[Getdp] getdp + petsc in parallel - partitioning ?
cag32 at case.edu
Thu Apr 20 14:47:42 CEST 2006
Thomas Jung wrote:
> I have built getdp with petsc- and metis support,
> trying to run it in parallel, I get this:
> Error : 1 partitions on 2 CPU
> Seems logical, I probably have to partition the mesh (or the matrix ????)
> somehow using metis, but how do I do that ?
The parallel PETSc version currently only works on specific test
problems, and will give *wrong results* in general. Please don't use it!
You can safely use the single processor PETSc version, though: it has
been extensively tested both in real and complex arithmetic.
> Again, thanks for any hint !
> Thomas Jung
> getdp mailing list
> getdp at geuz.org
Assistant Professor, Case Western Reserve University, Mathematics
More information about the getdp