EUVIMEDEUVIMED entdecken
Crossref

Concurrent Prediction of Timing and wire Length Using A Multi-Task Graph Neural Network

Yan Xing, Hongtao Hu, Weijun Li, Shuting Cai, Xiaoming Xiong

ACM Transactions on Design Automation of Electronic Systems · 31.07.2025 · 30 (4) · 1-20

DOI: 10.1145/3747181 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 18.07.2025. Verfasst von Yan Xing und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: Guangdong S&T Programme, National Natural Science Foundation of China, Science and Technology Planning Project of Guangzhou.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional supervised single-task learning models are used in timing-driven placement exploration to improve both effectiveness and efficiency by predicting wire length, wire delay, and cell delay separately. However, these metrics are interdependent, with the two delays being timing-based and wire length non-timing, which makes it difficult for single-task models to capture their complex relationships. Moreover, the limited existing multi-task learning methods can only predict either multiple timing or non-timing metrics. To address these limitations, this article introduces DLGNN, a novel multi-task graph learning model that simultaneously predicts these three metrics through an embedder-predictor architecture featuring two residual connections, a combination of both soft and hard parameter sharing, and a geometric loss strategy. Cross-design experimental results on the Nangate 45nm library demonstrate that DLGNN outperforms baseline models in terms of both predictive performance and time efficiency. Additionally, ablation studies emphasize the critical roles of the residual connections, the combination of soft and hard parameter sharing, and the geometric loss strategy in improving DLGNN’s predictive performance. The generalization experiment on the ASAP 7nm library further confirms DLGNN’s advantages for more advanced technology nodes.

Förderung

  • Guangdong S&T Programme
  • National Natural Science Foundation of China
  • Science and Technology Planning Project of Guangzhou

Zitieren

APA

Xing, Y., Hu, H., Li, W., Cai, S., & Xiong, X. (2025). Concurrent Prediction of Timing and wire Length Using A Multi-Task Graph Neural Network. ACM Transactions on Design Automation of Electronic Systems, 30(4), 1-20. https://doi.org/10.1145/3747181

Vancouver

Xing Y, Hu H, Li W, Cai S, Xiong X. Concurrent Prediction of Timing and wire Length Using A Multi-Task Graph Neural Network. ACM Transactions on Design Automation of Electronic Systems. 2025;30(4):1-20. doi:10.1145/3747181

BibTeX
@article{Xing2025,
  author = {Xing, Yan and Hu, Hongtao and Li, Weijun and Cai, Shuting and Xiong, Xiaoming},
  title = {Concurrent Prediction of Timing and wire Length Using A Multi-Task Graph Neural Network},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2025},
  volume = {30},
  number = {4},
  pages = {1--20},
  doi = {10.1145/3747181}
}
Kostenlos starten →