Author: Robert Hyatt
Date: 12:56:55 04/17/02
Go up one level in this thread
On April 17, 2002 at 13:50:10, K. Burcham wrote: > > >I am only interested in the 1997 Deep blue. >we know changes were made between the 1996 match >and the 1997 match that increased the strength. not only >in knowledge and software, but there was also a substantial >increase in kns with hardware improvements. below is taken from IBM >site. if all this is true, then 1997 Deep Blue was probably stronger than >1996 Deep Blue. > >thanks slate, >kburcham > > >The current version >The latest iteration of the Deep Blue computer is a 32-node IBM RS/6000 SP >high-performance computer, which utilizes the new Power Two Super Chip >processors (P2SC). Each node of the SP employs a single microchannel card >containing 8 dedicated VLSI chess processors, for a total of 256 processors >working in tandem. Deep Blue's programming code is written in C and runs under >the AIX operating system. The net result is a scalable, highly parallel system >capable of calculating 100-200 billions moves within three minutes, which is the >time allotted to each player's move in classical chess. > >Improvements in this year's model >The most prominent improvement in Deep Blue is its speed. The computer is now >running on a faster system, the latest version of the RS/6000 SP, which employs >the Power Two Super Chip (P2SC) processors. "That will give us a factor of two >speed-up over the system that played last year," says Deep Blue developer Murray >Campbell. "And in chess programs, speed is very important. The faster you are, >the stronger you play." > >This means that Deep Blue will be able to examine and evaluate twice as many >chess positions per second than last year. Exactly how many? According to the >development team, Deep Blue will be able to explore 200,000,000 positions per >second. Incidentally, Garry Kasparov can examine approximately three positions >per second. > >Deep Blue's "chess knowledge" has been significantly enhanced over the past 12 >months through the efforts of team consultant and international grandmaster Joel >Benjamin. Garry Kasparov is certainly a great chess player -- perhaps the >greatest in history -- but the new and improved Deep Blue offers a challenge >that even the world champion has yet to experience. > >The increase in computing power will also allow Deep Blue to adapt to new >strategies as the game progresses. Those following last year's match will >remember that Kasparov eventually defeated Deep Blue by switching strategies >mid-game. The development team feels that this tactic will not be as effective >this time around. > >Deep Blue's chess knowledge has also increased over the past 12 months. "We >spent a lot of time, several months, working with a grandmaster, Joel Benjamin," >states Campbell. "There are sometimes things that a grandmaster knows that are >sometimes difficult to put into a computer program. We are working hard to get >to know as much about chess as possible." Something is wrong with the writeup. DB2 used 480 chess processors, not 256. This from direct quotes from all team members and it was on the IBM site as well... Perhaps the above mixes DB1 and DB2 (I think DB1 did use 256)... Bob
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.