Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Multi processors chess question

Author: Tony Werten

Date: 00:19:08 03/06/01

Go up one level in this thread


On March 05, 2001 at 10:17:47, Bas Hamstra wrote:

>On March 05, 2001 at 06:13:35, Tony Werten wrote:
>
>>On March 05, 2001 at 03:07:09, Pham Minh Tri wrote:
>>
>>>Hi all,
>>>
>>>If a chess program runs on a computer with N processors, how many times is it
>>>faster? N times? (compare with the same computer with 1 processor)
>>
>>It's N times faster. Unfortunately it's doing some things double and can't
>>completely use all the knowledge gained from the search of the other processors.
>>
>>The best "effective speedup" I've seen is about 3 for 4 processors.
>>
>>cheers,
>>
>>Tony
>
>I hope this does not mean that you enter the May tourney in Leiden with Deep

Nope, I'll be in Greece in May.

>XiniX, ie a multi cpu version? Any case I will be there with the same laptop, a
>very aggressive Tao en a sharp book.

I'm working on the book too. Well, my program is. I think I finally got the
missing idea (Got it from a Shogi programmer )to make autocreating a book work.
It's really fun to see it "learn" gambits, without needing weeks of cpu time (my
idea)

>
>(If XiniX goes multi-cpu I suggest you change the name in XiXi!)

What you don't see ?

( For non-dutchspeakers, a wordjoke just changed into a childrensgame )

>Hope to see you!

It'll have to be oct/nov. Or is Tao going to the worldchampionships ?

cheers,

Tony

>
>:-)
>
>
>
>
>
>>
>>>
>>>Just a curious question because I have no computer with multiprocessor nor
>>>supercomputer :-(



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.