Is it good to say that between nodes (physical machines) we mostly use MPI while inside a node we often use shared-address model?
icebear101
Ah, I just saw the conclusion in slides 62: "Use shared address space programming within a multi-core node of a cluster, use message passing between nodes".
kayvonf
@icebear. Exactly. A pragmatic solution these days is to use a hybrid of programming models for big complex machines where different optimizations or strategies are best at different levels of the machine.
Is it good to say that between nodes (physical machines) we mostly use MPI while inside a node we often use shared-address model?