Graph Attention Network-Based Unified TCAD Modeling Enabling Fast Design Technology Co-Optimization Through Transfer Learning

An innovative framework that leverages artificial intelligence (AI) and graph representation for semiconductor device encoding in TCAD device simulation is proposed. A graph-based universal encoding scheme is presented that incorporates material-level and device-level embeddings, along with a novel spatial relationship embedding inspired by finite element meshing interpolation operations. This encoding approach seamlessly accommodates the unstructured mesh features of TCAD simulator, providing a standardized method for device representation, akin to modeling transistor as a graph, reminiscent of the unified representations commonly used in computer vision (CV) and natural language processing (NLP). The framework enables comprehensive data-driven modeling by employing a novel graph attention network with skip connections, referred to as RelGAT. This network is used to construct an end-to-end surrogate model, performing node-level potential emulation and graph-level current-voltage (I–V) prediction. Furthermore, this framework is effectively integrated into a design technology co-optimization (DTCO) flow for carbon nanotube (CNT)-based emerging technology through transfer learning, facilitating early-stage evaluations of new processes and reducing the computational cost. Comprehensive technical details based on the device simulator Sentaurus TCAD are presented, empowering researchers to adopt the proposed AI-driven electronic design automation (EDA) solution at the device level.