Author: Omid David Tabibi
Date: 17:35:18 08/06/03
Go up one level in this thread
On August 06, 2003 at 20:10:26, Gian-Carlo Pascutto wrote: >>I'm not familar with GCC. I guess you compared a x86-64 executable running on a >>single opteron processor, all sixteen 64-bit gp-registers used, with a x86-32 >>executable. > >Yes. The x86-32 executable has significant amounts of optimized assembly, >the AMD64 compile was straight from the reference C code. It compiled >directly BTW, no porting issues (unlike Mac OS version!). > >>A few questions: >> >>Do you use a lot of 64-bit stuff in Deep Sjeng? > >Depends on what a lot is :) Deep Sjeng can >certainly take advantage of the native 64 bit >processing, if that helps you. Is Sjeng bitboard based? It is interesting to know that in the context of the old discussion regarding the benefit of bitboard engines from 64-bit processors (in comparison to 0x88 and other non-bitboard engines...). > >>Did you use profile guided optimization? > >Yes. They give a performance gain of 0.8%. > >-- >GCP
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.