FIST: A Framework to Interleave Spiking Neural Networks on CGRAs

Abstract

<div> Coarse Grained Reconfigurable Architectures</div> <div> (CGRAs) are emerging as enabling platforms to meet the high</div> <div> performance demanded by modern embedded applications. In</div> <div> many application domains (e.g. robotics and cognitive embedded</div> <div> systems), the CGRAs are required to simultaneously host</div> <div> processing (e.g. Audio/video acquisition) and estimation (e.g.</div> <div> audio/video/image recognition) tasks. Recent works have revealed</div> <div> that the efficiency and scalability of the estimation algorithms</div> <div> can be significantly improved by using neural networks.</div> <div> However, existing CGRAs commonly employ homogeneous</div> <div> processing resources for both the tasks. To realize the best of</div> <div> both the worlds (conventional processing and neural networks),</div> <div> we present FIST. FIST allows the processing elements and the</div> <div> network to dynamically morph into either conventional CGRA</div> <div> or a neural network, depending on the hosted application. We</div> <div> have chosen the DRRA as a vehicle to study the feasibility and</div> <div> overheads of our approach. Synthesis results reveal that the</div> <div> proposed enhancements incur negligible overheads (4.4% area</div> <div> and 9.1% power) compared to the original DRRA cell.</div>