A Survey for Electronic Design Automation Based on Graph Neural Network

TIAN Chunsheng; CHEN Lei; WANG Yuan; WANG Shuo; ZHOU Jing; WANG Zhuoli; PANG Yongjiang; DU Zhong

doi:10.11999/JEIT230266

Volume 45 Issue 9

Sep. 2023

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2023 > 45(9): 3069-3082

TIAN Chunsheng, CHEN Lei, WANG Yuan, WANG Shuo, ZHOU Jing, WANG Zhuoli, PANG Yongjiang, DU Zhong. A Survey for Electronic Design Automation Based on Graph Neural Network[J]. Journal of Electronics & Information Technology, 2023, 45(9): 3069-3082. doi: 10.11999/JEIT230266

Citation:

TIAN Chunsheng, CHEN Lei, WANG Yuan, WANG Shuo, ZHOU Jing, WANG Zhuoli, PANG Yongjiang, DU Zhong. A Survey for Electronic Design Automation Based on Graph Neural Network[J]. Journal of Electronics & Information Technology, 2023, 45(9): 3069-3082. doi: 10.11999/JEIT230266

Citation:

PDF( 4617 KB)

A Survey for Electronic Design Automation Based on Graph Neural Network

doi: 10.11999/JEIT230266

1.
Beijing Microelectronics Technology Institute, Beijing 100076, China
2.
School of Integrated Circuits, Peking University, Beijing 100871, China

Funds: The National Natural Science Foundation of China (U20A20204), The National Key S&T Special Projects (2009ZYHJ0005)

Received Date: 2023-04-12
Rev Recd Date: 2023-07-12

Available Online: 2023-07-18

Publish Date: 2023-09-27

Abstract

Abstract

Driven by Moore’s law, the aggressive shrinking of feature sizes, and the complexity of the chip design is also steadily increasing. Electronic Design Automation (EDA) technology faces challenges from many aspects such as runtime and computing resources. To alleviate these challenges, machine learning methods are incorporated into the design process of EDA tools. At the same time, given the nature of circuit netlist as graphical data, the application of Graph Neural Network (GNN) in the EDA is becoming more and more common, bring new ideas for modeling complex problems and solving optimal problems. A brief overview of the concept GNN and EDA is presented. The main role of GNN in different EDA stages such as High Level Synthesis (HLS), logic synthesis, floorplan and placement, routing, reverse engineering, hardware trojan detection and test point insertion is summarized. The main role of GNN in the EDA design process is sorted out in detail, as well as some important explorations of current GNN-based EDA technology. It is hoped to provide reference for researchers in integrated circuit design automation and related fields, and provide technical support for China’s advanced integrated circuit industry.
- Electronic Design Automation (EDA),
- Graph Neural Network (GNN),
- Advanced integrated circuit technology,
- Agile design

FullText(HTML)

References(53)

