<p>At least send the PETSc stack trace.</p>
<p>PETSc always uses MatPartitioning, so you can use any partitioner. </p>
<div class="gmail_quote">On Jan 24, 2012 8:51 AM, "Dominik Szczerba" <<a href="mailto:dominik@itis.ethz.ch">dominik@itis.ethz.ch</a>> wrote:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
On Tue, Jan 24, 2012 at 1:37 PM, Jed Brown <<a href="mailto:jedbrown@mcs.anl.gov">jedbrown@mcs.anl.gov</a>> wrote:<br>
> The error is inside of METIS and this is just a bare assert, so there isn't<br>
> information regarding whether they think this is the result of invalid input<br>
> or a METIS bug. Get the full stack trace so we can determine where this is<br>
> happening, METIS is a partitioner, so it's not normally called as part of<br>
> assembling a matrix.<br>
<br>
This will be difficult because it happens only with 64 processes and I<br>
am on a cray where I can not run gdb.<br>
I will try to run the same on my quadcore, but am not sure what I get.<br>
<br>
Is it possible to replace calls to parmetis with chaco or party for<br>
"internal" usage (and NOT explicit partitioning that I do myself)? Is<br>
it supported/good idea?<br>
<br>
Many thanks<br>
Dominik<br>
</blockquote></div>