ABSTRACT Simulation Between Enhanced Meshes and the Multiple Associative Computing (MASC) Model

MASC (for Multiple Associative Computing) is a practical, highly scalable joint control parallel, data parallel model that naturally supports massive parallelism and a wide range of applications. In this paper, we propose efficient algorithms for the MASC model with a 2-D mesh to simulate enhanced meshes, e.g., meshes with multiple broadcasting (MMB), and basic reconfigurable meshes (BRM). The results not only show the power of the MASC model in terms of the enhanced mesh models but also provide an automatic conversion of numerous algorithms designed for enhanced meshes to the MASC model