Large circuit models:opportunities and challenges  

作　　者：Lei CHEN Yiqi CHEN Zhufei CHU Wenji FANG Tsung-Yi HO Ru HUANG Yu HUANG Sadaf KHAN Min LI Xingquan LI Yu LI Yun LIANG Jinwei LIU Yi LIU Yibo LIN Guojie LUO Hongyang PAN Zhengyuan SHI Guangyu SUN Dimitrios TSARAS Runsheng WANG Ziyi WANG Xinming WEI Zhiyao XIE Qiang XU Chenhao XUE Junchi YAN Jun YANG Bei YU Mingxuan YUAN Evangeline F.Y.YOUNG Xuan ZENG Haoyi ZHANG Zuodong ZHANG Yuxiang ZHAO Hui-Ling ZHEN Ziyang ZHENG Binwu ZHU Keren ZHU Sunan ZOU 

机构地区：[1]Department of Computer Science and Engineering,The Chinese University of Hong Kong,Hong Kong 999077,China [2]School of Microelectronics,State Key Laboratory of Integrated Chips and System,Fudan University,Shanghai 200433,China [3]Department of Electronic and Computer Engineering,Hong Kong University of Science and Technology,Hong Kong 999077,China [4]Huawei HiSilicon,Shenzhen 518129,China [5]Huawei Noah's Ark Lab,Hong Kong 999077,China [6]Faculty of Electrical Engineering and Computer Science,Ningbo University,Ningbo 315211,China [7]School of Integrated Circuits,Peking University,Beijing 100871,China [8]School of Computer Science,Peking University,Beijing 100871,China [9]Peng Cheng Laboratory,Shenzhen 518052,China [10]School of Artificial Intelligence,Shanghai Jiao Tong University,Shanghai 200240,China [11]School of Integrated Circuits,Southeast University,Nanjing 210096,China

出　　处：《Science China(Information Sciences)》2024年第10期21-62,共42页中国科学（信息科学）（英文版）

基　　金：supported in part by Hong Kong S.A.R.General Research Fund(Grant No.14212422);Research Matching(Grant No.CSE-7-2022)。

摘　　要：Within the electronic design automation(EDA)domain,artificial intelligence(AI)-driven solutions have emerged as formidable tools,yet they typically augment rather than redefine existing methodologies.These solutions often repurpose deep learning models from other domains,such as vision,text,and graph analytics,applying them to circuit design without tailoring to the unique complexities of electronic circuits.Such an“AI4EDA”approach falls short of achieving a holistic design synthesis and understanding,overlooking the intricate interplay of electrical,logical,and physical facets of circuit data.This study argues for a paradigm shift from AI4EDA towards AI-rooted EDA from the ground up,integrating AI at the core of the design process.Pivotal to this vision is the development of a multimodal circuit representation learning technique,poised to provide a comprehensive understanding by harmonizing and extracting insights from varied data sources,such as functional specifications,register-transfer level(RTL)designs,circuit netlists,and physical layouts.We champion the creation of large circuit models(LCMs)that are inherently multimodal,crafted to decode and express the rich semantics and structures of circuit data,thus fostering more resilient,efficient,and inventive design methodologies.Embracing this AI-rooted philosophy,we foresee a trajectory that transcends the current innovation plateau in EDA,igniting a profound“shift-left”in electronic design methodology.The envisioned advancements herald not just an evolution of existing EDA tools but a revolution,giving rise to novel instruments of design-tools that promise to radically enhance design productivity and inaugurate a new epoch where the optimization of circuit performance,power,and area(PPA)is achieved not incrementally,but through leaps that redefine the benchmarks of electronic systems'capabilities.

关 键 词：AI-rooted EDA large circuit models(LCMs) multimodal circuit representation learning circuit optimization 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TN702[自动化与计算机技术—控制科学与工程]