[petsc-users] Parallelizing a matrix-free code

Praveen C praveen at tifrbng.res.in
Mon Oct 16 02:59:54 CDT 2017

> On 16-Oct-2017, at 12:56 PM, Michael Werner <michael.werner at dlr.de> wrote:
> However, since its an unstructured grid, those subgrids are not necessarily made up of points with successive global IDs.

It should be easy to renumber the points so that each partition has contiguously numbered point ids. This is what we do in our CFD code during the stage where we partition the mesh with Metis.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20171016/3964e82f/attachment.html>

More information about the petsc-users mailing list