Design and Implementation of Energy-Efficient Binary Neural Networks Using Adiabatic Quantum-Flux-Parametron Logic

Adiabatic quantum-flux-parametron (AQFP) logic is a promising technology for future energy-efficient, high-performance information processing systems. It has significantly low power dissipation thanks to the adiabatic switching of Josephson junctions. In this paper, we introduce an AQFP-based binary neural network (BNN) design methodology utilizing an in-memory computing scheme, analog accumulation, and a crossbar structure. The proposed design can effectively resolve the memory issue in superconducting digital circuits by significantly reducing memory usage in a non-Von Neumann fashion compared to conventional neural networks. As a proof-of-concept, we designed and implemented an 8 × 8 AQFP BNN using the proposed design methodology targeted the AIST 10kA/cm
²
4-layer niobium process. The Josephson junction count and energy dissipation of the proposed 8 × 8 BNN design are 2236 and 11.18 aJ, respectively.