[Beowulf] AMD Opteron Linpack Benchmark
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