References

[1]	田春生, 陈雷, 王源, 等. 基于机器学习的FPGA电子设计自动化技术研究综述[J]. 电子与信息学报, 2023, 45(1): 1–13. doi: 10.11999/JEIT220183 TIAN Chunsheng, CHEN Lei, WANG Yuan, et al. A survey on FPGA electronic design automation technology based on machine learning[J]. Journal of Electronics &Information Technology, 2023, 45(1): 1–13. doi: 10.11999/JEIT220183
[2]	贺旭, 王耀, 傅智勇, 等. 敏捷设计中基于机器学习的静态时序分析方法综述[J]. 计算机辅助设计与图形学学报, 2023, 35(4): 640–652. doi: 10.3724/SP.J.1089.2023.19557 HE Xu, WANG Yao, FU Zhiyong, et al. A survey on machine learning-based technology for static timing analysis in agile design[J]. Journal of Computer-Aided Design &Computer Graphics, 2023, 35(4): 640–652. doi: 10.3724/SP.J.1089.2023.19557
[3]	KAHNG A B, LIENIG J, MARKOV I L, et al. VLSI Physical Design: From Graph Partitioning to Timing Closure[M]. Dordrecht: Springer, 2011.
[4]	ITRS. International technology roadmap for semiconductors 2.0 publication[EB/OL]. http://www.itrs2.net/itrs-reports.html.
[5]	殷佳琪, 潘涛. 集成电路产业综述[J]. 科技资讯, 2021, 19(28): 54–58,63. doi: 10.16661/j.cnki.1672-3791.2110-5042-8981 YIN Jiaqi and PAN Tao. Overview of integrated circuit industry[J]. Science &Technology Information, 2021, 19(28): 54–58,63. doi: 10.16661/j.cnki.1672-3791.2110-5042-8981
[6]	CHEN T. An ANN approach for modeling the multisource yield learning process with semiconductor manufacturing as an example[J]. Computers & Industrial Engineering, 2017, 103: 98–104. doi: 10.1016/j.cie.2016.11.021
[7]	DING Duo, TORRES J A, and PAN D Z. High performance lithography hotspot detection with successively refined pattern identifications and machine learning[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2011, 30(11): 1621–1634. doi: 10.1109/TCAD.2011.2164537
[8]	WARD S, DING D, and PAN D Z. PADE: A high-performance placer with automatic datapath extraction and evaluation through high-dimensional data learning[C]. DAC Design Automation Conference 2012, San Francisco, USA, 2012: 756–761.
[9]	WANG Fanchao, ZHU Hanbin, POPLI P, et al. Accelerating coverage directed test generation for functional verification: A neural network-based framework[C]. The 2018 on Great Lakes Symposium on VLSI, Chicago, USA, 2018: 207–212.
[10]	KIELY T and GIELEN G. Performance modeling of analog integrated circuits using least-squares support vector machines[C]. Design, Automation and Test in Europe Conference and Exhibition, Paris, France, 2004: 448–453.
[11]	KAHNG A B, LIN B, and NATH S. ORION 3.0: A comprehensive NoC router estimation tool[J]. IEEE Embedded Systems Letters, 2015, 7(2): 41–45. doi: 10.1109/LES.2015.2402197
[12]	YU Bei, PAN D Z, MATSUNAWA T, et al. Machine learning and pattern matching in physical design[C]. The 20th Asia and South Pacific Design Automation Conference, Chiba, Japan, 2015: 286–293.
[13]	HUANG Guyue, HU Jingbo, HE Yifan, et al. Machine learning for electronic design automation: A survey[J]. ACM Transactions on Design Automation of Electronic Systems, 2021, 26(5): 40. doi: 10.1145/3451179
[14]	田春生, 陈雷, 王源, 等. 面向FPGA的布局与布线技术研究综述[J]. 电子学报, 2022, 50(5): 1243–1254. doi: 10.12263/DZXB.20210637 TIAN Chunsheng, CHEN Lei, WANG Yuan, et al. Review on technology of placement and routing for the FPGA[J]. Acta Electronica Sinica, 2022, 50(5): 1243–1254. doi: 10.12263/DZXB.20210637
[15]	YIN Xiaoyan, LIN Wanyu, SUN Kexin, et al. A²S²-GNN: Rigging GNN-based social status by adversarial attacks in signed social networks[J]. IEEE Transactions on Information Forensics and Security, 2023, 18: 206–220. doi: 10.1109/TIFS.2022.3219342
[16]	LI Jianxin, PENG Hao, CAO Yuwei, et al. Higher-order attribute-enhancing heterogeneous graph neural networks[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(1): 560–574. doi: 10.1109/TKDE.2021.3074654
[17]	KIM M, KIM J, QU J, et al. Interpretable temporal graph neural network for prognostic prediction of Alzheimer’s disease using longitudinal neuroimaging data[C]. 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, USA, 2021: 1381–1384.
