Author: Robert Hyatt
Date: 14:46:02 08/22/02
Go up one level in this thread
On August 22, 2002 at 17:39:46, Dann Corbit wrote: >Dual 2.4 GHz Xeon (1.66 SMP gain for 2 CPU's): > >F:\crafty\release>craftysmpi >EPD Kit revision date: 1996.04.21 >unable to open book file [./book.bin] for "write". >learning is disabled >unable to open book file [./books.bin]. >unable to open book learning file [./book.lrn]. >learning disabled. >unable to open position learning file [./position.bin]. >learning disabled. >hash table memory = 48M bytes. >pawn hash table memory = 5M bytes. >EGTB cache memory = 32M bytes. >draw score set to 0.00 pawns. >choose from book moves randomly (using weights.) >choose from 5 best moves. >book learning enabled >result learning enabled >position learning enabled >threshold set to 9 pawns. >0 piece tablebase files found >EGTB access enabled >using tbpath=e:\programme\winboard\nalimov >0 piece tablebase files found > >Crafty v18.9 (1 cpus) > >White(1): mt=2 >max threads set to 2 >White(1): bench >Running benchmark. . . >...... >Total nodes: 72876680 >Raw nodes per second: 1550567 >Total elapsed time: 47 >SMP time-to-ply measurement: 13.617021 >White(1): mt=1 >max threads set to 1 >White(1): thread 1 exiting >bench >Running benchmark. . . >...... >Total nodes: 66292130 >Raw nodes per second: 849899 >Total elapsed time: 78 >SMP time-to-ply measurement: 8.205128 >White(1): One quick note. The above is probably a misrepresentative way to run the bench command. Hash tables are persistent in Crafty. You really should run the 1 cpu test, then run the 2 cpu test after restarting. That makes sure both runs start off with the same hash table content. Otherwise the second run will have more information than the first, which can change the shape of the trees...
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.