Author: Jeremiah Penery
Date: 05:59:15 06/29/03
Go up one level in this thread
On June 29, 2003 at 02:14:10, Sune Fischer wrote: >On June 28, 2003 at 21:35:42, Jeremiah Penery wrote: > >>On June 28, 2003 at 19:12:16, Ricardo Gibert wrote: >> >>>Elsewhere in this thread, someone asserted that for chess, the Opteron "not much >>>faster" Mhz per Mhz as an Athlon XP. I thought this didn't seem right, but >>>looking at the crafty sections of SPECint2000 at >>>http://www.aceshardware.com/SPECmine/ makes it look like a fair (?) assessment. >> >>Did you look at the same numbers as I did? 1800MHz Opteron performs about where >>you'd expect to see a 2100MHz Athlon for Crafty, according to SPEC numbers. So, >>Opteron is performing some 16% better per MHz than the Athlon here. > >This is not another one of those "gee let's test the performance of the bran new >64 bit chip using old non-optimized 32 bit applications" tests, is it? The SPEC results for the Opteron were compiled with ICC 7.0 and MSVC .NET - both 32-bit compilers. What's wrong with that kind of test? It shows that Opteron performs better than Athlon on the same 'old non-optimized 32 bit applications'. So we can expect even better when we have 'new optimized 64 bit applications'.
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.