Author: Sune Fischer
Date: 00:44:09 06/30/03
Go up one level in this thread
On June 29, 2003 at 23:21:42, Eugene Nalimov wrote: >On June 29, 2003 at 23:00:29, Jay Urbanski wrote: > >>On June 29, 2003 at 22:19:48, Robert Hyatt wrote: >> >>>My point was not that it will be bad. But that it _could_ be better. Going >>>to 64 bits while supporting legacy X86 architecture stuff is not the way to >>>fastest performance. >> >>Bob you should see if Intel are hiring Itanium sales people :) >> >>I'm certainly happy to be able to run all my exisiting software faster than any >>other processor on the planet can run it. And Opteron is currently the fastest >>shipping processor around for Integer performance, period. Yeah Itanium II and >>Madison are faster in floating point - but they cost several thousand dollars a >>pop also. > > >SPECint 2K: > >Opteron: 1095 (base) / 1170 (peak) >P4: 1164 (base) / 1200 (peak) > >http://www.spec.org/cpu2000/results/res2003q2/cpu2000-20030421-02108.html >http://www.spec.org/cpu2000/results/res2003q2/cpu2000-20030422-02135.html > >Thanks, >Eugene Maybe for clarity it should be added that the Opteron was running 32 bit binaries. "Opteron" could confuse people into thinking this was a 64-bit test. :) -S.
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.