ram, has_event(ram), math.nan)
+  gpu = Event("power/energy\-gpu/")
+  cond_gpu = Select(gpu, has_event(gpu), math.nan)
+  psys = Event("power/energy\-psys/")
+  cond_psys = Select(psys, has_event(psys), math.nan)
+  scale = 2.3283064365386962890625e-10
+  metrics = [
+      Metric("cpu_power_pkg", "",
+             d_ratio(cond_pkg * scale, interval_sec), "Watts"),
+      Metric("cpu_power_cores", "",
+             d_ratio(cond_cores * scale, interval_sec), "Watts"),
+      Metric("cpu_power_ram", "",
+             d_ratio(cond_ram * scale, interval_sec), "Watts"),
+      Metric("cpu_power_gpu", "",
+             d_ratio(cond_gpu * scale, interval_sec), "Watts"),
+      Metric("cpu_power_psys", "",
+             d_ratio(cond_psys * scale, interval_sec), "Watts"),
+  ]
+
+  return MetricGroup("cpu_power", metrics,
+                     description="Processor socket power consumption estimates")
+
+
+all_metrics = MetricGroup("", [
+    Rapl(),
+])
 
 if args.metricgroups:
   print(JsonEncodeMetricGroupDescriptions(all_metrics))
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
#2 lore raw

Re: [PATCH v1 01/20] perf jevents: Add RAPL metrics for all Intel models

Quoted 54 lines · Ian Rogers

Add a 'cpu_power' metric group that computes the power consumption from RAPL events if they are present.

---
 tools/perf/pmu-events/intel_metrics.py | 45 ++++++++++++++++++++++++--
 1 file changed, 42 insertions(+), 3 deletions(-)
tools/perf/pmu-events/intel_metrics.py +27 -3
index 4fbb31c9eccd..5827f555005f 100755
@@ -1,9 +1,10 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-from metric import (JsonEncodeMetric, JsonEncodeMetricGroupDescriptions, LoadEvents,
-                    MetricGroup)
+from metric import (d_ratio, has_event, Event, JsonEncodeMetric, JsonEncodeMetricGroupDescriptions,
+                    LoadEvents, Metric, MetricGroup, Select)
 import argparse
 import json
+import math
 import os
 
 parser = argparse.ArgumentParser(description="Intel perf json generator")
@@ -14,7 +15,45 @@ args = parser.parse_args()
 directory = f"{os.path.dirname(os.path.realpath(__file__))}/arch/x86/{args.model}/"
 LoadEvents(directory)
 
-all_metrics = MetricGroup("",[])
+interval_sec = Event("duration_time")
+
+def Rapl() -> MetricGroup:
+  """Processor socket power consumption estimate.
+
+  Use events from the running average power limit (RAPL) driver.
+  """
+  # Watts = joules/second
+  pkg = Event("power/energy\-pkg/")
+  cond_pkg = Select(pkg, has_event(pkg), math.nan)
+  cores = Event("power/energy\-cores/")
+  cond_cores = Select(cores, has_event(cores), math.nan)
+  ram = Event("power/energy\-ram/")
+  cond_ram = Select(ram, has_event(ram), math.nan)
+  gpu = Event("power/energy\-gpu/")
+  cond_gpu = Select(gpu, has_event(gpu), math.nan)
+  psys = Event("power/energy\-psys/")
+  cond_psys = Select(psys, has_event(psys), math.nan)
+  scale = 2.3283064365386962890625e-10
+  metrics = [
+      Metric("cpu_power_pkg", "",
+             d_ratio(cond_pkg * scale, interval_sec), "Watts"),
+      Metric("cpu_power_cores", "",
+             d_ratio(cond_cores * scale, interval_sec), "Watts"),

tools/perf/pmu-events/intel_metrics.py args = parser.parse_args() · line 51

Quoted 10 lines
tools/perf/pmu-events/intel_metrics.py +10 -0
+      Metric("cpu_power_ram", "",
+             d_ratio(cond_ram * scale, interval_sec), "Watts"),
+      Metric("cpu_power_gpu", "",
+             d_ratio(cond_gpu * scale, interval_sec), "Watts"),
+      Metric("cpu_power_psys", "",
+             d_ratio(cond_psys * scale, interval_sec), "Watts"),
+  ]
+
+  return MetricGroup("cpu_power", metrics,
+                     description="Processor socket power consumption estimates")

As far as I know, the RAPL counters are to monitor energy consumption across different domains. The scope may not always be a socket. I think the description may brings confusions.
Maybe we just call it "RAPL power consumption estimates", or "Running Average Power Limit (RAPL) power consumption estimates".

Thanks,
Kan

Quoted 8 lines
tools/perf/pmu-events/intel_metrics.py +5 -0
+
+
+all_metrics = MetricGroup("", [
+    Rapl(),
+])
 
 if args.metricgroups:
   print(JsonEncodeMetricGroupDescriptions(all_metrics))
author reviewer
#3 lore raw

Re: [PATCH v1 01/20] perf jevents: Add RAPL metrics for all Intel models

Quoted 66 lines · Kan
Quoted 62 lines · Ian Rogers

Add a 'cpu_power' metric group that computes the power consumption from RAPL events if they are present.

---
 tools/perf/pmu-events/intel_metrics.py | 45 ++++++++++++++++++++++++--
 1 file changed, 42 insertions(+), 3 deletions(-)
tools/perf/pmu-events/intel_metrics.py +35 -3
index 4fbb31c9eccd..5827f555005f 100755
@@ -1,9 +1,10 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-from metric import (JsonEncodeMetric, JsonEncodeMetricGroupDescriptions, LoadEvents,
-                    MetricGroup)
+from metric import (d_ratio, has_event, Event, JsonEncodeMetric, JsonEncodeMetricGroupDescriptions,
+                    LoadEvents, Metric, MetricGroup, Select)
 import argparse
 import json
+import math
 import os
 
 parser = argparse.ArgumentParser(description="Intel perf json generator")
@@ -14,7 +15,45 @@ args = parser.parse_args()
 directory = f"{os.path.dirname(os.path.realpath(__file__))}/arch/x86/{args.model}/"
 LoadEvents(directory)
 
-all_metrics = MetricGroup("",[])
+interval_sec = Event("duration_time")
+
+def Rapl() -> MetricGroup:
+  """Processor socket power consumption estimate.
+
+  Use events from the running average power limit (RAPL) driver.
+  """
+  # Watts = joules/second
+  pkg = Event("power/energy\-pkg/")
+  cond_pkg = Select(pkg, has_event(pkg), math.nan)
+  cores = Event("power/energy\-cores/")
+  cond_cores = Select(cores, has_event(cores), math.nan)
+  ram = Event("power/energy\-ram/")
+  cond_ram = Select(ram, has_event(ram), math.nan)
+  gpu = Event("power/energy\-gpu/")
+  cond_gpu = Select(gpu, has_event(gpu), math.nan)
+  psys = Event("power/energy\-psys/")
+  cond_psys = Select(psys, has_event(psys), math.nan)
+  scale = 2.3283064365386962890625e-10
+  metrics = [
+      Metric("cpu_power_pkg", "",
+             d_ratio(cond_pkg * scale, interval_sec), "Watts"),
+      Metric("cpu_power_cores", "",
+             d_ratio(cond_cores * scale, interval_sec), "Watts"),
+      Metric("cpu_power_ram", "",
+             d_ratio(cond_ram * scale, interval_sec), "Watts"),
+      Metric("cpu_power_gpu", "",
+             d_ratio(cond_gpu * scale, interval_sec), "Watts"),
+      Metric("cpu_power_psys", "",
+             d_ratio(cond_psys * scale, interval_sec), "Watts"),
+  ]
+
Quoted 8 lines

tools/perf/pmu-events/intel_metrics.py args = parser.parse_args() · line 51

Quoted 2 lines
tools/perf/pmu-events/intel_metrics.py +2 -0
+  return MetricGroup("cpu_power", metrics,
+                     description="Processor socket power consumption estimates")

As far as I know, the RAPL counters are to monitor energy consumption across different domains. The scope may not always be a socket. I think the description may brings confusions.
Maybe we just call it "RAPL power consumption estimates", or "Running Average Power Limit (RAPL) power consumption estimates".

Ack. Will fix in v2.

Thanks,
Ian

Quoted 10 lines

Thanks,
Kan

Quoted 8 lines
tools/perf/pmu-events/intel_metrics.py +5 -0
+
+
+all_metrics = MetricGroup("", [
+    Rapl(),
+])
 
 if args.metricgroups:
   print(JsonEncodeMetricGroupDescriptions(all_metrics))
author reviewer
#4 lore raw

PATCH 2/20 perf jevents: Add idle metric for Intel models

In reply to Ian Rogers

Compute using the msr PMU the percentage of wallclock cycles where the CPUs are in a low power state.

---
 tools/perf/pmu-events/intel_metrics.py | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)
tools/perf/pmu-events/intel_metrics.py +14 -2
index 5827f555005f..46866a25b166 100755
@@ -1,7 +1,8 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
-from metric import (d_ratio, has_event, Event, JsonEncodeMetric, JsonEncodeMetricGroupDescriptions,
-                    LoadEvents, Metric, MetricGroup, Select)
+from metric import (d_ratio, has_event, max, Event, JsonEncodeMetric,
+                    JsonEncodeMetricGroupDescriptions, LoadEvents, Metric,
+                    MetricGroup, Select)
 import argparse
 import json
 import math
@@ -17,6 +18,16 @@ LoadEvents(directory)
 
 interval_sec = Event("duration_time")
 
+def Idle() -> Metric:
+  cyc = Event("msr/mperf/")
+  tsc = Event("msr/tsc/")
+  low = max(tsc - cyc, 0)
+  return Metric(
+      "idle",
+      "Percentage of total wallclock cycles where CPUs are in low power state (C1 or deeper sleep state)",
+      d_ratio(low, tsc), "100%")
+
+
 def Rapl() -> MetricGroup:
   """Processor socket power consumption estimate.
 
@@ -52,6 +63,7 @@ def Rapl() -> MetricGroup:
 
 
 all_metrics = MetricGroup("", [
+    Idle(),
     Rapl(),
 ])
 
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
#5 lore raw

Re: [PATCH v1 02/20] perf jevents: Add idle metric for Intel models

tools/perf/pmu-events/intel_metrics.py LoadEvents(directory) · line 28

Quoted 8 lines
tools/perf/pmu-events/intel_metrics.py +8 -0
+def Idle() -> Metric:
+  cyc = Event("msr/mperf/")
+  tsc = Event("msr/tsc/")
+  low = max(tsc - cyc, 0)
+  return Metric(
+      "idle",
+      "Percentage of total wallclock cycles where CPUs are in low power state (C1 or deeper sleep state)",
+      d_ratio(low, tsc), "100%")

TBH I fail to see the advantage over the JSON. That's much more verbose and we don't expect to have really complex metrics anyways.

And then we have a gigantic patch kit for what gain?

The motivation was the lack of comments in JSON? We could just add some to the parser (e.g. with /* */ ). And we could allow an JSON array for the expression to get multiple lines.

-Andi

author reviewer
#6 lore raw

Re: [PATCH v1 02/20] perf jevents: Add idle metric for Intel models

Quoted 10 lines · Andi Kleen

tools/perf/pmu-events/intel_metrics.py LoadEvents(directory) · line 28

Quoted 9 lines
tools/perf/pmu-events/intel_metrics.py +8 -0
+def Idle() -> Metric:
+  cyc = Event("msr/mperf/")
+  tsc = Event("msr/tsc/")
+  low = max(tsc - cyc, 0)
+  return Metric(
+      "idle",
+      "Percentage of total wallclock cycles where CPUs are in low power state (C1 or deeper sleep state)",
+      d_ratio(low, tsc), "100%")
Quoted 2 lines

TBH I fail to see the advantage over the JSON. That's much more verbose and we don't expect to have really complex metrics anyways.

Are you saying this is more verbose or the json? Here is an example of a json metric:

https://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git/tree/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json?h=perf-tools-next#n652

```
    {
        "BriefDescription": "Probability of Core Bound bottleneck
hidden by SMT-profiling artifacts",
        "MetricExpr": "(100 * (1 - tma_core_bound /
(((EXE_ACTIVITY.EXE_BOUND_0_PORTS + tma_core_bound *
RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD *
(CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) /
CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD +
(EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring *
EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if
ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL -
CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL +
tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD)
if tma_core_bound < (((EXE_ACTIVITY.EXE_BOUND_0_PORTS + tma_core_bound
* RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD *
(CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) /
CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD +
(EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring *
EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if
ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL -
CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL +
tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD)
else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
        "MetricGroup": "Cor;SMT;TopdownL1;tma_L1_group",
        "MetricName": "tma_info_botlnk_core_bound_likely",
        "MetricgroupNoGroup": "TopdownL1"
    },
```

Even with common metrics like tma_core_bound, tma_retiring and tma_info_system_smt_2t_utilization replacing sections of the metric, I think anyone has to admit the expression is pretty unintelligible because of its size/verbosity. To understand the metric would at a first step involve adding newlines. Comments would be nice, etc.

Quoted 1 line

And then we have a gigantic patch kit for what gain?

I see some of the gains as:
- metrics that are human intelligible,
- metrics for models that are no longer being updated,
- removing copy-paste of metrics like tsx and smi across each model's
metric json (less lines-of-code),
- validation of events in a metric expression being in the event json
for a model,
- removal of forward porting metrics to a new model if the event
names of the new model line up with those of previous,
- in this patch kit there are metrics added that don't currently
exist (more metrics should be better for users - yes there can always be bugs).

I also hope the metric grouping is clearer, etc, etc.

Quoted 3 lines

The motivation was the lack of comments in JSON? We could just add some to the parser (e.g. with /* */ ). And we could allow an JSON array for the expression to get multiple lines.

Imo, a non-json variant of json would just be taking on a tech debt burden for something that is inferior to this approach and a wasted effort. We already generate the json from other more intelligible sources using python - so I don't find the approach controversial:
https://github.com/intel/perfmon/blob/main/scripts/create_perf_json.py

The goal here has been to make a bunch of inhouse metrics public. It also gives a foundation for vendors and other concerned people to add metrics in a concise, with documentation and safe (broken events cause compile time failures) way. There are some similar things like common events/metrics on ARM:
https://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git/tree/tools/perf/pmu-events/arch/arm64/arm/cmn/sys?h=perf-tools-next
but this lacks the structure, validation, documentation, etc. that's present here so my preference would be for more of the common things to be done in the python way started here.

Thanks,
Ian

Quoted 1 line

-Andi

#7 lore raw

Re: [PATCH v1 02/20] perf jevents: Add idle metric for Intel models

Quoted 13 lines

I see some of the gains as:
- metrics that are human intelligible,
- metrics for models that are no longer being updated,
- removing copy-paste of metrics like tsx and smi across each model's
metric json (less lines-of-code),
- validation of events in a metric expression being in the event json
for a model,
- removal of forward porting metrics to a new model if the event
names of the new model line up with those of previous,
- in this patch kit there are metrics added that don't currently
exist (more metrics should be better for users - yes there can always be bugs).

But then we have two ways to do things, and we already have a lot of problems with regressions from complexity and a growing bug backlog that nobody fixes.

Multiple ways to do basic operations seems just a recipe for more and more fragmentation and similar problems.

The JSON format is certainly not perfect and has its share of issues, but at least it's a standard now that is supported by many vendors and creating new standards just because you don't like some minor aspects doesn't seem like a good approach. I'm sure the next person will come around why wants Ruby metrics and the third would prefer to write them in Rust. Who knows where it will stop.

Also in my experience this python stuff is unreliable because half the people who build perf forget to install the python libraries. Json at least works always.

Incrementional improvements are usually the way to do these things.

-Andi

author reviewer
#8 lore raw

Re: [PATCH v1 02/20] perf jevents: Add idle metric for Intel models

Quoted 15 lines · Andi Kleen
Quoted 14 lines

I see some of the gains as:
- metrics that are human intelligible,
- metrics for models that are no longer being updated,
- removing copy-paste of metrics like tsx and smi across each model's
metric json (less lines-of-code),
- validation of events in a metric expression being in the event json
for a model,
- removal of forward porting metrics to a new model if the event
names of the new model line up with those of previous,
- in this patch kit there are metrics added that don't currently
exist (more metrics should be better for users - yes there can always be bugs).

Quoted 3 lines

But then we have two ways to do things, and we already have a lot of problems with regressions from complexity and a growing bug backlog that nobody fixes.

If you want something to work you put a test on it. We have a number of both event and metric tests. I'm not sure what the bug backlog you are mentioning is, but as far as I can see the tool is in the best condition it has ever been. All tests passing with address sanitizer was a particular milestone last year.

Quoted 10 lines

Multiple ways to do basic operations seems just a recipe for more and more fragmentation and similar problems.

The JSON format is certainly not perfect and has its share of issues, but at least it's a standard now that is supported by many vendors and creating new standards just because you don't like some minor aspects doesn't seem like a good approach. I'm sure the next person will come around why wants Ruby metrics and the third would prefer to write them in Rust. Who knows where it will stop.

