ATHLON vs XEON: number crunching
maurice at harddata.com
Sat Jun 22 10:10:21 PDT 2002
With regards to your message at 10:01 AM 6/22/02,
beowulf-request at beowulf.org. Where you stated:
>As I said in my original email I used PGI compilers (the code is a mixture
>of F90 and C), it uses MPI, not OpenMP.
>This morning I already mentioned about my new tests, when I loaded both
>processors in both Athlon and Xeon nodes. The load was done by running
>mpirun -np 2. Both Myrinet and Gigabit ethernet gave approximately the
>same timing which is what you would expect in the absence of internode
>I could not make comparison of scalability because I don't have more than
>1 node available.
>My results remain unchanged: Xeon 2.2 GHz is 1.5 times faster than Xeon XP
I suggest you try the Intel compiler.
With our best regards,
Maurice W. Hilarius Telephone: 01-780-456-9771
Hard Data Ltd. FAX: 01-780-456-9772
11060 - 166 Avenue mailto:maurice at harddata.com
Edmonton, AB, Canada http://www.harddata.com/
Ask me about the UP1500 Alpha - Full systems from $3,500!
More information about the Beowulf