Unifying FPGAs and SIMD arrays

Single-Instruction Multiple-Data (SIMD) processing arrays share many architectural features. In both architectures, an array of simple, ne-grained logic elements is employed to provide high-speed, customizable, bit-wise computation. In this paper, we present a uni ed computational array model which encompasses both FPGAs and SIMD arrays. Within this framework, we examine the di erences and similarities between these array structures and touch upontechniques and lessons which canbe transfered between the architectures. The uni ed model also exposes promising prospects for hybrid array architectures. We introduce the Dynamically Programmable Gate Array (DPGA) which combines the best features from FPGAs and SIMD arrays into a single array architecture.