Eric, we would welcome an implementation that batched together a run-time-specified number of RHS vectors and used MUMPS' native multiple-RHS routines. The problem is that there has to be enough memory to store them all on rank 0, which is non-scalable, but the MUMPS developers do not care to fix that aspect of their interface. The current implementation solves only one at a time, which is less efficient than solving several at a time.
On Thu, Dec 6, 2012 at 10:20 AM, Hong Zhang <hzhang at mcs.anl.gov> wrote: > Eric : > > > I just want to know if there is a known difficulty or unfeasible task if > > someone would like to implement MatMatSolve_MUMPS? > > MatMatSolve_MUMPS is supported in petsc-dev. > It calls MatMatSolve_Basic() with then calls MatSolve_MUMPS > in a loop. > > MUMPS own matmatsolve requires entire rhs matrix store in the host > which is non-scalable. > > Hong > -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20121206/a8212a6b/attachment.html>
