[Trilinos-Users] Partitioning Tpetra matrices

Devine, Karen D kddevin at sandia.gov
Fri Jan 24 13:22:24 MST 2014


The bug that you reported below in Zoltan2 is now fixed.  You can access
the code from the Trilinos public git repository; see
http://trilinos.org/?page_id=140 for details.

As Erik previously noted, use of Isorropia with Tpetra is deprecated.

Please let me know if you see further problems.

On 12/6/13 10:27 AM, "Pavel Jiránek" <pavel.jiranek at gmail.com> wrote:

>I was wondering what are the options for partitioning Tpetra matrices (no
>geometry, pure graph partitioning) in Trilinos (in particular with long
>integer global indices).
>I've noticed that there might be some support for Tpetra through
>Isorropia (although only for normal integers, I guess because Zoltan is
>hard-coded with int types), however, Trilinos does not compile after
>using Isorropia_ENABLE_TPETRA=ON in my
> config script.
>I've also tried Zoltan2. I understand that, at this moment, the only
>option for graph partitioning is through the interface to PT-Scotch (I
>suppose working as well for long integers as soon as PT-Scotch is built
>with the proper option for integer
> length). It seems to work well for improving partitionings of already
>distributed matrices/graphs, however, the program crashes (it seems that
>somewhere in the construction of a GraphModel instance) on processes
>which do not contain any rows. For instance,
> this happens when reading a (rather small) matrix on process 0 and
>computing a partitioning from scratch. Interestingly, this problem can be
>fixed by first naively redistributing the matrix to a uniform map and
>then applying Zoltan2 to the redistributed matrix.
>Thanks for any feedback.

More information about the Trilinos-Users mailing list