Author: Robert Hyatt
Date: 07:07:24 09/07/02
Go up one level in this thread
On September 06, 2002 at 22:06:37, K. Burcham wrote: > > > >thanks. >I find this one very interesting. > >"Average Solve Time speedup over 14 positions: 1.42x" > >kburcham That seems to be a common number for AMD machines. Eugene has posted several results where Intel boxes were doing 1.9x on some particular test, and two different 2-cpu AMD boxes were getting 1.4X. Similar things happen with raw NPS which suggests that the AMD boxes have a memory bottleneck that really becomes apparent with two cpus..
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.