On Thu, Aug 25, 2011 at 9:15 PM, Tabrez Ali <span dir="ltr"><<a href="mailto:stali@geology.wisc.edu">stali@geology.wisc.edu</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;">
Hello<br>
<br>
I have an unstructured FE mesh which I am partitioning using Metis.<br>
<br>
In the first case I only use the element partitioning info and discard the nodal partitioning info i.e., the original ordering is same as petsc's global ordering. In the second case I do use the nodal partitioning info and nodes are distributed accordingly.<br>
<br>
I would expect that in the 2nd scenario the total number of MPI messages (at the end of the solve) would be lower than the 1st. However I see that opposite is true. See the plot at <a href="http://stali.freeshell.org/mpi.png" target="_blank">http://stali.freeshell.org/<u></u>mpi.png</a><br>
<br>
The number on the y axis is the last column of the "MPI messages:" field from the -log_summary output.<br>
<br>
Any ideas as to why this is happening. Does relying on total number of MPI messages as a performance measure even make sense. Please excuse my ignorance on the subject.<br>
<br>
Alternatively what is a good way to measure how good the Metis partitioning is?<br></blockquote><div><br></div><div>The thing to do here is take a case like 2 proc that can be completely understood, and get down to the details. I</div>
<div>think there is a probably just a simple misunderstanding here.</div><div><br></div><div>The first thing to check is that you are partitioning what you think. By default, Metis partitions the vertices of a graph,</div>
<div>not elements, Thus you usually have to give Metis the "dual" of your finite element mesh. I would take a small (maybe</div><div>8 or 10 elements) mesh and look at the original and Metis partitions. If Metis does not look better, something is wrong.</div>
<div><br></div><div> Matt</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
Thanks in advance<br><font color="#888888">
<br>
Tabrez<br>
<br>
</font></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<br>