DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks
DNN-Opt: An RL Inspired Optimization for Analog Circuit Sizing using Deep Neural Networks
复制标题
DOI：
10.1109/dac18074.2021.9586139
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
A. Budak;Prateek Bhansali;Bo Liu;Nan Sun;D. Pan;Chandramouli V. Kashyap
中科院分区：
文献类型：
--
作者：
A. Budak;Prateek Bhansali;Bo Liu;Nan Sun;D. Pan;Chandramouli V. Kashyap
在典型的设计周期中，模拟电路尺寸的确定需要大量的手工工作。随着快速发展的技术和紧迫的时间表，带来自动化解决方案的大小已经引起了极大的关注。本文介绍了DNN-Opt，这是一种受强化学习（RL）启发的基于深度神经网络（DNN）的黑盒优化框架，用于模拟电路规模调整。本文的主要贡献是利用RL actor-critic算法的新型样本高效两阶段深度学习优化框架，以及使用关键设备识别将其扩展到大型工业电路的方法。与其他黑盒优化方法相比，我们的方法在小型构建块和大型工业电路上都显示出5- 30倍的采样效率，具有更好的性能指标。据我们所知，这是基于DNN的电路规模在工业规模电路上的首次应用。
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.