L2O-ILT: Learning to Optimize Inverse Lithography Techniques

Binwu Zhu; Su Zheng; Ziyang Yu; Guojin Chen; Yuzhe Ma; Fan Yang; Bei Yu; Martin D.F. Wong

doi:10.1109/TCAD.2023.3323164

L2O-ILT: Learning to Optimize Inverse Lithography Techniques

Binwu Zhu, Su Zheng, Ziyang Yu, Guojin Chen, Yuzhe Ma, Fan Yang, Bei Yu, Martin D.F. Wong

Research output: Contribution to journal › Article › peer-review

Abstract

Inverse lithography technique (ILT) is one of the most widely used resolution enhancement techniques (RETs) to compensate for the diffraction effect in the lithography process. However, ILT suffers from runtime overhead issues with the shrinking size of technology nodes. In this paper, our proposed L2O-ILT framework unrolls the iterative ILT optimization algorithm into a learnable neural network with high interpretability, which can generate a high-quality initial mask for fast refinement. Experimental results demonstrate that our method achieves better performance on both mask printability and runtime than previous methods.

Original language	English (US)
Pages (from-to)	1
Number of pages	1
Journal	IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
DOIs	https://doi.org/10.1109/TCAD.2023.3323164
State	Accepted/In press - 2023
Externally published	Yes

Keywords

Adaptive optics
Computational modeling
Kernel
Lithography
Optical diffraction
Optical imaging
Optimization

ASJC Scopus subject areas

Software
Computer Graphics and Computer-Aided Design
Electrical and Electronic Engineering

Online availability

10.1109/TCAD.2023.3323164

Cite this

@article{3e456f2fb78e49d0a017645473c3d0ef,

title = "L2O-ILT: Learning to Optimize Inverse Lithography Techniques",

abstract = "Inverse lithography technique (ILT) is one of the most widely used resolution enhancement techniques (RETs) to compensate for the diffraction effect in the lithography process. However, ILT suffers from runtime overhead issues with the shrinking size of technology nodes. In this paper, our proposed L2O-ILT framework unrolls the iterative ILT optimization algorithm into a learnable neural network with high interpretability, which can generate a high-quality initial mask for fast refinement. Experimental results demonstrate that our method achieves better performance on both mask printability and runtime than previous methods.",

keywords = "Adaptive optics, Computational modeling, Kernel, Lithography, Optical diffraction, Optical imaging, Optimization",

author = "Binwu Zhu and Su Zheng and Ziyang Yu and Guojin Chen and Yuzhe Ma and Fan Yang and Bei Yu and Wong, {Martin D.F.}",

note = "Publisher Copyright: IEEE",

year = "2023",

doi = "10.1109/TCAD.2023.3323164",

language = "English (US)",

pages = "1",

journal = "IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems",

issn = "0278-0070",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - L2O-ILT

T2 - Learning to Optimize Inverse Lithography Techniques

AU - Zhu, Binwu

AU - Zheng, Su

AU - Yu, Ziyang

AU - Chen, Guojin

AU - Ma, Yuzhe

AU - Yang, Fan

AU - Yu, Bei

AU - Wong, Martin D.F.

N1 - Publisher Copyright: IEEE

PY - 2023

Y1 - 2023

N2 - Inverse lithography technique (ILT) is one of the most widely used resolution enhancement techniques (RETs) to compensate for the diffraction effect in the lithography process. However, ILT suffers from runtime overhead issues with the shrinking size of technology nodes. In this paper, our proposed L2O-ILT framework unrolls the iterative ILT optimization algorithm into a learnable neural network with high interpretability, which can generate a high-quality initial mask for fast refinement. Experimental results demonstrate that our method achieves better performance on both mask printability and runtime than previous methods.

AB - Inverse lithography technique (ILT) is one of the most widely used resolution enhancement techniques (RETs) to compensate for the diffraction effect in the lithography process. However, ILT suffers from runtime overhead issues with the shrinking size of technology nodes. In this paper, our proposed L2O-ILT framework unrolls the iterative ILT optimization algorithm into a learnable neural network with high interpretability, which can generate a high-quality initial mask for fast refinement. Experimental results demonstrate that our method achieves better performance on both mask printability and runtime than previous methods.

KW - Adaptive optics

KW - Computational modeling

KW - Kernel

KW - Lithography

KW - Optical diffraction

KW - Optical imaging

KW - Optimization

UR - http://www.scopus.com/inward/record.url?scp=85174847215&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85174847215&partnerID=8YFLogxK

U2 - 10.1109/TCAD.2023.3323164

DO - 10.1109/TCAD.2023.3323164

M3 - Article

AN - SCOPUS:85174847215

SN - 0278-0070

SP - 1

JO - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

JF - IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

ER -

L2O-ILT: Learning to Optimize Inverse Lithography Techniques

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Related links

Fingerprint

Cite this