Hi,
Mulyadi Santosa wrote:
> Pardon me, just trying to clear my own confusion. So, the key here, the
> code path, which is taken when the "likely()" test return TRUE, is
> placed right below the "jump" test so the CPU doesn't get punished by
> wrong branch prediction and therefore save a couple of CPU cycle eaten
> by code prefetch...CMIIW
I'm not sure I clearly understand your question.
When you do :
if (likely(something)) {
...
}
Then GCC arranges the code, so that the code is optimized for the case
where "something" is TRUE.
Does it makes the thing clearer ?
Thomas
--
Thomas Petazzoni
thomas.petazzoni@xxxxxxxx
--
Kernelnewbies: Help each other learn about the Linux kernel.
Archive: http://mail.nl.linux.org/kernelnewbies/
FAQ: http://kernelnewbies.org/faq/