These patches don't make the json format disappear, we use python to generate the json metrics as json strings are a poor programming language.

I agree we have too many formats, but json is part of the problem there not the solution. I would like to make the only format the sysfs one, and then we can do like a unionfs type thing in the perf tool where we can have sysfs, a sysfs layer built into the tool (out of the json) and possibly user specified layers. This would allow customizability once the binary is built, but it would also allow us to test with a sysfs for a machine we don't have. Linux on M1 macs are a particular issue, but we recently had an issue with the layout of the format directory for Intel uncore_pcu pre-Skylake which doesn't have a umask. Finding such machines to test on is the challenge, and abstracting sysfs as a unionfs type thing is, I think, the correct approach.

I don't think the Linux build has tooling around Ruby, and there are no host tools written in Rust yet. Will it happen? Probably, and I think it is good the codebase keeps moving forward. Before the C reference count checking implementation, we were talking about rewriting at least pieces like libperf in Rust - the code was leaking memory and it seemed unsolvable as reasonable fixes would yield use-after-frees and crashes. I've even mentioned this in LWN comments on articles around Rust, nobody stepped up with a fix until I did the reference count checking.

Python is a good choice for reading json as the inbuilt library is of a reasonable quality. Python is good for what I've done here as the operator overloading makes the expressions readable. We can read in and out of the python tree format, and do so in jevents.py to validate the metrics can parse (we still have the C parse test). We haven't written a full expression parser in python, although it wouldn't be hard, we just ack the string and pretty much call eval. It'd be relatively easy to add an output function to the python code to make it convert the expressions to a different programming language, for example the ToPython code here:
https://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git/tree/tools/perf/pmu-events/metric.py?h=perf-tools-next#n17

Quoted 3 lines

Also in my experience this python stuff is unreliable because half the people who build perf forget to install the python libraries. Json at least works always.

It has been the case for about a year (v6.4):
https://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.git/commit/?h=perf-tools-next&id=175f9315f76345e88e3abdc947c1e0030ab99da3
that if we can't build jevents because of python then the build fails. You can explicitly request not to use python/jevents with NO_JEVENTS=1, but it is an explicit opt-out.
I don't think this is unreliable. We've recently made BPF opt-out rather than opt-in in a similar way, and that requires clang, etc. It has been a problem in the past that implicit opt-in and opt-out could give you a perf tool that a distribution couldn't ship (mixed GPLv2 and v3 code) or that was missing useful things. I think we've fixed the bug by making the build fail unless you explicitly opt-out of options we think you should have.

Fwiw, there is a similar bug that BTF support in the kernel is opt-in rather than opt-out, meaning distributions ship BPF tools that can't work for the kernel they've built. If there were more time I'd be looking to make BTF opt-out rather than opt-in, I reported the issue on the BPF mailing list.

Quoted 2 lines

Incrementional improvements are usually the way to do these things.

We've had jevents as python for nearly 2 years. metric.py that this code is building off has been in the tree for 15 months. I wrote the code and there is a version of it for:
https://github.com/intel/perfmon/commits/main/scripts/create_perf_json.py
which is 2 years old. I don't see anything non-incremental, if anything things have been slow to move forward. It's true vendors haven't really adopted the code outside of Intel's perfmon, I've at least discussed it with them in face-to-faces like LPC. Hopefully this work is a foundation for vendors to write more metrics, it should be little more struggle than it is for them to document the metric in their manuals.

ARM have a python based json tool for perf (similar to the perfmon one) here:
https://gitlab.arm.com/telemetry-solution/telemetry-solution/-/tree/main/tools/perf_json_generator
So I'd say that python and perf json is a standard approach. ARM's converter is just over a year old.

Thanks,
Ian

Quoted 1 line

-Andi

author reviewer
#9 lore raw

PATCH 3/20 perf jevents: Add smi metric group for Intel models

In reply to Ian Rogers

Allow duplicated metric to be dropped from json files.

---
 tools/perf/pmu-events/intel_metrics.py | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)
tools/perf/pmu-events/intel_metrics.py +17 -1
index 46866a25b166..20c25d142f24 100755
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 from metric import (d_ratio, has_event, max, Event, JsonEncodeMetric,
                     JsonEncodeMetricGroupDescriptions, LoadEvents, Metric,
-                    MetricGroup, Select)
+                    MetricGroup, MetricRef, Select)
 import argparse
 import json
 import math
@@ -62,9 +62,25 @@ def Rapl() -> MetricGroup:
                      description="Processor socket power consumption estimates")
 
 
+def Smi() -> MetricGroup:
+    aperf = Event('msr/aperf/')
+    cycles = Event('cycles')
+    smi_num = Event('msr/smi/')
+    smi_cycles = Select((aperf - cycles) / aperf, smi_num > 0, 0)
+    return MetricGroup('smi', [
+        Metric('smi_num', 'Number of SMI interrupts.',
+               smi_num, 'SMI#'),
+        # Note, the smi_cycles "Event" is really a reference to the metric.
+        Metric('smi_cycles',
+               'Percentage of cycles spent in System Management Interrupts.',
+               smi_cycles, '100%', threshold=(MetricRef('smi_cycles') > 0.10))
+    ])
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
+    Smi(),
 ])
 
 if args.metricgroups:
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
#10 lore raw

Re: [PATCH v1 03/20] perf jevents: Add smi metric group for Intel models

Quoted 21 lines · Ian Rogers

Allow duplicated metric to be dropped from json files.

---
 tools/perf/pmu-events/intel_metrics.py | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)
tools/perf/pmu-events/intel_metrics.py +1 -1
index 46866a25b166..20c25d142f24 100755
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 from metric import (d_ratio, has_event, max, Event, JsonEncodeMetric,
                     JsonEncodeMetricGroupDescriptions, LoadEvents, Metric,
-                    MetricGroup, Select)
+                    MetricGroup, MetricRef, Select)
 import argparse
 import json
 import math

tools/perf/pmu-events/intel_metrics.py def Rapl() -> MetricGroup: · line 66

Quoted 5 lines
tools/perf/pmu-events/intel_metrics.py +2 -0
@@ -62,9 +62,25 @@ def Rapl() -> MetricGroup:
                      description="Processor socket power consumption estimates")
 
 
+def Smi() -> MetricGroup:
+    aperf = Event('msr/aperf/')

There are CPUID enumeration for the aperf and mperf. I believe they should be always available for a newer bare metal. But they may not be enumerated in an virtualization env. Should we add a has_event() check before using it?

Thanks,
Kan

Quoted 20 lines
tools/perf/pmu-events/intel_metrics.py +14 -0
+    cycles = Event('cycles')
+    smi_num = Event('msr/smi/')
+    smi_cycles = Select((aperf - cycles) / aperf, smi_num > 0, 0)
+    return MetricGroup('smi', [
+        Metric('smi_num', 'Number of SMI interrupts.',
+               smi_num, 'SMI#'),
+        # Note, the smi_cycles "Event" is really a reference to the metric.
+        Metric('smi_cycles',
+               'Percentage of cycles spent in System Management Interrupts.',
+               smi_cycles, '100%', threshold=(MetricRef('smi_cycles') > 0.10))
+    ])
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
+    Smi(),
 ])
 
 if args.metricgroups:
author reviewer
#11 lore raw

Re: [PATCH v1 03/20] perf jevents: Add smi metric group for Intel models

Quoted 28 lines · Kan
Quoted 24 lines · Ian Rogers

Allow duplicated metric to be dropped from json files.

---
 tools/perf/pmu-events/intel_metrics.py | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)
tools/perf/pmu-events/intel_metrics.py +1 -1
index 46866a25b166..20c25d142f24 100755
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 from metric import (d_ratio, has_event, max, Event, JsonEncodeMetric,
                     JsonEncodeMetricGroupDescriptions, LoadEvents, Metric,
-                    MetricGroup, Select)
+                    MetricGroup, MetricRef, Select)
 import argparse
 import json
 import math
@@ -62,9 +62,25 @@ def Rapl() -> MetricGroup:
                      description="Processor socket power consumption estimates")
 
 
Quoted 7 lines

tools/perf/pmu-events/intel_metrics.py def Rapl() -> MetricGroup: · line 66

Quoted 2 lines
tools/perf/pmu-events/intel_metrics.py +2 -0
+def Smi() -> MetricGroup:
+    aperf = Event('msr/aperf/')

There are CPUID enumeration for the aperf and mperf. I believe they should be always available for a newer bare metal. But they may not be enumerated in an virtualization env. Should we add a has_event() check before using it?

It would make sense to have the has_event so that the metric doesn't fail in perf test. I'll add it.

Thanks,
Ian

Quoted 23 lines

Thanks,
Kan

Quoted 20 lines
tools/perf/pmu-events/intel_metrics.py +14 -0
+    cycles = Event('cycles')
+    smi_num = Event('msr/smi/')
+    smi_cycles = Select((aperf - cycles) / aperf, smi_num > 0, 0)
+    return MetricGroup('smi', [
+        Metric('smi_num', 'Number of SMI interrupts.',
+               smi_num, 'SMI#'),
+        # Note, the smi_cycles "Event" is really a reference to the metric.
+        Metric('smi_cycles',
+               'Percentage of cycles spent in System Management Interrupts.',
+               smi_cycles, '100%', threshold=(MetricRef('smi_cycles') > 0.10))
+    ])
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
+    Smi(),
 ])
 
 if args.metricgroups:
author reviewer
#12 lore raw

PATCH 4/20 perf jevents: Add tsx metric group for Intel models

In reply to Ian Rogers

Allow duplicated metric to be dropped from json files.

---
 tools/perf/pmu-events/intel_metrics.py | 51 ++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
tools/perf/pmu-events/intel_metrics.py +51 -0
index 20c25d142f24..1096accea2aa 100755
@@ -7,6 +7,7 @@ import argparse
 import json
 import math
 import os
+from typing import Optional
 
 parser = argparse.ArgumentParser(description="Intel perf json generator")
 parser.add_argument("-metricgroups", help="Generate metricgroups data", action='store_true')
@@ -77,10 +78,60 @@ def Smi() -> MetricGroup:
     ])
 
 
+def Tsx() -> Optional[MetricGroup]:
+    if args.model not in [
+        'alderlake',
+        'cascadelakex',
+        'icelake',
+        'icelakex',
+        'rocketlake',
+        'sapphirerapids',
+        'skylake',
+        'skylakex',
+        'tigerlake',
+    ]:
+        return None
+
+    pmu = "cpu_core" if args.model == "alderlake" else "cpu"
+    cycles = Event('cycles')
+    cycles_in_tx = Event(f'{pmu}/cycles\-t/')
+    transaction_start = Event(f'{pmu}/tx\-start/')
+    cycles_in_tx_cp = Event(f'{pmu}/cycles\-ct/')
+    metrics = [
+        Metric('tsx_transactional_cycles',
+                      'Percentage of cycles within a transaction region.',
+                      Select(cycles_in_tx / cycles, has_event(cycles_in_tx), 0),
+                      '100%'),
+        Metric('tsx_aborted_cycles', 'Percentage of cycles in aborted transactions.',
+                      Select(max(cycles_in_tx - cycles_in_tx_cp, 0) / cycles,
+                                    has_event(cycles_in_tx),
+                                    0),
+                      '100%'),
+        Metric('tsx_cycles_per_transaction',
+                      'Number of cycles within a transaction divided by the number of transactions.',
+                      Select(cycles_in_tx / transaction_start,
+                                    has_event(cycles_in_tx),
+                                    0),
+                      "cycles / transaction"),
+    ]
+    if args.model != 'sapphirerapids':
+        elision_start = Event(f'{pmu}/el\-start/')
+        metrics += [
+            Metric('tsx_cycles_per_elision',
+                          'Number of cycles within a transaction divided by the number of elisions.',
+                          Select(cycles_in_tx / elision_start,
+                                        has_event(elision_start),
+                                        0),
+                          "cycles / elision"),
+        ]
+    return MetricGroup('transaction', metrics)
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
     Smi(),
+    Tsx(),
 ])
 
 if args.metricgroups:
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
#13 lore raw

Re: [PATCH v1 04/20] perf jevents: Add tsx metric group for Intel models

Quoted 24 lines · Ian Rogers

Allow duplicated metric to be dropped from json files.

---
 tools/perf/pmu-events/intel_metrics.py | 51 ++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
tools/perf/pmu-events/intel_metrics.py +2 -0
index 20c25d142f24..1096accea2aa 100755
@@ -7,6 +7,7 @@ import argparse
 import json
 import math
 import os
+from typing import Optional
 
 parser = argparse.ArgumentParser(description="Intel perf json generator")
 parser.add_argument("-metricgroups", help="Generate metricgroups data", action='store_true')
@@ -77,10 +78,60 @@ def Smi() -> MetricGroup:
     ])
 
 
+def Tsx() -> Optional[MetricGroup]:

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup: · line 91

Quoted 10 lines
tools/perf/pmu-events/intel_metrics.py +10 -0
+    if args.model not in [
+        'alderlake',
+        'cascadelakex',
+        'icelake',
+        'icelakex',
+        'rocketlake',
+        'sapphirerapids',
+        'skylake',
+        'skylakex',
+        'tigerlake',> +    ]:

Can we get ride of the model list? Otherwise, we have to keep updating the list.

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup: · line 93

Quoted 2 lines
tools/perf/pmu-events/intel_metrics.py +2 -0
+        return None
+> +    pmu = "cpu_core" if args.model == "alderlake" else "cpu"

Is it possible to change the check to the existence of the "cpu" PMU here? has_pmu("cpu") ? "cpu" : "cpu_core"

Quoted 12 lines
tools/perf/pmu-events/intel_metrics.py +12 -0
+    cycles = Event('cycles')
+    cycles_in_tx = Event(f'{pmu}/cycles\-t/')
+    transaction_start = Event(f'{pmu}/tx\-start/')
+    cycles_in_tx_cp = Event(f'{pmu}/cycles\-ct/')
+    metrics = [
+        Metric('tsx_transactional_cycles',
+                      'Percentage of cycles within a transaction region.',
+                      Select(cycles_in_tx / cycles, has_event(cycles_in_tx), 0),
+                      '100%'),
+        Metric('tsx_aborted_cycles', 'Percentage of cycles in aborted transactions.',
+                      Select(max(cycles_in_tx - cycles_in_tx_cp, 0) / cycles,
+                                    has_event(cycles_in_tx),

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup: · line 117

Quoted 10 lines
tools/perf/pmu-events/intel_metrics.py +10 -0
+                                    0),
+                      '100%'),
+        Metric('tsx_cycles_per_transaction',
+                      'Number of cycles within a transaction divided by the number of transactions.',
+                      Select(cycles_in_tx / transaction_start,
+                                    has_event(cycles_in_tx),
+                                    0),
+                      "cycles / transaction"),
+    ]
+    if args.model != 'sapphirerapids':

Add the "tsx_cycles_per_elision" metric only if
has_event(f'{pmu}/el\-start/')?

Thanks,
Kan

Quoted 20 lines
tools/perf/pmu-events/intel_metrics.py +13 -0
+        elision_start = Event(f'{pmu}/el\-start/')
+        metrics += [
+            Metric('tsx_cycles_per_elision',
+                          'Number of cycles within a transaction divided by the number of elisions.',
+                          Select(cycles_in_tx / elision_start,
+                                        has_event(elision_start),
+                                        0),
+                          "cycles / elision"),
+        ]
+    return MetricGroup('transaction', metrics)
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
     Smi(),
+    Tsx(),
 ])
 
 if args.metricgroups:
author reviewer
#14 lore raw

Re: [PATCH v1 04/20] perf jevents: Add tsx metric group for Intel models

Quoted 27 lines · Kan
Quoted 23 lines · Ian Rogers

Allow duplicated metric to be dropped from json files.

---
 tools/perf/pmu-events/intel_metrics.py | 51 ++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
tools/perf/pmu-events/intel_metrics.py +1 -0
index 20c25d142f24..1096accea2aa 100755
@@ -7,6 +7,7 @@ import argparse
 import json
 import math
 import os
+from typing import Optional
 
 parser = argparse.ArgumentParser(description="Intel perf json generator")
 parser.add_argument("-metricgroups", help="Generate metricgroups data", action='store_true')
@@ -77,10 +78,60 @@ def Smi() -> MetricGroup:
     ])
 
 
Quoted 14 lines

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup:

Quoted 11 lines
tools/perf/pmu-events/intel_metrics.py +11 -0
+def Tsx() -> Optional[MetricGroup]:
+    if args.model not in [
+        'alderlake',
+        'cascadelakex',
+        'icelake',
+        'icelakex',
+        'rocketlake',
+        'sapphirerapids',
+        'skylake',
+        'skylakex',
+        'tigerlake',> +    ]:

Can we get ride of the model list? Otherwise, we have to keep updating the list.

Do we expect the list to update? :-) The issue is the events are in sysfs and not the json. If we added the tsx events to json then this list wouldn't be necessary, but it also would mean the events would be present in "perf list" even when TSX is disabled.

