[petsc-users] Euclid/Hypre running slow

[Manav Bhatia]

Hi,

    I am using ilu(k) preconditioner from Euclid/Hypre on my Mac OS 10.9
box with 12 processors and openmpi v1.7.3 from macports.

    I find that for 1 CPU (-np 1) the code runs reasonably fast, but when
multiple processors are included the solver runs significantly slow (by
orders of magnitude). I ran the time profiler on one of the processes
spawned by openmpirun, and it seems to be taking a lot of time in
MPI_Waitall called from Euclid_dhSetup.

    This could very well be a Hypre issue, but I wanted to check to see if
anynoe on the Petsc list has experience a similar problem.

    Any suggestions/inputs are welcome.

Thanks,
Manav
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-users/attachments/20131119/9813ad75/attachment.html>