Author: Dann Corbit
Date: 15:43:01 02/03/06
Go up one level in this thread
On February 03, 2006 at 17:37:40, Richard Harrison wrote: >"Very interesting article that talks about building a machine that is the equal >of Deep Blue using off the shelf parts. Along the way it tells us a lot about >how Deep Blue is put together." > >http://rootprompt.org/article.php3?article=9669 The author of the article does not understand SMP loss or even that there is (currently) no such thing as a 44 CPU SMP box. The ChessBrain project mentioned gets about 1% efficiency when scaled to a degree necessary for DeepBlue like numbers. Here is the hardware of what they call "BabyBlue" 2 ea. 2.2GHz 64-bit dual-core AMD Opteron (model 275) microprocessors Here is the software: Deep Fritz 8 Multiprocessor Edition I would hazard a guess that a half dozen systems of posters in this forum would be equal or better. The article is interesting enough, but the author is a chess enthusiast who does not seem to know a whole lot about computer chess programs and systems. In my opinion, the title of the article does not match the content. I would classify the article as about 70% accurate (which translates to about 30% wrong). IMO-YMMV
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.