Author: Robert Hyatt
Date: 15:17:09 07/03/03
Go up one level in this thread
On July 03, 2003 at 17:16:40, Jeremiah Penery wrote: >On July 03, 2003 at 01:57:28, Ricardo Gibert wrote: > >>On July 02, 2003 at 18:53:22, Dan Andersson wrote: >> >>> For those that have waited for a faster compiler for AMD64. >>>http://www.theinquirer.org/?article=10292 >>>The links in the document contain useful information. >>>Wonder what it will do for chess programs. >>> >>>MvH Dan Andersson >> >>If you look at http://www.pgroup.com/images/pg50vpg41.jpg you will see they only >>give the relative performance to a previous version of the same compiler. No >>absolute scores. Since they do not offer any absolute scores, I would assume >>they are nothing to brag about. A 375% percent improvement over junk can still >>be junk. Do not expect miracles. > >It can be, but there's no reason to expect it to be junk. Look at Sun's >optimization of 179.art to see an extraordinary example to the contrary. >AFAIK, PCG's compiler has always had pretty good performance. It has been very good. We have used both their C and FORTRAN compilers on my cluster here with good results. I think the Intel C++ compiler is a bit better in terms of speed, however.
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.