PERFORMANCE EVALUATION AND OPTIMIZATION IN LOW-COST CELLULAR SIMD SYSTEMS

Low-cost massively parallel architectures are generally characterized by a number of processors which is often far lower that the size of th e data set, and by a limited amount of memory owned by each Processing Element, As a consequence, low-cost mesh-connected architectures can utilize only a specific processor virtualization mechanism which is ba sed on the sequential scanning of the data set stored in an external m emory, As a consequence of this virtualization mechanism, applications must be developed according to some precise criteria, This paper pres ents the optimization of some key parameters for the improvement of sy stem performance. These optimizations are validated through an image p rocessing case study.