Author: Robert Hyatt
Date: 10:12:53 07/13/00
Go up one level in this thread
On July 13, 2000 at 11:20:10, blass uri wrote: >On July 13, 2000 at 11:14:08, Robert Hyatt wrote: > >>On July 13, 2000 at 02:21:31, Joshua Lee wrote: >> >>>On July 13, 2000 at 01:30:03, Dann Corbit wrote: >>> >>>>On July 13, 2000 at 01:24:59, blass uri wrote: >>>> >>>>>On July 13, 2000 at 01:05:06, Joshua Lee wrote: >>>>> >>>>>> a dual 500Mhz Machine for the SMP programs >>>>>>a 1Ghz machine for those programs that are not...this should be equal in speed. >>>>> >>>>>Your assumption is wrong. >>>>>2 processors are less than twice faster than one processor. >>>> >>>>A dual 600 should be about right. Also, probably a lot cheaper than the 1GHz >>>>machine. >>> >>>I think Dann's response answers my question which was going to be then what dual >>>processor system would be equal? >>> >>>Just as long as the ZD CPUMark scores were the same so Hardware is not the >>>result of a victory like the WCCC's everybody is on the same Speed. >>> >>>Thankyou >> >> >>This is the wrong way to do this. If you want equal hardware, use two 1ghz >>machines. Forget the 2x600 == 1x1000 math. The purpose of SMP searching is to >>go faster, not "go equal". > >The problem is that 2*600 is cheaper than 1*1000 and some people have not enough >money for two 1ghz machines > >Uri then the right answer is to use the 2*600 for the match, one program on each cpu. Equalizing hardware for a SMP vs non-SMP program is worse than pointless.
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.