Conference proceeding
Differentiable Graph Neural Networks for Wirelength Estimation
IEEE International Symposium on Circuits and Systems proceedings, pp 1-5
25 May 2025
Abstract
A model that utilizes a graph neural network (GNN) is proposed to estimate wirelength in the early stages of physical design. The model predicts the post-routing wirelength of a net, which addresses the limitations of current estimators including half-perimeter wirelength (HPWL) that tend to under-estimate the true post-routed wirelength of complex nets. Utilizing a dataset of 18 benchmark circuits, the GNN achieves an average R 2 of 0.825, outperforming HPWL, which yields an R 2 of 0.764. The GNN demonstrates consistent performance across nets of varying lengths, providing significantly improved accuracy over HPWL for long and multi-path nets. The GNN model is differentiable and compatible with gradient-based optimization methods, while providing an 8× improvement in inference time.
Metrics
3 Record Views
Details
- Title
- Differentiable Graph Neural Networks for Wirelength Estimation
- Creators
- Zhengfeng Wu - Drexel UniversityPratik Shrestha - Drexel UniversitySaran Phatharodom - Drexel UniversityIoannis Savidis - Drexel University
- Publication Details
- IEEE International Symposium on Circuits and Systems proceedings, pp 1-5
- Publisher
- IEEE
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Electrical and Computer Engineering; College of Engineering
- Scopus ID
- 2-s2.0-105010632631
- Other Identifier
- 991022061538204721