Computer Chess Club Archives

Search

Messages

Subject: Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!!

Author: Robert Hyatt

Date: 07:05:38 10/13/02

Go up one level in this thread

On October 13, 2002 at 06:33:27, Gian-Carlo Pascutto wrote:

>On October 12, 2002 at 18:49:41, James T. Walker wrote:
>
>>They would
>>have to be getting almost 100% efficiency out of the 8 cpus to hit 3.5M/nps.
>
>No, that is not true. You can get an 100% speedup in NPS without
>getting 100% efficiency. This is quite easy, in fact.
>
>--
>GCP


But not on an 8-way using the fusion chipset.  the quads scale well due to 4-way
memory
interleaving.  The 8-way still uses 4-way interleaving ahd produces a
significant memory
bottleneck...

• Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!! Gian-Carlo Pascutto 07:21:05 10/13/02
  • Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!! Robert Hyatt 19:00:01 10/13/02
    • Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!! Vincent Diepeveen 08:36:41 10/14/02
      • Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!! Robert Hyatt 11:06:43 10/14/02
    • Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!! Gian-Carlo Pascutto 23:38:25 10/13/02
      • Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!! Robert Hyatt 11:07:48 10/14/02
        • Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!! Gian-Carlo Pascutto 11:35:10 10/14/02
          • Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!! Robert Hyatt 12:29:42 10/14/02
            • Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!! Gian-Carlo Pascutto 12:59:42 10/14/02
      • Re: Deep Fritz 8 Experimental hit 3.5 Millions Node Count !!! Vincent Diepeveen 08:39:41 10/14/02

This page took 0.01 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.