NAHAS: Neural Architecture and Hardware Accelerator Search

Yanqi Zhou, Xuanyi Dong, Daiyi Peng, Ethan Zhu, Amir Yazdanbakhsh, Berkin Akin, Mingxing Tan, James Laudon

Keywords: neural architecture search, systems, hardware

Abstract:

Neural architectures and hardware accelerators have been two driving forces for the rapid progress in deep learning.
Although previous works have optimized either neural architectures given fixed hardware, or hardware given fixed neural architectures, none has considered optimizing them jointly. In this paper, we study the importance of co-designing neural architectures and hardware accelerators. To this end, we propose NAHAS, an automated hardware design paradigm that jointly searches for the best configuration for both neural architecture and accelerator. In NAHAS, accelerator hardware design is conditioned on the dynamically explored neural networks for the targeted application, instead of fixed architectures, thus providing better performance opportunities. Our experiments with an industry-standard edge accelerator show that NAHAS consistently outperforms previous platform-aware neural architecture search and state-of-the-art EfficientNet on all latency targets by 0.5% - 1% ImageNet top-1 accuracy, while reducing latency by about 20%. Joint optimization reduces the search samples by 2x and reduces the latency constraint violations from 3 violations to 1 violation per 4 searches, compared to independently optimizing the two sub spaces.

One-sentence Summary: We propose NAHAS, a latency-driven software/hardware co-optimizer that jointly optimize the design of neural architectures and a mobile edge processor.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=XAINZ05nBy