[petsc-users] MatCreateMPIAIJ with zero size on some ranks

Matthew Knepley knepley at gmail.com
Wed Apr 25 06:38:11 CDT 2012


On Wed, Apr 25, 2012 at 3:21 AM, Thomas Witkowski <
thomas.witkowski at tu-dresden.de> wrote:

> Is it possible to create a parallel matrix (MPIAIJ) with empty size on
> some ranks? Even if this should work, does it make sense (with respect to
> runtime and efficiency) to collect all ranks having a nonempty contribution
> the the global matrix in an mpi group and to use this communicator for
> matrix create/computations?


1) Yes

2) It depends. If there are a bunch of empty procs and you do reductions,
it may make sense to leave them out. But
    you would have to be on a large number of processes.

     Matt


>
> Thomas
>



-- 
What most experimenters take for granted before they begin their
experiments is infinitely more interesting than any results to which their
experiments lead.
-- Norbert Wiener
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120425/6ee0760f/attachment-0001.htm>


More information about the petsc-users mailing list