<div dir="ltr">On Thu, Mar 21, 2013 at 11:25 AM, Karl Rupp <span dir="ltr"><<a href="mailto:rupp@mcs.anl.gov" target="_blank">rupp@mcs.anl.gov</a>></span> wrote:<br><div class="gmail_extra"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Hi guys,<div class="im"><br>
<br>
> I vote a). No new function, gets rid of a stupid optimization that<br>
> does no one any good, and is the simplest.<br>
><br>
><br>
> I also think (b) is becoming over-complicated. If someone knows their<br>
> stencil and cares about memory usage, they can just pass the correct<br>
> values. The defaults are terribly for anything but a 5-point stencil anyway.<br>
<br>
<br></div>
for completeness, here's how b) would look like:<br>
<br>
<a href="https://bitbucket.org/petsc/petsc/commits/814b6bb1ec0ea67e05a42f7f07cab1169a9be913" target="_blank">https://bitbucket.org/petsc/<u></u>petsc/commits/<u></u>814b6bb1ec0ea67e05a42f7f07cab1<u></u>169a9be913</a><br>
<br>
This has the additional freedom of being able to deal with different defaults for on- and off-processor blocks correctly at the expense of a separate function MatSeqAIJSetPreallocation_<u></u>SeqAIJAlloc()<br>
<br>
I can confirm that this fixes the issues with GPUs. If, on the other hand, we pick a), then code gets substantially simpler even than it is now. As noted, the only drawback is that the default preallocation for on- and off-processor values is the same. I can live with that.<br>
</blockquote><div><br></div><div style>Still want simpler.</div><div style><br></div><div style> Matt</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Best regards,<br>
Karli<br>
<br>
<br>
<br>
</blockquote></div><br><br clear="all"><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>