diff options
| author | Rich Felker <dalias@aerifal.cx> | 2011-03-30 08:58:25 -0400 |
|---|---|---|
| committer | Rich Felker <dalias@aerifal.cx> | 2011-03-30 08:58:25 -0400 |
| commit | 124b4ebc8a293e616cc0a7eaba3587c9b7ff13ec (patch) | |
| tree | 80c2bdc3f961b6acb7344d5b8eaf725d219458d0 /src/math/i386 | |
| parent | 680630011d38eb9f96f92b2f080cc60f38f6df21 (diff) | |
| download | musl-124b4ebc8a293e616cc0a7eaba3587c9b7ff13ec.tar.gz musl-124b4ebc8a293e616cc0a7eaba3587c9b7ff13ec.tar.xz musl-124b4ebc8a293e616cc0a7eaba3587c9b7ff13ec.zip | |
cheap special-case optimization for normal mutexes
cycle-level benchmark on atom cpu showed typical pthread_mutex_lock call dropping from ~120 cycles to ~90 cycles with this change. benefit may vary with compiler options and version, but this optimization is very cheap to make and should always help some.
Diffstat (limited to 'src/math/i386')
0 files changed, 0 insertions, 0 deletions