Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators release_v6qkinbvjngk7hsoolebgbxeb4

by Weiwen Jiang, Qiuwen Lou, Zheyu Yan, Lei Yang, Jingtong Hu, Xiaobo Sharon Hu, Yiyu Shi

Released as a article .

2019  

Abstract

Co-exploration of neural architectures and hardware design is promising to simultaneously optimize network accuracy and hardware efficiency. However, state-of-the-art neural architecture search algorithms for the co-exploration are dedicated for the conventional von-neumann computing architecture, whose performance is heavily limited by the well-known memory wall. In this paper, we are the first to bring the computing-in-memory architecture, which can easily transcend the memory wall, to interplay with the neural architecture search, aiming to find the most efficient neural architectures with high network accuracy and maximized hardware efficiency. Such a novel combination makes opportunities to boost performance, but also brings a bunch of challenges. The design space spans across multiple layers from device type, circuit topology to neural architecture. In addition, the performance may degrade in the presence of device variation. To address these challenges, we propose a cross-layer exploration framework, namely NACIM, which jointly explores device, circuit and architecture design space and takes device variation into consideration to find the most robust neural architectures. Experimental results demonstrate that NACIM can find the robust neural network with 0.45% accuracy loss in the presence of device variation, compared with a 76.44% loss from the state-of-the-art NAS without consideration of variation; in addition, NACIM achieves an energy efficiency up to 16.3 TOPs/W, 3.17X higher than the state-of-the-art NAS.
In text/plain format

Archived Files and Locations

application/pdf  651.5 kB
file_laa6bao7onfypfrtirq5uuszli
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2019-10-31
Version   v1
Language   en ?
arXiv  1911.00139v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 5d01ebe7-1230-4e64-ad69-1b06781cbcb0
API URL: JSON