Quoted 5 lines

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup: · line 93

Quoted 2 lines
tools/perf/pmu-events/intel_metrics.py +2 -0
+        return None
+> +    pmu = "cpu_core" if args.model == "alderlake" else "cpu"

Is it possible to change the check to the existence of the "cpu" PMU here? has_pmu("cpu") ? "cpu" : "cpu_core"

The "Unit" on "cpu" events in json always just blank. On hybrid it is either "cpu_core" or "cpu_atom", so I can make this something like:

pmu = "cpu_core" if metrics.HasPmu("cpu_core") else "cpu"

which would be a build time test.

Quoted 23 lines
Quoted 12 lines
tools/perf/pmu-events/intel_metrics.py +12 -0
+    cycles = Event('cycles')
+    cycles_in_tx = Event(f'{pmu}/cycles\-t/')
+    transaction_start = Event(f'{pmu}/tx\-start/')
+    cycles_in_tx_cp = Event(f'{pmu}/cycles\-ct/')
+    metrics = [
+        Metric('tsx_transactional_cycles',
+                      'Percentage of cycles within a transaction region.',
+                      Select(cycles_in_tx / cycles, has_event(cycles_in_tx), 0),
+                      '100%'),
+        Metric('tsx_aborted_cycles', 'Percentage of cycles in aborted transactions.',
+                      Select(max(cycles_in_tx - cycles_in_tx_cp, 0) / cycles,
+                                    has_event(cycles_in_tx),

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup: · line 117

Quoted 10 lines
tools/perf/pmu-events/intel_metrics.py +10 -0
+                                    0),
+                      '100%'),
+        Metric('tsx_cycles_per_transaction',
+                      'Number of cycles within a transaction divided by the number of transactions.',
+                      Select(cycles_in_tx / transaction_start,
+                                    has_event(cycles_in_tx),
+                                    0),
+                      "cycles / transaction"),
+    ]
+    if args.model != 'sapphirerapids':
Quoted 2 lines

Add the "tsx_cycles_per_elision" metric only if
has_event(f'{pmu}/el\-start/')?

It's a sysfs event, so this wouldn't work :-(

Thanks,
Ian

Quoted 23 lines

Thanks,
Kan

Quoted 20 lines
tools/perf/pmu-events/intel_metrics.py +13 -0
+        elision_start = Event(f'{pmu}/el\-start/')
+        metrics += [
+            Metric('tsx_cycles_per_elision',
+                          'Number of cycles within a transaction divided by the number of elisions.',
+                          Select(cycles_in_tx / elision_start,
+                                        has_event(elision_start),
+                                        0),
+                          "cycles / elision"),
+        ]
+    return MetricGroup('transaction', metrics)
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
     Smi(),
+    Tsx(),
 ])
 
 if args.metricgroups:
#15 lore raw

Re: [PATCH v1 04/20] perf jevents: Add tsx metric group for Intel models

Quoted 43 lines · Ian Rogers
Quoted 27 lines · Kan
Quoted 23 lines · Ian Rogers

Allow duplicated metric to be dropped from json files.

---
 tools/perf/pmu-events/intel_metrics.py | 51 ++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
tools/perf/pmu-events/intel_metrics.py +1 -0
index 20c25d142f24..1096accea2aa 100755
@@ -7,6 +7,7 @@ import argparse
 import json
 import math
 import os
+from typing import Optional
 
 parser = argparse.ArgumentParser(description="Intel perf json generator")
 parser.add_argument("-metricgroups", help="Generate metricgroups data", action='store_true')
@@ -77,10 +78,60 @@ def Smi() -> MetricGroup:
     ])
 
 
Quoted 14 lines

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup:

Quoted 11 lines
tools/perf/pmu-events/intel_metrics.py +11 -0
+def Tsx() -> Optional[MetricGroup]:
+    if args.model not in [
+        'alderlake',
+        'cascadelakex',
+        'icelake',
+        'icelakex',
+        'rocketlake',
+        'sapphirerapids',
+        'skylake',
+        'skylakex',
+        'tigerlake',> +    ]:

Can we get ride of the model list? Otherwise, we have to keep updating the list.

Quoted 1 line

Do we expect the list to update? :-)

Yes, at least for the meteorlake and graniterapids. They should be the same as alderlake and sapphirerapids. I'm not sure about the future platforms.

Maybe we can have a if args.model in list here to include all the non-hybrid models which doesn't support TSX. I think the list should not be changed shortly.

Quoted 4 lines

The issue is the events are in
sysfs and not the json. If we added the tsx events to json then this list wouldn't be necessary, but it also would mean the events would be present in "perf list" even when TSX is disabled.

I think there may an alternative way, to check the RTM events, e.g., RTM_RETIRED.START event. We only need to generate the metrics for the platform which supports the RTM_RETIRED.START event.

Quoted 7 lines
Quoted 6 lines

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup: · line 93

Quoted 3 lines
tools/perf/pmu-events/intel_metrics.py +2 -0
+        return None
+> +    pmu = "cpu_core" if args.model == "alderlake" else "cpu"

Is it possible to change the check to the existence of the "cpu" PMU here? has_pmu("cpu") ? "cpu" : "cpu_core"

Quoted 6 lines

The "Unit" on "cpu" events in json always just blank. On hybrid it is either "cpu_core" or "cpu_atom", so I can make this something like:

pmu = "cpu_core" if metrics.HasPmu("cpu_core") else "cpu"

which would be a build time test.

Yes, I think using the "Unit" is good enough.

Quoted 25 lines
Quoted 25 lines
Quoted 24 lines
tools/perf/pmu-events/intel_metrics.py +22 -0
+    cycles = Event('cycles')
+    cycles_in_tx = Event(f'{pmu}/cycles\-t/')
+    transaction_start = Event(f'{pmu}/tx\-start/')
+    cycles_in_tx_cp = Event(f'{pmu}/cycles\-ct/')
+    metrics = [
+        Metric('tsx_transactional_cycles',
+                      'Percentage of cycles within a transaction region.',
+                      Select(cycles_in_tx / cycles, has_event(cycles_in_tx), 0),
+                      '100%'),
+        Metric('tsx_aborted_cycles', 'Percentage of cycles in aborted transactions.',
+                      Select(max(cycles_in_tx - cycles_in_tx_cp, 0) / cycles,
+                                    has_event(cycles_in_tx),
+                                    0),
+                      '100%'),
+        Metric('tsx_cycles_per_transaction',
+                      'Number of cycles within a transaction divided by the number of transactions.',
+                      Select(cycles_in_tx / transaction_start,
+                                    has_event(cycles_in_tx),
+                                    0),
+                      "cycles / transaction"),
+    ]
+    if args.model != 'sapphirerapids':
Quoted 4 lines
Quoted 2 lines

Add the "tsx_cycles_per_elision" metric only if
has_event(f'{pmu}/el\-start/')?

It's a sysfs event, so this wouldn't work :-(

The below is the definition of el-start in the kernel.
EVENT_ATTR_STR(el-start, el_start, "event=0xc8,umask=0x1");

The corresponding event in the event list should be HLE_RETIRED.START

      "EventCode": "0xC8",
      "UMask": "0x01",
      "EventName": "HLE_RETIRED.START",

I think we may check the HLE_RETIRED.START instead. If the HLE_RETIRED.START doesn't exist, I don't see a reason why the tsx_cycles_per_elision should be supported.

Again, in the virtualization world, it's possible that the HLE_RETIRED.START exists in the event list but el_start isn't available in the sysfs. I think it has to be specially handle in the test as well.

Thanks,
Kan

Quoted 28 lines

Thanks,
Ian

Quoted 23 lines

Thanks,
Kan

Quoted 20 lines
tools/perf/pmu-events/intel_metrics.py +13 -0
+        elision_start = Event(f'{pmu}/el\-start/')
+        metrics += [
+            Metric('tsx_cycles_per_elision',
+                          'Number of cycles within a transaction divided by the number of elisions.',
+                          Select(cycles_in_tx / elision_start,
+                                        has_event(elision_start),
+                                        0),
+                          "cycles / elision"),
+        ]
+    return MetricGroup('transaction', metrics)
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
     Smi(),
+    Tsx(),
 ])
 
 if args.metricgroups:
author reviewer
#16 lore raw

Re: [PATCH v1 04/20] perf jevents: Add tsx metric group for Intel models

Quoted 121 lines · Kan
Quoted 43 lines · Ian Rogers
Quoted 27 lines · Kan
Quoted 23 lines · Ian Rogers

Allow duplicated metric to be dropped from json files.

---
 tools/perf/pmu-events/intel_metrics.py | 51 ++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
tools/perf/pmu-events/intel_metrics.py +1 -0
index 20c25d142f24..1096accea2aa 100755
@@ -7,6 +7,7 @@ import argparse
 import json
 import math
 import os
+from typing import Optional
 
 parser = argparse.ArgumentParser(description="Intel perf json generator")
 parser.add_argument("-metricgroups", help="Generate metricgroups data", action='store_true')
@@ -77,10 +78,60 @@ def Smi() -> MetricGroup:
     ])
 
 
Quoted 14 lines

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup:

Quoted 11 lines
tools/perf/pmu-events/intel_metrics.py +11 -0
+def Tsx() -> Optional[MetricGroup]:
+    if args.model not in [
+        'alderlake',
+        'cascadelakex',
+        'icelake',
+        'icelakex',
+        'rocketlake',
+        'sapphirerapids',
+        'skylake',
+        'skylakex',
+        'tigerlake',> +    ]:

Can we get ride of the model list? Otherwise, we have to keep updating the list.

Quoted 1 line

Do we expect the list to update? :-)

Yes, at least for the meteorlake and graniterapids. They should be the same as alderlake and sapphirerapids. I'm not sure about the future platforms.

Maybe we can have a if args.model in list here to include all the non-hybrid models which doesn't support TSX. I think the list should not be changed shortly.

Quoted 4 lines

The issue is the events are in
sysfs and not the json. If we added the tsx events to json then this list wouldn't be necessary, but it also would mean the events would be present in "perf list" even when TSX is disabled.

I think there may an alternative way, to check the RTM events, e.g., RTM_RETIRED.START event. We only need to generate the metrics for the platform which supports the RTM_RETIRED.START event.

Quoted 7 lines
Quoted 6 lines

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup: · line 93

Quoted 3 lines
tools/perf/pmu-events/intel_metrics.py +2 -0
+        return None
+> +    pmu = "cpu_core" if args.model == "alderlake" else "cpu"

Is it possible to change the check to the existence of the "cpu" PMU here? has_pmu("cpu") ? "cpu" : "cpu_core"

Quoted 6 lines

The "Unit" on "cpu" events in json always just blank. On hybrid it is either "cpu_core" or "cpu_atom", so I can make this something like:

pmu = "cpu_core" if metrics.HasPmu("cpu_core") else "cpu"

which would be a build time test.

Yes, I think using the "Unit" is good enough.

Quoted 25 lines
Quoted 25 lines
Quoted 24 lines
tools/perf/pmu-events/intel_metrics.py +22 -0
+    cycles = Event('cycles')
+    cycles_in_tx = Event(f'{pmu}/cycles\-t/')
+    transaction_start = Event(f'{pmu}/tx\-start/')
+    cycles_in_tx_cp = Event(f'{pmu}/cycles\-ct/')
+    metrics = [
+        Metric('tsx_transactional_cycles',
+                      'Percentage of cycles within a transaction region.',
+                      Select(cycles_in_tx / cycles, has_event(cycles_in_tx), 0),
+                      '100%'),
+        Metric('tsx_aborted_cycles', 'Percentage of cycles in aborted transactions.',
+                      Select(max(cycles_in_tx - cycles_in_tx_cp, 0) / cycles,
+                                    has_event(cycles_in_tx),
+                                    0),
+                      '100%'),
+        Metric('tsx_cycles_per_transaction',
+                      'Number of cycles within a transaction divided by the number of transactions.',
+                      Select(cycles_in_tx / transaction_start,
+                                    has_event(cycles_in_tx),
+                                    0),
+                      "cycles / transaction"),
+    ]
+    if args.model != 'sapphirerapids':
Quoted 4 lines
Quoted 2 lines

Add the "tsx_cycles_per_elision" metric only if
has_event(f'{pmu}/el\-start/')?

It's a sysfs event, so this wouldn't work :-(

The below is the definition of el-start in the kernel.
EVENT_ATTR_STR(el-start, el_start, "event=0xc8,umask=0x1");

The corresponding event in the event list should be HLE_RETIRED.START

      "EventCode": "0xC8",
      "UMask": "0x01",
      "EventName": "HLE_RETIRED.START",
Quoted 7 lines

I think we may check the HLE_RETIRED.START instead. If the HLE_RETIRED.START doesn't exist, I don't see a reason why the tsx_cycles_per_elision should be supported.

Again, in the virtualization world, it's possible that the HLE_RETIRED.START exists in the event list but el_start isn't available in the sysfs. I think it has to be specially handle in the test as well.

So we keep the has_event test on the sysfs event to handle the virtualization and disabled case. We use HLE_RETIRED.START to detect whether the model supports TSX. Should the event be the sysfs or json version? i.e.

        "MetricExpr": "(cycles\\-t / el\\-start if

has_event(el\\-start) else 0)",

or

"MetricExpr": "(cycles\\-t / HLE_RETIRED.START if
has_event(el\\-start) else 0)",

I think I favor the former for some consistency with the has_event.

Using HLE_RETIRED.START means the set of TSX models goes from:

        'alderlake',
        'cascadelakex',
        'icelake',
        'icelakex',
        'rocketlake',
        'sapphirerapids',
        'skylake',
        'skylakex',
        'tigerlake',

To:
broadwell
broadwellde
broadwellx
cascadelakex
haswell
haswellx
icelake
rocketlake
skylake
skylakex

Using RTM_RETIRED.START it goes to:
broadwell
broadwellde
broadwellx
cascadelakex
emeraldrapids
graniterapids
haswell
haswellx
icelake
icelakex
rocketlake
sapphirerapids
skylake
skylakex
tigerlake

So I'm not sure it is working equivalently to what we have today, which may be good or bad. Here is what I think the code should look like:

def Tsx() -> Optional[MetricGroup]:
pmu = "cpu_core" if CheckPmu("cpu_core") else "cpu" cycles = Event('cycles')
cycles_in_tx = Event(f'{pmu}/cycles\-t/') cycles_in_tx_cp = Event(f'{pmu}/cycles\-ct/')
try:
# Test if the tsx event is present in the json, prefer the # sysfs version so that we can detect its presence at runtime. transaction_start = Event("RTM_RETIRED.START") transaction_start = Event(f'{pmu}/tx\-start/')
except:
return None

elision_start = None
try:
# Elision start isn't supported by all models, but we'll not # generate the tsx_cycles_per_elision metric in that # case. Again, prefer the sysfs encoding of the event. elision_start = Event("HLE_RETIRED.START") elision_start = Event(f'{pmu}/el\-start/')
except:
pass

return MetricGroup('transaction', [
Metric('tsx_transactional_cycles',
'Percentage of cycles within a transaction region.', Select(cycles_in_tx / cycles, has_event(cycles_in_tx), 0), '100%'),
Metric('tsx_aborted_cycles', 'Percentage of cycles in aborted
transactions.',
Select(max(cycles_in_tx - cycles_in_tx_cp, 0) / cycles,
has_event(cycles_in_tx),
0),
'100%'),
Metric('tsx_cycles_per_transaction',
'Number of cycles within a transaction divided by the
number of transactions.',
Select(cycles_in_tx / transaction_start,
has_event(cycles_in_tx),
0),
"cycles / transaction"),
Metric('tsx_cycles_per_elision',
'Number of cycles within a transaction divided by the
number of elisions.',
Select(cycles_in_tx / elision_start,
has_event(elision_start),
0),
"cycles / elision") if elision_start else None,
], description="Breakdown of transactional memory statistics")

Wdyt?

Thanks,
Ian

Quoted 31 lines

Thanks,
Kan

Quoted 28 lines

Thanks,
Ian

Quoted 23 lines

Thanks,
Kan

Quoted 20 lines
tools/perf/pmu-events/intel_metrics.py +13 -0
+        elision_start = Event(f'{pmu}/el\-start/')
+        metrics += [
+            Metric('tsx_cycles_per_elision',
+                          'Number of cycles within a transaction divided by the number of elisions.',
+                          Select(cycles_in_tx / elision_start,
+                                        has_event(elision_start),
+                                        0),
+                          "cycles / elision"),
+        ]
+    return MetricGroup('transaction', metrics)
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
     Smi(),
+    Tsx(),
 ])
 
 if args.metricgroups:
#17 lore raw

Re: [PATCH v1 04/20] perf jevents: Add tsx metric group for Intel models

Quoted 126 lines · Ian Rogers
Quoted 125 lines · Kan
Quoted 43 lines · Ian Rogers
Quoted 27 lines · Kan
Quoted 23 lines · Ian Rogers

Allow duplicated metric to be dropped from json files.

