[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Gnu-arch-users] hackerlab str_ functions performance
From: |
Jani Monoses |
Subject: |
[Gnu-arch-users] hackerlab str_ functions performance |
Date: |
Fri, 3 Sep 2004 13:53:46 +0300 |
Hello
hackerlab's str_cmp, str_length and str_cpy are among the top CPU users when
running changes and inventory at least, totalling 40% of tla cpu time.
%
14664 20.3263 str_cmp
9685 13.4247 str_length
9178 12.7220 is_simple_anchored_regexp
5442 7.5434 rx_dfa_advance_to_final
5265 7.2980 str_cpy
a similar topic was raised a while ago related to mem_set0.
This crude patch changes them to calling glibc's routines and yields about a
15-20% speedup(not much)
the head of profile output changes to
14686 20.6924 is_simple_anchored_regexp
8642 12.1765 rx_dfa_advance_to_final
4459 6.2827 hash_key
3094 4.3594 mem_move
2474 3.4858 rx_regmatch
Most of the times tla is I/O bound so these optimizations might not be that
important though.
Jani
- [Gnu-arch-users] hackerlab str_ functions performance,
Jani Monoses <=
- Re: [Gnu-arch-users] hackerlab str_ functions performance, Yann Droneaud, 2004/09/03
- Re: [Gnu-arch-users] hackerlab str_ functions performance, Andrew Suffield, 2004/09/03
- Re: [Gnu-arch-users] hackerlab str_ functions performance, Yann Droneaud, 2004/09/03
- Re: [Gnu-arch-users] hackerlab str_ functions performance, Andrew Suffield, 2004/09/03
- Re: [Gnu-arch-users] hackerlab str_ functions performance, Florian Weimer, 2004/09/05
- Re: [Gnu-arch-users] hackerlab str_ functions performance, Jan Hudec, 2004/09/05
- Re: [Gnu-arch-users] hackerlab str_ functions performance, Florian Weimer, 2004/09/05
- Re: [Gnu-arch-users] hackerlab str_ functions performance, Yann Droneaud, 2004/09/05