Faster CPython Benchmark Infrastructure

🔒 ▶️ START A BENCHMARK RUN

Results

Here are some recent and important revisions. 👉 Complete list of results.

Most recent pystats on main (22a4421)

linux x86_64 (linux)

date	fork/ref	hash/flags	vs. 3.12.6:	vs. 3.13.0rc2:	vs. base:
2025-01-31	python/d89a5f6a6e65511a5f6e	d89a5f6 (NOGIL)	1.035x ↓ 📄📈	1.072x ↓ 📄📈	1.100x ↓ 📄📈🧠
2025-01-31	python/d89a5f6a6e65511a5f6e	d89a5f6	1.074x ↑ 📄📈	1.035x ↑ 📄📈
2025-01-30	python/10ee2d9d3bcde27c75f1	10ee2d9	1.089x ↑ 📄📈	1.049x ↑ 📄📈
2025-01-30	python/10ee2d9d3bcde27c75f1	10ee2d9 (NOGIL)	1.051x ↓ 📄📈	1.083x ↓ 📄📈	1.127x ↓ 📄📈🧠
2025-01-30	python/a549f439384b4509b256	a549f43 (NOGIL)	1.047x ↓ 📄📈	1.082x ↓ 📄📈	1.111x ↓ 📄📈🧠
2025-01-30	python/a549f439384b4509b256	a549f43	1.077x ↑ 📄📈	1.034x ↑ 📄📈
2025-01-28	python/828b27680f07f1ed8302	828b276	1.030x ↑ 📄📈	1.008x ↓ 📄📈
2025-01-28	python/828b27680f07f1ed8302	828b276 (NOGIL)	1.095x ↓ 📄📈	1.128x ↓ 📄📈	1.117x ↓ 📄📈🧠

linux x86_64 (vultr)

date	fork/ref	hash/flags	vs. 3.12.6:	vs. 3.13.0rc2:	vs. base:
2025-01-31	nascheme/gh_129201_gc_mark_pr	abfc49a (NOGIL)	1.043x ↓ 📄📈	1.074x ↓ 📄📈	1.005x ↑ 📄📈🧠
2025-01-31	python/54f74b80aef8b581f2b1	54f74b8 (NOGIL)	1.026x ↓ 📄📈	1.058x ↓ 📄📈
2025-01-31	python/c3ae5c9e4ad121f8ba60	c3ae5c9 (NOGIL)	1.029x ↓ 📄📈	1.061x ↓ 📄📈	1.029x ↑ 📄📈🧠
2025-01-31	python/31c82c28f927b7e55c7d	31c82c2 (NOGIL)	1.057x ↓ 📄📈	1.087x ↓ 📄📈
2025-01-31	python/main	d89a5f6 (NOGIL)	1.026x ↓ 📄📈	1.057x ↓ 📄📈	1.104x ↓ 📄📈🧠
2025-01-31	python/d89a5f6a6e65511a5f6e	d89a5f6 (NOGIL)	1.027x ↓ 📄📈	1.059x ↓ 📄📈	1.106x ↓ 📄📈🧠
2025-01-31	python/d89a5f6a6e65511a5f6e	d89a5f6	1.086x ↑ 📄📈	1.047x ↑ 📄📈
2025-01-30	python/10ee2d9d3bcde27c75f1	10ee2d9	1.097x ↑ 📄📈	1.058x ↑ 📄📈
2025-01-30	python/10ee2d9d3bcde27c75f1	10ee2d9 (NOGIL)	1.050x ↓ 📄📈	1.080x ↓ 📄📈	1.134x ↓ 📄📈🧠
2025-01-30	nascheme/gh_129201_gc_mark_pr	e12dd2e (NOGIL)	1.054x ↓ 📄📈	1.085x ↓ 📄📈	1.006x ↓ 📄📈🧠
2025-01-30	python/4ca9fc08f89bf7172d41	4ca9fc0 (NOGIL)	1.048x ↓ 📄📈	1.079x ↓ 📄📈
2025-01-30	python/a549f439384b4509b256	a549f43 (NOGIL)	1.045x ↓ 📄📈	1.076x ↓ 📄📈	1.134x ↓ 📄📈🧠
2025-01-30	python/a549f439384b4509b256	a549f43	1.101x ↑ 📄📈	1.062x ↑ 📄📈
2025-01-29	python/25cf79a0829422bd8479	25cf79a (NOGIL)	1.072x ↓ 📄📈	1.102x ↓ 📄📈
2025-01-29	colesbury/gh_128563_revert	8014514 (NOGIL)	1.042x ↓ 📄📈	1.073x ↓ 📄📈	1.002x ↑ 📄📈🧠
2025-01-29	python/99ed3025fe8fa9079b4c	99ed302 (NOGIL)	1.043x ↓ 📄📈	1.075x ↓ 📄📈
2025-01-29	Yhg1s/load_const_defer	fcfb942 (NOGIL)	1.079x ↓ 📄📈	1.109x ↓ 📄📈	1.008x ↓ 📄📈🧠
2025-01-28	python/828b27680f07f1ed8302	828b276	1.093x ↑ 📄📈	1.054x ↑ 📄📈
2025-01-28	python/828b27680f07f1ed8302	828b276 (NOGIL)	1.076x ↓ 📄📈	1.107x ↓ 📄📈	1.155x ↓ 📄📈🧠

* indicates that the exact same versions of pyperformance was not used.

Improvement of the geometric mean of key merged benchmarks, computed with pyperf compare. The results have a resolution of 0.01 (1%).

Documentation

Running benchmarks from the GitHub web UI

Visit the 🔒 benchmark action and click the "Run Workflow" button.

The available parameters are:

• fork: The fork of CPython to benchmark. If benchmarking a pull request, this would normally be your GitHub username.
• ref: The branch, tag or commit SHA to benchmark. If a SHA, it must be the full SHA, since finding it by a prefix is not supported.
• machine: The machine to run on. One of linux-amd64 (default), windows-amd64, darwin-arm64 or all.
• benchmark_base: If checked, the base of the selected branch will also be benchmarked. The base is determined by running git merge-base upstream/main $ref.
• pystats: If checked, collect the pystats from running the benchmarks.

To watch the progress of the benchmark, select it from the 🔒 benchmark action page. It may be canceled from there as well. To show only your benchmark workflows, select your GitHub ID from the "Actor" dropdown.

When the benchmarking is complete, the results are published to this repository and will appear in the complete table. Each set of benchmarks will have:

• The raw .json results from pyperformance.
• Comparisons against important reference releases, as well as the merge base of the branch if benchmark_base was selected. These include
  • A markdown table produced by pyperf compare_to.
  • A set of "violin" plots showing the distribution of results for each benchmark.

The most convenient way to get results locally is to clone this repo and git pull from it.

Running benchmarks from the GitHub CLI

To automate benchmarking runs, it may be more convenient to use the GitHub CLI. Once you have gh installed and configured, you can run benchmarks by cloning this repository and then from inside it:

gh workflow run benchmark.yml -f fork=me -f ref=my_branch

Any of the parameters described above are available at the commandline using the -f key=value syntax.

Collecting Linux perf profiling data

To collect Linux perf sampling profile data for a benchmarking run, run the _benchmark action and check the perf checkbox. Follow this by a run of the _generate action to regenerate the plots.

License

This repo is licensed under the BSD 3-Clause License, as found in the LICENSE file.