Hi all, 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 http://glaros.dtc.umn.edu/gkhome/metis/parmetis/changes) . I do not see this version of ParMetis in the petsc ftp site, what version is used in petsc-dev?
Mohammad On Thu, Mar 1, 2012 at 10:32 AM, Sean Farley <sean at mcs.anl.gov> wrote: > On Thu, Mar 1, 2012 at 12:09 PM, John Fettig <john.fettig at gmail.com>wrote: > >> 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? > > > It'd be pretty murky to do this. Start by looking at this changeset: > > http://petsc.cs.iit.edu/petsc/petsc-dev/rev/0c0bf07c7a32 > > Luckily, you just need to look at revisions that I authored ( > sean at mcs.anl.gov): 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. > > Related question, would it be a problem to just use petsc-dev? > -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120301/c932d37a/attachment.htm>
