Hello all, I am relatively new to mpi computing. I am doing particle simulations. So far, I only used pure mpi and I never had a problem. But for my system, its the best if one uses hybrid programming. But I always fail to correctly bind all processes and receive binding errors from cluster. Could one of you please clarify correct parameters for mpirun for below two cases:
1) I would like to use lets say two mpi tasks and 16 processors as openmp threads. I request nodes:2:ppn=16. 2) For the same case, how should i give parameters such that i have 4 mpi tasks and 8 openmp threads. I also tried options with --map-by and it happened that sometimes both mpi tasks are being selected from same node and other node is idle. I really appreciate your help. And my openmp version is 1.8. -- Kind Regards, Anil. ********* "Its impossible" - said Pride "Its risky" - said Experience "Its pointless" - said Reason "Give it a try" - whispered the heart *********
_______________________________________________ users mailing list users@lists.open-mpi.org https://lists.open-mpi.org/mailman/listinfo/users
