Orthogonal Processor Groups for Message-Passing Programs

We consider a generalization of the SPMD programming model to orthogonal processor groups. In this model different partitions of the processors into disjoint processor groups can be exploited in a single parallel implementation. The parallel programming model is appropriate for grid based applications with computations and dependence pattern mainly aligned in horizontal or vertical directions. For those applications we propose a systematic development process for message-passing programs using orthogonal processor groups. The development process starts with an SPMD-like specification of tasks indicating horizontal and vertical sections. A mapping to orthogonal processor groups realizes a group SPMD execution model with different orthogonal processor groups and a final transformation generates the corresponding MPI program. In this paper, we describe the approach and present example applications which can benefit from an implementation with orthogonal processor groups. The runtimes are measured on a Cray T3E.