Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Intel 8 vs MSVC 6 /w Crafty

Author: Ingo Bauer

Date: 03:17:33 02/16/04

Go up one level in this thread


Hi

I am running your binaries on a single Athlon XP/Barton with 2400 MHz (real
MHz). The fastest one is the MSVC6.SMP.



wcrafty-I8-nonsmp

EPD Kit revision date: 1996.04.21
unable to open book file [./book.bin].
book is disabled
unable to open book file [./books.bin].

Crafty v19.10

White(1): bench
Running benchmark. . .
......
Total nodes: 89942714
Raw nodes per second: 899427
Total elapsed time: 100
SMP time-to-ply measurement: 6.400000
White(1):



wcrafty-I8-smp

Initializing multiple threads.
System is SMP, not NUMA.
EPD Kit revision date: 1996.04.21
unable to open book file [./book.bin].
book is disabled
unable to open book file [./books.bin].

Crafty v19.10 (1 cpus)

White(1): bench
Running benchmark. . .
......
Total nodes: 89942714
Raw nodes per second: 881791
Total elapsed time: 102
SMP time-to-ply measurement: 6.274510
White(1):



wcrafty-MSVC6-nonsmp

EPD Kit revision date: 1996.04.21
unable to open book file [./book.bin].
book is disabled
unable to open book file [./books.bin].

Crafty v19.10

White(1): bench
Running benchmark. . .
......
Total nodes: 90002615
Raw nodes per second: 900026
Total elapsed time: 100
SMP time-to-ply measurement: 6.400000
White(1):


wcrafty-MSVC6-smp

Initializing multiple threads.
System is SMP, not NUMA.
EPD Kit revision date: 1996.04.21
unable to open book file [./book.bin].
book is disabled
unable to open book file [./books.bin].

Crafty v19.10 (1 cpus)

White(1): bench
Running benchmark. . .
......
Total nodes: 89942714
Raw nodes per second: 1022076
Total elapsed time: 88
SMP time-to-ply measurement: 7.272727
White(1):


>I was reading alot of the posts lately and I thought I would try the same as
>others with Crafty. I finally got Crafty to compile correctly after making my
>own makefile, and well winging it :)
>
>Here are the results of both compilers with a non-smp and smp build:
>
>Intel 8 SMP Build
>
>Initializing multiple threads.
>System is SMP, not NUMA.
>EPD Kit revision date: 1996.04.21
>unable to open book file [./book.bin].
>book is disabled
>unable to open book file [./books.bin].
>
>Crafty v19.10 (1 cpus)
>
>White(1): bench
>Running benchmark. . .
>......
>Total nodes: 89942714
>Raw nodes per second: 768741
>Total elapsed time: 117
>SMP time-to-ply measurement: 5.470085
>White(1):
>
>Intel 8 Non-SMP BUild
>
>EPD Kit revision date: 1996.04.21
>unable to open book file [./book.bin].
>book is disabled
>unable to open book file [./books.bin].
>
>Crafty v19.10
>
>White(1): bench
>Running benchmark. . .
>......
>Total nodes: 89942714
>Raw nodes per second: 768741
>Total elapsed time: 117
>SMP time-to-ply measurement: 5.470085
>White(1):
>
>MSVC 6.0 sp5 Non-SMP Build
>
>EPD Kit revision date: 1996.04.21
>unable to open book file [./book.bin].
>book is disabled
>unable to open book file [./books.bin].
>
>Crafty v19.10
>
>White(1): bench
>Running benchmark. . .
>......
>Total nodes: 89942714
>Raw nodes per second: 686585
>Total elapsed time: 131
>SMP time-to-ply measurement: 4.885496
>White(1):
>
>MSVC 6.0 sp5 SMP Build
>
>Initializing multiple threads.
>System is SMP, not NUMA.
>EPD Kit revision date: 1996.04.21
>unable to open book file [./book.bin].
>book is disabled
>unable to open book file [./books.bin].
>
>Crafty v19.10 (1 cpus)
>
>White(1): bench
>Running benchmark. . .
>......
>Total nodes: 89942714
>Raw nodes per second: 691867
>Total elapsed time: 130
>SMP time-to-ply measurement: 4.923077
>White(1):
>
>
>Obviously the Intel 8 compiler won.
>
>The Intel 8 compile was 12% faster than the MSVC 6.0 non-smp build, and 11%
>faster than the smp build.
>
>That is quite a speed up.
>
>I have made all 4 builds available for download for people to test, and possiby
>post their results. I would like to see a few:
>
>http://members.shaw.ca/craftychess/wcrafty-test.zip
>
>Peter.



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.