A 617 TOPS/W All Digital Binary Neural Network Accelerator in 10nm FinFET CMOS

Phil C. Knag, Gregory K. Chen, Huseyin Ekin Sumbul, Raghavan Kumar, Mark A. Anders, Himanshu Kaul, Steven K. Hsu, Amit Agarwal, Monodeep Kar, Seongjong Kim, Ram K. Krishnamurthy

Abstract: A 10nm digital Binary Neural Network (BNN) chip implements 1b activations and weights for compute density of 418TOPS/mm2 and memory density of 414KB/mm2. The chip achieves an energy efficiency of 617TOPS/W by leveraging Compute Near Memory (CNM), parallel inner product compute, and Near-Threshold Voltage (NTV) operation. The digital BNN design approaches the energy efficiency of analog in-memory techniques while also ensuring deterministic, scalable, and precise operation.