Temperature-Aware Optimization of Monolithic 3D Deep Neural Network Accelerators

We propose an automated method to facilitate the design of energy- efficient Mono3D DNN accelerators with safe on-chip temperatures for mobile systems. We introduce an optimizer to investigate the effect of different aspect ratios and footprint specifications of the chip, and select energy-efficient accelerators under user-specified thermal and performance constraints. We also demonstrate that using our optimizer, we can reduce energy consumption by 1.6× and area by 2× with a maximum of 9.5% increase in latency compared to a Mono3D DNN accelerator optimized only for performance.