A Circuit Attention Network-Based Actor-Critic Learning Approach to Robust Analog Transistor Sizing

Yaguang Li, Yishuang Lin, Meghna Madhusudan, Arvind K Sharma, Sachin Sapatnekar, Ramesh Harjani, Jiang Hu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Analog integrated circuit design is highly complex and its automation is a long-standing challenge. We present a reinforcement learning approach to automatic transistor sizing, a key step in determining analog circuit performance. A circuit attention network technique is developed to capture the impact of transistor sizing on circuit performance in an actor-critic learning framework. Our approach also includes a stochastic technique for addressing layout effect, another important factor affecting performance. Compared to Bayesian optimization (BO) and Graph Convolutional Network-based reinforcement learning (GCN-RL), two state-of-the-art methods, the proposed approach significantly improves robustness against layout uncertainty while achieving better post-layout performance. BO and GCN-RL can be enhanced with our stochastic technique to reach solution quality similar to ours, but still suffer from a much slower convergence rate. Moreover, the knowledge transfer in our approach is more effective than that in GCN-RL.

Original languageEnglish (US)
Title of host publication2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD, MLCAD 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665431668
DOIs
StatePublished - Aug 30 2021
Event3rd ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2021 - Raleigh, United States
Duration: Aug 30 2021Sep 3 2021

Publication series

Name2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD (MLCAD)

Conference

Conference3rd ACM/IEEE Workshop on Machine Learning for CAD, MLCAD 2021
Country/TerritoryUnited States
CityRaleigh
Period8/30/219/3/21

Bibliographical note

Funding Information:
ACKNOWLEDGEMENT This work is supported by the DARPA ERI IDEA program.

Publisher Copyright:
© 2021 IEEE.

Fingerprint

Dive into the research topics of 'A Circuit Attention Network-Based Actor-Critic Learning Approach to Robust Analog Transistor Sizing'. Together they form a unique fingerprint.

Cite this