[petsc-dev] Integrating PFLOTRAN, PETSC & SAMRAI

[Jed Brown]

On Tue, Jun 7, 2011 at 21:07, Philip, Bobby <philipb at ornl.gov> wrote:

> Every apply call from KSP does need to initialize data over the whole
> hierarchy that is consistent across the levels.
>

Why not encapsulate this whole operation into a scatter of some sort? I'm
having a hard time visualizing this operation being a large cost compared to
other operations like physics/smoother for fundamental reasons. Of course
the current interfaces could make it expensive and I understand not
prioritizing low-level changes when the current solution works.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20110607/92ff563e/attachment.html>