Guangxi Fan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Guangxi Fan has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Kain Lu Low
School of Advanced Technology, Xian JiaotongLiverpool University, Suzhou, China
3 shared publications - Leilai Shao
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China
2 shared publications Tianliang Ma
School of Mechanical Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China
1 shared publication- Tianliang Ma
Shanghai Jiao Tong Univ, Shanghai, Peoples R China
1 shared publication Xuguang Sun
School of Mechanical Engineering, Shanghai Jiao Tong University (SJTU), Shanghai, China
1 shared publication- Xuguang Sun
Shanghai Jiao Tong University, Shanghai, Shanghai, China
1 shared publication
Latest Publications
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 72 (1) , 474-481
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.
- 14 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 72 (1) , 474-481
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.
- Open Access
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Late Breaking Results: Fast System Technology Co-Optimization Framework for Emerging Technology Based on Graph Neural Networks
This paper proposes a fast system technology co-optimization (STCO) framework that optimizes power, performance, and area (PPA) for next-generation IC design, addressing the challenges and opportunities presented by novel materials and device architectures. We focus on accelerating the technology level of STCO using AI techniques, by employing graph neural network (GNN)-based approaches for both TCAD simulation and cell library characterization, which are interconnected through a unified compact model, collectively achieving over a 100X speedup over traditional methods. These advancements enable comprehensive STCO iterations with runtime speedups ranging from 1.9X to 14.1X and supports both emerging and traditional technologies.
- 23 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessLate Breaking Results: Fast System Technology Co-Optimization Framework for Emerging Technology Based on Graph Neural Networks
This paper proposes a fast system technology co-optimization (STCO) framework that optimizes power, performance, and area (PPA) for next-generation IC design, addressing the challenges and opportunities presented by novel materials and device architectures. We focus on accelerating the technology level of STCO using AI techniques, by employing graph neural network (GNN)-based approaches for both TCAD simulation and cell library characterization, which are interconnected through a unified compact model, collectively achieving over a 100X speedup over traditional methods. These advancements enable comprehensive STCO iterations with runtime speedups ranging from 1.9X to 14.1X and supports both emerging and traditional technologies.
- Open Access
- 1 September 2023
- Published by The Electrochemical Society in ECS Journal of Solid State Science and Technology
- Vol. 12 (9) , 091005
Physics-Integrated Machine Learning for Efficient Design and Optimization of a Nanoscale Carbon Nanotube Field-Effect Transistor
We propose an efficient framework for optimizing the design of Carbon Nanotube Field-Effect Transistor (CNTFET) through the integration of device physics, machine learning (ML), and multi-objective optimization (MOO). Firstly, we leverage the calibrated TCAD model based on experimental data to dissect the physical mechanisms of CNTFET, gaining insights into its operational principles and unique physical properties. This model also serves as a foundation, enabling multi-scale performance evaluations essential for dataset construction. In the ML phase, a chain structure of Support Vector Regression (SVR Chain) guided by a comprehensive statistical analysis of the design metrics is utilized to predict the design metrics. The surrogate model based on the SVR Chain achieves an average mean absolute percentage error (MAPE) of 1.59% across all design metrics without overfitting, even with limited data. The established ML model exhibits its competence in rapidly producing a global response surface for multi-scale CNTFET. Remarkably, an anomalous equivalent oxide thickness (EOT) and ON-state current (I on ) relationship is observed in CNTFET behavior due to extreme gate length scaling in long channel devices. This intriguing observation is further elucidated through a physics-based explanation. We further compare shallow and deep learning-based TCAD digital twins for model selection guidance. Using the Non-Dominated Sorted Genetic Algorithm-II (NSGA-II) in MOO, we harmonize metrics at both device and circuit levels, significantly reducing the design space. The closed-loop framework expedites the early-stage development of advanced transistors, overcoming the challenges posed by limited data.
- 1 September 2023
- Published by The Electrochemical Society in ECS Journal of Solid State Science and Technology
- Vol. 12 (9) , 091005
Open AccessPhysics-Integrated Machine Learning for Efficient Design and Optimization of a Nanoscale Carbon Nanotube Field-Effect Transistor
We propose an efficient framework for optimizing the design of Carbon Nanotube Field-Effect Transistor (CNTFET) through the integration of device physics, machine learning (ML), and multi-objective optimization (MOO). Firstly, we leverage the calibrated TCAD model based on experimental data to dissect the physical mechanisms of CNTFET, gaining insights into its operational principles and unique physical properties. This model also serves as a foundation, enabling multi-scale performance evaluations essential for dataset construction. In the ML phase, a chain structure of Support Vector Regression (SVR Chain) guided by a comprehensive statistical analysis of the design metrics is utilized to predict the design metrics. The surrogate model based on the SVR Chain achieves an average mean absolute percentage error (MAPE) of 1.59% across all design metrics without overfitting, even with limited data. The established ML model exhibits its competence in rapidly producing a global response surface for multi-scale CNTFET. Remarkably, an anomalous equivalent oxide thickness (EOT) and ON-state current (I on ) relationship is observed in CNTFET behavior due to extreme gate length scaling in long channel devices. This intriguing observation is further elucidated through a physics-based explanation. We further compare shallow and deep learning-based TCAD digital twins for model selection guidance. Using the Non-Dominated Sorted Genetic Algorithm-II (NSGA-II) in MOO, we harmonize metrics at both device and circuit levels, significantly reducing the design space. The closed-loop framework expedites the early-stage development of advanced transistors, overcoming the challenges posed by limited data.