---
 tools/perf/pmu-events/intel_metrics.py | 51 ++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)
tools/perf/pmu-events/intel_metrics.py +1 -0
index 20c25d142f24..1096accea2aa 100755
@@ -7,6 +7,7 @@ import argparse
 import json
 import math
 import os
+from typing import Optional
 
 parser = argparse.ArgumentParser(description="Intel perf json generator")
 parser.add_argument("-metricgroups", help="Generate metricgroups data", action='store_true')
@@ -77,10 +78,60 @@ def Smi() -> MetricGroup:
     ])
 
 
Quoted 14 lines

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup:

Quoted 11 lines
tools/perf/pmu-events/intel_metrics.py +11 -0
+def Tsx() -> Optional[MetricGroup]:
+    if args.model not in [
+        'alderlake',
+        'cascadelakex',
+        'icelake',
+        'icelakex',
+        'rocketlake',
+        'sapphirerapids',
+        'skylake',
+        'skylakex',
+        'tigerlake',> +    ]:

Can we get ride of the model list? Otherwise, we have to keep updating the list.

Quoted 1 line

Do we expect the list to update? :-)

Yes, at least for the meteorlake and graniterapids. They should be the same as alderlake and sapphirerapids. I'm not sure about the future platforms.

Maybe we can have a if args.model in list here to include all the non-hybrid models which doesn't support TSX. I think the list should not be changed shortly.

Quoted 4 lines

The issue is the events are in
sysfs and not the json. If we added the tsx events to json then this list wouldn't be necessary, but it also would mean the events would be present in "perf list" even when TSX is disabled.

I think there may an alternative way, to check the RTM events, e.g., RTM_RETIRED.START event. We only need to generate the metrics for the platform which supports the RTM_RETIRED.START event.

Quoted 7 lines
Quoted 6 lines

tools/perf/pmu-events/intel_metrics.py def Smi() -> MetricGroup: · line 93

Quoted 3 lines
tools/perf/pmu-events/intel_metrics.py +2 -0
+        return None
+> +    pmu = "cpu_core" if args.model == "alderlake" else "cpu"

Is it possible to change the check to the existence of the "cpu" PMU here? has_pmu("cpu") ? "cpu" : "cpu_core"

Quoted 6 lines

The "Unit" on "cpu" events in json always just blank. On hybrid it is either "cpu_core" or "cpu_atom", so I can make this something like:

pmu = "cpu_core" if metrics.HasPmu("cpu_core") else "cpu"

which would be a build time test.

Yes, I think using the "Unit" is good enough.

Quoted 25 lines
Quoted 25 lines
Quoted 24 lines
tools/perf/pmu-events/intel_metrics.py +22 -0
+    cycles = Event('cycles')
+    cycles_in_tx = Event(f'{pmu}/cycles\-t/')
+    transaction_start = Event(f'{pmu}/tx\-start/')
+    cycles_in_tx_cp = Event(f'{pmu}/cycles\-ct/')
+    metrics = [
+        Metric('tsx_transactional_cycles',
+                      'Percentage of cycles within a transaction region.',
+                      Select(cycles_in_tx / cycles, has_event(cycles_in_tx), 0),
+                      '100%'),
+        Metric('tsx_aborted_cycles', 'Percentage of cycles in aborted transactions.',
+                      Select(max(cycles_in_tx - cycles_in_tx_cp, 0) / cycles,
+                                    has_event(cycles_in_tx),
+                                    0),
+                      '100%'),
+        Metric('tsx_cycles_per_transaction',
+                      'Number of cycles within a transaction divided by the number of transactions.',
+                      Select(cycles_in_tx / transaction_start,
+                                    has_event(cycles_in_tx),
+                                    0),
+                      "cycles / transaction"),
+    ]
+    if args.model != 'sapphirerapids':
Quoted 4 lines
Quoted 2 lines

Add the "tsx_cycles_per_elision" metric only if
has_event(f'{pmu}/el\-start/')?

It's a sysfs event, so this wouldn't work :-(

The below is the definition of el-start in the kernel.
EVENT_ATTR_STR(el-start, el_start, "event=0xc8,umask=0x1");

The corresponding event in the event list should be HLE_RETIRED.START

      "EventCode": "0xC8",
      "UMask": "0x01",
      "EventName": "HLE_RETIRED.START",

I think we may check the HLE_RETIRED.START instead. If the HLE_RETIRED.START doesn't exist, I don't see a reason why the tsx_cycles_per_elision should be supported.

Quoted 7 lines
Quoted 3 lines

Again, in the virtualization world, it's possible that the HLE_RETIRED.START exists in the event list but el_start isn't available in the sysfs. I think it has to be specially handle in the test as well.

So we keep the has_event test on the sysfs event to handle the virtualization and disabled case. We use HLE_RETIRED.START to detect whether the model supports TSX.

Yes. I think the JSON event always keeps the latest status of an event. If an event is deprecated someday, I don't think there is a reason to keep any metrics including the event. So we should use it to check whether to generate a metrics.

The sysfs event tells if the current kernel support the event. It should be used to check whether a metrics should be used/enabled.

Quoted 4 lines

Should the event be the sysfs or json
version? i.e.

        "MetricExpr": "(cycles\\-t / el\\-start if
Quoted 9 lines

has_event(el\\-start) else 0)",

or

"MetricExpr": "(cycles\\-t / HLE_RETIRED.START if
has_event(el\\-start) else 0)",

I think I favor the former for some consistency with the has_event.

Agree, the former looks good to me too.

Quoted 40 lines

Using HLE_RETIRED.START means the set of TSX models goes from:

        'alderlake',
        'cascadelakex',
        'icelake',
        'icelakex',
        'rocketlake',
        'sapphirerapids',
        'skylake',
        'skylakex',
        'tigerlake',

To:
broadwell
broadwellde
broadwellx
cascadelakex
haswell
haswellx
icelake
rocketlake
skylake
skylakex

Using RTM_RETIRED.START it goes to:
broadwell
broadwellde
broadwellx
cascadelakex
emeraldrapids
graniterapids
haswell
haswellx
icelake
icelakex
rocketlake
sapphirerapids
skylake
skylakex
tigerlake

Quoted 3 lines

So I'm not sure it is working equivalently to what we have today, which may be good or bad. Here is what I think the code should look like:

Yes, there should be some changes. But I think the changes should be good.

For icelakex, the HLE_RETIRED.START has been deprecated. I don't see a reason why should perf keep the tsx_cycles_per_elision metric.

For alderlake, TSX is deprecated. The perf should drop the related metrics as well.
https://edc.intel.com/content/www/us/en/design/ipla/software-development-platforms/client/platforms/alder-lake-desktop/12th-generation-intel-core-processors-datasheet-volume-1-of-2/001/deprecated-technologies/

Quoted 51 lines

def Tsx() -> Optional[MetricGroup]:
pmu = "cpu_core" if CheckPmu("cpu_core") else "cpu" cycles = Event('cycles')
cycles_in_tx = Event(f'{pmu}/cycles\-t/') cycles_in_tx_cp = Event(f'{pmu}/cycles\-ct/')
try:
# Test if the tsx event is present in the json, prefer the # sysfs version so that we can detect its presence at runtime. transaction_start = Event("RTM_RETIRED.START") transaction_start = Event(f'{pmu}/tx\-start/')
except:
return None

elision_start = None
try:
# Elision start isn't supported by all models, but we'll not # generate the tsx_cycles_per_elision metric in that # case. Again, prefer the sysfs encoding of the event. elision_start = Event("HLE_RETIRED.START") elision_start = Event(f'{pmu}/el\-start/')
except:
pass

return MetricGroup('transaction', [
Metric('tsx_transactional_cycles',
'Percentage of cycles within a transaction region.', Select(cycles_in_tx / cycles, has_event(cycles_in_tx), 0), '100%'),
Metric('tsx_aborted_cycles', 'Percentage of cycles in aborted
transactions.',
Select(max(cycles_in_tx - cycles_in_tx_cp, 0) / cycles,
has_event(cycles_in_tx),
0),
'100%'),
Metric('tsx_cycles_per_transaction',
'Number of cycles within a transaction divided by the
number of transactions.',
Select(cycles_in_tx / transaction_start,
has_event(cycles_in_tx),
0),
"cycles / transaction"),
Metric('tsx_cycles_per_elision',
'Number of cycles within a transaction divided by the
number of elisions.',
Select(cycles_in_tx / elision_start,
has_event(elision_start),
0),
"cycles / elision") if elision_start else None,
], description="Breakdown of transactional memory statistics")

Quoted 1 line

Wdyt?

Looks good to me.

Thanks,
Kan

Quoted 35 lines

Thanks,
Ian

Quoted 31 lines

Thanks,
Kan

Quoted 28 lines

Thanks,
Ian

Quoted 23 lines

Thanks,
Kan

Quoted 20 lines
tools/perf/pmu-events/intel_metrics.py +13 -0
+        elision_start = Event(f'{pmu}/el\-start/')
+        metrics += [
+            Metric('tsx_cycles_per_elision',
+                          'Number of cycles within a transaction divided by the number of elisions.',
+                          Select(cycles_in_tx / elision_start,
+                                        has_event(elision_start),
+                                        0),
+                          "cycles / elision"),
+        ]
+    return MetricGroup('transaction', metrics)
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
     Smi(),
+    Tsx(),
 ])
 
 if args.metricgroups:
author reviewer
#18 lore raw

PATCH 5/20 perf jevents: Add br metric group for branch statistics on Intel

In reply to Ian Rogers

The br metric group for branches itself comprises metric groups for total, taken, conditional, fused and far metric groups using json events. Condtional taken and not taken metrics are specific to Icelake and later generations, so a model to generation look up is added.

---
 tools/perf/pmu-events/intel_metrics.py | 139 +++++++++++++++++++++++++
 1 file changed, 139 insertions(+)
tools/perf/pmu-events/intel_metrics.py +139 -0
index 1096accea2aa..bee5da19d19d 100755
@@ -19,6 +19,7 @@ LoadEvents(directory)
 
 interval_sec = Event("duration_time")
 
+
 def Idle() -> Metric:
   cyc = Event("msr/mperf/")
   tsc = Event("msr/tsc/")
@@ -127,11 +128,149 @@ def Tsx() -> Optional[MetricGroup]:
     return MetricGroup('transaction', metrics)
 
 
+def IntelBr():
+  ins = Event("instructions")
+
+  def Total() -> MetricGroup:
+    br_all = Event ("BR_INST_RETIRED.ALL_BRANCHES", "BR_INST_RETIRED.ANY")
+    br_m_all = Event("BR_MISP_RETIRED.ALL_BRANCHES",
+                     "BR_INST_RETIRED.MISPRED",
+                     "BR_MISP_EXEC.ANY")
+    br_clr = None
+    try:
+      br_clr = Event("BACLEARS.ANY", "BACLEARS.ALL")
+    except:
+      pass
+
+    br_r = d_ratio(br_all, interval_sec)
+    ins_r = d_ratio(ins, br_all)
+    misp_r = d_ratio(br_m_all, br_all)
+    clr_r = d_ratio(br_clr, interval_sec) if br_clr else None
+
+    return MetricGroup("br_total", [
+        Metric("br_total_retired",
+               "The number of branch instructions retired per second.", br_r,
+               "insn/s"),
+        Metric(
+            "br_total_mispred",
+            "The number of branch instructions retired, of any type, that were "
+            "not correctly predicted as a percentage of all branch instrucions.",
+            misp_r, "100%"),
+        Metric("br_total_insn_between_branches",
+               "The number of instructions divided by the number of branches.",
+               ins_r, "insn"),
+        Metric("br_total_insn_fe_resteers",
+               "The number of resync branches per second.", clr_r, "req/s"
+               ) if clr_r else None
+    ])
+
+  def Taken() -> MetricGroup:
+    br_all = Event("BR_INST_RETIRED.ALL_BRANCHES", "BR_INST_RETIRED.ANY")
+    br_m_tk = None
+    try:
+      br_m_tk = Event("BR_MISP_RETIRED.NEAR_TAKEN",
+                      "BR_MISP_RETIRED.TAKEN_JCC",
+                      "BR_INST_RETIRED.MISPRED_TAKEN")
+    except:
+      pass
+    br_r = d_ratio(br_all, interval_sec)
+    ins_r = d_ratio(ins, br_all)
+    misp_r = d_ratio(br_m_tk, br_all) if br_m_tk else None
+    return MetricGroup("br_taken", [
+        Metric("br_taken_retired",
+               "The number of taken branches that were retired per second.",
+               br_r, "insn/s"),
+        Metric(
+            "br_taken_mispred",
+            "The number of retired taken branch instructions that were "
+            "mispredicted as a percentage of all taken branches.", misp_r,
+            "100%") if misp_r else None,
+        Metric(
+            "br_taken_insn_between_branches",
+            "The number of instructions divided by the number of taken branches.",
+            ins_r, "insn"),
+    ])
+
+  def Conditional() -> Optional[MetricGroup]:
+    try:
+      br_cond = Event("BR_INST_RETIRED.COND",
+                      "BR_INST_RETIRED.CONDITIONAL",
+                      "BR_INST_RETIRED.TAKEN_JCC")
+      br_m_cond = Event("BR_MISP_RETIRED.COND",
+                        "BR_MISP_RETIRED.CONDITIONAL",
+                        "BR_MISP_RETIRED.TAKEN_JCC")
+    except:
+      return None
+
+    br_cond_nt = None
+    br_m_cond_nt = None
+    try:
+      br_cond_nt = Event("BR_INST_RETIRED.COND_NTAKEN")
+      br_m_cond_nt = Event("BR_MISP_RETIRED.COND_NTAKEN")
+    except:
+      pass
+    br_r = d_ratio(br_cond, interval_sec)
+    ins_r = d_ratio(ins, br_cond)
+    misp_r = d_ratio(br_m_cond, br_cond)
+    taken_metrics = [
+        Metric("br_cond_retired", "Retired conditional branch instructions.",
+               br_r, "insn/s"),
+        Metric("br_cond_insn_between_branches",
+               "The number of instructions divided by the number of conditional "
+               "branches.", ins_r, "insn"),
+        Metric("br_cond_mispred",
+               "Retired conditional branch instructions mispredicted as a "
+               "percentage of all conditional branches.", misp_r, "100%"),
+    ]
+    if not br_m_cond_nt:
+      return MetricGroup("br_cond", taken_metrics)
+
+    br_r = d_ratio(br_cond_nt, interval_sec)
+    ins_r = d_ratio(ins, br_cond_nt)
+    misp_r = d_ratio(br_m_cond_nt, br_cond_nt)
+
+    not_taken_metrics = [
+        Metric("br_cond_retired", "Retired conditional not taken branch instructions.",
+               br_r, "insn/s"),
+        Metric("br_cond_insn_between_branches",
+               "The number of instructions divided by the number of not taken conditional "
+               "branches.", ins_r, "insn"),
+        Metric("br_cond_mispred",
+               "Retired not taken conditional branch instructions mispredicted as a "
+               "percentage of all not taken conditional branches.", misp_r, "100%"),
+    ]
+    return MetricGroup("br_cond", [
+        MetricGroup("br_cond_nt", not_taken_metrics),
+        MetricGroup("br_cond_tkn", taken_metrics),
+    ])
+
+  def Far() -> Optional[MetricGroup]:
+    try:
+      br_far = Event("BR_INST_RETIRED.FAR_BRANCH")
+    except:
+      return None
+
+    br_r = d_ratio(br_far, interval_sec)
+    ins_r = d_ratio(ins, br_far)
+    return MetricGroup("br_far", [
+        Metric("br_far_retired", "Retired far control transfers per second.",
+               br_r, "insn/s"),
+        Metric(
+            "br_far_insn_between_branches",
+            "The number of instructions divided by the number of far branches.",
+            ins_r, "insn"),
+    ])
+
+  return MetricGroup("br", [Total(), Taken(), Conditional(), Far()],
+                     description="breakdown of retired branch instructions")
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
     Smi(),
     Tsx(),
+    IntelBr(),
 ])
 
 if args.metricgroups:
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
#19 lore raw

Re: [PATCH v1 05/20] perf jevents: Add br metric group for branch statistics on Intel

Quoted 15 lines · Ian Rogers

The br metric group for branches itself comprises metric groups for total, taken, conditional, fused and far metric groups using json events. Condtional taken and not taken metrics are specific to Icelake and later generations, so a model to generation look up is added.

---
 tools/perf/pmu-events/intel_metrics.py | 139 +++++++++++++++++++++++++
 1 file changed, 139 insertions(+)
tools/perf/pmu-events/intel_metrics.py +0 -0
index 1096accea2aa..bee5da19d19d 100755

tools/perf/pmu-events/intel_metrics.py LoadEvents(directory) · line 22

Quoted 4 lines
tools/perf/pmu-events/intel_metrics.py +1 -0
@@ -19,6 +19,7 @@ LoadEvents(directory)
 
 interval_sec = Event("duration_time")
 
+

Unnecessary empty line.

