CTS-Bench: Benchmarking Graph Coarsening Trade-offs for GNNs in Clock Tree Synthesis
This work addresses scalability issues for researchers and engineers in Electronic Design Automation, though it is incremental as it focuses on benchmarking rather than proposing a new method.
The paper tackles the problem of high memory and runtime costs in deploying Graph Neural Networks for Clock Tree Synthesis analysis by introducing CTS-Bench, a benchmark suite to evaluate graph coarsening trade-offs, showing that coarsening reduces GPU memory usage by up to 17.2x and speeds training by up to 3x but often leads to negative R² scores in accuracy.
Graph Neural Networks (GNNs) are increasingly explored for physical design analysis in Electronic Design Automation, particularly for modeling Clock Tree Synthesis behavior such as clock skew and buffering complexity. However, practical deployment remains limited due to the prohibitive memory and runtime cost of operating on raw gate-level netlists. Graph coarsening is commonly used to improve scalability, yet its impact on CTS-critical learning objectives is not well characterized. This paper introduces CTS-Bench, a benchmark suite for systematically evaluating the trade-offs between graph coarsening, prediction accuracy, and computational efficiency in GNN-based CTS analysis. CTS-Bench consists of 4,860 converged physical design solutions spanning five architectures and provides paired raw gate-level and clustered graph representations derived from post-placement designs. Using clock skew prediction as a representative CTS task, we demonstrate a clear accuracy-efficiency trade-off. While graph coarsening reduces GPU memory usage by up to 17.2x and accelerates training by up to 3x, it also removes structural information essential for modeling clock distribution, frequently resulting in negative $R^2$ scores under zero-shot evaluation. Our findings indicate that generic graph clustering techniques can fundamentally compromise CTS learning objectives, even when global physical metrics remain unchanged. CTS-Bench enables principled evaluation of CTS-aware graph coarsening strategies, supports benchmarking of GNN architectures and accelerators under realistic physical design constraints, and provides a foundation for developing learning-assisted CTS analysis and optimization techniques.