Folks,
for the records, this was investigated off-list
- the root cause was bad permissions on the /.../lib/openmpi directory
(no components could be found)
- then it was found tm support was not built-in, so mpirun did not
behave as expected under torque/pbs
Cheers,
Gilles
On 5/15/2
On Sat, Oct 24, 2009 at 07:00:11PM -0600, Damien Hocking wrote:
> Roberto,
>
> Ipopt doesn't use MPI. It can use the MUMPS parallel linear solver in
> sequential mode, but nothing is set up in IPOPT to use the parallel MPI
> version. For sequential mode, MUMPS dummies out the MPI headers. Th
Roberto,
Ipopt doesn't use MPI. It can use the MUMPS parallel linear solver in
sequential mode, but nothing is set up in IPOPT to use the parallel MPI
version. For sequential mode, MUMPS dummies out the MPI headers. The
dummy headers are part of the MUMPS distribution in the libseq
directo
