Revolutionizing TCAD Simulations with Universal Device Encoding and Graph Attention Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Fan, Guangxi, Shao, Leilai, Low, Kain Lu
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909080216403968
author Fan, Guangxi
Shao, Leilai
Low, Kain Lu
author_facet Fan, Guangxi
Shao, Leilai
Low, Kain Lu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_11624
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Revolutionizing TCAD Simulations with Universal Device Encoding and Graph Attention Networks
Fan, Guangxi
Shao, Leilai
Low, Kain Lu
Machine Learning
Artificial Intelligence
Hardware Architecture
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.
title Revolutionizing TCAD Simulations with Universal Device Encoding and Graph Attention Networks
topic Machine Learning
Artificial Intelligence
Hardware Architecture
url https://arxiv.org/abs/2308.11624