A 0.11 pJ/Op, 0.32-128 TOPS, Scalable Multi-Chip-Module-based Deep Neural Network Accelerator with Ground-Reference Signaling in 16nm

Brian Zimmer, Rangharajan Venkatesan, Yakun Sophia Shao, Jason Clemons, Matthew Fojtik, Nan Jiang, Ben Keller, Alicia Klinefelter, Nathaniel Ross Pinckney, Priyanka Raina, Stephen G. Tell, Yanqing Zhang, William J. Dally, Joel S. Emer, C. Thomas Gray, Stephen W. Keckler, Brucek Khailany

Abstract: This work presents a scalable deep neural network (DNN) accelerator consisting of 36 chips connected in a mesh network on a multi-chip-module (MCM) using ground-referenced signaling (GRS). While previous accelerators fabricated on a single monolithic die are limited to specific network sizes, the proposed architecture enables flexible scaling for efficient inference on a wide range of DNNs, from mobile to data center domains. The 16nm prototype achieves 1.29 TOPS/mm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> , 0.11 pJ/op energy efficiency, 4.01 TOPS peak performance for a 1chip system, and 127.8 peak TOPS and 2615 images/s ResNet50 inference for a 36-chip system.