As the complexity and density of electronic components continue to grow, 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 limited potential advancements in this area. To address this gap, we introduce PCBRouteNet, a comprehensive large-scale dataset specifically designed to accelerate ML innovations in automated PCB routing. To manage the high complexity of PCB data and improve extraction efficiency, we propose a dynamic, adjustable quadrilateral network flow model to construct a network flow graph composed of quadrilateral tiles. This method efficiently converts original design data into a network flow-based format, facilitating feature extraction for both global and detailed routing. Our dataset includes over 1,000 samples of real-world PCB designs, featuring diverse layouts with varying complexities, such as multi-layer boards and high-density interconnects. Additionally, we propose several practical ML tasks that utilize PCBRouteNet to showcase its potential in advancing the efficiency and effectiveness of automated PCB routing solutions.

As electronic devices become increasingly compact, designing printed circuit boards (PCBs) has become more challenging, particularly in the routing step, which is now more complex and time-consuming. In this work, we propose a method that applies generative pretrained transformers (GPTs) for PCB routing, referred to as GPCB routing. Initially, we convert the detailed routing information of the PCB into network flow-based encodings. Consequently, GPCB routing tokenizes routing patterns, effectively transforming the routing task into a form of token encoding prediction. To enhance prediction accuracy, we implement a 2-D sliding window with a local memory scheme, thereby expanding the sensing area of GPCB. Additionally, we propose a multi-information fusion scheme to identify the start and end points of multiple wires to further improve the prediction accuracy. Compared to existing routing methods, GPCB has the distinct advantage of learning routing strategies from human experts, breaking the limitations of traditional model-based routing approaches. Moreover, GPCB operates as a parallel routing method capable of predicting multiple routes simultaneously, resulting in significant enhancements in routing performance. Based on the experimental results, GPCB consistently outperforms in terms of routability, runtime, and wirelength.