On Apr 24, 2012, at 3:01 PM, Tom Rosmond wrote:
> My question is this: If the cartesian mapping is done so the two
> spacial dimensions are the 'most rapidly varying' in equivalent 1-D
> processor mapping, will Open-mpi automatically assign those 2 dimensions
> 'on-node', and assign the 'ensemble' dimension as the slowest varying
> and across nodes? If not, how can we guarantee this to happen?
Sadly, the MPI mapping functions in Open MPI are effectively no-ops -- if you ask for re-ordering, OMPI says "sure!" but then gives you back exactly the same mapping. :-(
That being said, the mapping functionality is actually a plugin in Open MPI (in the "topo" framework). It would not be too difficult to write a plugin for the mapping that you want.
Would this be of interest to you? I'd be happy to talk you through the process of writing such a plugin.
For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/