A scalable strategy for the parallelization of multiphysics unstructured mesh iterative codes on distributed-memory systems

Realizing scalable performance on high performance computing systems is not straightforward for single-phenomenon codes (such as computational fluid d ynamics [CFD]). This task is magnified considerably when the target softwar e involves the interactions of a range of phenomena that have distinctive s olution procedures involving different discretization methods. The problems of addressing the key issues of retaining data integrity and the ordering of the calculation procedures are significant. A strategy for parallelizing this multiphysics family of codes is described for software exploiting fin ite-volume discretization methods on unstructured meshes using iterative so lution procedures. A mesh partitioning-based SPMD approach is used. However , since different variables use distinct discretization schemes, this means that distinct partitions are required; techniques for addressing this issu e are described using the mesh-partitioning tool, JOSTLE. In this contribut ion, the strategy is tested for a variety of test cases under a wide range of conditions (e.g., problem size, number of processors, asynchronous/synch ronous communications, etc.) using a variety of strategies for mapping the mesh partition onto the processor topology.