>> On 03/19/2013 06:06 PM, Michael Di Domenico wrote: snip > You're absolutely right. While i absolutely respect HPL (and it's > creators) as a valid benchmark and we do use it is a generalization on > expected performance. It doesn't give us any real indication on the > maximum potential of a computers performance with respect to our > codes.
The old joke in this sector. If you want to be an expert in HPC, you only need to know one answer -- "It all depends" Of course to deliver results you need the second part of the answer, which often has little to do with HPL. -- Doug > _______________________________________________ > Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing > To change your subscription (digest mode or unsubscribe) visit > http://www.beowulf.org/mailman/listinfo/beowulf > > -- > Mailscanner: Clean > -- Doug -- Mailscanner: Clean _______________________________________________ Beowulf mailing list, Beowulf@beowulf.org sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
