AIrchitect: Automating Hardware Architecture and Mapping Optimization

Ananda Samajdar, Jan Moritz Joseph, Tushar Krishna

Abstract: Design space exploration and optimization is an essential but iterative step in custom accelerator design involving costly search based method to extract maximum performance and energy efficiency. State-of-the-art methods employ data centric approaches to reduce the cost of each iteration but still rely on search algorithms to obtain the optima. This work proposes a learned, constant time optimizer that uses a custom recommendation network called AIrchitect, which is capable of learning the architecture design and mapping space with a 94.3% test accuracy, and predicting optimal configurations, which achieve on an average (GeoMean) 99.9% of the best possible performance on a test dataset with 10⁵ GEMM (GEneral Matrix-matrix Multiplication) workloads.