Author: Slater Wold
Date: 12:21:42 03/30/02
Go up one level in this thread
On March 30, 2002 at 15:16:59, Jonas Cohonas wrote: >On March 30, 2002 at 14:59:20, martin fierz wrote: > >>On March 30, 2002 at 03:07:29, Slater Wold wrote: >> >>>Dan Corbit once called Crafty the "N-Reactor of Chess Engines". If this is >>>true, I might be creating the worlds largest N-Reactor Chess Program. >>> >>> >>>In the coming months, I will be working with a few people to create a hardware >>>based move generator for Crafty. I myself have written my own chess program >>>over the last few years, however find it inadequate for this project, mostly >>>because it's too simple. (Man, I am a glutton.) A 10M nps (basic) alpha/beta >>>search will prove nothing, while a "tried and true" engine like Crafty will >>>truly show the power of nodes. How does a 2M nps Crafty compare with a 10M nps >>>Crafty? Well, that's my question! >>> >>>The hardware will consist of a single FPGA on a PCI card that will be inserted >>>into the host computer. The FPGA will be used for move ordering (and returning >>>those moves in a predefined order) and generating all legal moves and passing >>>them back to the software. >>> >>>My goal in this project is to answer the age-old question, which is better, >>>quality or quantity? >>> >>>I will be using the version of Crafty that is newest release when I begin. And >>>all tests/comparisons will of course be done with the same version. The true >>>value of "hardware speedup" will be obvious here. >>> >>>My long-term goals are as follows: >>> >>>1.) to determine whether or not a significant nps increase will strengthen >>>Crafty's performance by a considerable margin; >>> >>>2.) to determine the relation between Elo and nps; >>> >>>3.) to determine if greater nps actual make and engine "smarter" >>> >> >>i don't understand your post. of course, creating a faster crafty with hardware >>is an interesting project (cf brutus). but all these questions you raise here >>can be answered without it! you can have a crafty play other engines and give it >>much more time for example (ok, pondering has to be off for this), and elo/nps >>relationship can also be done this way. i don't know what you mean by "smarter", >>but running a crafty with more time on a test suite should give you the >>answer... >>i did lots of this stuff with my checkers program, to see how much more speed >>(simulated through higher search depth) increases the playing strength. and i >>never had to program an FPGA for that :-) >> >>aloha >> martin >> >I guess the difference here is the real time aspect, which you don't get from >just having the engine run longer than the opponent or on a given test position. >If i understand Slaters post (and i am sure i don't completely) then there will >be some changes to Crafty aswell, and that along with a hardware based >corralation will either help Crafty (based on an increase in nps) or it won't. >Also if he succeeds in improving Crafty's performance, this might be a huge step >in terms of compchess, since all programs would probably benefit from this >approach too, without adding knowledge or rewriting the prog, just modifying it >as is, anyway that was my layman's view on Slaters post, maybe i am way off, but >i find the project extremly interesting, go Slater! > >Regards >Jonas > >Regards >Jonas Asking a GM to play a game, and then asking for 2 or 3 times more time wouldn't go over very well. Running Nolot for 48 hours to get a 24 hour result isn't something I am interested in. HW based move ordering is *always* more efficent and cannot usually be reproduced with software under any circumstance. There is a LOT that changes with a program when one of it's heaviest pieces are done in almost 0 time. Changes you cannot reproduce with more time. And thanks Jonas. ;)
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.