Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Are bitboards really faster on 64-bit hardware?

Author: Russell Reagan

Date: 19:44:43 11/06/03

Go up one level in this thread


On November 06, 2003 at 19:24:48, Robert Hyatt wrote:

>First question:  are you running the _same_ test Eugene ran?  If not,
>comparisons mean little.

Originally I just ran the bench command. If I change the pawn hash size as he
did, it runs slower on my machine (1,281,173 nps), which results in about a 52%
increase, not 59%.

I don't have Crafty 19.5, and 19.3 doesn't display the output of the bench
command like Eugene's post does. I just get dots. So I don't know if it's
searching the same positions or not. Is there a way to turn that on? Or is that
something new in 19.4 or 19.5?

--------------------------------------------------------------------------------

Crafty v19.3 (1 cpus)

White(1): hashp 1m
pawn hash table memory =  768K bytes.
White(1): hashp 8m
pawn hash table memory =    6M bytes.
White(1): bench
Running benchmark. . .
......
Total nodes: 62777490
Raw nodes per second: 1281173
Total elapsed time: 49
SMP time-to-ply measurement: 13.061224
White(1): bench
Running benchmark. . .
......
Total nodes: 62777490
Raw nodes per second: 1281173
Total elapsed time: 49
SMP time-to-ply measurement: 13.061224
White(1):



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.