Application of Neural Networks for Routing Congestion Prediction in VLSI Design Using Initial Layout Parameters
Marat Khalitovich SAIBODALOV,
Maxim Vadimovich DASHIEV,
Iakov Mikhailovich KARANDASHEV,
Nikita Vladimirovich ZHELUDKOV,
Elizaveta Sergeevna KOCHEVA https://doi.org/10.15514/ISPRAS-2025-37(3)-1
Abstract
This paper considers the problem of congestion map prediction at the pre-routing stage of VLSI layout design of digital blocks by applying neural network models. Early prediction of congestion will allow the VLSI design engineer to modify floorplan, macro placement and input-output port placement to prevent interconnect routing issues at later stages, thereby reducing the number of EDA tool runs and the overall circuit design runtime. In this work we propose the use of the initial layout parameters, which were not considered in previous works and allow for a more accurate congestion prediction.
Supporting agencies: The work was carried out within the framework of the state task of the NRC «Kurchatov Institute» – SRISA on the topic FNEF-2024-0001 «Development and deployment of trusted AI systems based on new mathematical and algorithmic approaches and fast computing models compatible with domestic computer hardware» (1023032100070-3-1.2.1).
About the Authors
Marat Khalitovich SAIBODALOV
NRC «Kurchatov Institute» – SRISA, The Patrice Lumumba Peoples' Friendship University of Russia
Russian Federation
Russian Federation
Postgraduate student at RUDN University, junior researcher at SRISA. Research interests: graph neural networks, VLSI design automation.
Maxim Vadimovich DASHIEV
NRC «Kurchatov Institute» – SRISA, Moscow Institute of Physics and Technology
Russian Federation
Russian Federation
Engineer at SRISA, master degree student at MIPT. Research interests: development of machine learning methods and neural networks to solve applied problems in various fields.
Iakov Mikhailovich KARANDASHEV
NRC «Kurchatov Institute» – SRISA, The Patrice Lumumba Peoples' Friendship University of Russia
Russian Federation
Russian Federation
Cand. Sci. (Phys.-Math.), leading researcher at SRISA. Research interests: computer vision, image segmentation.
Nikita Vladimirovich ZHELUDKOV
NRC «Kurchatov Institute» – SRISA
Russian Federation
Russian Federation
Junior researcher at SRISA. Research interests: VLSI design automation, application of machine learning methods to solve integrated circuit topology design problems, increasing the stability of VLSI digital blocks.
Elizaveta Sergeevna KOCHEVA
NRC «Kurchatov Institute» – SRISA
Russian Federation
Russian Federation
Engineer at SRISA. Research interests: VLSI topological design, application of machine learning methods to solve integrated circuit topology design problems.
References
1. Ajayi et. al. OpenROAD: Toward a Self-Driving, Open-Source Digital Layout Implementation Tool Chain. Proc. GOMACTECH, 2019, pp. 1105–1110.
2. R. Kirby, S. Godil, R. Roy, and B. Catanzaro. CongestionNet: routing congestion prediction using deep graph neural networks. IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC), Cuzco, Peru, 2019, pp. 217–222.
3. A. Ghose, V. Zhang, Y. Zhang, D. Liu, W. Liu, and V. Coates. Generalizable cross-graph embedding for GNN-based congestion prediction. IEEE/ACM International Conference on Computer Aided Design (ICCAD), 2021.
4. P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Lió, and Y. Bengio. Graph attention networks. arXiv (Cornell University), 2018.
5. W. L. Hamilton, R. Ying, and J. Leskovec. Versatile multi-stage graph neural network for circuit representation. arXiv (Cornell University), 2017.
6. S. Yang, Z. Yang, D. Li, Y. Zhang, Z. Zhang, G. Song, and J. Hao. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems, 2022, vol. 35.
7. B. Wang, G. Shen, D. Liu, J. Hao, W. Liu, Y. Huang, H. Wu, Y. Lin, G. Chen, and P. Heng. LHNN: Lattice hypergraph neural network for VLSI congestion prediction. arXiv (Cornell University), 2022.
8. M. Saibodalov, I. Karandashev, Z. Sokhova, E. Kocheva, and N. Zheludkov. Routing Congestion Prediction in VLSI Design Using Graph Neural Networks. DSPA 2024 26th International Conference on Digital Signal Processing and its Applications, Moscow, Russian Federation, 2024, pp. 1-4.
9. P. Spindler and F. M. Johannes. Fast and accurate routing demand estimation for efficient routability-driven placement. EDA Consortium Proceedings of the Conference on Design, Automation and Test in Europe, San Jose, CA, USA, 2007, pp. 1226–1231.
10. A. B. Chowdhury, B. Tan, R. Karri, and S. Garg. OpenABC-D: a large-scale dataset for machine learning guided integrated circuit synthesis. arXiv (Cornell University), 2021.
11. Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv (Cornell University), 2015.
12. Ozan Oktay et al. Attention U-Net: Learning Where to Look for the Pancreas. arXiv (Cornell University), 2018.
13. Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A. Efros. Image-to-Image Translation with Conditional Adversarial Networks. arXiv (Cornell University), 2016.
Review
For citations:
SAIBODALOV M.Kh., DASHIEV M.V., KARANDASHEV I.M., ZHELUDKOV N.V., KOCHEVA E.S. Application of Neural Networks for Routing Congestion Prediction in VLSI Design Using Initial Layout Parameters. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2025;37(3):9-18. (In Russ.) https://doi.org/10.15514/ISPRAS-2025-37(3)-1
Email this article 