[petsc-dev] MatMatSolve_MUMPS

[Eric Chamberland]

Jed, Hong,

thank you for your answers!

Eric

Le 12/06/2012 01:25 PM, Jed Brown a écrit :
> 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 
> <mailto: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
>
>