[18]	REN Haoxiang, NATH S, ZHANG Yanqing, et al. Why are graph neural networks effective for EDA problems[C]. 2022 IEEE/ACM International Conference On Computer Aided Design (ICCAD), San Diego, USA, 2022: 1–8.
[19]	LU Y C and LIM S K. On advancing physical design using graph neural networks[C]. The 41st IEEE/ACM International Conference on Computer-Aided Design, San Diego, USA, 2022: 2.
[20]	MA Yuzhe, HE Zhuolun, LI Wei, et al. Understanding graphs in EDA: From shallow to deep learning[C]. The 2020 International Symposium on Physical Design, Taipei, China, 2020: 119–126.
[21]	KHAILANY B. Accelerating chip design with machine learning[C]. The 2020 ACM/IEEE Workshop on Machine Learning for CAD, Iceland, 2020: 33.
[22]	李甜甜, 张荣梅, 张佳慧. 图神经网络技术研究综述[J]. 河北省科学院学报, 2022, 39(2): 1–13. doi: 10.16191/j.cnki.hbkx.2022.02.007 LI Tiantian, ZHANG Rongmei, and ZHANG Jiahui. Research review of graph neural network technology[J]. Journal of the Hebei Academy of Sciences, 2022, 39(2): 1–13. doi: 10.16191/j.cnki.hbkx.2022.02.007
[23]	马帅, 刘建伟, 左信. 图神经网络综述[J]. 计算机研究与发展, 2022, 59(1): 47–80. doi: 10.7544/issn1000-1239.20201055 MA Shuai, LIU Jianwei, and ZUO Xin. Survey on graph neural network[J]. Journal of Computer Research and Development, 2022, 59(1): 47–80. doi: 10.7544/issn1000-1239.20201055
[24]	SÁNCHEZ D, SERVADEI L KIPRIT G N, et al. A comprehensive survey on electronic design automation and graph neural networks: Theory and applications[J]. ACM Transactions on Design Automation of Electronic Systems, 2023, 28(2): 15. doi: 10.1145/3543853
[25]	林亦波, 高笑涵, 陈廷欢, 等. 机器学习辅助数字集成电路后端设计方法[J]. 微纳电子与智能制造, 2021, 3(2): 11–20. doi: 10.19816/j.cnki.10-1594/tn.2021.02.011 LIN Y B, GAO X H, CHEN T H, et al. Machine learning for digital circuit backend design[J]. Micro/Nano Electronics and Intelligent Manufacturing, 2021, 3(2): 11–20. doi: 10.19816/j.cnki.10-1594/tn.2021.02.011
[26]	USTUN E, DENG Chenhui, PAL D, et al. Accurate operation delay prediction for FPGA HLS using graph neural networks[C]. The 39th International Conference on Computer-Aided Design, New York, USA, 2020: 87.
[27]	WU Nan, YANG Hang, XIE Yuan, et al. High-level synthesis performance prediction using GNNs: Benchmarking, modeling, and advancing[C]. The 59th ACM/IEEE Design Automation Conference, San Francisco California, USA, 2022: 49–54.
[28]	WU Nan, XIE Huan, and HAO Cang. IronMan: GNN-assisted design space exploration in high-level synthesis via reinforcement learning[C]. 2021 on Great Lakes Symposium on VLSI, New York, USA, 2021: 39–44.
[29]	WU Nan, XIE Yuan, and HAO Cong. IRONMAN-PRO: Multiobjective design space exploration in HLS via reinforcement learning and graph neural network-based modeling[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2023, 42(3): 900–913. doi: 10.1109/TCAD.2022.3185540
[30]	WU Nan, LEE J, XIE Yuan, et al. LOSTIN: Logic optimization via spatio-temporal information with hybrid graph models[C]. 2022 IEEE 33rd International Conference on Application-specific Systems, Architectures and Processors (ASAP), Gothenburg, Sweden, 2022: 11–18.
[31]	MIRHOSEINI A, GOLDIE A, YAZGAN M, et al. A graph placement methodology for fast chip design[J]. Nature, 2021, 594(7862): 207–212. doi: 10.1038/s41586–021-03544-w
[32]	AGNESINA A, PENTAPATI S, and LIM S K. A general framework for VLSI tool parameter optimization with deep reinforcement learning[C/OL]. The NeurIPS 2020 Workshop on Machine Learning for Systems, 2020: 6–12.
[33]	LU Yichen, PENTAPATI S, and LIM S K. The law of attraction: Affinity-aware placement optimization using graph neural networks[C/OL]. The 2021 International Symposium on Physical Design, 2021: 7–14.
[34]	CHENG Ruoyu and YAN Junchi. On joint Learning for solving placement and routing in chip design[C/OL]. 35th Conference on Neural Information Processing Systems, 2021: 16508–16519.
[35]	KIRBY R, GODIL S, ROY R, et al. CongestionNet: Routing congestion prediction using deep graph neural networks[C]. 2019 IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC), Cuzco, Peru, 2019: 217–222.