Thanks,
Kan

Quoted 153 lines
tools/perf/pmu-events/intel_metrics.py +138 -0
 def Idle() -> Metric:
   cyc = Event("msr/mperf/")
   tsc = Event("msr/tsc/")
@@ -127,11 +128,149 @@ def Tsx() -> Optional[MetricGroup]:
     return MetricGroup('transaction', metrics)
 
 
+def IntelBr():
+  ins = Event("instructions")
+
+  def Total() -> MetricGroup:
+    br_all = Event ("BR_INST_RETIRED.ALL_BRANCHES", "BR_INST_RETIRED.ANY")
+    br_m_all = Event("BR_MISP_RETIRED.ALL_BRANCHES",
+                     "BR_INST_RETIRED.MISPRED",
+                     "BR_MISP_EXEC.ANY")
+    br_clr = None
+    try:
+      br_clr = Event("BACLEARS.ANY", "BACLEARS.ALL")
+    except:
+      pass
+
+    br_r = d_ratio(br_all, interval_sec)
+    ins_r = d_ratio(ins, br_all)
+    misp_r = d_ratio(br_m_all, br_all)
+    clr_r = d_ratio(br_clr, interval_sec) if br_clr else None
+
+    return MetricGroup("br_total", [
+        Metric("br_total_retired",
+               "The number of branch instructions retired per second.", br_r,
+               "insn/s"),
+        Metric(
+            "br_total_mispred",
+            "The number of branch instructions retired, of any type, that were "
+            "not correctly predicted as a percentage of all branch instrucions.",
+            misp_r, "100%"),
+        Metric("br_total_insn_between_branches",
+               "The number of instructions divided by the number of branches.",
+               ins_r, "insn"),
+        Metric("br_total_insn_fe_resteers",
+               "The number of resync branches per second.", clr_r, "req/s"
+               ) if clr_r else None
+    ])
+
+  def Taken() -> MetricGroup:
+    br_all = Event("BR_INST_RETIRED.ALL_BRANCHES", "BR_INST_RETIRED.ANY")
+    br_m_tk = None
+    try:
+      br_m_tk = Event("BR_MISP_RETIRED.NEAR_TAKEN",
+                      "BR_MISP_RETIRED.TAKEN_JCC",
+                      "BR_INST_RETIRED.MISPRED_TAKEN")
+    except:
+      pass
+    br_r = d_ratio(br_all, interval_sec)
+    ins_r = d_ratio(ins, br_all)
+    misp_r = d_ratio(br_m_tk, br_all) if br_m_tk else None
+    return MetricGroup("br_taken", [
+        Metric("br_taken_retired",
+               "The number of taken branches that were retired per second.",
+               br_r, "insn/s"),
+        Metric(
+            "br_taken_mispred",
+            "The number of retired taken branch instructions that were "
+            "mispredicted as a percentage of all taken branches.", misp_r,
+            "100%") if misp_r else None,
+        Metric(
+            "br_taken_insn_between_branches",
+            "The number of instructions divided by the number of taken branches.",
+            ins_r, "insn"),
+    ])
+
+  def Conditional() -> Optional[MetricGroup]:
+    try:
+      br_cond = Event("BR_INST_RETIRED.COND",
+                      "BR_INST_RETIRED.CONDITIONAL",
+                      "BR_INST_RETIRED.TAKEN_JCC")
+      br_m_cond = Event("BR_MISP_RETIRED.COND",
+                        "BR_MISP_RETIRED.CONDITIONAL",
+                        "BR_MISP_RETIRED.TAKEN_JCC")
+    except:
+      return None
+
+    br_cond_nt = None
+    br_m_cond_nt = None
+    try:
+      br_cond_nt = Event("BR_INST_RETIRED.COND_NTAKEN")
+      br_m_cond_nt = Event("BR_MISP_RETIRED.COND_NTAKEN")
+    except:
+      pass
+    br_r = d_ratio(br_cond, interval_sec)
+    ins_r = d_ratio(ins, br_cond)
+    misp_r = d_ratio(br_m_cond, br_cond)
+    taken_metrics = [
+        Metric("br_cond_retired", "Retired conditional branch instructions.",
+               br_r, "insn/s"),
+        Metric("br_cond_insn_between_branches",
+               "The number of instructions divided by the number of conditional "
+               "branches.", ins_r, "insn"),
+        Metric("br_cond_mispred",
+               "Retired conditional branch instructions mispredicted as a "
+               "percentage of all conditional branches.", misp_r, "100%"),
+    ]
+    if not br_m_cond_nt:
+      return MetricGroup("br_cond", taken_metrics)
+
+    br_r = d_ratio(br_cond_nt, interval_sec)
+    ins_r = d_ratio(ins, br_cond_nt)
+    misp_r = d_ratio(br_m_cond_nt, br_cond_nt)
+
+    not_taken_metrics = [
+        Metric("br_cond_retired", "Retired conditional not taken branch instructions.",
+               br_r, "insn/s"),
+        Metric("br_cond_insn_between_branches",
+               "The number of instructions divided by the number of not taken conditional "
+               "branches.", ins_r, "insn"),
+        Metric("br_cond_mispred",
+               "Retired not taken conditional branch instructions mispredicted as a "
+               "percentage of all not taken conditional branches.", misp_r, "100%"),
+    ]
+    return MetricGroup("br_cond", [
+        MetricGroup("br_cond_nt", not_taken_metrics),
+        MetricGroup("br_cond_tkn", taken_metrics),
+    ])
+
+  def Far() -> Optional[MetricGroup]:
+    try:
+      br_far = Event("BR_INST_RETIRED.FAR_BRANCH")
+    except:
+      return None
+
+    br_r = d_ratio(br_far, interval_sec)
+    ins_r = d_ratio(ins, br_far)
+    return MetricGroup("br_far", [
+        Metric("br_far_retired", "Retired far control transfers per second.",
+               br_r, "insn/s"),
+        Metric(
+            "br_far_insn_between_branches",
+            "The number of instructions divided by the number of far branches.",
+            ins_r, "insn"),
+    ])
+
+  return MetricGroup("br", [Total(), Taken(), Conditional(), Far()],
+                     description="breakdown of retired branch instructions")
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
     Smi(),
     Tsx(),
+    IntelBr(),
 ])
 
 if args.metricgroups:
author reviewer
#20 lore raw

Re: [PATCH v1 05/20] perf jevents: Add br metric group for branch statistics on Intel

Quoted 20 lines · Kan
Quoted 16 lines · Ian Rogers

The br metric group for branches itself comprises metric groups for total, taken, conditional, fused and far metric groups using json events. Condtional taken and not taken metrics are specific to Icelake and later generations, so a model to generation look up is added.

---
 tools/perf/pmu-events/intel_metrics.py | 139 +++++++++++++++++++++++++
 1 file changed, 139 insertions(+)
tools/perf/pmu-events/intel_metrics.py +0 -0
index 1096accea2aa..bee5da19d19d 100755
@@ -19,6 +19,7 @@ LoadEvents(directory)
 
Quoted 5 lines

tools/perf/pmu-events/intel_metrics.py LoadEvents(directory) · line 22

Quoted 3 lines
tools/perf/pmu-events/intel_metrics.py +1 -0
 interval_sec = Event("duration_time")
 
+

Unnecessary empty line.

Ack. Will fix in v2.

Thanks,
Ian

Quoted 156 lines

Thanks,
Kan

Quoted 153 lines
tools/perf/pmu-events/intel_metrics.py +138 -0
 def Idle() -> Metric:
   cyc = Event("msr/mperf/")
   tsc = Event("msr/tsc/")
@@ -127,11 +128,149 @@ def Tsx() -> Optional[MetricGroup]:
     return MetricGroup('transaction', metrics)
 
 
+def IntelBr():
+  ins = Event("instructions")
+
+  def Total() -> MetricGroup:
+    br_all = Event ("BR_INST_RETIRED.ALL_BRANCHES", "BR_INST_RETIRED.ANY")
+    br_m_all = Event("BR_MISP_RETIRED.ALL_BRANCHES",
+                     "BR_INST_RETIRED.MISPRED",
+                     "BR_MISP_EXEC.ANY")
+    br_clr = None
+    try:
+      br_clr = Event("BACLEARS.ANY", "BACLEARS.ALL")
+    except:
+      pass
+
+    br_r = d_ratio(br_all, interval_sec)
+    ins_r = d_ratio(ins, br_all)
+    misp_r = d_ratio(br_m_all, br_all)
+    clr_r = d_ratio(br_clr, interval_sec) if br_clr else None
+
+    return MetricGroup("br_total", [
+        Metric("br_total_retired",
+               "The number of branch instructions retired per second.", br_r,
+               "insn/s"),
+        Metric(
+            "br_total_mispred",
+            "The number of branch instructions retired, of any type, that were "
+            "not correctly predicted as a percentage of all branch instrucions.",
+            misp_r, "100%"),
+        Metric("br_total_insn_between_branches",
+               "The number of instructions divided by the number of branches.",
+               ins_r, "insn"),
+        Metric("br_total_insn_fe_resteers",
+               "The number of resync branches per second.", clr_r, "req/s"
+               ) if clr_r else None
+    ])
+
+  def Taken() -> MetricGroup:
+    br_all = Event("BR_INST_RETIRED.ALL_BRANCHES", "BR_INST_RETIRED.ANY")
+    br_m_tk = None
+    try:
+      br_m_tk = Event("BR_MISP_RETIRED.NEAR_TAKEN",
+                      "BR_MISP_RETIRED.TAKEN_JCC",
+                      "BR_INST_RETIRED.MISPRED_TAKEN")
+    except:
+      pass
+    br_r = d_ratio(br_all, interval_sec)
+    ins_r = d_ratio(ins, br_all)
+    misp_r = d_ratio(br_m_tk, br_all) if br_m_tk else None
+    return MetricGroup("br_taken", [
+        Metric("br_taken_retired",
+               "The number of taken branches that were retired per second.",
+               br_r, "insn/s"),
+        Metric(
+            "br_taken_mispred",
+            "The number of retired taken branch instructions that were "
+            "mispredicted as a percentage of all taken branches.", misp_r,
+            "100%") if misp_r else None,
+        Metric(
+            "br_taken_insn_between_branches",
+            "The number of instructions divided by the number of taken branches.",
+            ins_r, "insn"),
+    ])
+
+  def Conditional() -> Optional[MetricGroup]:
+    try:
+      br_cond = Event("BR_INST_RETIRED.COND",
+                      "BR_INST_RETIRED.CONDITIONAL",
+                      "BR_INST_RETIRED.TAKEN_JCC")
+      br_m_cond = Event("BR_MISP_RETIRED.COND",
+                        "BR_MISP_RETIRED.CONDITIONAL",
+                        "BR_MISP_RETIRED.TAKEN_JCC")
+    except:
+      return None
+
+    br_cond_nt = None
+    br_m_cond_nt = None
+    try:
+      br_cond_nt = Event("BR_INST_RETIRED.COND_NTAKEN")
+      br_m_cond_nt = Event("BR_MISP_RETIRED.COND_NTAKEN")
+    except:
+      pass
+    br_r = d_ratio(br_cond, interval_sec)
+    ins_r = d_ratio(ins, br_cond)
+    misp_r = d_ratio(br_m_cond, br_cond)
+    taken_metrics = [
+        Metric("br_cond_retired", "Retired conditional branch instructions.",
+               br_r, "insn/s"),
+        Metric("br_cond_insn_between_branches",
+               "The number of instructions divided by the number of conditional "
+               "branches.", ins_r, "insn"),
+        Metric("br_cond_mispred",
+               "Retired conditional branch instructions mispredicted as a "
+               "percentage of all conditional branches.", misp_r, "100%"),
+    ]
+    if not br_m_cond_nt:
+      return MetricGroup("br_cond", taken_metrics)
+
+    br_r = d_ratio(br_cond_nt, interval_sec)
+    ins_r = d_ratio(ins, br_cond_nt)
+    misp_r = d_ratio(br_m_cond_nt, br_cond_nt)
+
+    not_taken_metrics = [
+        Metric("br_cond_retired", "Retired conditional not taken branch instructions.",
+               br_r, "insn/s"),
+        Metric("br_cond_insn_between_branches",
+               "The number of instructions divided by the number of not taken conditional "
+               "branches.", ins_r, "insn"),
+        Metric("br_cond_mispred",
+               "Retired not taken conditional branch instructions mispredicted as a "
+               "percentage of all not taken conditional branches.", misp_r, "100%"),
+    ]
+    return MetricGroup("br_cond", [
+        MetricGroup("br_cond_nt", not_taken_metrics),
+        MetricGroup("br_cond_tkn", taken_metrics),
+    ])
+
+  def Far() -> Optional[MetricGroup]:
+    try:
+      br_far = Event("BR_INST_RETIRED.FAR_BRANCH")
+    except:
+      return None
+
+    br_r = d_ratio(br_far, interval_sec)
+    ins_r = d_ratio(ins, br_far)
+    return MetricGroup("br_far", [
+        Metric("br_far_retired", "Retired far control transfers per second.",
+               br_r, "insn/s"),
+        Metric(
+            "br_far_insn_between_branches",
+            "The number of instructions divided by the number of far branches.",
+            ins_r, "insn"),
+    ])
+
+  return MetricGroup("br", [Total(), Taken(), Conditional(), Far()],
+                     description="breakdown of retired branch instructions")
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
     Smi(),
     Tsx(),
+    IntelBr(),
 ])
 
 if args.metricgroups:
author reviewer
#21 lore raw

PATCH 6/20 perf jevents: Add software prefetch (swpf) metric group for Intel

In reply to Ian Rogers

Add metrics that breakdown software prefetch instruction use.

---
 tools/perf/pmu-events/intel_metrics.py | 65 ++++++++++++++++++++++++++
 1 file changed, 65 insertions(+)
tools/perf/pmu-events/intel_metrics.py +65 -0
index bee5da19d19d..f11273e9935c 100755
@@ -265,12 +265,77 @@ def IntelBr():
                      description="breakdown of retired branch instructions")
 
 
+def IntelSwpf() -> Optional[MetricGroup]:
+  ins = Event("instructions")
+  try:
+    s_ld = Event("MEM_INST_RETIRED.ALL_LOADS", "MEM_UOPS_RETIRED.ALL_LOADS")
+    s_nta = Event("SW_PREFETCH_ACCESS.NTA")
+    s_t0 = Event("SW_PREFETCH_ACCESS.T0")
+    s_t1 = Event("SW_PREFETCH_ACCESS.T1_T2")
+    s_w = Event("SW_PREFETCH_ACCESS.PREFETCHW")
+  except:
+    return None
+
+  all_sw = s_nta + s_t0 + s_t1 + s_w
+  swp_r = d_ratio(all_sw, interval_sec)
+  ins_r = d_ratio(ins, all_sw)
+  ld_r = d_ratio(s_ld, all_sw)
+
+  return MetricGroup("swpf", [
+      MetricGroup("swpf_totals", [
+          Metric("swpf_totals_exec", "Software prefetch instructions per second",
+                swp_r, "swpf/s"),
+          Metric("swpf_totals_insn_per_pf",
+                 "Average number of instructions between software prefetches",
+                 ins_r, "insn/swpf"),
+          Metric("swpf_totals_loads_per_pf",
+                 "Average number of loads between software prefetches",
+                 ld_r, "loads/swpf"),
+      ]),
+      MetricGroup("swpf_bkdwn", [
+          MetricGroup("swpf_bkdwn_nta", [
+              Metric("swpf_bkdwn_nta_per_swpf",
+                     "Software prefetch NTA instructions as a percent of all prefetch instructions",
+                     d_ratio(s_nta, all_sw), "100%"),
+              Metric("swpf_bkdwn_nta_rate",
+                     "Software prefetch NTA instructions per second",
+                     d_ratio(s_nta, interval_sec), "insn/s"),
+          ]),
+          MetricGroup("swpf_bkdwn_t0", [
+              Metric("swpf_bkdwn_t0_per_swpf",
+                     "Software prefetch T0 instructions as a percent of all prefetch instructions",
+                     d_ratio(s_t0, all_sw), "100%"),
+              Metric("swpf_bkdwn_t0_rate",
+                     "Software prefetch T0 instructions per second",
+                     d_ratio(s_t0, interval_sec), "insn/s"),
+          ]),
+          MetricGroup("swpf_bkdwn_t1_t2", [
+              Metric("swpf_bkdwn_t1_t2_per_swpf",
+                     "Software prefetch T1 or T2 instructions as a percent of all prefetch instructions",
+                     d_ratio(s_t1, all_sw), "100%"),
+              Metric("swpf_bkdwn_t1_t2_rate",
+                     "Software prefetch T1 or T2 instructions per second",
+                     d_ratio(s_t1, interval_sec), "insn/s"),
+          ]),
+          MetricGroup("swpf_bkdwn_w", [
+              Metric("swpf_bkdwn_w_per_swpf",
+                     "Software prefetch W instructions as a percent of all prefetch instructions",
+                     d_ratio(s_w, all_sw), "100%"),
+              Metric("swpf_bkdwn_w_rate",
+                     "Software prefetch W instructions per second",
+                     d_ratio(s_w, interval_sec), "insn/s"),
+          ]),
+      ]),
+  ], description="Sofware prefetch instruction breakdown")
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
     Smi(),
     Tsx(),
     IntelBr(),
+    IntelSwpf(),
 ])
 
 if args.metricgroups:
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#22 lore raw

PATCH 7/20 perf jevents: Add ports metric group giving utilization on Intel

In reply to Ian Rogers

The ports metric group contains a metric for each port giving its utilization as a ratio of cycles. The metrics are created by looking for UOPS_DISPATCHED.PORT events.

