EUVIMEDEUVIMED entdecken
Crossref

ECO-GNN: Signoff Power Prediction Using Graph Neural Networks with Subgraph Approximation

Yi-Chen Lu, Siddhartha Nath, Sai Pentapati, Sung Kyu Lim

ACM Transactions on Design Automation of Electronic Systems · 31.07.2023 · 28 (4) · 1-22

DOI: 10.1145/3569942 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Design Automation of Electronic Systems, online erschienen am 17.05.2023. Verfasst von Yi-Chen Lu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 33 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modern electronic design automation flows depend on both implementation and signoff tools to perform timing-constrained power optimization through Engineering Change Orders (ECOs), which involve gate sizing and threshold-voltage ( V th )-assignment of standard cells. However, the signoff ECO optimization is highly time-consuming, and the power improvement is hard to predict in advance. Ever since the industrial benchmarks released by the ISPD-2012 gate-sizing contest, active research has been conducted extensively to improve the optimization process. Nonetheless, previous works were mostly based on heuristics or analytical methods whose timing models were oversimplified and lacked of formal validations from commercial signoff tools. In this article, we propose ECO-graph neural networks (GNN), a transferable graph-learning-based framework, which harnesses GNNs to perform commercial-quality signoff power optimization through discrete ( V th -assignment. One of the highlights of our framework is that it generates tool-accurate optimization results instantly on unseen netlists that are not utilized in the training process. Furthermore, we propose a subgraph approximation technique to improve training and inferencing time of the proposed GNN model. We show that design instances with non-overlapping subgraphs can be optimized in parallel so as to improve the inference time of the learning-based model. Finally, we implement a GNN-based explanation method to interpret the optimization results achieved by our framework. Experimental results on 14 industrial designs, including a RISC-V-based multi-core system and the renowned ISPD-2012 benchmarks, demonstrate that our framework achieves up to 14× runtime improvement with similar signoff power optimization quality compared with Synopsys PrimeTime , an industry-leading signoff tool.

Zitieren

APA

Lu, Y., Nath, S., Pentapati, S., & Lim, S. K. (2023). ECO-GNN: Signoff Power Prediction Using Graph Neural Networks with Subgraph Approximation. ACM Transactions on Design Automation of Electronic Systems, 28(4), 1-22. https://doi.org/10.1145/3569942

Vancouver

Lu Y, Nath S, Pentapati S, Lim SK. ECO-GNN: Signoff Power Prediction Using Graph Neural Networks with Subgraph Approximation. ACM Transactions on Design Automation of Electronic Systems. 2023;28(4):1-22. doi:10.1145/3569942

BibTeX
@article{Lu2023,
  author = {Lu, Yi-Chen and Nath, Siddhartha and Pentapati, Sai and Lim, Sung Kyu},
  title = {ECO-GNN: Signoff Power Prediction Using Graph Neural Networks with Subgraph Approximation},
  journal = {ACM Transactions on Design Automation of Electronic Systems},
  year = {2023},
  volume = {28},
  number = {4},
  pages = {1--22},
  doi = {10.1145/3569942}
}
Kostenlos starten →