Author: Robert Hyatt
Date: 12:19:54 04/23/01
Go up one level in this thread
On April 23, 2001 at 14:30:59, Jonas Cohonas wrote: >I have read a lot of posts here about the speedup on dual machines being about >1.4-1.8 depending on the program, hardware etc... but can anyone with dual >systems post their kN/s results v results from single processor results, with >Deep Fritz, Deep Junior, Deep shredder etc? > >Regards >Jonas NPS is the _wrong_ thing to measure. On a dual it should be close to 2x what it is on an equivalent single. Unfortunately the dual will search _more_ nodes for a given position (search overhead) that causes the less- than-perfect speedup. 1.7x is a good number...
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.