Netlist-Based ASIC Area and Delay Prediction Using Machine Learning
Mikhail Sergeyevich LEBEDEV,
Daria Alexeevna DYSKINA,
Anastasia Yuryevna EREMENKO,
Fedor Aleksandrovich KABANOV,
Ilya Aleksandrovich KOZMIN,
Daniil Mikhailovich PETRENKO,
Nikita Basuevich POUDIAL,
Andrey Alekseevich SERGEEV,
Rena Afrail kyzy SHIRINOVA https://doi.org/10.15514/ISPRAS-2025-37(2)-4
Abstract
Hardware development is a time-consuming process that includes logic synthesis, placement and routing as its main steps. Despite that these steps are automated in modern CADs, their execution can take hours or even days. The application of machine learning methods can help predict synthesis results and thereby speed up the development process. This article describes the experience of creating and evaluating eight machine learning models for predicting area and delay of the synthesized ASIC using its netlist at the logic synthesis step. The results obtained show the benefits of this approach and indicate directions for further research.
Supporting agencies: This research was carried out at Plekhanov Russian University of Economics at the expense of a grant from the Russian Science Foundation, № 23-21-00313, https://rscf.ru/project/23-21-00313.
About the Authors
Mikhail Sergeyevich LEBEDEV
Plekhanov Russian University of Economics
Ivannikov Institute for System Programming of the Russian Academy of Sciences
Russian Federation
Russian Federation
Senior researcher at the «Heterogeneous computer systems» laboratory of Plekhanov RUE, and a researcher at Ivannikov Institute for System Programming of the RAS. His research interests are: logic synthesis, machine learning, neural networks, digital hardware.
Daria Alexeevna DYSKINA
Plekhanov Russian University of Economics
Russian Federation
Russian Federation
Student of the «Information Security» program at the Plekhanov Russian University of Economics. Her scientific activities are related to the application of machine learning methods in the process of optimizing digital circuits.
Anastasia Yuryevna EREMENKO
Plekhanov Russian University of Economics
Russian Federation
Russian Federation
Student of the «Applied Mathematics and Computer science» program at the Plekhanov Russian University of Economics. Her research interests include data analytics, machine learning and artificial intelligence.
Fedor Aleksandrovich KABANOV
Plekhanov Russian University of Economics
Russian Federation
Russian Federation
Student of the «Information Security» program at Plekhanov Russian University of Economics. His scientific activities are related to the application of machine learning methods in the process of optimizing digital circuits.
Ilya Aleksandrovich KOZMIN
Plekhanov Russian University of Economics
Russian Federation
Russian Federation
Student of the «Applied Mathematics and Computer science» program at the Plekhanov Russian University of Economics. His research interests include artificial intelligence, big data, netlist optimization methods.
Daniil Mikhailovich PETRENKO
Plekhanov Russian University of Economics
Russian Federation
Russian Federation
Student of the «Information Security» program at the Plekhanov Russian University of Economics. His research interests are related to the application of machine learning to netlist analysis.
Nikita Basuevich POUDIAL
Plekhanov Russian University of Economics
Russian Federation
Russian Federation
Student of the «Information Security» program at Plekhanov Russian University of Economics. His research activity is related to the usage of machine learning to analyze massive data.
Andrey Alekseevich SERGEEV
Plekhanov Russian University of Economics
Russian Federation
Russian Federation
Student at the «Information Security» program at the Plekhanov Russian University of Economics. His research interests include the study of neural networks and processes related to their optimization.
Rena Afrail kyzy SHIRINOVA
Plekhanov Russian University of Economics
Russian Federation
Russian Federation
Student of the «Applied Mathematics and Computer science in economics» program at the Plekhanov Russian University of Economics. Her research interests include machine learning, in particular, reinforcement learning.
References
1. Chowdhury A.B., Tan B., Karri R., Garg S. OpenABC-D: A Large-Scale Dataset For Machine Learning Guided Integrated Circuit Synthesis. ArXiv, abs/2110.11292 (online). Доступно по ссылке: https://arxiv.org/pdf/2110.11292.pdf, 2021.
2. Kirby R., Godil S., Roy R., Catanzaro B. CongestionNet: Routing congestion prediction using deep graph neural networks. IFIP/IEEE 27th International Conference on Very Large Scale Integration (VLSI-SoC), 2019, pp. 217—222.
3. Guo Z., Liu M., Gu J., Zhang S., Pan D.Z., Lin Y. A timing engine inspired graph neural network model for pre-routing slack prediction. Proceedings of the ACM/IEEE Design Automation Conference (DAC), 2022, pp. 1207–1212.
4. Barboza E. C., Shukla N., Chen Y., Hu J. Machine Learning-Based Pre-Routing Timing Prediction with Reduced Pessimism. ACM/IEEE Design Automation Conference (DAC), 2019, pp. 1-6.
5. Xie Z., Liang R., Xu X., Hu J., Chang C.-C., Pan J., Chen Y. Preplacement Net Length and Timing Estimation by Customized Graph Neural Network. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 41, No. 11, 2022, pp. 4667-4680.
6. Berkeley Logic Synthesis and Verification Group, ABC: A System for Sequential Synthesis and Verification. Доступно по ссылке: http://www.eecs.berkeley.edu/~alanmi/abc, дата обращения: 12.12.2023.
7. Формат файлов GraphML. Доступно по ссылке: http://graphml.graphdrawing.org, дата обращения 12.12.2023.
8. Brglez F., Bryan D., Kozminski K. Combinational profiles of sequential benchmark circuits. 1989 IEEE International Symposium on Circuits and Systems (ISCAS), vol.3, 1989, pp. 1929-1934.
9. Библиотека машинного обучения Pytorch. Доступно по ссылке: https://pytorch.org, дата обращения 12.12.2023.
10. Библиотека машинного обучения Tensorflow. Доступно по ссылке: https://www.tensorflow.org, дата обращения 12.12.2023.
11. Библиотека машинного обучения SciKit-Learn. Доступно по ссылке: https://scikit-learn.org, дата обращения 12.12.2023.
12. Библиотека градиентного бустинга XGBoost. Доступно по ссылке: https://github.com/dmlc/xgboost, дата обращения 12.12.2023.
13. Библиотека градиентного бустинга LightGBM. Доступно по ссылке: https://github.com/microsoft/LightGBM, дата обращения 12.12.2023.
Review
For citations:
LEBEDEV M.S., DYSKINA D.A., EREMENKO A.Yu., KABANOV F.A., KOZMIN I.A., PETRENKO D.M., POUDIAL N.B., SERGEEV A.A., SHIRINOVA R.A. Netlist-Based ASIC Area and Delay Prediction Using Machine Learning. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2025;37(2):49-60. (In Russ.) https://doi.org/10.15514/ISPRAS-2025-37(2)-4
Email this article 