EUVIMEDOtkrijte EUVIMED
Open access · CC BY 4.0

Fast Electromigration Analysis of Multi-segment Interconnects Based on Recurrent Neural Networks

Huailin Xu, Shiqi Lin, Yue Li, Jianjun Liu, Junhui Zheng, Zihui Zhang, Peng Gao, Fei Yu, Xiaoming Xiong, Shuting Cai

ACM Transactions on Design Automation of Electronic Systems · 2027-01-31 · 32 (1) · 1-28

DOI: 10.1145/3819829 ↗

At a glance

Journal article in ACM Transactions on Design Automation of Electronic Systems, published online on 2026-11-03. Written by Huailin Xu and 9 co-authors. Cited 1 times so far (Crossref); 35 references. The full text is freely available (open access, CC BY 4.0). Funded by: Key Area R & D Program of Guangdong Province.

SažetakBibliografski podaciCiteRelated studies

Abstract (original language)

Predicting electromigration (EM) stress is a critical reliability challenge in power delivery networks. Existing semi-analytical Multilayer Perceptron (MLP) models neglect the Markovian sequential dependencies of EM diffusion and suffer from severe scalability issues due to global topological evaluations. To address these architectural and computational bottlenecks, this article proposes a dynamic spatiotemporal stress forecasting framework. Specifically, a physics-aligned Recurrent Neural Network (RNN) is constructed to directly model the Markovian sequential evolution of EM stress. This is integrated with a tensor mapping-based dynamic local subgraph extraction strategy, effectively isolating spatial complexity from the global interconnect scale. At the numerical integration level, we develop a physics-driven adaptive hybrid convolution algorithm. Regulated by a stress relaxation time constant, this algorithm dynamically invokes discrete convolution during the early acceleration phase to strictly preserve the abrupt variations of the auxiliary function used for stress computation, and seamlessly switches to Gauss-Legendre quadrature during stable periods to maximize precision while eliminating smoothing artifacts. Furthermore, a simulation-time-based optimization strategy is incorporated to mitigate the prediction error gap between early and late simulation stages. Experimental results validate the efficiency of the proposed framework. Compared with the MLP baseline, our model achieves up to a 93.2% reduction in relative error and a 117.79× computational speedup. Against the Finite Element Method (FEM), it delivers up to 1335.6× acceleration while maintaining engineering-grade accuracy.

Funding

  • Key Area R & D Program of Guangdong Province

Cite

APA

Xu, H., Lin, S., Li, Y., Liu, J., Zheng, J., Zhang, Z., Gao, P., Yu, F., Xiong, X., & Cai, S. (2027). Fast Electromigration Analysis of Multi-segment Interconnects Based on Recurrent Neural Networks. ACM Transactions on Design Automation of Electronic Systems, 32(1), 1-28. https://doi.org/10.1145/3819829

Vancouver

Xu H, Lin S, Li Y, Liu J, Zheng J, Zhang Z, et al. Fast Electromigration Analysis of Multi-segment Interconnects Based on Recurrent Neural Networks. ACM Transactions on Design Automation of Electronic Systems. 2027;32(1):1-28. doi:10.1145/3819829

BibTeX
@article{Xu2027,
  author = {Xu, Huailin and Lin, Shiqi and Li, Yue and Liu, Jianjun and Zheng, Junhui and Zhang, Zihui and Gao, Peng and Yu, Fei and Xiong, Xiaoming and Cai, Shuting},
  title = {Fast Electromigration Analysis of Multi-segment Interconnects Based on Recurrent Neural Networks},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2027},
  volume = {32},
  number = {1},
  pages = {1--28},
  doi = {10.1145/3819829}
}
Start for free →