[petsc-users] AO versus DM for 3D CG solve

[Ronald M. Caplan]

Yes sorry I mean 64 cores.

On Thu, Sep 6, 2012 at 11:49 AM, Jed Brown <five9a2 at gmail.com> wrote:

>
> On Sep 6, 2012 1:12 PM, "Ronald M. Caplan" <caplanr at predsci.com> wrote:
> >
> > Hi,
> >
> > I am trying to implement petsc into an existing (very large) FORTRAN
> code which splits a 3D grid in each dimension (so for a 100x100x100 problem
> on 4 cores, each core gets a 25x25x25 part of the grid).
>
> Do you mean 4^3 = 64 cores?
>
> >
> > The default partitioning for petsc just assigns contiguous rows of the
> coefficient matrix to each core which is hampering performance.
> >
> > From looking around I have found that there are AO routines and DM
> routines in petsc.
> >
> > What is the difference between using either of them for my problem?
> > Should I be using DM to partition the petsc matrices/vectors so that
> they match the grid points on each node, or do I use AO routines to do that?
> > Or do AO routines just map the default petsc partitioning indices to my
> problem's indices in which case I want to use DM?
> >
> > Thanks
> >
> > Ron Caplan
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20120907/5d04ac08/attachment.html>