Author: Robert Hyatt
Date: 20:18:07 05/03/00
Go up one level in this thread
On May 03, 2000 at 23:15:14, KarinsDad wrote: >On May 03, 2000 at 20:51:04, Robert Hyatt wrote: > >[snip] >>> >>>I don't buy this memory theory. >>> >>>A "fair" test is one of 50% cache for each side (cache memory being more >>>important) and 50% cpu cycles. But other resources should be based on what is >>>required to run the program. For example, if you need 100 MB for one program, >>>well, you'd better have 100 MB + OS requirements + other program requirements. >>>If you need 3GB for egtbs for one program, then you'd better have it. >>> >>>Now, forcing resource allocation is a different issue. And, of course, there >>>will be a resource delay on both sides based on what the other side is doing (if >>>both sides are looking at their egtbs, then there will be a competition for head >>>location on the hard disk). So, you are correct that there will be hidden >>>problems (and a program could be penalized based on how it is coded since it >>>could assume it can grab a large portion of the cache to run in). >>> >>>But I do not believe that spliting main memory 50-50 is required for a fair >>>test. >>> >>>KarinsDad :) >> >> >>(a) why not? >> >>(b) who gets the bigger chunk? >> >>(c) why? >> >>How can it _possibly_ be fair to give one program more hash than another? Or >>give one program more cpu than another? >> >>Cache is immaterial since the thing doesn't context switch that often, >>particularly with ponder=off. So cache simply doesn't factor in, and there is >>no way to control it anyway. >> >>But for the rest??? > > >The issue is not one of who gets more of a given resource. The issue is one of >fairness. If program A works well with a small hash and program B works well >with a large one, then why penalize program A over some 50/50 rule? > >Granted, the entire issue is moot since without knowing all of the factors, >there is no way to force any level of fairness, regardless of which fairness >criteria you specify. > >And I did not say that one program should get more cpu. I said that cpu and >cache should be split evenly to be fair, but that the rest of system resources >should be based on some overall "type of program" criteria. > >As for cache, I was talking about when pondering=on. Of course, you cannot >control it, so like I said, it is moot. > >And, you cannot even be fair if you pick two identical machines. Program A could >work well on Macs and Alphas with NT, and program B could work well with >Celerons using DOS and you wouldn't even be able to come up with an identical >system fair to both programs. > >KarinsDad :) You got it. :) I consider my quad xeon perfectly 'fair'. :) 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.