Stampede did not run at full scale. Anyway, HPCG is all about memory bandwidth, flops is the wrong metric to use. They should have reported the total memory bandwidth of the machine.
M On Thu, Jul 3, 2014 at 9:32 AM, Kilian Cavalotti < kilian.cavalotti.w...@gmail.com> wrote: > On Thu, Jul 3, 2014 at 12:41 AM, Olli-Pekka Lehto > <olli-pekka.le...@csc.fi> wrote: > > Here are some interesting new results of how HPCG ranking changes the top > > system > > ranking in HPL: > > https://twitter.com/a_z_e_t/status/482062498477383680/photo/1 > > Wow, that's interesting. Stampede takes quite a hit. > What did Jack Dongarra say about this, given he's at the origin of > both benchmarks? > > Cheers, > -- > Kilian > _______________________________________________ > 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 >
_______________________________________________ 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
