STINNER Victor added the comment: I ran again the benchmark on long_fl.patch of issue #26341 with -b all. The problem is that I don't know what to think about the benchmark, to me all these number only look like noise :-/ If we ignore changes smaller than 1.05 (positive or negative), the patch has no impact on performance on such macro benchmark.
I didn't say that the patches are useless :-) We may focus on micro-benchmark? $ ~/bin/taskset_isolated.py time python3 -u perf.py --rigorous ../default/python.orig ../default/python_long_fl -b all Report on Linux smithers 4.3.4-300.fc23.x86_64 #1 SMP Mon Jan 25 13:39:23 UTC 2016 x86_64 x86_64 Total CPU cores: 8 ### call_method ### Min: 0.316851 -> 0.308606: 1.03x faster Avg: 0.317870 -> 0.309778: 1.03x faster Significant (t=480.37) Stddev: 0.00014 -> 0.00026: 1.8165x larger ### etree_parse ### Min: 0.266148 -> 0.255969: 1.04x faster Avg: 0.267591 -> 0.257492: 1.04x faster Significant (t=67.72) Stddev: 0.00108 -> 0.00103: 1.0478x smaller ### etree_process ### Min: 0.218512 -> 0.225462: 1.03x slower Avg: 0.220441 -> 0.227143: 1.03x slower Significant (t=-37.15) Stddev: 0.00128 -> 0.00127: 1.0035x smaller ### fannkuch ### Min: 0.962323 -> 0.984226: 1.02x slower Avg: 0.965782 -> 0.985413: 1.02x slower Significant (t=-73.63) Stddev: 0.00213 -> 0.00160: 1.3276x smaller ### float ### Min: 0.252470 -> 0.257536: 1.02x slower Avg: 0.259895 -> 0.265731: 1.02x slower Significant (t=-9.15) Stddev: 0.00426 -> 0.00474: 1.1125x larger ### json_dump_v2 ### Min: 2.717022 -> 2.814488: 1.04x slower Avg: 2.743981 -> 2.835444: 1.03x slower Significant (t=-46.41) Stddev: 0.01375 -> 0.01411: 1.0264x larger ### mako_v2 ### Min: 0.039410 -> 0.037304: 1.06x faster Avg: 0.040038 -> 0.038094: 1.05x faster Significant (t=138.56) Stddev: 0.00024 -> 0.00037: 1.5234x larger ### meteor_contest ### Min: 0.182787 -> 0.191944: 1.05x slower Avg: 0.183526 -> 0.193532: 1.05x slower Significant (t=-147.53) Stddev: 0.00031 -> 0.00060: 1.9114x larger ### nbody ### Min: 0.232746 -> 0.221279: 1.05x faster Avg: 0.233580 -> 0.222623: 1.05x faster Significant (t=67.66) Stddev: 0.00052 -> 0.00153: 2.9467x larger ### nqueens ### Min: 0.254579 -> 0.263282: 1.03x slower Avg: 0.256874 -> 0.264082: 1.03x slower Significant (t=-57.86) Stddev: 0.00110 -> 0.00059: 1.8689x smaller ### pickle_dict ### Min: 0.502160 -> 0.490473: 1.02x faster Avg: 0.502456 -> 0.490759: 1.02x faster Significant (t=654.42) Stddev: 0.00014 -> 0.00011: 1.1950x smaller ### raytrace ### Min: 1.271059 -> 1.309407: 1.03x slower Avg: 1.274115 -> 1.313171: 1.03x slower Significant (t=-206.50) Stddev: 0.00123 -> 0.00144: 1.1698x larger ### richards ### Min: 0.162761 -> 0.158441: 1.03x faster Avg: 0.164611 -> 0.160229: 1.03x faster Significant (t=30.03) Stddev: 0.00107 -> 0.00099: 1.0761x smaller ### simple_logging ### Min: 0.279392 -> 0.286003: 1.02x slower Avg: 0.280746 -> 0.287228: 1.02x slower Significant (t=-59.16) Stddev: 0.00075 -> 0.00080: 1.0760x larger ### telco ### Min: 0.012419 -> 0.011853: 1.05x faster Avg: 0.012500 -> 0.011968: 1.04x faster Significant (t=93.79) Stddev: 0.00003 -> 0.00005: 1.3307x larger The following not significant results are hidden, use -v to show them: 2to3, call_method_slots, call_method_unknown, call_simple, chameleon_v2, chaos, django_v3, etree_generate, etree_iterparse, fastpickle, fastunpickle, formatted_logging, go, hexiom2, json_load, normal_startup, pathlib, pickle_list, pidigits, regex_compile, regex_effbot, regex_v8, silent_logging, spectral_norm, startup_nosite, tornado_http, unpack_sequence, unpickle_list. ---------- _______________________________________ Python tracker <rep...@bugs.python.org> <http://bugs.python.org/issue24165> _______________________________________ _______________________________________________ Python-bugs-list mailing list Unsubscribe: https://mail.python.org/mailman/options/python-bugs-list/archive%40mail-archive.com
