Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: A [halfway portable] program to benchmark the two approaches

Author: Scott Gasch

Date: 00:18:59 06/18/02

Go up one level in this thread


You might want to __forceinline your shift function (or make it a #define).  I
think you'll find that both methods are blazingly fast -- your call to rand() is
going to dominate the loop.  The shift will prove faster in real life
situations, I think, because your p2 array being in processor cache all the time
is unrealistic.  A shift is always one cycle, a memory access is slower if it
doesn't hit the cache (and maybe even if it does).

Scott



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.