Computer Chess Club Archives

Search

Messages

Subject: Re: G4+ branch misprediction

Author: Tom Kerrigan

Date: 11:23:08 01/29/02

Go up one level in this thread

On January 28, 2002 at 16:28:46, Dan Andersson wrote:

>But he ratio will be big due to the small number of stages. And that makes any
>new G# processors likely to plummet in performance. Unless they do a radical
>re-design.
>
>MvH Dan Andersson

What ratio? You're confused. Smaller pipelines are always better for IPC, just
not clock speed.
-Tom

• Re: G4+ branch misprediction Dan Andersson 12:30:51 01/29/02
  • Re: G4+ branch misprediction Tom Kerrigan 20:48:32 01/29/02
    • Re: G4+ branch misprediction Dan Andersson 10:17:58 01/30/02
      • Re: G4+ branch misprediction Eugene Nalimov 10:37:41 01/30/02
        • Re: G4+ branch misprediction Dan Andersson 10:46:12 01/30/02
          • Re: G4+ branch misprediction Eugene Nalimov 13:44:26 01/30/02
            • Re: G4+ branch misprediction Dan Andersson 15:08:41 01/30/02
              • And I prefer the COSBI benchmark to the SPEC for several reasons. Dan Andersson 15:12:30 01/30/02
    • Re: G4+ branch misprediction Eugene Nalimov 22:00:19 01/29/02
      • Re: G4+ branch misprediction Vincent Diepeveen 05:27:06 01/30/02
        • Re: G4+ branch misprediction Eugene Nalimov 10:15:25 01/30/02
      • Re: G4+ branch misprediction Tom Kerrigan 23:45:29 01/29/02
        • Re: G4+ branch misprediction Eugene Nalimov 10:13:40 01/30/02
        • Re: G4+ branch misprediction Robert Hyatt 07:37:41 01/30/02
          • Re: G4+ branch misprediction Eugene Nalimov 10:14:12 01/30/02

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.