CAMO: Correlation-Aware Mask Optimization with Modulated Reinforcement Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Liang, Xiaoxiao, Yang, Haoyu, Liu, Kang, Yu, Bei, Ma, Yuzhe
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917627321909248
author Liang, Xiaoxiao
Yang, Haoyu
Liu, Kang
Yu, Bei
Ma, Yuzhe
author_facet Liang, Xiaoxiao
Yang, Haoyu
Liu, Kang
Yu, Bei
Ma, Yuzhe
contents Optical proximity correction (OPC) is a vital step to ensure printability in modern VLSI manufacturing. Various OPC approaches based on machine learning have been proposed to pursue performance and efficiency, which are typically data-driven and hardly involve any particular considerations of the OPC problem, leading to potential performance or efficiency bottlenecks. In this paper, we propose CAMO, a reinforcement learning-based OPC system that specifically integrates important principles of the OPC problem. CAMO explicitly involves the spatial correlation among the movements of neighboring segments and an OPC-inspired modulation for movement action selection. Experiments are conducted on both via layer patterns and metal layer patterns. The results demonstrate that CAMO outperforms state-of-the-art OPC engines from both academia and industry.
format Preprint
id arxiv_https___arxiv_org_abs_2404_00980
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CAMO: Correlation-Aware Mask Optimization with Modulated Reinforcement Learning
Liang, Xiaoxiao
Yang, Haoyu
Liu, Kang
Yu, Bei
Ma, Yuzhe
Computer Vision and Pattern Recognition
Hardware Architecture
Optical proximity correction (OPC) is a vital step to ensure printability in modern VLSI manufacturing. Various OPC approaches based on machine learning have been proposed to pursue performance and efficiency, which are typically data-driven and hardly involve any particular considerations of the OPC problem, leading to potential performance or efficiency bottlenecks. In this paper, we propose CAMO, a reinforcement learning-based OPC system that specifically integrates important principles of the OPC problem. CAMO explicitly involves the spatial correlation among the movements of neighboring segments and an OPC-inspired modulation for movement action selection. Experiments are conducted on both via layer patterns and metal layer patterns. The results demonstrate that CAMO outperforms state-of-the-art OPC engines from both academia and industry.
title CAMO: Correlation-Aware Mask Optimization with Modulated Reinforcement Learning
topic Computer Vision and Pattern Recognition
Hardware Architecture
url https://arxiv.org/abs/2404.00980