Thanks for the info. This data makes sense and shows that the dual CPU costs about 4% in performance. Not a whole lot but it does make the cost/performance come out on the side of separate boxes. I kind of expected that the dual Zeon box would come out better on a cost/performance basis, but it didn't.
Terry At 02:26 PM 3/22/2003 -0800, Anurag Garg wrote:
2 P4s is definitely better than a dual Xeon. In a Xeon the two CPUs have to share a bus and because of the contention there is a slow down. There is some hard data to prove this on the Distributed Computing Forum of Ars.
http://arstechnica.infopop.net/OpenTopic/page?a=tpc&s=50009562&f=122097561&m=3680928671&r=5450987973#5450987973
Garo
_Terry S. Arnold 2975 B Street San Diego, CA 92102 USA
[EMAIL PROTECTED] (619) 235-8181 (voice) (619) 235-0016 (fax)
_________________________________________________________________________ Unsubscribe & list info -- http://www.ndatech.com/mersenne/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
