COMPARISON OF 2 APPLICATION-SPECIFIC ARCHITECTURES FOR 2-D MESH COMPUTATIONS

This paper considers the question of whether a mesh-connected machine is always better than a multi-pipelined machine for iterative 2-d mesh computations. Optimal throughput is determined as a function of a uni fied measure of resources (cost). The resulting performance curves for the two architectures show that there is a cost below which the pipel ined architecture is an order of magnitude faster than the mesh, and a bove which this relationship is reversed. This methodology of comparin g architectures using throughput-versus-cost modeling may prove useful in other contexts. (C) 1994 Academic Press, Inc.