Sergey Fedoseev <fedoseev.ser...@gmail.com> added the comment:
I added WIP PR with discussed micro-optimization, here are benchmark results: $ python -m perf compare_to --min-speed 1 -G master.json tuple-untracked.json Slower (1): - sqlite_synth: 5.16 us +- 0.10 us -> 5.22 us +- 0.08 us: 1.01x slower (+1%) Faster (19): - python_startup: 12.9 ms +- 0.7 ms -> 12.2 ms +- 0.0 ms: 1.06x faster (-5%) - python_startup_no_site: 8.96 ms +- 0.29 ms -> 8.56 ms +- 0.03 ms: 1.05x faster (-4%) - raytrace: 882 ms +- 11 ms -> 854 ms +- 12 ms: 1.03x faster (-3%) - mako: 27.9 ms +- 0.8 ms -> 27.1 ms +- 0.3 ms: 1.03x faster (-3%) - scimark_monte_carlo: 176 ms +- 4 ms -> 171 ms +- 5 ms: 1.03x faster (-3%) - logging_format: 17.7 us +- 0.4 us -> 17.2 us +- 0.3 us: 1.03x faster (-3%) - telco: 11.0 ms +- 0.2 ms -> 10.8 ms +- 0.4 ms: 1.02x faster (-2%) - richards: 123 ms +- 2 ms -> 120 ms +- 2 ms: 1.02x faster (-2%) - pathlib: 35.1 ms +- 0.7 ms -> 34.6 ms +- 0.5 ms: 1.01x faster (-1%) - scimark_sparse_mat_mult: 6.97 ms +- 0.20 ms -> 6.88 ms +- 0.29 ms: 1.01x faster (-1%) - scimark_sor: 327 ms +- 6 ms -> 323 ms +- 3 ms: 1.01x faster (-1%) - scimark_fft: 570 ms +- 5 ms -> 562 ms +- 4 ms: 1.01x faster (-1%) - float: 184 ms +- 2 ms -> 182 ms +- 2 ms: 1.01x faster (-1%) - logging_simple: 15.8 us +- 0.4 us -> 15.6 us +- 0.3 us: 1.01x faster (-1%) - deltablue: 12.6 ms +- 0.2 ms -> 12.5 ms +- 0.3 ms: 1.01x faster (-1%) - crypto_pyaes: 186 ms +- 2 ms -> 184 ms +- 2 ms: 1.01x faster (-1%) - hexiom: 17.3 ms +- 0.1 ms -> 17.2 ms +- 0.1 ms: 1.01x faster (-1%) - sqlalchemy_declarative: 253 ms +- 4 ms -> 251 ms +- 3 ms: 1.01x faster (-1%) - spectral_norm: 225 ms +- 2 ms -> 223 ms +- 3 ms: 1.01x faster (-1%) ---------- _______________________________________ Python tracker <rep...@bugs.python.org> <https://bugs.python.org/issue36030> _______________________________________ _______________________________________________ Python-bugs-list mailing list Unsubscribe: https://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com
