EUVIMEDEUVIMED entdecken
Crossref

Optimizing FPGA Routing with Explainable Co-Learning of Congestion and Wirelength

Wenhao Liu, Yan Xing, Shuting Cai, Weijun Li, Xiaoming Xiong

ACM Transactions on Design Automation of Electronic Systems · 07.04.2025

DOI: 10.1145/3728467 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 07.04.2025. Verfasst von Wenhao Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 40 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In FPGA routing, machine learning-based optimization methods have achieved improved routing solutions by integrating traditional heuristics with predictive capabilities. However, these approaches mostly relied on single-task learning models with black-box nature and often neglected the complex trade-offs and inter-dependencies between routing metrics. To address these limitations, this paper introduces a novel multi-task learning-based routing optimization method. In the congestion-wirelength co-learning stage, the simultaneous prediction of congestion and wirelength is formulated as a multi-task learning problem. A multi-task learning model, named CWNet, is proposed to tackle this challenge effectively. During the congestion-wirelength impact interpretation, the contribution of congestion to wirelength is quantified using an XAI technique known as DeepSHAP, producing a congestion-wirelength impact map. In the congestion-wirelength co-guided routing optimization (CWRO) stage, the VTR router’s lookahead map is enhanced based on the impact map, guiding the router to avoid locations where congestion significantly affect wirelength. Experimental results demonstrate that CWNet outperforms most baseline learning models in terms of both prediction performance and computational efficiency. Additionally, the impact map visually illustrates the complex and nonlinear relationship between congestion and wirelength. Ultimately, CWRO significantly reduces congestion, wirelength, and critical path delay, while maintaining a competitive runtime compared to baseline routers.

Zitieren

APA

Liu, W., Xing, Y., Cai, S., Li, W., & Xiong, X. (2025). Optimizing FPGA Routing with Explainable Co-Learning of Congestion and Wirelength. ACM Transactions on Design Automation of Electronic Systems. https://doi.org/10.1145/3728467

Vancouver

Liu W, Xing Y, Cai S, Li W, Xiong X. Optimizing FPGA Routing with Explainable Co-Learning of Congestion and Wirelength. ACM Transactions on Design Automation of Electronic Systems. 2025. doi:10.1145/3728467

BibTeX
@article{Liu2025,
  author = {Liu, Wenhao and Xing, Yan and Cai, Shuting and Li, Weijun and Xiong, Xiaoming},
  title = {Optimizing FPGA Routing with Explainable Co-Learning of Congestion and Wirelength},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2025},
  doi = {10.1145/3728467}
}
Kostenlos starten →