<div dir="ltr"><div>Hi all,</div><div><br></div>I was also having this problem (assertion fails) when using ParMetis 3.2 as a part of PETSc 3.2-p6. I could fix it by installing ParMetis 4.0.2 directly and passing the header/libs to petsc (check the chages in <a href="http://glaros.dtc.umn.edu/gkhome/metis/parmetis/changes">http://glaros.dtc.umn.edu/gkhome/metis/parmetis/changes</a>) . I do not see this version of ParMetis in the petsc ftp site, what version is used in petsc-dev?<div>
<br></div><div>Mohammad<br><br><div class="gmail_quote">On Thu, Mar 1, 2012 at 10:32 AM, Sean Farley <span dir="ltr"><<a href="mailto:sean@mcs.anl.gov">sean@mcs.anl.gov</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="im"><div class="gmail_quote">On Thu, Mar 1, 2012 at 12:09 PM, John Fettig <span dir="ltr"><<a href="mailto:john.fettig@gmail.com" target="_blank">john.fettig@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Sorry to dig up an old thread (I seem to have a tendency of doing that here!), but this problem exists in petsc-3.2-p6 with MUMPS and Metis as well. Looking at the differences between the dev version of mump.c and the release version, I don't see anything that would have obviously fixed this. Could you give me a hint about what was changed? Is it as simple as using the updated Metis package (in dev)? How difficult would it be to backport the fix to the released version?</blockquote>
</div><br></div><div>It'd be pretty murky to do this. Start by looking at this changeset:</div><div><br></div><div><a href="http://petsc.cs.iit.edu/petsc/petsc-dev/rev/0c0bf07c7a32" target="_blank">http://petsc.cs.iit.edu/petsc/petsc-dev/rev/0c0bf07c7a32</a></div>
<div><br></div><div>Luckily, you just need to look at revisions that I authored (<a href="mailto:sean@mcs.anl.gov" target="_blank">sean@mcs.anl.gov</a>): hg log -r 'user(sean)'. The *real* difficultly would be the changes I made to SuperLU_DIST, MUMPS, and SuiteSparse and hope that it all works together for 3.2p6.</div>
<div><br></div><div>Related question, would it be a problem to just use petsc-dev?</div>
</blockquote></div><br></div></div>