Methods of Circuit and Topological Synthesis of Analog Integrated Circuits According to Specification using Machine Learning and Differentiable Programming Methods
Denis Sergeevich SHCHEPETOV,
Aleksandr Gennadyevich TIMOSHENKO,
Vladimir Anatolyevich GARANZHA,
Igor Evgenievich KAPORIN,
Dmitry Nikolaevich KARGIN https://doi.org/10.15514/ISPRAS-2025-37(2)-3
Abstract
The problem of schematic development (netlist generation), which arises in the development of analog integrated circuits, is formulated as an optimization problem for a differentiable smooth function using a combination of differentiable programming and machine learning methods. It is shown that this approach allows one to achieve the specification requirements and propose an optimal combination of circuit templates that make up an analog integrated circuit, without involving combinatorial optimization and reinforcement learning methods. It is shown that this approach provides significant speed advantages compared to traditional methods based on reinforcement learning. The possibility of fully automatic synthesis of an analog IC from specification to topology without expert participation using open-source software is investigated. The advantages and disadvantages of this approach are shown.
About the Authors
Denis Sergeevich SHCHEPETOV
Federal Research Center "Informatics and Control" of the Russian Academy of Sciences"
Russian Federation
Russian Federation
Cand. Sci. (Tech.), Leading Specialist of the FRC ICS RAS. Research interests: multicriteria optimization, machine learning methods, robotic systems.
Aleksandr Gennadyevich TIMOSHENKO
National Research University "MIET"
Russian Federation
Russian Federation
Cand. Sci. (Tech.), associate professor of the National Research University of Electronic Technology. Research interests: analog and mixed signals IC design, signal processing, circuit design.
Vladimir Anatolyevich GARANZHA
Federal Research Center "Informatics and Control" of the Russian Academy of Sciences"
Russian Federation
Russian Federation
Dr. Sci. (Phys.-Math.), Professor of the RAS, Chief Researcher FRC ICS RAS. Research interests: differential geometry, multicriterial optimization, parallel programming, construction of computational grids.
Igor Evgenievich KAPORIN
Federal Research Center "Informatics and Control" of the Russian Academy of Sciences"
Russian Federation
Russian Federation
Dr. Sci. (Phys.-Math.), Chief Researcher FRC ICS RAS. Research interests: iterative algorithms for solving SLAE, gradient-free methods for optimizing large problems, parallel programming.
Dmitry Nikolaevich KARGIN
Moscow Polytechnic University
Russian Federation
Russian Federation
Postgraduate student, Moscow Polytechnic University. Research interests: parallel programming, robotic systems, multicriterial optimization.
References
1. Hastings A. The art of analog layout. – Prentice hall New Jersey, 2001, 576 p.
2. Settaluri, K., Haj-Ali, A., Huang, Q., Hakhamaneshi, K., & Nikolic, B. (2020, March). Autockt: Deep reinforcement learning of analog circuit designs. In 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE) (pp. 490-495). IEEE.
3. Budak, A. F., Jiang, Z., Zhu, K., Mirhoseini, A., Goldie, A., & Pan, D. Z. (2022, January). Reinforcement learning for electronic design automation: Case studies and perspectives. In 2022 27th Asia and South Pacific Design Automation Conference (ASP-DAC) (pp. 500-505). IEEE.
4. Khan, S., Shi, Z., Li, M., & Xu, Q. (2024, March). DeepSeq: Deep Sequential Circuit Learning. In 2024 Design, Automation & Test in Europe Conference & Exhibition (DATE) (pp. 1-2). IEEE.
5. Xu, B., Zhu, K., Liu, M., Lin, Y., Li, S., Tang, X., ... & Pan, D. Z. (2019, November). MAGICAL: Toward fully automated analog IC layout leveraging human and machine intelligence. In 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD) (pp. 1-8). IEEE.
6. Kunal, K., Madhusudan, M., Sharma, A. K., Xu, W., Burns, S. M., Harjani, R., ... & Sapatnekar, S. S. (2019, June). ALIGN: Open-source analog layout automation from the ground up. In Proceedings of the 56th Annual Design Automation Conference 2019 (pp. 1-4).
7. Abel, I., Neuner, M., & Graeb, H. E. (2021). A hierarchical performance equation library for basic op-amp design. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 41(7), 1976-1989.
8. Blondel, M., & Roulet, V. (2024). The elements of differentiable programming. arXiv preprint arXiv:2403.14606.
9. Baydin A. G. et al. Automatic differentiation in machine learning: a survey //Journal of machine learning research. – 2018. – Т. 18. – №. 153. – С. 1-43.
10. Doersch, C. (2016). Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908.
11. Malkov, Y. A., & Yashunin, D. A. (2018). Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. IEEE transactions on pattern analysis and machine intelligence, 42(4), 824-836.
12. Dodge, H. D. (2020). Xyce Case Study (No. SAND-2020-2877R). Sandia National Lab.(SNL-NM), Albuquerque, NM (United States).
13. Rahman, M. S., Suvo, S. H., Kamal, Z., & Rahman, T. (2024, May). Standard Cell Library Characterization Flow Using Open Source Tools with Google+ SkyWater 130nm PDK. In 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT) (pp. 1175-1180). IEEE.
Review
For citations:
SHCHEPETOV D.S., TIMOSHENKO A.G., GARANZHA V.A., KAPORIN I.E., KARGIN D.N. Methods of Circuit and Topological Synthesis of Analog Integrated Circuits According to Specification using Machine Learning and Differentiable Programming Methods. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2025;37(2):33-48. (In Russ.) https://doi.org/10.15514/ISPRAS-2025-37(2)-3
Email this article 