Hi Alain,

On Sep 22, 2014, at 10:10 AM, Alain Miniussi <alain.miniussi@oca.eu> wrote:

----- Original Message -----

The Cartesian decomposition part of the MPI spec does not seems to be

present in boost mpi.

Is it just due to a lack of resources or is it useless for some

reason ?

I'd like to look into it but would like to make sure there is a
point.

I think you’ll find that most codes perform parallel decomposition using other tools (e.g. Geometric, Graph, Hyper-graph, etc…) partitioners so this particular MPI capability isn’t as broadly useful as other approaches. I suspect that’s why it was never implemented.

— Noel