Author: Robert Hyatt
Date: 16:39:43 07/17/04
Go up one level in this thread
On July 17, 2004 at 17:15:15, Sune Fischer wrote: >On July 17, 2004 at 16:18:07, Robert Hyatt wrote: >> >>The correct number is around 45%, gcc 32 bit vs gcc 64 bit, or msvc 32 bit vs >>msvc 64 bit. I believe AMD has already published these numbers in fact... > >...which is still higher than the 1.4 :) > >>And Microsoft's compiler is at _least_ 10% faster than GCC. More can be said by >>Eugene if he wants... >> >>I was simply pointing out that there was absolutely no way a quad is 4x faster >>than a 1-cpu box. > >Actually there is, if you use a quad 2.4 GHz against a single at 2.0 GHz :) > >-S. Nope. Again, going over the math. First, assume that the 2.4ghz machine runs like a 2.2ghz box due to the missing NUMA kernel. My testing shows that the 2.2ghz box searched one position at 2.07M nodes per second (1 cpu) where the 2.4ghz searched the same position at 2.1M nodes per second, almost identical. Now, take the parallel speedup of 3.1X, and multiply that by the CPU speed, and you get 6.82 effective ghz. Divide that by 2.0ghz to see the difference and you get 3.41... which is not 4x as I said... And all those numbers are real... not guesses...
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.