Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: A quote from Hsu's IEEE Micro article

Author: Andrew Williams

Date: 04:21:28 07/27/00

Go up one level in this thread


On July 26, 2000 at 18:04:58, Robert Hyatt wrote:

>On July 26, 2000 at 17:22:38, Tom Kerrigan wrote:
>
>>On July 26, 2000 at 14:55:04, Robert Hyatt wrote:
>>

[LARGE SNIP]

>>
>>In fact, it's directly contradicted by two articles. One article says 200M NPS.
>>The other article says 277M to 555M NPS. Even the IBM web site says 100M, and
>>you'd think it would have the most optimistic number.
>
>
>It has the DB1 number, for reasons unknown.  IE it appears (to me) that
>perhaps someone started to update it, but never finished, leaving old and
>new numbers mixed up horribly.
>

I've snipped a lot of the "debate" because I don't believe it is worth
repeating. However, I do have the IEEE article to hand here, so here is
what Hsu said.


=== QUOTE FROM IEEE ARTICLE STARTS ===
"The chess chips provided enormous computational power. On a general-purpose
computer, the computation done by the chess chip for a single chess position
requires up to 40000 general-purpose instructions. At 2 to 2.5 million chess
positions/s, one chess chip operates at the equivalent of a 100-billion-
instructions/s supercomputer. Because this speed was adequate, I did not
spend much time optimizing speed."

[IRRELEVANT REFERENCE TO A DIAGRAM SNIPPED]

"The 1997 version of Deep Blue included 480 chess chips. Since each chess
chip could search 2 to 2.5 million chess positions/s, the "guaranteed not
to exceed" system speed reached one billion chess positions per second, or
40 tera operations. This assumes that, on average, each chess position needs
40000 general purpose instructions to process. The sustained speed reached
200 million chess positions/s, or about 8 tera operations."
=== QUOTE FROM IEEE ARTICLE ENDS ===

I think it's possible to find most of the figures that have been used in
the discussion here in the snippet I have quoted. The reference for this
article is:

Feng-hsiung Hsu, "IBM's Deep Blue Chess Grandmaster Chips", IEEE Micro,
March-April 1999, pages 70-81

Andrew Williams



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.