Question about TBB and MPI technology

[postaquestion]

I have a question about TBB and MPI technology.
As far as i see now, after downloading evaluation versions of products, they aren't connected together.
But i'm interested in having something like that:
I'm writing Code using Threads (i.e. with TBB) and loading some library that can manage threads inside of my applicaton and execute them thru the cluster.
Is it possible whith Intel tools? or what nearest solution can Intel offer?

[TimP]

You could use TBB to thread with shared memory model on each node, combined with MPI to run across a cluster. More often, this hybrid model is accomplished with OpenMP. Intel Cluster OpenMP extends OpenMP threading to a distributed memory model across a small cluster.

[jimdempseyatthecove]

MPI is a process to process collaboration via a message passing mechanism. Although this can be on a shared memory system it need not be. TBB and OpenMP (or Cluster OpenMP or other thread mechanism) is generally designed around a shared memory module. The two can be combined as a hybrid.

Usually you would code the OpenMP/TBB application such that outside the parallel sections the master thread runs the MPI message loop which then calls into routines that spawn multiple threads, performs the work, then upon completion, exits the parallel section and returns to the master threadMPI message loop. The MPI does not have a concept of having a thread within a spawned application.

Jim Dempsey