Hyperthreading in P4 Xeon (question)

Michael Prinkey mikeprinkey at hotmail.com
Wed Apr 3 10:10:10 PST 2002


I can amplify that point.  A commercial CFD application ran significantly 
slower using 4 threads vs 2 on a dual Prestonia system.  Anything memory 
limited will probably behave the same way.

Mike Prinkey
Aeolus Research, Inc.



>From: Mark Hahn <hahn at physics.mcmaster.ca>
>To: William Park <opengeometry at yahoo.ca>
>CC: <beowulf at beowulf.org>
>Subject: Re: Hyperthreading in P4 Xeon (question)
>Date: Wed, 3 Apr 2002 10:50:06 -0500 (EST)
>
> > What is the realistic effect of "hyperthreading" in P4 Xeon?  I'm not
> > versed in the latest CPU trends.  Does it mean that dual-P4Xeon will
> > behave like 4-way SMP?
>
>for some value of "behave like" ;)
>that is, it will definitely NOT get twice as fast.  but it will appear
>to have 4 CPUs, and can run 4 threads/procs at once (for values of
>"once" > 1 clock cycle ;)
>
>we did a quick test on a dual-prestonia here, and saw a ~5% speedup
>on a probably cache-friendly, compute-bound task.
>
>_______________________________________________
>Beowulf mailing list, Beowulf at beowulf.org
>To change your subscription (digest mode or unsubscribe) visit 
>http://www.beowulf.org/mailman/listinfo/beowulf
>


_________________________________________________________________
Chat with friends online, try MSN Messenger: http://messenger.msn.com




More information about the Beowulf mailing list