arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.04056cs.LGcs.AI
收藏

基于卷积傅里叶神经算子和光刻引导自训练的大规模掩模优化

Large Scale Mask Optimization Via Convolutional Fourier Neural Operator and Litho-Guided Self Training

NVIDIA Corp.(英伟达公司);Caltech(加州理工学院)

Haoyu Yang, Zongyi Li, Kumara Sastry, Saumyadip Mukhopadhyay, Anima Anandkumar, Brucek Khailany, Vivek Singh, Haoxing Ren

摘要:

机器学习技术在掩模优化问题中得到了广泛的研究,旨在提高掩模的印刷适性、缩短周转时间、提高掩模的可制造性等,但这些研究大多集中在小设计区域的初始解生成上。为了进一步实现机器学习技术在掩模优化任务上的潜力,我们提出了一种卷积傅立叶神经运算符(CFNO),它可以有效地学习布局图块依赖性,从而在传统工具的有限干预下实现无干扰的大规模掩模优化。我们发现了在解决非凸优化问题时,通过训练的机器学习模型进行Litho-guided self-training(LGST)的可能性,这允许迭代模型和数据集更新,并带来显着的模型性能改进。实验结果表明,第一次,我们的机器学习为基础的框架优于国家的最先进的学术数值掩模优化的数量级加速比。

英文摘要:

Machine learning techniques have been extensively studied for mask optimization problems, aiming at better mask printability, shorter turnaround time, better mask manufacturability, and so on. However, most of these researches are focusing on the initial solution generation of small design regions. To further realize the potential of machine learning techniques on mask optimization tasks, we present a Convolutional Fourier Neural Operator (CFNO) that can efficiently learn layout tile dependencies and hence promise stitch-less large-scale mask optimization with the limited intervention of legacy tools. We discover the possibility of litho-guided self-training (LGST) through a trained machine learning model when solving non-convex optimization problems, which allows iterative model and dataset update and brings significant model performance improvement. Experimental results show that, for the first time, our machine learning-based framework outperforms state-of-the-art academic numerical mask optimizers with an order of magnitude speedup.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