Communication Aspects of Parallel Processing

Abstract : Parallel processing was motivated by the need to solve very large computational problems, such as the numerical solutions of partial differential equations in the context of computational fluid dynamics, structural mechanics, image processing, etc. This report surveys recent literature on parallel processing algorithms for mainly rings, meshes, and hypercubes. These algorithms include vector, matrix computations, fixed point iterations and linear equation solvers. A group property of above topologies has also been explored in an attempt to develop tools for algorithms and performance analysis. Some special sparsity structure of the iteration dependencies has also been examined. A necessary and sufficient condition for the reducibility of a dependency matrix with sparse, nonzero extended diagonals has been derived. Keywords: Communications traffic, Traffic distributions.