GAT-Steiner: Rectilinear Steiner Minimal Tree Prediction Using GNNs
This addresses a fundamental bottleneck in VLSI design by providing a fast, parallelizable solution that reduces computational time compared to traditional methods, though it is incremental as it builds on existing GNN techniques.
The paper tackled the NP-hard Rectilinear Steiner Minimum Tree problem in VLSI placement and routing by using Graph Neural Networks to predict optimal Steiner points, achieving over 99.8% accuracy on benchmarks with wire length increases of only about 0.45%.
The Rectilinear Steiner Minimum Tree (RSMT) problem is a fundamental problem in VLSI placement and routing and is known to be NP-hard. Traditional RSMT algorithms spend a significant amount of time on finding Steiner points to reduce the total wire length or use heuristics to approximate producing sub-optimal results. We show that Graph Neural Networks (GNNs) can be used to predict optimal Steiner points in RSMTs with high accuracy and can be parallelized on GPUs. In this paper, we propose GAT-Steiner, a graph attention network model that correctly predicts 99.846% of the nets in the ISPD19 benchmark with an average increase in wire length of only 0.480% on suboptimal wire length nets. On randomly generated benchmarks, GAT-Steiner correctly predicts 99.942% with an average increase in wire length of only 0.420% on suboptimal wire length nets.