[Beowulf] AMD Opteron Linpack Benchmark

Toon Knapen toon.knapen at fft.be
Thu Sep 21 23:38:04 PDT 2006

Craig Tierney wrote:

>> Anyone has good suggestions of combination of compiler (appreciate if 
>> includes compiler flags) + math lib on AMD platforms?
>> thanks a lot.
> Compiler and flags don't matter.  HPL spends about 99.999% of its
> time in BLAS.  Use GotoBLAS, it is very fast.

If you compile GotoBLAS yourself, you can select to compile for opteron 
with or without SSE3. I actually benchmarked both (in our application) 
and the difference in performance was not significant.


More information about the Beowulf mailing list