enable shared memory for >1 node

[jeffhammond]

Currently, SMP optimizations only works when MPI_COMM_WORLD is an SMP. This is easy enough to fix and should be implemented.

[jeffhammond]

This is much easier to do with MPI 4.1: https://www.mpi-forum.org/docs/mpi-4.1/mpi41-report/node311.htm