Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: Hardware chess evaluation for everyone

Author: Robert Hyatt

Date: 16:45:00 07/02/98

Go up one level in this thread


On July 02, 1998 at 16:42:50, Tim Mann wrote:

>Digital (now part of Compaq) has a PCI board based on high-end Xilinx FPGAs,
>called the PAMette.  There are five FPGAs on the board, four SIMM slots for
>additional RAM, and some other stuff.  The price is $2495.00 to educational and
>research customers, about 100 times what you're aiming for, but you should take
>a look at the Web page, http://www.research.digital.com/SRC/pamette/.  It has a
>lot of interesting information.
>
>As I understand it, PCI is very complex and ill-specified. It's possible to do a
>PCI interface in a Xilinx, avoiding the need for a separate PCI bridge chip --
>and indeed the PAMette works this way -- but designing the circuit from scratch
>would be a major effort. The PAMette actually dedicates one of the Xilinx chips
>to the PCI interface, though perhaps there is enough room left on the chip to do
>other things too; I don't know about that.
>
>I get the impression from the hardware folks here that programming FPGAs is
>quite hard in general, and that there aren't many algorithms that actually run
>faster in an FPGA than on a general purpose sequential CPU.  But maybe chess
>would be one of them...
>
>	--Tim
>
>On June 29, 1998 at 18:57:34, David Fotland wrote:
>
>>
>>Field programmable gate arrays range from 40,000 gates at $3 to over 500K
>>gates with 270K bits of RAM, and can clock up to 80 Mhz.  This is at least
>>as dense and fast as the Deep Blue chips.  See www.xilinx.com for example.
>>
>>It would be easy to put together a PCI card with one of these chips on it.
>>Chess developers would then all have access to similar hardare
>>technology as Deep Blue.  If someone designed the basic hardware eval
>>and search blocks, it would be easy for someone with a software background
>>to modify the evaluation function and reprogram the FPGA.
>>
>>I did a short search and didn't find anyone already selling an FPGA PCI
>>evaluation card, but there may be one.  We may even be able to convince
>>an FPGA vendor to design the PCI card for the publicity.  If not I could
>>do it, or anyone with a little bit of hardware background.
>>
>>Anyone interested in using or buying such a card?  With a little volume
>>the card would be inexpensive.  Perhaps $25 since it just a small PC board,
>>a cheap connector, and the FPGA chip (which would also be the PCI interface).
>>
>>David Fotland


the main difficulty is in thinking about the application in terms of
a finite state automaton, rather than a procedural-oriented piece of
software as most now do.  I've programmed these things in the past,
and they are actually fairly simple devices, but using them efficiently
becomes a headache since (at least when I did it) there was no good
"silicon-type compiler" I could use to help me...



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.