VUSA: Virtually Upscaled Systolic Array Architecture to Exploit Unstructured Sparsity in AI Acceleration
Shereef Helal, Alberto García-Ortiz, Lennart Bamberg · 2025
Leveraging high degrees of unstructured sparsity is a promising approach to enhance the efficiency of deep neural network (DNN) accelerators-particularly important for emerging EdgeAI applications. We introduce VUSA, a systolic-array architecture that virtually grows based on the present sparsity to perform larger matrix multiplications with the same number of physical multiply-accumulate (MAC) units. The proposed architecture achieves saving by 37 % and 68 % in area and power efficiency, respectively, at the same peak-performance, compared to a baseline systolic array architecture in a commercial 16-nm technology. Still, the proposed architecture supports acceleration for any DNN with any sparsity-even no sparsity at all. Thus, the proposed architecture is application-independent, making it viable for generalpurpose AI acceleration.