On Wed, Dec 22, 2010 at 10:11 AM, Yongjun Chen <span dir="ltr"><<a href="mailto:yjxd.chen@gmail.com">yjxd.chen@gmail.com</a>></span> wrote:<br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<div><div></div><div class="h5"><br><br><div class="gmail_quote">On Wed, Dec 22, 2010 at 6:53 PM, Satish Balay <span dir="ltr"><<a href="mailto:balay@mcs.anl.gov" target="_blank">balay@mcs.anl.gov</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0pt 0pt 0pt 0.8ex;border-left:1px solid rgb(204, 204, 204);padding-left:1ex">
<div>On Wed, 22 Dec 2010, Yongjun Chen wrote:<br>
<br>
> On Wed, Dec 22, 2010 at 6:32 PM, Satish Balay <<a href="mailto:balay@mcs.anl.gov" target="_blank">balay@mcs.anl.gov</a>> wrote:<br>
><br>
</div><div>> > Thanks a lot, Satish. It is much clear now. But for the choice of the two,<br>
> the program dmidecode does not show this information. Do you know any way to<br>
> get it?<br>
<br>
</div>why do you expect dmidecode to show that?<br>
<br>
You'll have to look for the CPU/chipset hardware documentation - and<br>
look at the details - and sometimes they mention these details..<br>
<font color="#888888"><br>
Satish<br>
</font></blockquote></div><br><br></div></div>Thanks, Satish. Yes, I need to check it.<br>Just now I re-configured PETSC with the option --with-device=ch3:nemsis. The results are almost the same as --with-device=ch3:sock. As can be seen in the attachment.<br>
I hope the matrix partitioning - reordering algorithm would have some positive effects. <br></blockquote><div><br></div><div>1) To see a large gain, the ordering you start with would have to be very bad. Maybe it is. These</div>
<div> orderings try to minimize bandwidth, which means minimize communication in the MatMult.</div><div><br></div><div>2) If you use incomplete facotrization, the ordering can have a large effect on conditioning, so</div>
<div> number of iterations, which does not improve scalability. This would impact scalability if you</div><div> use a parallel IC, however all those packages reorder your matrix already.</div><div><br></div><div>In short, I suspect this will not help a lot, except maybe with conditioning, which is what I was refering to in the quote.</div>
<div><br></div><div> Matt</div><div> </div></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<br>