Author: Robert Hyatt
Date: 20:29:09 09/03/02
Go up one level in this thread
On September 03, 2002 at 22:03:41, Eugene Nalimov wrote: >On September 03, 2002 at 20:13:00, Robert Hyatt wrote: > >[... skipped ...] > >>That is up to you to believe or not. Doesn't matter to me. Any more than >>it matters whether vincent thinks I can get a speedup > 1.4 on 2 cpus or not. >>What he _believes_ simply doesn't matter. The _results_ matter... And those >>I stand by, completely... > >That 1.4x looks suspiciously close to 1.4x raw nps speedup I observed for Crafty >on the dual Athlon system. Guess what system Vincent uses himself if in several >CCC posts he mentioned "dual K7 system"? > >Actually, today I measured Crafty's nps raw on another Athlon system in friend's >office. It was 1.41x. Of course that is better than 1.4x I reported earlier, >but... > >Somebody here reported ~1.6x speedup for the dual Athlon, but that is still much >worse than 1.9x for dual PIII and 1.89x for dual P4. > >Answering some question: "my" Athlon has Asus motherboard. > >Thanks, >Eugene I had already told vincent about your previous post about speedups on AMD vs speedups on Intel. But of course he isn't going to let that get in the way of his "you can't do > 1.4 with two processors because that is all you get on my machine." Even after explaining it to him, it won't matter one iota... I ran a test on a dual PIV/2ghz WinXP machine, and it looked pretty good. The dual PIV was no faster than my quad 700, but the one to two cpu comparison was 1.91 over two quick test runs... This is a dell machine btw... it seemed to hit about 1.6M NPS which seemed low, but it is also one of the slow memory boxes that seems to not do so well on random accesses.
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.