STINNER Victor added the comment: Good news. On a microbenchmark, the patch makes func(*tuple) between 14% and 18% faster. See attached bench.py. I ran the benchmark on Linux with isolated CPUs to get reliable results. https://haypo-notes.readthedocs.org/microbenchmark.html
$ ./python-orig ~/prog/HG/misc/python/benchmark.py script bench.py --file=orig $ ./python-patched ~/prog/HG/misc/python/benchmark.py script bench.py --file=patch $ ./python-orig ~/prog/HG/misc/python/benchmark.py compare_to orig patch Common platform: CPU model: Intel(R) Core(TM) i7-2600 CPU @ 3.40GHz SCM: hg revision=75f40345d784 branch=default date="2016-04-19 22:29 +0200" Timer info: namespace(adjustable=False, implementation='clock_gettime(CLOCK_MONOTONIC)', monotonic=True, resolution=1e-09) Timer: time.perf_counter Bits: int=32, long=64, long long=64, size_t=64, void*=64 Python unicode implementation: PEP 393 CFLAGS: -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes Platform: Linux-4.4.4-301.fc23.x86_64-x86_64-with-fedora-23-Twenty_Three Platform of campaign orig: Timer precision: 62 ns Python version: 3.6.0a0 (default:75f40345d784, Apr 19 2016, 23:07:49) [GCC 5.3.1 20151207 (Red Hat 5.3.1-2)] Date: 2016-04-19 23:08:21 Platform of campaign patch: Timer precision: 61 ns Python version: 3.6.0a0 (default:084d5315dd50, Apr 19 2016, 23:06:38) [GCC 5.3.1 20151207 (Red Hat 5.3.1-2)] Date: 2016-04-19 23:08:39 -----------------------------------------------------+------------+-------------- Tests | orig | patch -----------------------------------------------------+------------+-------------- def func(a, b, c): pass args=(1, 2, 3); func(*args) | 127 ns (*) | 104 ns (-18%) def func(*args): pass args=(1, 2, 3); func(*args) | 147 ns (*) | 126 ns (-14%) def func(*args): pass args=(2, 3, 4); func(1, *args) | 154 ns (*) | 154 ns -----------------------------------------------------+------------+-------------- Total | 429 ns (*) | 384 ns (-10%) -----------------------------------------------------+------------+-------------- ---------- Added file: http://bugs.python.org/file42524/bench.py _______________________________________ Python tracker <rep...@bugs.python.org> <http://bugs.python.org/issue26802> _______________________________________ _______________________________________________ Python-bugs-list mailing list Unsubscribe: https://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com
