Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: benchmark test for fun (and for Vincent) , that means *1.862 Speedup

Author: Robert Hyatt

Date: 10:24:34 09/05/02

Go up one level in this thread


On September 05, 2002 at 12:52:06, Volker Pittlik wrote:

>On September 05, 2002 at 11:07:38, Robert Hyatt wrote:
>
>...
>>
>>He ran the test wrong.  It won't affect the NPS much, however, as
>>we are not measuring SMP speedup, but simply raw NPS speedup, to
>>address your ridiculous claim about smp vs non-smp crafty.
>...
>
>Sorry, I've restarted Crafty every time. My logfiles show the same thing every
>time. But this is possibly another problem what is not important in this debate.
>Just ignore my results.
>
>Volker

OK... your output looked like you first ran with mt=1, then did a
"new" and "mt=2" and ran again.  If you edited what you sent, then that
would explain this.

Personally, I don't think it is a big deal either way as we are not measuring
hashing or anything else, just raw NPS.  If you restarted between the two
runs, then your data belongs in the total.  I will try to re-read all the
posts this afternoon and post a new summary.



>
>...
>
>>>>>              clearing hash tables
>>>>>              time surplus   0.00  time limit 3:00 (3:00)
>>>>>         nss  depth   time  score   variation (1)
>>>>>                8->   0.80  -0.63   1. ... Bxe4 2. Bxe4 <HT>  //*I have no idea why



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.