Author: Matthew Hull
Date: 13:56:24 04/28/05
Go up one level in this thread
On April 28, 2005 at 16:38:08, Jay Scott wrote: >On April 27, 2005 at 12:11:33, Matthew Hull wrote: > >>Unless someone could figure out how to use the vector processor for chess >>knowledge. Bob did that on Cray machines, but the "altivec" type processor is >>probably much more primitive and less flixible than the Cray. > >AltiVec is a short-vector processor, which on the face of it ought to be more >suitable for chess than a Cray pipeline-vector processor. In either case, to get >big wins you have to code for it from the ground up--that's the holdup. > > Jay I wonder if Bob has a comment on the relative merits of modern vector processors here. I know crafty was designed to get away from hardware specific coding, though it does have special assember routines for x86 and Sparc.
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.