Author: Tom Kerrigan
Date: 21:18:30 08/22/04
Go up one level in this thread
On August 22, 2004 at 23:43:32, Robert Hyatt wrote: >>No, you're not an idiot for that. (Duh.) You're an idiot for not knowing if your >>program takes ~1MB of memory or ~16MB of memory. I mean, seriously, you're off >>by more than an order of magnitude here. > >No I'm not. I simply _always_ run a full version, supporting threads, endgame >tables, everything. Never occurs to me to test with something that I don't >actually use in real games... Who said anything about testing? I know roughly how much memory every part of my own program takes because I _WROTE_ it. >Now, unless something further comes up, I'll leave the last word to you. I >don't see much point in continuing to argue about working set size without some >_real_ data. Interesting that you quit the discussion right when we have some new data that conclusively proves my assertion. The maximum possible size that Crafty's working set could possibly be is 1236k (5076-3840). So we can throw out all of your hypotheticals about the cache getting thrashed so much during search that cache size doesn't affect performance--with e.g. a 1024k L2 cache, you only have 212k left to thrash it with!! I could write more but I wouldn't want to embarrass you even more. -Tom
This page took 0.01 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.