Author: fca
Date: 01:48:56 08/12/98
Go up one level in this thread
On August 11, 1998 at 13:42:20, Moritz Berger wrote: >On August 11, 1998 at 13:11:26, fca wrote: > >>>Higher NPS -> higher memory throughput -> less cache efficiency (just imagine a >>>program that uses e.g. 64 KB hash and "lives" completely in the 512 KB 2nd level >>>cache of a PII in comparison with Fritz which fills up hundreds of megabytes of >>>hash tables in a couple of minutes). >> >>Put that way, seductive, Moritz. :-) >> >>But this case you conveniently quote is of course most highly and outrageously >>unrepresentative. At important time controls (ssdf, 40/2 and similar) how many >>programs only use <= 512Kb hash ! CST? >> >>So I cannot tell one way or the other... >> >>We are talking about programs that all consume significantly more than 512Kb >>hash - some absurdly more (F5 seems like an engine to fill memory with some sort >>of data! ;-) ) > >Very easy to verify: Just turn off 2nd level cache in your BIOS and see what >happens. AFAIR Fritz was only about 30% slower without 2nd level cache, but I >leave it up to you to post some exact data and correlate the effect on different >programs. :-) I'll try this, but of course switching off L2 entirely *may* not properly indicate the effect of a smaller or slower L2, which was what was being discussed... I really think this problem is complex. When my faster machine arrives I can do the tests on both (i.e. 166/256K and 450/512K) and will report. I'd be interested, Moritz, to your views on Bob's reply to the above-quoted post from me (August 11, 1998 13:11:26) in this thread. I tend to agree with Bob - as you recall, the parentage of this discussion was my surprise that such a huge speed ratio for Junior existed between the P200MMX and P2/300, which others later attributed to L2-cache size/MHz. I disagreed. Kind regards fca
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.