Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: its possible to make 1 billion nodes/sec chip 2day- Hsu

Author: Slater Wold

Date: 10:29:12 10/16/02

Go up one level in this thread


On October 16, 2002 at 12:30:16, Gian-Carlo Pascutto wrote:

>On October 16, 2002 at 11:40:35, Slater Wold wrote:
>
>>On October 16, 2002 at 11:28:34, Gian-Carlo Pascutto wrote:
>>
>>>On October 16, 2002 at 11:03:33, emerson tan wrote:
>>>
>>>>If the cost is not that high maybe Hsu should make ala chessmachine that can be
>>>>plug into computers (assuming that he has no legal obligation from ibm) The
>>>>desktop pc is a long way from hiting 1billion nodes/sec. I think most of the
>>>>professional chessplayers and serious chess hobbyist will buy. He can easily >get 1 million orders. 1 billion nodes/sec, mmm....:)
>>>
>>>I would keep my eyes open at Brutus. Got 3Mnps with an extensive evaluation
>>>in a 25 (or 33?) Mhz package. And it's still in development.
>>>
>>>Has already proven it's strength at the World Championships (contrary to..),
>>>is new technology, and made by the team of Donninger and Kure.
>>>
>>>If this ever goes into a fast chipversion, I'd fear it much more than I'd fear
>>>Hsu's thing.
>>>
>>>--
>>>GCP
>>
>>Comparing FPGAs to what DB was is just wrong.
>
>I'll be the first to admit few technical knowledge in this area, but isn't
>it (relatively!) easy to convert the logic to a chip once you've got it
>running in a FPGA?

Yes.

>Moreover, the FPGA and Brutus are here and playing. I know, because
>they beat me :)  This is why I fear them much more than I do a vaporware
>DB chip.

Well, of course.  But it's not really fair to call DB vaporware.  It played
longer than Sjeng has.  It just doesn't play today.

>--
>GCP



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.