Author: Vincent Diepeveen
Date: 17:04:37 06/30/04
Go up one level in this thread
On June 30, 2004 at 18:48:31, Andreas Guettinger wrote: >On June 30, 2004 at 12:57:26, Vincent Diepeveen wrote: > >>Hello, >> >>For diep moving from 32 to 64 bits is not so interesting. But the 8==>16 >>registers is. >> >>All tested with same diep version : >> >>at windows 64 bits : >> >>net2003 32 bits : 135k nps >>amd SDK 64 bits : 130k nps >>gcc 3.4 32 bits : 130k nps (with pgo) >> >>at linux (gentoo) 64 bits : >>gcc 3.3.3 64 bits : 140k nps >> >>So it's trivial that moving from 8 to 16 registers increased it by 10k nps, >>despite also losing to larger instruction sizes. > > >Do you know if there'd be a improvement in knps using gcc 3.4 over 3.3.3 in >linux? > >regards >Andy I had problems getting bugfree compiles with 3.4, 3.3.3 editted by gentoo looked more stable to me. 3.4 i tried using mingw. -O3 at 3.3.3 already slowed diep down. all those fancy options in 3.4 didn't seem to work anyway for diep when compared with default compiles. perhaps i'll get latest snapshot from 3.4 at the dual opteron real soon too and try for the wcc 2004 version. For sure is that it's in 64 bits using 16 registers considerable faster than any windows compiler is. Linux is the place to be now!
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.