Unifying FPGAs and SIMD Arrays
Michael Bolotski Andr, DeHon Thomas, Frederick K. Knight · 1994
Field-Programmable Gate Arrays (FPGAs) and 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 unied computational array model which encompasses both FPGAs and SIMD arrays. Within this framework, we examine the dierences and similarities between these array structures and touch upon techniques and lessons which can be transfered between the architectures. The unied 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.