[petsc-dev] MatTransposeMatMult

Hong hzhang at mcs.anl.gov
Fri Sep 22 11:05:51 CDT 2017

Jed :
New implementation for seqaij is in branch hzhang/opt-mattransposematmult.
petsc/src/mat/examples/tests/ex209.c is a test.
Please give it a try and let me know if you have any comment.

I'll remove previous implementation and optimize MatTransposeMatMult() for
mpiaij matrices.


Hong <hzhang at mcs.anl.gov> writes:
> > It was implemented a decade ago for small to medium matrices.
> > Your matrix structure reveals the worst part of outer product.
> >
> > After discussing it with Barry, we decided to replace the algorithm (not
> > API) using At=A^T and C=At*B  for sequential implementation.
> > In parallel, I'll do local MatTranspose (used for PtAP).
> > I'll give you this new implementation in few days.
> Perfect, thanks!
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20170922/ab551b10/attachment.html>

More information about the petsc-dev mailing list