Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: FPGAs playing chess--an expert opinion

Author: Robert Hyatt

Date: 07:02:04 12/21/99

Go up one level in this thread


On December 21, 1999 at 00:29:33, Greg Lindahl wrote:

>On December 20, 1999 at 21:34:15, Robert Hyatt wrote:
>
>>Depends.  But if you don't pass the repetition list, then you aren't planning
>>on doing an 'engine in hardware'.
>
>Hello? I've said repeatedly that I wasn't planning on doing what you claimed I
>was; that's what the entire thread about "straw men" was about.

And as I have said before, if you don't do the entire engine, the performance
is not going to be much to write home about.  Can we get past this?  If you are
going to do only a piece of the engine, it isn't worth it.  It will be a
novelty to be sure, but not exactly on the forefront of computer chess since
the complete engine has been done in hardware for 20 years already.

>
>>As I said before, if you don't put the _entire_ engine on the board, then the
>>speedup is not going to be particularly attractive.
>
>And as I said before, I disagree with your assumptions behind your claim.


Disagree all you want.  I'll also categorically state that 2+2=4.  There
isn't any more room to argue with that than there is in my previous statement
you disagree with.  I find it interesting that (a) you state you know next to
nothing about computer chess, but then follow up with (b) you disagree with
someone that has been doing it for over 30 years and who is aware of what has
already been done hardware-wise.





>
>>So instead of bantying words, exactly _what_ are you suggesting putting on this
>>FPGA-based board?
>
>I've said repeatedly that I don't yet know. However, I have pointed out that an
>engine which spends 90% of its time doing evaluation might be able to get away
>with just putting evaluation on an FPGA-based board. I have no idea if that's
>the right idea.
>
>And no, I haven't been "bantying words".
>
>-- g



As I have said repeatedly, this was done a long time ago and found wanting.  It
is interesting, but it sounds like trying to design/build an Intel 4004
microprocessor in today's world of 700mhz Pentium III devices.  This is a non-
trivial amount of time to invest.  Shouldn't it be invested to make something
_interesting_???



This page took 0.01 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.