On Mon, May 16, 2011 at 6:44 AM, Jed Brown <jed at 59a2.org> wrote: > On Mon, May 16, 2011 at 13:30, Dmitry Karpeev <karpeev at mcs.anl.gov> wrote: >> >> The overlapping logic goes elsewhere (MatSetValuesLocal). > > Note that the MatSetValuesLocal() kind of overlap (the > ISLocalToGlobalMapping) is now part of PetscLayout.
True, although MatSetValuesLocal (not the default implementation in the interface) is a way to extend the mechanism that relies on ISLocalToGlobalMapping. This can include whatever semantics are appropriate to handle the overlaps, etc. I think this is a reasonable splitting of functionality between PetscLayout and MatSetValuesLocal().
