[petsc-dev] Distributed MatSolve

[Matthew Knepley]

On Sat, Sep 14, 2013 at 9:16 AM, Jose David Bermeol <jbermeol at purdue.edu>wrote:

> Hi, if I,m using a distributed MatSolve rows in A matrix should correspond
> with the elements in vector b. That means if my MPI process have matrix A
> with rows from 5 to 10, vector b should have elements from 5 to 10 or that
> depends on the MatSolve implementation?
>

Yes, our parallel distribution is by rows.

  Thanks,

     Matt


> Thanks
>



-- 
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-dev/attachments/20130914/b83b5632/attachment.html>