PCBRouteNet: Dynamic Quadrilateral-Flow Dataset and Benchmarks for Machine-Learning PCB Routing

As the complexity and density of electronic components continue to increase, manual printed circuit board (PCB) routing has become an increasingly labor-intensive and costly task. However, the lack of large, publicly available datasets for training machine-learning (ML) models has hindered potential advancements in this field. To address this gap, we introduce PCBRouteNet, a comprehensive, large-scale dataset specifically designed to accelerate ML innovations in automated PCB routing. To handle the high complexity of PCB data and enhance extraction efficiency, we propose a dynamic, adjustable, quadrilateral network flow model. This model constructs a network flow graph composed of quadrilateral tiles, efficiently transforming the original design data into a network flow-based format. This format facilitates feature extraction for both global and detailed routing tasks. Additionally, we introduce and analyze various flow-encoding methods to explore the generalization and relationships between data size and network parameters, leveraging scaling laws. Our dataset features a diverse array of layouts with varying complexities, such as multilayer boards and high-density interconnects. Furthermore, we propose several practical ML tasks that utilize PCBRouteNet to demonstrate its potential in improving the efficiency and effectiveness of automated PCB routing solutions.