| |||||||||||||
Speeding up the page allocatorSpeeding up the page allocatorPosted Feb 26, 2009 22:45 UTC (Thu) by iabervon (subscriber, #722)In reply to: Speeding up the page allocator by bluefoxicy Parent article: Speeding up the page allocator
Why would the processor be any less likely to mispredict rep than loop? In both cases, the processor can tell exactly how many iterations should go into the pipeline because nothing else in the loop writes to the count register.
(Log in to post comments)
Speeding up the page allocator Posted Feb 27, 2009 0:01 UTC (Fri) by bluefoxicy (guest, #25366) [Link]
I was more banking on the processor realizing it doesn't even have to attempt branch prediction. *shrug*
As another poster said, rep may or may not be faster/slower than open coded loops.
|
|||||||||||||