[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[gnugo-devel] weird performance problem
From: |
Arend Bayer |
Subject: |
[gnugo-devel] weird performance problem |
Date: |
Fri, 16 Apr 2004 08:45:27 +0200 (CEST) |
Tracking back some spurious 50% slowdowns for regression runs,
I found out (with oprofile) that 50% of CPU time was spent in libc.
Not completely reproducable, however. In particular, I cannot
reproduce it when linked against libc_p (profiled version) instead of
libc.
According to top, gnugo is running with over 90% of CPU time, so
it should be caused by gnugo.
Does anybody have any idea what could cause this? Below is a flat
profile of libc during such a run (according to oprofile). An update
from SuSE 8.2 to 9.0 didn't solve the problem.
Arend
Profiling through timer interrupt
samples % symbol name
6769 86.3393 __mcount_internal
665 8.4821 mcount
189 2.4107 __i686.get_pc_thunk.bx
170 2.1684 memset
27 0.3444 memcpy
6 0.0765 _int_malloc
3 0.0383 __GI___mbrtowc
2 0.0255 _int_free
1 0.0128 __GI___gettimeofday_internal
1 0.0128 __GI__dl_mcount_wrapper_check
1 0.0128 __malloc
1 0.0128 __realloc
1 0.0128 _int_realloc
1 0.0128 _nl_explode_name
1 0.0128 _nl_make_l10nflist
1 0.0128 index
1 0.0128 strlen
- [gnugo-devel] weird performance problem,
Arend Bayer <=
- Re: [gnugo-devel] weird performance problem, Paul Pogonyshev, 2004/04/16
- Re: [gnugo-devel] weird performance problem, Arend Bayer, 2004/04/16
- Re: [gnugo-devel] weird performance problem, Paul Pogonyshev, 2004/04/16
- Re: [gnugo-devel] weird performance problem, Arend Bayer, 2004/04/16
- Re: [gnugo-devel] weird performance problem, Paul Pogonyshev, 2004/04/16
- Re: [gnugo-devel] weird performance problem, Arend Bayer, 2004/04/16
- Re: [gnugo-devel] weird performance problem, Paul Pogonyshev, 2004/04/16
- [gnugo-devel] oprofile, Arend Bayer, 2004/04/18
- Re: [gnugo-devel] oprofile, Gunnar Farneback, 2004/04/18
- Re: [gnugo-devel] oprofile, Evan Daniel, 2004/04/18