Hi,
I'm trying to compile a hybrid pmemd with both MPI and OpenMP and it's
not acting the way I expect. It seems to build ok, the run_cmake step
indicates that OpenMP is included and the pmemd.MPI binary acts exactly
as I would expect with no OpenMP - exactly one core per rank.
I set OMP_NUM_THREADS, launch with either mpirun or srun, no change. I
ditch the scheduler entirely and run manually on a whole node, no change.
Is there a known good procedure to get one MPI rank per node and OpenMP
threading across that node with pmemd?
Thanks,
Bill Abbott
Office of Advanced Research Computing
Rutgers University
_______________________________________________
AMBER mailing list
AMBER.ambermd.org
http://lists.ambermd.org/mailman/listinfo/amber
Received on Tue Oct 27 2020 - 12:30:02 PDT