Temperature-Aware Monolithic 3D DNN Accelerators for Biomedical Applications

03/29/2022

∙

by   Prachi Shukla, et al.

∙

0

∙

share

In this paper, we focus on temperature-aware Monolithic 3D (Mono3D) deep neural network (DNN) inference accelerators for biomedical applications. We develop an optimizer that tunes aspect ratios and footprint of the accelerator under user-defined performance and thermal constraints, and generates near-optimal configurations. Using the proposed Mono3D optimizer, we demonstrate up to 61 applications over a performance-optimized accelerator.