Revolutionizing TCAD Simulations with Universal Device Encoding and Graph Attention Networks

Guangxi Fan, Leilai Shao, Kain Lu Low
8/1/2023
cs.LGcs.AIcs.AR

No confident code implementation found for this paper.

Abstract

An innovative methodology 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 not only considers material-level and device-level embeddings, but also introduces a novel spatial relationship embedding inspired by interpolation operations typically used in finite element meshing. Universal physical laws from device simulations are leveraged for comprehensive data-driven modeling, which encompasses surrogate Poisson emulation and current-voltage (IV) prediction based on drift-diffusion model. Both are achieved using a novel graph attention network, referred to as RelGAT. 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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Rapid FinFET Modelling Using an Autoencoder

80% match2026

Device Image-IV Mapping using Variational Autoencoder for Inverse Design and Forward Prediction

80% match2023

SuperCond-GNN: Scalable Graph Neural Network Surrogate for Superconducting Circuit Simulations

79% match2026

KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits

77% match1 repo42026

Addressing Class Imbalance and Data Limitations in Advanced Node Semiconductor Defect Inspection: A Generative Approach for SEM Images

77% match2024

Learning Mesh-Based Simulation with Graph Networks

77% match1 repo15.2k2020

Cite this paper

@article{fan2023revolutionizing,
  title  = {Revolutionizing TCAD Simulations with Universal Device Encoding and Graph Attention Networks},
  author = {Guangxi Fan and Leilai Shao and Kain Lu Low},
  year   = {2023},
  eprint = {2308.11624},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.11624v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.11624.svg)](https://codeofpaper.com/paper/2308.11624)

Discussion