I'm want to run two mpi (MPICH2) codes in my cluster.
I send the first work distributed with round robin and all is ok.
The problem appear when I send the second work. The memory used by the second one is from the cpu used by the first work and doesn't use the memory of the other, almost free, cpu.
There is a flag with which I can tell to MPICH2 that it should use the memory free cpus?
I'm in no way an expert on using MPICH2 (being most familiar with the Intel MPI Library), but the following MPICH2 Wiki article discusses using the Hydra Process Managerto bind processes to particular cores via the -binding option. Hydra is compiled into MPICH2 distributions starting with version 1.1 (as
I'm not sure how you can pin processes otherwise with the default MPICH2 configuration. I'd also suggest posting on one of the MPICH2 mailing lists, or checking out the archives (links available on that same page).