Author: Dann Corbit
Date: 09:26:57 04/12/05
Go up one level in this thread
On April 11, 2005 at 21:09:03, pavel wrote: >On April 11, 2005 at 21:03:48, Dann Corbit wrote: > >>On April 11, 2005 at 20:07:14, pavel wrote: >> >>>On April 11, 2005 at 10:56:45, Dann Corbit wrote: >>> >>>>On April 10, 2005 at 12:37:10, Jorge Pichard wrote: >>>> >>>>>When will the SSDF upgrade their Hardwares? >>>>> >>>>>If we look at history, the next hardware is usually more than twice as fast as >>>>>its predecessor; Pentium 90 to Pentium 200MMX, 200MMX to Pentium II 450, Pentium >>>>>II 450 to Athlon 1200Mhz. I guess the next processor will be at least 2.5 Ghz >>>>>Athlon. It is about time for the SSDF to Upgrade their Hardware :-) >>>> >>>>This stems from a fundamental misunderstanding of SSDF testing. >>>> >>>>The older programs on 450 MHz have the most games played. >>>> >>>>Therefore, they tell us more information about the strength of a program than >>>>playing against the same program on faster hardware. >>>> >>>>In fact, you would have to completely recalibrate the older programs on the >>>>faster machines to even use the data. >>>> >>>>Consider the following: >>>> >>>> THE SSDF RATING LIST 2005-02-25 %101022 games played by 270 computers >>>> Rating + - Games Won Oppo >>>> 63 SOS 128MB K6-2 450 MHz 2518 15 -16 2085 37% 2610 >>>> 47 Junior 6.0 128MB K6-2 450 MHz 2593 15 -15 2144 49% 2598 >>>> 66 Fritz 5.32 64MB P200 MMX 2494 14 -14 2563 42% 2549 >>>> >>>>Notice that these engines have a rating of about 2500, and an error bar of about >>>>30 Elo. That means we know the strength of these engines to an incredibly good >>>>degree. We can consider these as micrometers. >>> >>>Dann, I am not very good at math. How many games needs to be played between two >>>programs in order to achieve 0 error margin (if it's possible)? >> >>Infinity. >> >>Probably, a few hundred thousand would give you one Elo or so (just a guess). >>But by that time, the program would be a few decades old and nobody would care. > >Unless the games are at 1-2 min blitz. :) > >I think I am gonna run something like that, just to achieve a 1 error margin. That's a few hundred thousand for EACH program. ;-) There are only 86400 seconds in a day, and 1440 minutes. Sounds like a long project to 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.