Author: Vincent Diepeveen
Date: 09:14:04 10/22/02
Go up one level in this thread
On October 22, 2002 at 11:41:08, Robert Hyatt wrote: >On October 22, 2002 at 11:15:33, Vincent Diepeveen wrote: > >>On October 22, 2002 at 01:13:43, Timothy J. Frohlick wrote: >> >>fritz is in pc assembly. Only DIEP would work on this machine >>at the biggest partition of it. I do not know which other >>programs would work on it. You need to special write for it. > >This is not a NUMA machine... therefore my limitation 'within the same partition'. Using NUMA is superb of course but my thing works on such cluster partitions too when using that library. Of course it's a bit slower for each cpu than NUMA, but that's no major worry. You get multiplied by the speed of the number of cpu's within the same partition then. Of course i do not know what the maximum number of cpu's of this machine will be that can run within the same partition instead of hosted on other nodes with hundreds of thousands of clocks of latency :) > >> >>>Sandia Labs is just down the street from me on Kirtland Air Force Base. >>>I lived about 1 kilometer from the labs when I lived on base. This "Red >>>Storm" machine will do 40,000,000,000,000 operations per second. Put Fritz X >>>on that and smoke it. >>> >>> >>>TJF >>> >>>On October 22, 2002 at 00:06:51, Sally Weltrop wrote: >>> >>>>http://www.theregister.co.uk/content/3/27718.html
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.