[36]	GHOSE A, ZHANG V, ZHANG Yingxue, et al. Generalizable cross-graph embedding for GNN-based congestion prediction[C]. 2021 IEEE/ACM International Conference on Computer Aided Design (ICCAD), Munich, Germany, 2021: 1–9.
[37]	CHEN Xuan, DI Zhixiong, WU Wei, et al. Detailed routing short violation prediction using graph-based deep learning model[J]. IEEE Transactions on Circuits and Systems II:Express Briefs, 2022, 69(2): 564–568. doi: 10.1109/TCSII.2021.3093420
[38]	TABRIZI A F, RAKAI L, DARAV N K, et al. A machine learning Framework to identify detailed routing short violations from a placed netlist[C]. 2018 55th ACM/ESDA/IEEE Design Automation Conference (DAC), San Francisco, USA, 2018: 1–6.
[39]	LI Wenchao, GASCOM A, SUBRAMANYAN P, et al. WordRev: Finding word-level structures in a sea of bit-level gates[C]. 2013 IEEE International Symposium on Hardware-Oriented Security and Trust (HOST), Austin, USA, 2013: 67–74.
[40]	LI Wenchao, WASSON Z, and SESHIA S A. Reverse engineering circuits using behavioral pattern mining[C]. 2012 IEEE International Symposium on Hardware-Oriented Security and Trust, San Francisco, USA, 2012: 83–88.
[41]	SUBRAMANYAN P, TSISKARIDZE N, LI Wenchao, et al. Reverse engineering digital circuits using structural and functional analyses[J]. IEEE Transactions on Emerging Topics in Computing, 2014, 2(1): 63–80. doi: 10.1109/TETC.2013.2294918
[42]	GASCÓM A, SUBRAMANYAN P, DUTERTRE B, et al. Template-based circuit understanding[C]. 2014 Formal Methods in Computer-Aided Design (FMCAD), Lausanne, Switzerland, 2014: 83–90.
[43]	ALRAHIS L, SENGUPTA A, KNECHTEL J, et al. GNN-RE: Graph neural networks for reverse engineering of gate-level netlists[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2022, 41(8): 2435–2448. doi: 10.1109/TCAD.2021.3110807
[44]	HE Zhuolun, WANG Ziyi, BAIL C, et al. Graph learning-based arithmetic block identification[C]. 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD), Munich, Germany, 2021: 1–8.
[45]	YASAEI R, YU S Y, and AI FARUQUE M A. GNN4TJ: Graph neural networks for hardware Trojan detection at register transfer level[C]. 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE), Grenoble, France, 2021: 1504–1509.
[46]	HASEGAWA K, YAMASHITA K, HIDANO S, et al. Node-wise hardware trojan detection based on graph learning[J]. IEEE Transactions on Computers. To be published.
[47]	MURALIDHAR N, ZUBAIR A, WEIDLER N, et al. Contrastive graph convolutional networks for hardware Trojan detection in third party IP cores[C]. 2021 IEEE International Symposium on Hardware Oriented Security and Trust (HOST), Tysons Corner, USA, 2021: 181–191.
[48]	CHENG Dong, DONG Chen, HE Wenwu, et al. GNN4Gate: A bi-directional graph neural network for gate-level hardware Trojan detection[C/OL]. 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2022: 1315–1320.
[49]	YASAEI R, YU S Y, NAEINI E K, et al. GNN4IP: Graph neural network for hardware intellectual property piracy detection[C]. 2021 58th ACM/IEEE Design Automation Conference (DAC), San Francisco, USA, 2021: 217–222.
[50]	ZHANG Yanqing, REN Haoxing, and KHAILANY B. GRANNITE: Graph neural network inference for transferable power estimation[C]. 2020 57th ACM/IEEE Design Automation Conference (DAC), San Francisco, USA, 2020: 1–6.
[51]	MA Yuzhe, REN Haoxing, KHAILANY B, et al. High performance graph convolutional networks with applications in testability analysis[C]. The 56th Annual Design Automation Conference 2019, Las Vegas, USA, 2019: 18.
[52]	CHAI Zhuomin, ZHAO Yuxiang, LIN Yibo, et al. CircuitNet: An open-source dataset for machine learning applications in electronic design automation (EDA)[J]. Science China Information Sciences, 2022, 65(12): 227401. doi: 10.1007/s11432-022-3571-8
[53]	YU Yunxuan, ZHAO Tiandong, WANG Mingyu, et al. Uni-OPU: An FPGA-based uniform accelerator for convolutional and transposed convolutional networks[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2020, 28(7): 1545–1556. doi: 10.1109/TVLSI.2020.2995741