---
 tools/perf/pmu-events/intel_metrics.py | 33 ++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)
tools/perf/pmu-events/intel_metrics.py +31 -2
index f11273e9935c..63d46ee1dca9 100755
@@ -1,12 +1,13 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 from metric import (d_ratio, has_event, max, Event, JsonEncodeMetric,
-                    JsonEncodeMetricGroupDescriptions, LoadEvents, Metric,
-                    MetricGroup, MetricRef, Select)
+                    JsonEncodeMetricGroupDescriptions, Literal, LoadEvents,
+                    Metric, MetricGroup, MetricRef, Select)
 import argparse
 import json
 import math
 import os
+import re
 from typing import Optional
 
 parser = argparse.ArgumentParser(description="Intel perf json generator")
@@ -18,6 +19,11 @@ directory = f"{os.path.dirname(os.path.realpath(__file__))}/arch/x86/{args.model
 LoadEvents(directory)
 
 interval_sec = Event("duration_time")
+core_cycles = Event("CPU_CLK_UNHALTED.THREAD_P_ANY",
+                    "CPU_CLK_UNHALTED.DISTRIBUTED",
+                    "cycles")
+# Number of CPU cycles scaled for SMT.
+smt_cycles = Select(core_cycles / 2, Literal("#smt_on"), core_cycles)
 
 
 def Idle() -> Metric:
@@ -265,6 +271,28 @@ def IntelBr():
                      description="breakdown of retired branch instructions")
 
 
+def IntelPorts() -> Optional[MetricGroup]:
+  pipeline_events = json.load(open(f"{os.path.dirname(os.path.realpath(__file__))}"
+                                   f"/arch/x86/{args.model}/pipeline.json"))
+
+  metrics = []
+  for x in pipeline_events:
+    if "EventName" in x and re.search("^UOPS_DISPATCHED.PORT", x["EventName"]):
+      name = x["EventName"]
+      port = re.search(r"(PORT_[0-9].*)", name).group(0).lower()
+      if name.endswith("_CORE"):
+        cyc = core_cycles
+      else:
+        cyc = smt_cycles
+      metrics.append(Metric(port, f"{port} utilization (higher is better)",
+                            d_ratio(Event(name), cyc), "100%"))
+  if len(metrics) == 0:
+    return None
+
+  return MetricGroup("ports", metrics, "functional unit (port) utilization -- "
+                     "fraction of cycles each port is utilized (higher is better)")
+
+
 def IntelSwpf() -> Optional[MetricGroup]:
   ins = Event("instructions")
   try:
@@ -335,6 +363,7 @@ all_metrics = MetricGroup("", [
     Smi(),
     Tsx(),
     IntelBr(),
+    IntelPorts(),
     IntelSwpf(),
 ])
 
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#23 lore raw

PATCH 8/20 perf jevents: Add L2 metrics for Intel

In reply to Ian Rogers

Give a breakdown of various L2 counters as metrics, including totals, reads, hardware prefetcher, RFO, code and evictions.

---
 tools/perf/pmu-events/intel_metrics.py | 158 +++++++++++++++++++++++++
 1 file changed, 158 insertions(+)
tools/perf/pmu-events/intel_metrics.py +158 -0
index 63d46ee1dca9..d22a1abca8d9 100755
@@ -271,6 +271,163 @@ def IntelBr():
                      description="breakdown of retired branch instructions")
 
 
+def IntelL2() -> Optional[MetricGroup]:
+  try:
+    DC_HIT = Event("L2_RQSTS.DEMAND_DATA_RD_HIT")
+  except:
+    return None
+  try:
+    DC_MISS = Event("L2_RQSTS.DEMAND_DATA_RD_MISS")
+    l2_dmnd_miss = DC_MISS
+    l2_dmnd_rd_all = DC_MISS + DC_HIT
+  except:
+    DC_ALL = Event("L2_RQSTS.ALL_DEMAND_DATA_RD")
+    l2_dmnd_miss = DC_ALL - DC_HIT
+    l2_dmnd_rd_all = DC_ALL
+  l2_dmnd_mrate = d_ratio(l2_dmnd_miss, interval_sec)
+  l2_dmnd_rrate = d_ratio(l2_dmnd_rd_all, interval_sec)
+
+  DC_PFH = None
+  DC_PFM = None
+  l2_pf_all = None
+  l2_pf_mrate = None
+  l2_pf_rrate = None
+  try:
+    DC_PFH = Event("L2_RQSTS.PF_HIT")
+    DC_PFM = Event("L2_RQSTS.PF_MISS")
+    l2_pf_all = DC_PFH + DC_PFM
+    l2_pf_mrate = d_ratio(DC_PFM, interval_sec)
+    l2_pf_rrate = d_ratio(l2_pf_all, interval_sec)
+  except:
+    pass
+
+  DC_RFOH = Event("L2_RQSTS.RFO_HIT")
+  DC_RFOM = Event("L2_RQSTS.RFO_MISS")
+  l2_rfo_all = DC_RFOH + DC_RFOM
+  l2_rfo_mrate  = d_ratio(DC_RFOM, interval_sec)
+  l2_rfo_rrate  = d_ratio(l2_rfo_all, interval_sec)
+
+  DC_CH = Event("L2_RQSTS.CODE_RD_HIT")
+  DC_CM = Event("L2_RQSTS.CODE_RD_MISS")
+  DC_IN = Event("L2_LINES_IN.ALL")
+  DC_OUT_NS = None
+  DC_OUT_S = None
+  l2_lines_out = None
+  l2_out_rate = None
+  wbn = None
+  isd = None
+  try:
+    DC_OUT_NS = Event("L2_LINES_OUT.NON_SILENT",
+                      "L2_LINES_OUT.DEMAND_DIRTY",
+                      "L2_LINES_IN.S")
+    DC_OUT_S = Event("L2_LINES_OUT.SILENT",
+                     "L2_LINES_OUT.DEMAND_CLEAN",
+                     "L2_LINES_IN.I")
+    if DC_OUT_S.name == "L2_LINES_OUT.SILENT" and (
+        args.model.startswith("skylake") or
+        args.model == "cascadelakex"):
+      DC_OUT_S.name = "L2_LINES_OUT.SILENT/any/"
+    # bring is back to per-CPU
+    l2_s  = Select(DC_OUT_S / 2, Literal("#smt_on"), DC_OUT_S)
+    l2_ns = DC_OUT_NS
+    l2_lines_out = l2_s + l2_ns;
+    l2_out_rate = d_ratio(l2_lines_out, interval_sec);
+    nlr = max(l2_ns - DC_WB_U - DC_WB_D, 0)
+    wbn = d_ratio(nlr, interval_sec)
+    isd = d_ratio(l2_s, interval_sec)
+  except:
+    pass
+  DC_OUT_U = None
+  l2_pf_useless = None
+  l2_useless_rate = None
+  try:
+    DC_OUT_U = Event("L2_LINES_OUT.USELESS_HWPF")
+    l2_pf_useless = DC_OUT_U
+    l2_useless_rate = d_ratio(l2_pf_useless, interval_sec)
+  except:
+    pass
+  DC_WB_U = None
+  DC_WB_D = None
+  wbu = None
+  wbd = None
+  try:
+    DC_WB_U = Event("IDI_MISC.WB_UPGRADE")
+    DC_WB_D = Event("IDI_MISC.WB_DOWNGRADE")
+    wbu = d_ratio(DC_WB_U, interval_sec)
+    wbd = d_ratio(DC_WB_D, interval_sec)
+  except:
+    pass
+
+  l2_lines_in = DC_IN
+  l2_code_all = DC_CH + DC_CM
+  l2_code_rate = d_ratio(l2_code_all, interval_sec)
+  l2_code_miss_rate = d_ratio(DC_CM, interval_sec)
+  l2_in_rate = d_ratio(l2_lines_in, interval_sec)
+
+  return MetricGroup("l2", [
+    MetricGroup("l2_totals", [
+      Metric("l2_totals_in", "L2 cache total in per second",
+             l2_in_rate, "In/s"),
+      Metric("l2_totals_out", "L2 cache total out per second",
+             l2_out_rate, "Out/s") if l2_out_rate else None,
+    ]),
+    MetricGroup("l2_rd", [
+      Metric("l2_rd_hits", "L2 cache data read hits",
+             d_ratio(DC_HIT, l2_dmnd_rd_all), "100%"),
+      Metric("l2_rd_hits", "L2 cache data read hits",
+             d_ratio(l2_dmnd_miss, l2_dmnd_rd_all), "100%"),
+      Metric("l2_rd_requests", "L2 cache data read requests per second",
+             l2_dmnd_rrate, "requests/s"),
+      Metric("l2_rd_misses", "L2 cache data read misses per second",
+             l2_dmnd_mrate, "misses/s"),
+    ]),
+    MetricGroup("l2_hwpf", [
+      Metric("l2_hwpf_hits", "L2 cache hardware prefetcher hits",
+             d_ratio(DC_PFH, l2_pf_all), "100%"),
+      Metric("l2_hwpf_misses", "L2 cache hardware prefetcher misses",
+             d_ratio(DC_PFM, l2_pf_all), "100%"),
+      Metric("l2_hwpf_useless", "L2 cache hardware prefetcher useless prefetches per second",
+             l2_useless_rate, "100%") if l2_useless_rate else None,
+      Metric("l2_hwpf_requests", "L2 cache hardware prefetcher requests per second",
+             l2_pf_rrate, "100%"),
+      Metric("l2_hwpf_misses", "L2 cache hardware prefetcher misses per second",
+             l2_pf_mrate, "100%"),
+    ]) if DC_PFH else None,
+    MetricGroup("l2_rfo", [
+      Metric("l2_rfo_hits", "L2 cache request for ownership (RFO) hits",
+             d_ratio(DC_RFOH, l2_rfo_all), "100%"),
+      Metric("l2_rfo_misses", "L2 cache request for ownership (RFO) misses",
+             d_ratio(DC_RFOM, l2_rfo_all), "100%"),
+      Metric("l2_rfo_requests", "L2 cache request for ownership (RFO) requests per second",
+             l2_rfo_rrate, "requests/s"),
+      Metric("l2_rfo_misses", "L2 cache request for ownership (RFO) misses per second",
+             l2_rfo_mrate, "misses/s"),
+    ]),
+    MetricGroup("l2_code", [
+      Metric("l2_code_hits", "L2 cache code hits",
+             d_ratio(DC_CH, l2_code_all), "100%"),
+      Metric("l2_code_misses", "L2 cache code misses",
+             d_ratio(DC_CM, l2_code_all), "100%"),
+      Metric("l2_code_requests", "L2 cache code requests per second",
+             l2_code_rate, "requests/s"),
+      Metric("l2_code_misses", "L2 cache code misses per second",
+             l2_code_miss_rate, "misses/s"),
+    ]),
+    MetricGroup("l2_evict", [
+      MetricGroup("l2_evict_mef_lines", [
+        Metric("l2_evict_mef_lines_l3_hot_lru", "L2 evictions M/E/F lines L3 hot LRU per second",
+               wbu, "HotLRU/s") if wbu else None,
+        Metric("l2_evict_mef_lines_l3_norm_lru", "L2 evictions M/E/F lines L3 normal LRU per second",
+               wbn, "NormLRU/s") if wbn else None,
+        Metric("l2_evict_mef_lines_dropped", "L2 evictions M/E/F lines dropped per second",
+               wbd, "dropped/s") if wbd else None,
+        Metric("l2_evict_is_lines_dropped", "L2 evictions I/S lines dropped per second",
+               isd, "dropped/s") if isd else None,
+      ]),
+    ]),
+  ], description = "L2 data cache analysis")
+
+
 def IntelPorts() -> Optional[MetricGroup]:
   pipeline_events = json.load(open(f"{os.path.dirname(os.path.realpath(__file__))}"
                                    f"/arch/x86/{args.model}/pipeline.json"))
@@ -363,6 +520,7 @@ all_metrics = MetricGroup("", [
     Smi(),
     Tsx(),
     IntelBr(),
+    IntelL2(),
     IntelPorts(),
     IntelSwpf(),
 ])
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#24 lore raw

PATCH 9/20 perf jevents: Add load store breakdown metrics ldst for Intel

In reply to Ian Rogers

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

---
 tools/perf/pmu-events/intel_metrics.py | 86 +++++++++++++++++++++++++-
 1 file changed, 85 insertions(+), 1 deletion(-)
tools/perf/pmu-events/intel_metrics.py +85 -1
index d22a1abca8d9..0035e2441d6b 100755
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
 from metric import (d_ratio, has_event, max, Event, JsonEncodeMetric,
                     JsonEncodeMetricGroupDescriptions, Literal, LoadEvents,
-                    Metric, MetricGroup, MetricRef, Select)
+                    Metric, MetricConstraint, MetricGroup, MetricRef, Select)
 import argparse
 import json
 import math
@@ -514,6 +514,89 @@ 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")
+
+
 all_metrics = MetricGroup("", [
     Idle(),
     Rapl(),
@@ -521,6 +604,7 @@ all_metrics = MetricGroup("", [
     Tsx(),
     IntelBr(),
     IntelL2(),
+    IntelLdSt(),
     IntelPorts(),
     IntelSwpf(),
 ])
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#25 lore raw

PATCH 10/20 perf jevents: Add ILP metrics for Intel

In reply to Ian Rogers

Use the counter mask (cmask) to see how many cycles an instruction takes to retire. Present as a set of ILP metrics.

---
 tools/perf/pmu-events/intel_metrics.py | 30 ++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)
tools/perf/pmu-events/intel_metrics.py +30 -0
index 0035e2441d6b..0ca72aeec1ea 100755
@@ -271,6 +271,35 @@ def IntelBr():
                      description="breakdown of retired branch instructions")
 
 
+def IntelIlp() -> MetricGroup:
+    tsc = Event("msr/tsc/")
+    c0 = Event("msr/mperf/")
+    low = tsc - c0
+    inst_ret = Event("INST_RETIRED.ANY_P")
+    inst_ret_c = [Event(f"{inst_ret.name}/cmask={x}/") for x in range(1, 6)]
+    ilp = [d_ratio(max(inst_ret_c[x] - inst_ret_c[x + 1], 0), core_cycles) for x in range(0, 4)]
+    ilp.append(d_ratio(inst_ret_c[4], core_cycles))
+    ilp0 = 1
+    for x in ilp:
+        ilp0 -= x
+    return MetricGroup("ilp", [
+        Metric("ilp_idle", "Lower power cycles as a percentage of all cycles",
+               d_ratio(low, tsc), "100%"),
+        Metric("ilp_inst_ret_0", "Instructions retired in 0 cycles as a percentage of all cycles",
+               ilp0, "100%"),
+        Metric("ilp_inst_ret_1", "Instructions retired in 1 cycles as a percentage of all cycles",
+               ilp[0], "100%"),
+        Metric("ilp_inst_ret_2", "Instructions retired in 2 cycles as a percentage of all cycles",
+               ilp[1], "100%"),
+        Metric("ilp_inst_ret_3", "Instructions retired in 3 cycles as a percentage of all cycles",
+               ilp[2], "100%"),
+        Metric("ilp_inst_ret_4", "Instructions retired in 4 cycles as a percentage of all cycles",
+               ilp[3], "100%"),
+        Metric("ilp_inst_ret_5", "Instructions retired in 5 or more cycles as a percentage of all cycles",
+               ilp[4], "100%"),
+    ])
+
+
 def IntelL2() -> Optional[MetricGroup]:
   try:
     DC_HIT = Event("L2_RQSTS.DEMAND_DATA_RD_HIT")
@@ -603,6 +632,7 @@ all_metrics = MetricGroup("", [
     Smi(),
     Tsx(),
     IntelBr(),
+    IntelIlp(),
     IntelL2(),
     IntelLdSt(),
     IntelPorts(),
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#26 lore raw

PATCH 11/20 perf jevents: Add context switch metrics for Intel

In reply to Ian Rogers

Metrics break down context switches for different kinds of instruction.

