Author: Robert Hyatt
Date: 21:07:46 12/13/03
Go up one level in this thread
On December 13, 2003 at 20:50:05, Omid David Tabibi wrote: >On December 13, 2003 at 20:29:30, Jeremiah Penery wrote: > >>On December 13, 2003 at 16:25:42, Omid David Tabibi wrote: >> >>>Vincent should have run his program on a PC for the whole event. The >>>supercomputer version of DIEP didn't have extension, nor access to EGTBs. >> >>He reported EGTB access often enough. Where did you get that information? > >Accessing EGTB is practically impossible when running on such a high number of >processors. Why? It's a NUMA box. With normal I/O available. On NUMA memory is the issue. But I/O is still _way_ slower than any remote NUMA memory.
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.