<div dir="ltr">Stampede did not run at full scale.<div>Anyway, HPCG is all about memory bandwidth, flops is the wrong metric to use.</div><div>They should have reported the total memory bandwidth of the machine.</div><div>
<br></div><div>M</div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Thu, Jul 3, 2014 at 9:32 AM, Kilian Cavalotti <span dir="ltr"><<a href="mailto:kilian.cavalotti.work@gmail.com" target="_blank">kilian.cavalotti.work@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="">On Thu, Jul 3, 2014 at 12:41 AM, Olli-Pekka Lehto<br>
<<a href="mailto:olli-pekka.lehto@csc.fi">olli-pekka.lehto@csc.fi</a>> wrote:<br>
> Here are some interesting new results of how HPCG ranking changes the top<br>
> system<br>
> ranking in HPL:<br>
> <a href="https://twitter.com/a_z_e_t/status/482062498477383680/photo/1" target="_blank">https://twitter.com/a_z_e_t/status/482062498477383680/photo/1</a><br>
<br>
</div>Wow, that's interesting. Stampede takes quite a hit.<br>
What did Jack Dongarra say about this, given he's at the origin of<br>
both benchmarks?<br>
<br>
Cheers,<br>
<span class="HOEnZb"><font color="#888888">--<br>
Kilian<br>
</font></span><div class="HOEnZb"><div class="h5">_______________________________________________<br>
Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org">Beowulf@beowulf.org</a> sponsored by Penguin Computing<br>
To change your subscription (digest mode or unsubscribe) visit <a href="http://www.beowulf.org/mailman/listinfo/beowulf" target="_blank">http://www.beowulf.org/mailman/listinfo/beowulf</a><br>
</div></div></blockquote></div><br></div>