---
 tools/perf/pmu-events/intel_metrics.py | 55 ++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)
tools/perf/pmu-events/intel_metrics.py +55 -0
index 0ca72aeec1ea..6ee708e84863 100755
@@ -271,6 +271,60 @@ def IntelBr():
                      description="breakdown of retired branch instructions")
 
 
+def IntelCtxSw() -> MetricGroup:
+  cs = Event("context\-switches")
+  metrics = [
+      Metric("cs_rate", "Context switches per second", d_ratio(cs, interval_sec), "ctxsw/s")
+  ]
+
+  ev = Event("instructions")
+  metrics.append(Metric("cs_instr", "Instructions per context switch",
+                        d_ratio(ev, cs), "instr/cs"))
+
+  ev = Event("cycles")
+  metrics.append(Metric("cs_cycles", "Cycles per context switch",
+                        d_ratio(ev, cs), "cycles/cs"))
+
+  try:
+    ev = Event("MEM_INST_RETIRED.ALL_LOADS", "MEM_UOPS_RETIRED.ALL_LOADS")
+    metrics.append(Metric("cs_loads", "Loads per context switch",
+                          d_ratio(ev, cs), "loads/cs"))
+  except:
+    pass
+
+  try:
+    ev = Event("MEM_INST_RETIRED.ALL_STORES", "MEM_UOPS_RETIRED.ALL_STORES")
+    metrics.append(Metric("cs_stores", "Stores per context switch",
+                          d_ratio(ev, cs), "stores/cs"))
+  except:
+    pass
+
+  try:
+    ev = Event("BR_INST_RETIRED.NEAR_TAKEN", "BR_INST_RETIRED.TAKEN_JCC")
+    metrics.append(Metric("cs_br_taken", "Branches taken per context switch",
+                          d_ratio(ev, cs), "br_taken/cs"))
+  except:
+    pass
+
+  try:
+    l2_misses = (Event("L2_RQSTS.DEMAND_DATA_RD_MISS") +
+                 Event("L2_RQSTS.RFO_MISS") +
+                 Event("L2_RQSTS.CODE_RD_MISS"))
+    try:
+      l2_misses += Event("L2_RQSTS.HWPF_MISS", "L2_RQSTS.L2_PF_MISS", "L2_RQSTS.PF_MISS")
+    except:
+      pass
+
+    metrics.append(Metric("cs_l2_misses", "L2 misses per context switch",
+                          d_ratio(l2_misses, cs), "l2_misses/cs"))
+  except:
+    pass
+
+  return MetricGroup("cs", metrics,
+                     description = ("Number of context switches per second, instructions "
+                                    "retired & core cycles between context switches"))
+
+
 def IntelIlp() -> MetricGroup:
     tsc = Event("msr/tsc/")
     c0 = Event("msr/mperf/")
@@ -632,6 +686,7 @@ all_metrics = MetricGroup("", [
     Smi(),
     Tsx(),
     IntelBr(),
+    IntelCtxSw(),
     IntelIlp(),
     IntelL2(),
     IntelLdSt(),
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#27 lore raw

PATCH 12/20 perf jevents: Add FPU metrics for Intel

In reply to Ian Rogers

Metrics break down of floating point operations.

---
 tools/perf/pmu-events/intel_metrics.py | 90 ++++++++++++++++++++++++++
 1 file changed, 90 insertions(+)
tools/perf/pmu-events/intel_metrics.py +90 -0
index 6ee708e84863..dae44d296861 100755
@@ -325,6 +325,95 @@ 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("fpu", [
+      MetricGroup("fpu_total", [
+          Metric("fpu_total_flops", "Floating point operations per second",
+                 flop_r, "flops/s"),
+          Metric("fpu_total_flopc", "Floating point operations per cycle",
+                 flop_c, "flops/cycle", constraint=nmi_constraint),
+      ]),
+      MetricGroup("fpu_64", [
+          FpuMetrics("fpu_64_single", s_64, 1, "64-bit single"),
+          FpuMetrics("fpu_64_double", d_64, 1, "64-bit double"),
+      ]),
+      MetricGroup("fpu_128", [
+          FpuMetrics("fpu_128_single", s_128, 4, "128-bit packed single"),
+          FpuMetrics("fpu_128_double", d_128, 2, "128-bit packed double"),
+      ]),
+      MetricGroup("fpu_256", [
+          FpuMetrics("fpu_256_single", s_256, 8, "128-bit packed single"),
+          FpuMetrics("fpu_256_double", d_256, 4, "128-bit packed double"),
+      ]),
+      MetricGroup("fpu_512", [
+          FpuMetrics("fpu_512_single", s_512, 16, "128-bit packed single"),
+          FpuMetrics("fpu_512_double", d_512, 8, "128-bit packed double"),
+      ]),
+      Metric("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/")
@@ -687,6 +776,7 @@ all_metrics = MetricGroup("", [
     Tsx(),
     IntelBr(),
     IntelCtxSw(),
+    IntelFpu(),
     IntelIlp(),
     IntelL2(),
     IntelLdSt(),
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#28 lore raw

PATCH 13/20 perf jevents: Add cycles breakdown metric for Intel

In reply to Ian Rogers

Breakdown cycles to user, kernel and guest.

---
 tools/perf/pmu-events/intel_metrics.py | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
tools/perf/pmu-events/intel_metrics.py +18 -0
index dae44d296861..fef40969a4b8 100755
@@ -26,6 +26,23 @@ core_cycles = Event("CPU_CLK_UNHALTED.THREAD_P_ANY",
 smt_cycles = Select(core_cycles / 2, Literal("#smt_on"), core_cycles)
 
 
+def Cycles() -> MetricGroup:
+  cyc_k = Event("cycles:kHh")
+  cyc_g = Event("cycles:G")
+  cyc_u = Event("cycles:uH")
+  cyc = cyc_k + cyc_g + cyc_u
+
+  return MetricGroup("cycles", [
+      Metric("cycles_total", "Total number of cycles", cyc, "cycles"),
+      Metric("cycles_user", "User cycles as a percentage of all cycles",
+             d_ratio(cyc_u, cyc), "100%"),
+      Metric("cycles_kernel", "Kernel cycles as a percentage of all cycles",
+             d_ratio(cyc_k, cyc), "100%"),
+      Metric("cycles_guest", "Hypervisor guest cycles as a percentage of all cycles",
+             d_ratio(cyc_g, cyc), "100%"),
+  ], description = "cycles breakdown per privilege level (users, kernel, guest)")
+
+
 def Idle() -> Metric:
   cyc = Event("msr/mperf/")
   tsc = Event("msr/tsc/")
@@ -770,6 +787,7 @@ def IntelLdSt() -> Optional[MetricGroup]:
 
 
 all_metrics = MetricGroup("", [
+    Cycles(),
     Idle(),
     Rapl(),
     Smi(),
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
#29 lore raw

Re: [PATCH v1 13/20] perf jevents: Add cycles breakdown metric for Intel

Quoted 36 lines · Ian Rogers

Breakdown cycles to user, kernel and guest.

---
 tools/perf/pmu-events/intel_metrics.py | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
tools/perf/pmu-events/intel_metrics.py +17 -0
index dae44d296861..fef40969a4b8 100755
@@ -26,6 +26,23 @@ core_cycles = Event("CPU_CLK_UNHALTED.THREAD_P_ANY",
 smt_cycles = Select(core_cycles / 2, Literal("#smt_on"), core_cycles)
 
 
+def Cycles() -> MetricGroup:
+  cyc_k = Event("cycles:kHh")
+  cyc_g = Event("cycles:G")
+  cyc_u = Event("cycles:uH")
+  cyc = cyc_k + cyc_g + cyc_u
+
+  return MetricGroup("cycles", [
+      Metric("cycles_total", "Total number of cycles", cyc, "cycles"),
+      Metric("cycles_user", "User cycles as a percentage of all cycles",
+             d_ratio(cyc_u, cyc), "100%"),
+      Metric("cycles_kernel", "Kernel cycles as a percentage of all cycles",
+             d_ratio(cyc_k, cyc), "100%"),
+      Metric("cycles_guest", "Hypervisor guest cycles as a percentage of all cycles",
+             d_ratio(cyc_g, cyc), "100%"),
+  ], description = "cycles breakdown per privilege level (users, kernel, guest)")
+
+
 def Idle() -> Metric:
   cyc = Event("msr/mperf/")
   tsc = Event("msr/tsc/")

tools/perf/pmu-events/intel_metrics.py def IntelLdSt() -> Optional[MetricGroup]: · line 790

Quoted 4 lines
tools/perf/pmu-events/intel_metrics.py +1 -0
@@ -770,6 +787,7 @@ def IntelLdSt() -> Optional[MetricGroup]:
 
 
 all_metrics = MetricGroup("", [
+    Cycles(),

The metric group seem exactly the same on AMD and ARM. Maybe we can have tools/perf/pmu-events/common_metrics.py for all the common metrics.

Thanks,
Kan

Quoted 3 lines
tools/perf/pmu-events/intel_metrics.py +0 -0
     Idle(),
     Rapl(),
     Smi(),
author reviewer
#30 lore raw

Re: [PATCH v1 13/20] perf jevents: Add cycles breakdown metric for Intel

Quoted 42 lines · Kan
Quoted 38 lines · Ian Rogers

Breakdown cycles to user, kernel and guest.

---
 tools/perf/pmu-events/intel_metrics.py | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
tools/perf/pmu-events/intel_metrics.py +17 -0
index dae44d296861..fef40969a4b8 100755
@@ -26,6 +26,23 @@ core_cycles = Event("CPU_CLK_UNHALTED.THREAD_P_ANY",
 smt_cycles = Select(core_cycles / 2, Literal("#smt_on"), core_cycles)
 
 
+def Cycles() -> MetricGroup:
+  cyc_k = Event("cycles:kHh")
+  cyc_g = Event("cycles:G")
+  cyc_u = Event("cycles:uH")
+  cyc = cyc_k + cyc_g + cyc_u
+
+  return MetricGroup("cycles", [
+      Metric("cycles_total", "Total number of cycles", cyc, "cycles"),
+      Metric("cycles_user", "User cycles as a percentage of all cycles",
+             d_ratio(cyc_u, cyc), "100%"),
+      Metric("cycles_kernel", "Kernel cycles as a percentage of all cycles",
+             d_ratio(cyc_k, cyc), "100%"),
+      Metric("cycles_guest", "Hypervisor guest cycles as a percentage of all cycles",
+             d_ratio(cyc_g, cyc), "100%"),
+  ], description = "cycles breakdown per privilege level (users, kernel, guest)")
+
+
 def Idle() -> Metric:
   cyc = Event("msr/mperf/")
   tsc = Event("msr/tsc/")
@@ -770,6 +787,7 @@ def IntelLdSt() -> Optional[MetricGroup]:
 
 
Quoted 5 lines

tools/perf/pmu-events/intel_metrics.py def IntelLdSt() -> Optional[MetricGroup]: · line 790

Quoted 2 lines
tools/perf/pmu-events/intel_metrics.py +1 -0
 all_metrics = MetricGroup("", [
+    Cycles(),

The metric group seem exactly the same on AMD and ARM. Maybe we can have tools/perf/pmu-events/common_metrics.py for all the common metrics.

Agreed. I think we can drop cycles in the three sets and then once then do the common_metrics.py as a follow up.

Thanks,
Ian

Quoted 6 lines

Thanks,
Kan

Quoted 3 lines
tools/perf/pmu-events/intel_metrics.py +0 -0
     Idle(),
     Rapl(),
     Smi(),
#31 lore raw

Re: [PATCH v1 13/20] perf jevents: Add cycles breakdown metric for Intel

Quoted 43 lines · Ian Rogers
Quoted 42 lines · Kan
Quoted 38 lines · Ian Rogers

Breakdown cycles to user, kernel and guest.

---
 tools/perf/pmu-events/intel_metrics.py | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
tools/perf/pmu-events/intel_metrics.py +17 -0
index dae44d296861..fef40969a4b8 100755
@@ -26,6 +26,23 @@ core_cycles = Event("CPU_CLK_UNHALTED.THREAD_P_ANY",
 smt_cycles = Select(core_cycles / 2, Literal("#smt_on"), core_cycles)
 
 
+def Cycles() -> MetricGroup:
+  cyc_k = Event("cycles:kHh")
+  cyc_g = Event("cycles:G")
+  cyc_u = Event("cycles:uH")
+  cyc = cyc_k + cyc_g + cyc_u
+
+  return MetricGroup("cycles", [
+      Metric("cycles_total", "Total number of cycles", cyc, "cycles"),
+      Metric("cycles_user", "User cycles as a percentage of all cycles",
+             d_ratio(cyc_u, cyc), "100%"),
+      Metric("cycles_kernel", "Kernel cycles as a percentage of all cycles",
+             d_ratio(cyc_k, cyc), "100%"),
+      Metric("cycles_guest", "Hypervisor guest cycles as a percentage of all cycles",
+             d_ratio(cyc_g, cyc), "100%"),
+  ], description = "cycles breakdown per privilege level (users, kernel, guest)")
+
+
 def Idle() -> Metric:
   cyc = Event("msr/mperf/")
   tsc = Event("msr/tsc/")
@@ -770,6 +787,7 @@ def IntelLdSt() -> Optional[MetricGroup]:
 
 
Quoted 9 lines
Quoted 5 lines

tools/perf/pmu-events/intel_metrics.py def IntelLdSt() -> Optional[MetricGroup]: · line 790

Quoted 2 lines
tools/perf/pmu-events/intel_metrics.py +1 -0
 all_metrics = MetricGroup("", [
+    Cycles(),

The metric group seem exactly the same on AMD and ARM. Maybe we can have tools/perf/pmu-events/common_metrics.py for all the common metrics.

Agreed. I think we can drop cycles in the three sets and then once then do the common_metrics.py as a follow up.

Sounds good to me.

Thanks,
Kan

Quoted 10 lines

Thanks,
Ian

Quoted 6 lines

Thanks,
Kan

Quoted 3 lines
tools/perf/pmu-events/intel_metrics.py +0 -0
     Idle(),
     Rapl(),
     Smi(),
author reviewer
#32 lore raw

PATCH 14/20 perf jevents: Add Miss Level Parallelism (MLP) metric for Intel

In reply to Ian Rogers

Number of oustanding load misses per cycle.

---
 tools/perf/pmu-events/intel_metrics.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
tools/perf/pmu-events/intel_metrics.py +15 -0
index fef40969a4b8..e373f87d499d 100755
@@ -617,6 +617,20 @@ def IntelL2() -> Optional[MetricGroup]:
   ], description = "L2 data cache analysis")
 
 
+def IntelMlp() -> Optional[Metric]:
+  try:
+    l1d = Event("L1D_PEND_MISS.PENDING")
+    l1dc = Event("L1D_PEND_MISS.PENDING_CYCLES")
+  except:
+    return None
+
+  l1dc = Select(l1dc / 2, Literal("#smt_on"), l1dc)
+  ml = d_ratio(l1d, l1dc)
+  return Metric("mlp",
+                "Miss level parallelism - number of oustanding load misses per cycle (higher is better)",
+                ml, "load_miss_pending/cycle")
+
+
 def IntelPorts() -> Optional[MetricGroup]:
   pipeline_events = json.load(open(f"{os.path.dirname(os.path.realpath(__file__))}"
                                    f"/arch/x86/{args.model}/pipeline.json"))
@@ -798,6 +812,7 @@ all_metrics = MetricGroup("", [
     IntelIlp(),
     IntelL2(),
     IntelLdSt(),
+    IntelMlp(),
     IntelPorts(),
     IntelSwpf(),
 ])
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#33 lore raw

PATCH 15/20 perf jevents: Add mem_bw metric for Intel

In reply to Ian Rogers

Break down memory bandwidth using uncore counters. For many models this matches the memory_bandwidth_* metrics, but these metrics aren't made available on all models. Add support for free running counters. Query the event json when determining which what events/counters are available.

