Author: Larry Griffiths
Date: 12:28:15 01/24/01
Go up one level in this thread
On January 24, 2001 at 10:40:43, Dan Andersson wrote: >I tried different alignments and it got from bad to worse, I suspect my >implementation is very different from yours. I really can find no place where >the kind of vectorizing found in MMX would seriously improve my algorithm. But I >did implement a KPk player that did a parallel search using the wider registers, >as a curio only. > >Regards Dan Andersson I have a Pentium III and trying to optimize code is a lot different than the old days. I can reduce the number of instructions in a piece of code and the execution time increases sometimes. Go figure...
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.