mirror of
https://github.com/google/benchmark.git
synced 2025-01-16 14:50:22 +08:00
376ebc2635
* Support optional, user-directed collection of performance counters The patch allows an engineer wishing to drill into the root causes of a regression, for example. Currently, only single threaded runs are supported. The feature is a build-time opt in, and then a runtime opt in. The engineer may run the benchmark executable, passing a list of performance counter names (using libpfm's naming scheme) at the command line. The counter values will then be collected and reported back as UserCounters. This is different from #240 in that it is a benchmark user opt-in, and the counter collection is transparent to the benchmark. Currently, this is only supported on platforms where libpfm is supported. libpfm: http://perfmon2.sourceforge.net/ * 'Use' values param in Snapshot when BENCHMARK_OS_WINDOWS This is to avoid unused parameter warning-as-error * Added missing include for <vector> in perf_counters.cc * Moved doc to docs * Added license blurbs
35 lines
1.5 KiB
Markdown
35 lines
1.5 KiB
Markdown
<a name="perf-counters" />
|
|
|
|
# User-Requested Performance Counters
|
|
|
|
When running benchmarks, the user may choose to request collection of
|
|
performance counters. This may be useful in investigation scenarios - narrowing
|
|
down the cause of a regression; or verifying that the underlying cause of a
|
|
performance improvement matches expectations.
|
|
|
|
This feature is available if:
|
|
|
|
* The benchmark is run on an architecture featuring a Performance Monitoring
|
|
Unit (PMU),
|
|
* The benchmark is compiled with support for collecting counters. Currently,
|
|
this requires [libpfm](http://perfmon2.sourceforge.net/) be available at build
|
|
time, and
|
|
* Currently, there is a limitation that the benchmark be run on one thread.
|
|
|
|
The feature does not require modifying benchmark code. Counter collection is
|
|
handled at the boundaries where timer collection is also handled.
|
|
|
|
To opt-in:
|
|
|
|
* Install `libpfm4-dev`, e.g. `apt-get install libpfm4-dev`.
|
|
* Enable the cmake flag BENCHMARK_ENABLE_LIBPFM.
|
|
|
|
To use, pass a comma-separated list of counter names through the
|
|
`--benchmark_perf_counters` flag. The names are decoded through libpfm - meaning,
|
|
they are platform specific, but some (e.g. `CYCLES` or `INSTRUCTIONS`) are
|
|
mapped by libpfm to platform-specifics - see libpfm
|
|
[documentation](http://perfmon2.sourceforge.net/docs.html) for more details.
|
|
|
|
The counter values are reported back through the [User Counters](../README.md#custom-counters)
|
|
mechanism, meaning, they are available in all the formats (e.g. JSON) supported
|
|
by User Counters. |