<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote">On Wed, Aug 20, 2014 at 4:31 PM, Jed Brown <span dir="ltr"><<a href="mailto:jed@jedbrown.org" target="_blank">jed@jedbrown.org</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="">Barry Smith <<a href="mailto:bsmith@mcs.anl.gov">bsmith@mcs.anl.gov</a>> writes:<br>
> My statement is based on experience, not models. I stand by it and<br>
> yes it can be factors of that magnitude. Now one could argue 3<br>
> times faster so what, but if you are doing this solve millions of<br>
> times and it is the most time consuming part of the simulation (by<br>
> far) then it adds up.<br>
<br>
</div>Here is one comparison:<br>
<br>
<a href="http://dx.doi.org/10.1103/PhysRevE.88.063308" target="_blank">http://dx.doi.org/10.1103/PhysRevE.88.063308</a><br>
</blockquote></div><br>Can you understand the scaling plots in that thing? And they make no attempt</div><div class="gmail_extra">at modeling. These kind of paper may help a small segment of people running</div><div class="gmail_extra">
that exact problem on a similar architecture, but they really do not help sort this</div><div class="gmail_extra">out.</div><div class="gmail_extra"><br></div><div class="gmail_extra"> Matt</div><div class="gmail_extra">
<div><br></div>-- <br>What most experimenters take for granted before they begin their experiments is infinitely more interesting than any results to which their experiments lead.<br>-- Norbert Wiener
</div></div>