---
 tools/perf/pmu-events/intel_metrics.py | 62 ++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)
tools/perf/pmu-events/intel_metrics.py +62 -0
index e373f87d499d..8d02be83b491 100755
@@ -800,6 +800,67 @@ def IntelLdSt() -> Optional[MetricGroup]:
   ], description = "Breakdown of load/store instructions")
 
 
+def UncoreMemBw() -> Optional[MetricGroup]:
+  mem_events = []
+  try:
+    mem_events = json.load(open(f"{os.path.dirname(os.path.realpath(__file__))}"
+                                f"/arch/x86/{args.model}/uncore-memory.json"))
+  except:
+    pass
+
+  ddr_rds = 0
+  ddr_wrs = 0
+  ddr_total = 0
+  for x in mem_events:
+    if "EventName" in x:
+      name = x["EventName"]
+      if re.search("^UNC_MC[0-9]+_RDCAS_COUNT_FREERUN", name):
+        ddr_rds += Event(name)
+      elif re.search("^UNC_MC[0-9]+_WRCAS_COUNT_FREERUN", name):
+        ddr_wrs += Event(name)
+      #elif re.search("^UNC_MC[0-9]+_TOTAL_REQCOUNT_FREERUN", name):
+      #  ddr_total += Event(name)
+
+  if ddr_rds == 0:
+    try:
+      ddr_rds = Event("UNC_M_CAS_COUNT.RD")
+      ddr_wrs = Event("UNC_M_CAS_COUNT.WR")
+    except:
+      return None
+
+  ddr_total = ddr_rds + ddr_wrs
+
+  pmm_rds = 0
+  pmm_wrs = 0
+  try:
+    pmm_rds = Event("UNC_M_PMM_RPQ_INSERTS")
+    pmm_wrs = Event("UNC_M_PMM_WPQ_INSERTS")
+  except:
+    pass
+
+  pmm_total = pmm_rds + pmm_wrs
+
+  scale = 64 / 1_000_000
+  return MetricGroup("mem_bw", [
+      MetricGroup("mem_bw_ddr", [
+          Metric("mem_bw_ddr_read", "DDR memory read bandwidth",
+                 d_ratio(ddr_rds, interval_sec), f"{scale}MB/s"),
+          Metric("mem_bw_ddr_write", "DDR memory write bandwidth",
+                 d_ratio(ddr_wrs, interval_sec), f"{scale}MB/s"),
+          Metric("mem_bw_ddr_total", "DDR memory write bandwidth",
+                 d_ratio(ddr_total, interval_sec), f"{scale}MB/s"),
+      ], description = "DDR Memory Bandwidth"),
+      MetricGroup("mem_bw_pmm", [
+          Metric("mem_bw_pmm_read", "PMM memory read bandwidth",
+                 d_ratio(pmm_rds, interval_sec), f"{scale}MB/s"),
+          Metric("mem_bw_pmm_write", "PMM memory write bandwidth",
+                 d_ratio(pmm_wrs, interval_sec), f"{scale}MB/s"),
+          Metric("mem_bw_pmm_total", "PMM memory write bandwidth",
+                 d_ratio(pmm_total, interval_sec), f"{scale}MB/s"),
+      ], description = "PMM Memory Bandwidth") if pmm_rds != 0 else None,
+  ], description = "Memory Bandwidth")
+
+
 all_metrics = MetricGroup("", [
     Cycles(),
     Idle(),
@@ -815,6 +876,7 @@ all_metrics = MetricGroup("", [
     IntelMlp(),
     IntelPorts(),
     IntelSwpf(),
+    UncoreMemBw(),
 ])
 
 if args.metricgroups:
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#34 lore raw

PATCH 16/20 perf jevents: Add local/remote "mem" breakdown metrics for Intel

In reply to Ian Rogers

Breakdown local and remote memory bandwidth, read and writes. The implementation uses the HA and CHA PMUs present in server models broadwellde, broadwellx cascadelakex, emeraldrapids, haswellx, icelakex, ivytown, sapphirerapids and skylakex.

---
 tools/perf/pmu-events/intel_metrics.py | 27 ++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)
tools/perf/pmu-events/intel_metrics.py +27 -0
index 8d02be83b491..82fd23cf5500 100755
@@ -800,6 +800,32 @@ def IntelLdSt() -> Optional[MetricGroup]:
   ], description = "Breakdown of load/store instructions")
 
 
+def UncoreMem() -> Optional[MetricGroup]:
+  try:
+    loc_rds = Event("UNC_CHA_REQUESTS.READS_LOCAL", "UNC_H_REQUESTS.READS_LOCAL")
+    rem_rds = Event("UNC_CHA_REQUESTS.READS_REMOTE", "UNC_H_REQUESTS.READS_REMOTE")
+    loc_wrs = Event("UNC_CHA_REQUESTS.WRITES_LOCAL", "UNC_H_REQUESTS.WRITES_LOCAL")
+    rem_wrs = Event("UNC_CHA_REQUESTS.WRITES_REMOTE", "UNC_H_REQUESTS.WRITES_REMOTE")
+  except:
+    return None
+
+  scale = 64 / 1_000_000
+  return MetricGroup("mem", [
+      MetricGroup("mem_local", [
+          Metric("mem_local_read", "Local memory read bandwidth not including directory updates",
+                 d_ratio(loc_rds, interval_sec), f"{scale}MB/s"),
+          Metric("mem_local_write", "Local memory write bandwidth not including directory updates",
+                 d_ratio(loc_wrs, interval_sec), f"{scale}MB/s"),
+      ]),
+      MetricGroup("mem_remote", [
+          Metric("mem_remote_read", "Remote memory read bandwidth not including directory updates",
+                 d_ratio(rem_rds, interval_sec), f"{scale}MB/s"),
+          Metric("mem_remote_write", "Remote memory write bandwidth not including directory updates",
+                 d_ratio(rem_wrs, interval_sec), f"{scale}MB/s"),
+      ]),
+  ], description = "Memory Bandwidth breakdown local vs. remote (remote requests in). directory updates not included")
+
+
 def UncoreMemBw() -> Optional[MetricGroup]:
   mem_events = []
   try:
@@ -876,6 +902,7 @@ all_metrics = MetricGroup("", [
     IntelMlp(),
     IntelPorts(),
     IntelSwpf(),
+    UncoreMem(),
     UncoreMemBw(),
 ])
 
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#35 lore raw

PATCH 17/20 perf jevents: Add dir breakdown metrics for Intel

In reply to Ian Rogers

Breakdown directory hit, misses and requests. The implementation uses the M2M and CHA PMUs present in server models broadwellde, broadwellx cascadelakex, emeraldrapids, icelakex, sapphirerapids and skylakex.

---
 tools/perf/pmu-events/intel_metrics.py | 36 ++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)
tools/perf/pmu-events/intel_metrics.py +36 -0
index 82fd23cf5500..07aafdf77f79 100755
@@ -800,6 +800,41 @@ def IntelLdSt() -> Optional[MetricGroup]:
   ], description = "Breakdown of load/store instructions")
 
 
+def UncoreDir() -> Optional[MetricGroup]:
+  try:
+    m2m_upd = Event("UNC_M2M_DIRECTORY_UPDATE.ANY")
+    m2m_hits = Event("UNC_M2M_DIRECTORY_HIT.DIRTY_I")
+    # Turn the umask into a ANY rather than DIRTY_I filter.
+    m2m_hits.name += "/umask=0xFF,name=UNC_M2M_DIRECTORY_HIT.ANY/"
+    m2m_miss = Event("UNC_M2M_DIRECTORY_MISS.DIRTY_I")
+    # Turn the umask into a ANY rather than DIRTY_I filter.
+    m2m_miss.name += "/umask=0xFF,name=UNC_M2M_DIRECTORY_MISS.ANY/"
+    cha_upd = Event("UNC_CHA_DIR_UPDATE.HA")
+    # Turn the umask into a ANY rather than HA filter.
+    cha_upd.name += "/umask=3,name=UNC_CHA_DIR_UPDATE.ANY/"
+  except:
+    return None
+
+  m2m_total = m2m_hits + m2m_miss
+  upd = m2m_upd + cha_upd # in cache lines
+  upd_r = upd / interval_sec
+  look_r = m2m_total / interval_sec
+
+  scale = 64 / 1_000_000 # Cache lines to MB
+  return MetricGroup("dir", [
+      Metric("dir_lookup_rate", "",
+             d_ratio(m2m_total, interval_sec), "requests/s"),
+      Metric("dir_lookup_hits", "",
+             d_ratio(m2m_hits, m2m_total), "100%"),
+      Metric("dir_lookup_misses", "",
+             d_ratio(m2m_miss, m2m_total), "100%"),
+      Metric("dir_update_requests", "",
+             d_ratio(m2m_upd + cha_upd, interval_sec), "requests/s"),
+      Metric("dir_update_bw", "",
+             d_ratio(m2m_upd + cha_upd, interval_sec), f"{scale}MB/s"),
+  ])
+
+
 def UncoreMem() -> Optional[MetricGroup]:
   try:
     loc_rds = Event("UNC_CHA_REQUESTS.READS_LOCAL", "UNC_H_REQUESTS.READS_LOCAL")
@@ -902,6 +937,7 @@ all_metrics = MetricGroup("", [
     IntelMlp(),
     IntelPorts(),
     IntelSwpf(),
+    UncoreDir(),
     UncoreMem(),
     UncoreMemBw(),
 ])
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#36 lore raw

PATCH 18/20 perf jevents: Add C-State metrics from the PCU PMU for Intel

In reply to Ian Rogers

Use occupancy events fixed in:
https://lore.kernel.org/lkml/[email protected]/

Metrics are at the socket level referring to cores, not hyperthreads.

---
 tools/perf/pmu-events/intel_metrics.py | 27 ++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)
tools/perf/pmu-events/intel_metrics.py +27 -0
index 07aafdf77f79..1b9f7cd3b789 100755
@@ -800,6 +800,32 @@ def IntelLdSt() -> Optional[MetricGroup]:
   ], description = "Breakdown of load/store instructions")
 
 
+def UncoreCState() -> Optional[MetricGroup]:
+  try:
+    pcu_ticks = Event("UNC_P_CLOCKTICKS")
+    c0 = Event("UNC_P_POWER_STATE_OCCUPANCY.CORES_C0")
+    c3 = Event("UNC_P_POWER_STATE_OCCUPANCY.CORES_C3")
+    c6 = Event("UNC_P_POWER_STATE_OCCUPANCY.CORES_C6")
+  except:
+    return None
+
+  num_cores = Literal("#num_cores") / Literal("#num_packages")
+
+  max_cycles   = pcu_ticks * num_cores;
+  total_cycles = c0 + c3 + c6
+
+  # remove fused-off cores which show up in C6/C7.
+  c6 = Select(max(c6 - (total_cycles - max_cycles), 0),
+              total_cycles > max_cycles,
+              c6)
+
+  return MetricGroup("cstate", [
+      Metric("cstate_c0", "C-State cores in C0/C1", d_ratio(c0, pcu_ticks), "cores"),
+      Metric("cstate_c3", "C-State cores in C3", d_ratio(c3, pcu_ticks), "cores"),
+      Metric("cstate_c6", "C-State cores in C6/C7", d_ratio(c6, pcu_ticks), "cores"),
+  ])
+
+
 def UncoreDir() -> Optional[MetricGroup]:
   try:
     m2m_upd = Event("UNC_M2M_DIRECTORY_UPDATE.ANY")
@@ -937,6 +963,7 @@ all_metrics = MetricGroup("", [
     IntelMlp(),
     IntelPorts(),
     IntelSwpf(),
+    UncoreCState(),
     UncoreDir(),
     UncoreMem(),
     UncoreMemBw(),
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#37 lore raw

PATCH 19/20 perf jevents: Add local/remote miss latency metrics for Intel

In reply to Ian Rogers

Derive from CBOX/CHA occupancy and inserts the average latency as is provided in Intel's uncore performance monitoring reference.

---
 tools/perf/pmu-events/intel_metrics.py | 59 ++++++++++++++++++++++++++
 1 file changed, 59 insertions(+)
tools/perf/pmu-events/intel_metrics.py +59 -0
index 1b9f7cd3b789..cdeb58e17c5e 100755
@@ -617,6 +617,64 @@ def IntelL2() -> Optional[MetricGroup]:
   ], description = "L2 data cache analysis")
 
 
+def IntelMissLat() -> Optional[MetricGroup]:
+  try:
+    ticks = Event("UNC_CHA_CLOCKTICKS", "UNC_C_CLOCKTICKS")
+    data_rd_loc_occ = Event("UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL",
+                            "UNC_CHA_TOR_OCCUPANCY.IA_MISS",
+                            "UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE",
+                            "UNC_C_TOR_OCCUPANCY.MISS_OPCODE")
+    data_rd_loc_ins = Event("UNC_CHA_TOR_INSERTS.IA_MISS_DRD_LOCAL",
+                            "UNC_CHA_TOR_INSERTS.IA_MISS",
+                            "UNC_C_TOR_INSERTS.MISS_LOCAL_OPCODE",
+                            "UNC_C_TOR_INSERTS.MISS_OPCODE")
+    data_rd_rem_occ = Event("UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_REMOTE",
+                            "UNC_CHA_TOR_OCCUPANCY.IA_MISS",
+                            "UNC_C_TOR_OCCUPANCY.MISS_REMOTE_OPCODE",
+                            "UNC_C_TOR_OCCUPANCY.NID_MISS_OPCODE")
+    data_rd_rem_ins = Event("UNC_CHA_TOR_INSERTS.IA_MISS_DRD_REMOTE",
+                            "UNC_CHA_TOR_INSERTS.IA_MISS",
+                            "UNC_C_TOR_INSERTS.MISS_REMOTE_OPCODE",
+                            "UNC_C_TOR_INSERTS.NID_MISS_OPCODE")
+  except:
+    return None
+
+  if (data_rd_loc_occ.name == "UNC_C_TOR_OCCUPANCY.MISS_LOCAL_OPCODE" or
+      data_rd_loc_occ.name == "UNC_C_TOR_OCCUPANCY.MISS_OPCODE"):
+    data_rd = 0x182
+    for e in [data_rd_loc_occ, data_rd_loc_ins, data_rd_rem_occ, data_rd_rem_ins]:
+      e.name += f"/filter_opc={hex(data_rd)}/"
+  elif data_rd_loc_occ.name == "UNC_CHA_TOR_OCCUPANCY.IA_MISS":
+    # Demand Data Read - Full cache-line read requests from core for
+    # lines to be cached in S or E, typically for data
+    demand_data_rd = 0x202
+    #  LLC Prefetch Data - Uncore will first look up the line in the
+    #  LLC; for a cache hit, the LRU will be updated, on a miss, the
+    #  DRd will be initiated
+    llc_prefetch_data = 0x25a
+    local_filter = (f"/filter_opc0={hex(demand_data_rd)},"
+                    f"filter_opc1={hex(llc_prefetch_data)},"
+                    "filter_loc,filter_nm,filter_not_nm/")
+    remote_filter = (f"/filter_opc0={hex(demand_data_rd)},"
+                     f"filter_opc1={hex(llc_prefetch_data)},"
+                     "filter_rem,filter_nm,filter_not_nm/")
+    for e in [data_rd_loc_occ, data_rd_loc_ins]:
+      e.name += local_filter
+    for e in [data_rd_rem_occ, data_rd_rem_ins]:
+      e.name += remote_filter
+  else:
+    assert data_rd_loc_occ.name == "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_LOCAL", data_rd_loc_occ
+
+  loc_lat = interval_sec * 1e9 * data_rd_loc_occ / (ticks * data_rd_loc_ins)
+  rem_lat = interval_sec * 1e9 * data_rd_rem_occ / (ticks * data_rd_rem_ins)
+  return MetricGroup("miss_lat", [
+      Metric("miss_lat_loc", "Local to a socket miss latency in nanoseconds",
+             loc_lat, "ns"),
+      Metric("miss_lat_rem", "Remote to a socket miss latency in nanoseconds",
+             rem_lat, "ns"),
+  ])
+
+
 def IntelMlp() -> Optional[Metric]:
   try:
     l1d = Event("L1D_PEND_MISS.PENDING")
@@ -960,6 +1018,7 @@ all_metrics = MetricGroup("", [
     IntelIlp(),
     IntelL2(),
     IntelLdSt(),
+    IntelMissLat(),
     IntelMlp(),
     IntelPorts(),
     IntelSwpf(),
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog
author reviewer
#38 lore raw

PATCH 20/20 perf jevents: Add upi_bw metric for Intel

In reply to Ian Rogers

Break down UPI read and write bandwidth using uncore_upi counters.

---
 tools/perf/pmu-events/intel_metrics.py | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
tools/perf/pmu-events/intel_metrics.py +22 -0
index cdeb58e17c5e..219541a30450 100755
@@ -1006,6 +1006,27 @@ def UncoreMemBw() -> Optional[MetricGroup]:
   ], description = "Memory Bandwidth")
 
 
+def UncoreUpiBw() -> Optional[MetricGroup]:
+  try:
+    upi_rds = Event("UNC_UPI_RxL_FLITS.ALL_DATA")
+    upi_wrs = Event("UNC_UPI_TxL_FLITS.ALL_DATA")
+  except:
+    return None
+
+  upi_total = upi_rds + upi_wrs
+
+  # From "Uncore Performance Monitoring": When measuring the amount of
+  # bandwidth consumed by transmission of the data (i.e. NOT including
+  # the header), it should be .ALL_DATA / 9 * 64B.
+  scale = (64 / 9) / 1_000_000
+  return MetricGroup("upi_bw", [
+      Metric("upi_bw_read", "UPI read bandwidth",
+             d_ratio(upi_rds, interval_sec), f"{scale}MB/s"),
+      Metric("upi_bw_write", "DDR memory write bandwidth",
+             d_ratio(upi_wrs, interval_sec), f"{scale}MB/s"),
+  ], description = "UPI Bandwidth")
+
+
 all_metrics = MetricGroup("", [
     Cycles(),
     Idle(),
@@ -1026,6 +1047,7 @@ all_metrics = MetricGroup("", [
     UncoreDir(),
     UncoreMem(),
     UncoreMemBw(),
+    UncoreUpiBw(),
 ])
 
 if args.metricgroups:
Signature · 1 line
2.44.0.278.ge034bb2e1d-goog