Machine Learning Methods for Fast Evaluation of Static IR Drop Effect
With the continuous scaling of semiconductor design technologies, evaluating static IR drop has become a critical bottleneck in the physical synthesis flow. This paper presents a machine learning-based framework that transforms the power delivery network (PDN) analysis problem into an image-to-image translation task using a U-Net architecture with MaxViT and EfficientNet encoders. By implementing a novel SPICE-to-image conversion flow and an asymmetric loss function, our method achieved a Top 3 ranking in the ICCAD 2023 Contest (Problem C). The experimental results demonstrate that the proposed model achieves a Mean Absolute Error (MAE) below 15×10−5 V while providing up to a 30× speedup compared to NGSPICE.
Authors
- Roman Solovyev (ORCID: https://orcid.org/0000-0003-0312-452X)
- V. V. Zunin (ORCID: https://orcid.org/0000-0002-9117-4879)
- Alexander Stempkovskiy (ORCID: https://orcid.org/0000-0001-5585-014X)
- Dmitry Telpukhov (ORCID: https://orcid.org/0000-0001-9551-0748)
- A. V. Zablotskiy
- A. Yu. Romanov (ORCID: https://orcid.org/0000-0002-9410-9431)
- Ilya Ilyich Shafeev (ORCID: https://orcid.org/0009-0005-2323-3725)
- Alexander Murashov
- Evgeny Demidov
Institutions
- National Research University Higher School of Economics (RU)
- National Research University of Electronic Technology (RU)
- Alpha Technologies (Canada) (CA)
Publication Details
- Journal
- Technologies
- Published
- 2026-03-08
- DOI
- https://doi.org/10.3390/technologies14030169
- Primary Topic
- VLSI and FPGA Design Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Research University Higher School of Economics