Guardado en:
Detalles Bibliográficos
Autores principales: Li, Haoyuan, Yang, Dingcheng, Pei, Chunyan, Yu, Wenjian
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2408.13195
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916367840575488
author Li, Haoyuan
Yang, Dingcheng
Pei, Chunyan
Yu, Wenjian
author_facet Li, Haoyuan
Yang, Dingcheng
Pei, Chunyan
Yu, Wenjian
contents More accurate capacitance extraction is demanded for designing integrated circuits under advanced process technology. The pattern matching approach and the field solver for capacitance extraction have the drawbacks of inaccuracy and large computational cost, respectively. Recent work \cite{yang2023cnn} proposes a grid-based data representation and a convolutional neural network (CNN) based capacitance models (called CNN-Cap), which opens the third way for 3-D capacitance extraction to get accurate results with much less time cost than field solver. In this work, the techniques of neural architecture search (NAS) and data augmentation are proposed to train better CNN models for 3-D capacitance extraction. Experimental results on datasets from different designs show that the obtained NAS-Cap models achieve remarkably higher accuracy than CNN-Cap, while consuming less runtime for inference and space for model storage. Meanwhile, the transferability of the NAS is validated, as the once searched architecture brought similar error reduction on coupling/total capacitance for the test cases from different design and/or process technology.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13195
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NAS-Cap: Deep-Learning Driven 3-D Capacitance Extraction with Neural Architecture Search and Data Augmentation
Li, Haoyuan
Yang, Dingcheng
Pei, Chunyan
Yu, Wenjian
Hardware Architecture
Machine Learning
More accurate capacitance extraction is demanded for designing integrated circuits under advanced process technology. The pattern matching approach and the field solver for capacitance extraction have the drawbacks of inaccuracy and large computational cost, respectively. Recent work \cite{yang2023cnn} proposes a grid-based data representation and a convolutional neural network (CNN) based capacitance models (called CNN-Cap), which opens the third way for 3-D capacitance extraction to get accurate results with much less time cost than field solver. In this work, the techniques of neural architecture search (NAS) and data augmentation are proposed to train better CNN models for 3-D capacitance extraction. Experimental results on datasets from different designs show that the obtained NAS-Cap models achieve remarkably higher accuracy than CNN-Cap, while consuming less runtime for inference and space for model storage. Meanwhile, the transferability of the NAS is validated, as the once searched architecture brought similar error reduction on coupling/total capacitance for the test cases from different design and/or process technology.
title NAS-Cap: Deep-Learning Driven 3-D Capacitance Extraction with Neural Architecture Search and Data Augmentation
topic Hardware Architecture
Machine Learning
url https://arxiv.org/abs/2408.13195