Graph Attention Network-Based Unified TCAD Modeling Enabling Fast Design Technology Co-Optimization Through Transfer Learning
- 14 November 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 72 (1) , 474-481
Abstract
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.Keywords
Funding Information
- National Key Research and Development Program of China: Design Technology Co-Optimization Methodology (2023YFB4402700)
- Xi'an Jiaotong-Liverpool University (XJTLU) Research Development Fund (RDF-24-01-107)
This publication has 32 references indexed in Scilit:
- Fast Cell Library Characterization for Design Technology Co-Optimization Based on Graph Neural Networks2024
- Cold source field-effect transistors: Breaking the 60-mV/decade switching limit at room temperaturePhysics Reports, 2023
- Comprehensive Physics Based TCAD Model for 2D MX2 Channel Transistors2022
- Restructuring TCAD System: Teaching Traditional TCAD New Tricks2021
- A graph placement methodology for fast chip designNature, 2021
- Suppression of leakage current in carbon nanotube field-effect transistorsNano Research, 2020
- GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning2020
- DeepGCNs: Can GCNs Go As Deep As CNNs?2019
- Deep Residual Learning for Image Recognition2016
- Carbon Nanotube Feedback-Gate Field-Effect Transistor: Suppressing Current Leakage and Increasing On/Off RatioACS Nano, 2014