AI-based automated circuit design optimization technology

Yilin Yang

doi:10.1117/12.3052159

11 December 2024 AI-based automated circuit design optimization technology

Yilin Yang

Proceedings Volume 13445, International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2024); 134451A (2024) https://doi.org/10.1117/12.3052159
Event: International Conference on Electronics. Electrical and Information Engineering (ICEEIE 2024), 2024, Haikou, China

Abstract

This paper introduces a novel AI-based automated circuit design optimization method aimed at enhancing design quality and efficiency. The proposed modular architecture integrates artificial intelligence with circuit design expertise, comprising key components for data processing, optimization algorithms, circuit simulation, and feedback mechanisms. We implement and test this system on a high-performance computing cluster, utilizing a comprehensive test suite of both analog and digital circuits. Our method demonstrates significant improvements in critical performance metrics, including power consumption, delay, and area, with enhancements ranging from 10% to 30% compared to traditional design approaches. The system's ability to generate multiple optimized design candidates under various constraints provides designers with flexible trade-off options. Furthermore, the high degree of automation in our approach substantially reduces manual effort and accelerates the design process. These results underscore the potential of AI-driven techniques to revolutionize integrated circuit design methodologies.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yilin Yang "AI-based automated circuit design optimization technology", Proc. SPIE 13445, International Conference on Electronics, Electrical and Information Engineering (ICEEIE 2024), 134451A (11 December 2024); https://doi.org/10.1117/12.3052159

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available