An Energy-Efficient One-Shot Time-Based Neural Network Accelerator Employing Dynamic Threshold Error Correction in 65 nm Luke R. Everson , Student Member , IEEE, Muqing Liu , Student Member , IEEE

Abstract

As neural networks continue to infiltrate diverse application domains, computing will begin to move out of the cloud and onto edge devices necessitating fast, reliable, and low- power (LP) solutions. To meet these requirements, we propose a time-domain core using one-shot delay measurements and a lightweight post-processing technique, dynamic threshold error correction (DTEC). This design differs from traditional digital implementations in that it uses the delay accumulated through a simple inverter chain distributed through an SRAM array to intrinsically compute resource intensive multiply-accumulate (MAC) operations. Implemented in 65-nm LP CMOS, we achieve an energy efficiency of 104.8 TOp/s/W at 0.7-V with 3b resolution for 19.1 fJ/MAC.