Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Importance of L2 cache speed/size for diff programs (was:..Genius speed?

Author: Tom Kerrigan

Date: 09:49:59 08/14/98

Go up one level in this thread


It doesn't really matter if you're mistaken or not. I wasn't talking about one
chess program in particular, I was talking about _any_ program that runs much
faster than one would expect on a PII (vs. a P5).

I'm not sure what there is to disagree about here.

-Tom

On August 14, 1998 at 11:46:36, fca wrote:

>On August 13, 1998 at 08:47:35, Tom Kerrigan wrote:
>
>>I'm not sure if you're complicating the issue or simplifying it too much.
>
>A third possibility doubtless obtrudes  :-)
>
>>Here are the reasons why the PII/300 is faster than the P5/200:
>>1) higher clock speed (50% faster)
>>2) improved core (~50% faster)
>>3) faster L2 cache (~100% faster)
>
>>Now, when
>
>*If*: possibility of error always possible.  Also other factors, as did actually
>emerge as a result of clarifications by blass and post by Amir.
>
>>program X scales exceptionally well,the most important factor is
>>probably the faster L2 cache, simply because of the percentages above. That
>>should explain my original post on the subject.
>
>I thought a while before replying as I've no wish to offend.
>
>"IMO this is not based on sound logic"  ;-)
>
>We agree to disagree maybe...  The other storm soon pushes this off the front
>page anyway ;-(
>
>Kind regards
>
>fca



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.