Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Branchless code

Author: Russell Reagan

Date: 19:31:16 11/18/02

Go up one level in this thread


On November 18, 2002 at 21:40:36, Robert Hyatt wrote:

>It is way not clear.  A memory read is so much worse than a mis-predicted
>branch it isn't funny.  We are talking hundreds of clocks rather than dozens.
>
>So it is going to depend on whether the data is in cache or not, which means
>how long ago it was referenced, what has been referenced since, etc...

So how long is "recent enough" in computer time for it to still be in the cache?
Is 10 ms a long time or are we talking 10 seconds?

It seems like something referenced in the move generation or evaluation would be
referenced often enough to be in the cache.



This page took 0 seconds to execute

Last modified: Thu, 15 Apr 21 08:11:13 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.