[Beowulf] Opteron 275 performance
gorelsky at stanford.edu
Wed Jul 13 12:21:32 PDT 2005
>The original post by S.Gorelsky (re-sent by E.Leitl) was about good
>scalability of 4cores/dual-CPUs Opteron 275 server on Gaussian 03
>DFT/test397 test. I'm testing just now like Supermicro server
>w/2*Opteron 275 but w/DDR333 instead of DDR400 used by S.Gorelsky.
>I used SuSE 9.0 w/2.4.21 kernel.
>I understood, that original results of S.Gorelsky were obtained,
>probably, for shared memory parallelization!
This is correct. I did not use Linda parallelization. The reason
for that is Linda's "far-from-best" scalability with Gaussian 03.
Thus, we only use shared memory parallelization for Gaussian 03 and only
those results are shown on http://www.sg-chem.net/cluster/
More information about the Beowulf