[petsc-dev] [petsc-users] MatGetSubMatrices or VecCreateGhost

[hong at aspiritech.org]

I'm writing MatTransposeMatMult_MPIDense_MPIDense() without elemental now
(almost done).

It would be nice to have MatConvert() between MPIDense and elemental [VC,*]
- it seems we use elemental default (2D?).

Jed: do you know how to set [VC,*] for MatConvert_mpidense_elemental?

If we have MatConvert() without data movement, then we gain all dense
operations supported by elemental.

Hong


On Fri, Oct 16, 2015 at 1:29 PM, Jed Brown <jed at jedbrown.org> wrote:

> Barry Smith <bsmith at mcs.anl.gov> writes:
> >    We don't have a parallel
>
> Elemental makes sense here; the 2D distribution will scale much better.
>
> Note that MatTransposeMatMult_MPIDense_MPIDense is fairly trivial and
> very useful for tall-skinny matrices, which is the case in which the
> MPIDense distribution ([VC,*] in Elemental vernacular) actually makes
> sense.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20151016/51d33adb/attachment.html>