DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks

Budak, A. F., Bhansali, P., Liu, B. , Sun, N., Pan, D. Z. and Kashyap, C. V. (2021) DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks. In: 2021 58th ACM/IEEE Design Automation Conference (DAC), San Francisco, CA, USA, 05-09 Dec 2021, pp. 1219-1224. ISBN 9781665432740 (doi: 10.1109/DAC18074.2021.9586139)

Abstract

Analog circuit sizing takes a significant amount of manual effort in a typical design cycle. With rapidly developing technology and tight schedules, bringing automated solutions for sizing has attracted great attention. This paper presents DNN-Opt, a Reinforcement Learning (RL) inspired Deep Neural Network (DNN) based black-box optimization framework for analog circuit sizing. The key contributions of this paper are a novel sample-efficient two-stage deep learning optimization framework leveraging RL actor-critic algorithms, and a recipe to extend it on large industrial circuits using critical device identification. Our method shows 5—30x sample efficiency compared to other black-box optimization methods both on small building blocks and on large industrial circuits with better performance metrics. To the best of our knowledge, this is the first application of DNN-based circuit sizing on industrial scale circuits.

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Liu, Professor Bo and Budak, Ahmet
• Authors: Budak, A. F., Bhansali, P., Liu, B., Sun, N., Pan, D. Z., and Kashyap, C. V.
• College/School: College of Science and Engineering > School of Engineering > Systems Power and Energy
• ISSN: 0738-100X
• ISBN: 9781665432740
• Copyright Holders: Copyright © 2021 IEEE
• Publisher Policy: Reproduced in accordance with the copyright policy of the publisher

Related URLs

• Organisation
• Publisher