TEMPO: Fast Mask Topography Effect Modeling with Deep Learning

With the continuous shrinking of the semiconductor device dimensions, mask topography effects stand out among the major factors influencing the lithography process. Including these effects in the lithography optimization procedure has become necessary for advanced technology nodes. However, conventional rigorous simulation for mask topography effects is extremely computationally expensive for high accuracy. In this work, we propose TEMPO as a novel generative learning-based framework for efficient and accurate 3D aerial image prediction. At its core, TEMPO comprises a generative adversarial network capable of predicting aerial image intensity at different resist heights. Compared to the default approach of building a unique model for each desired height, TEMPO takes as one of its inputs the desired height to produce the corresponding aerial image. In this way, the global model in TEMPO can capture the shared behavior among different heights, thus, resulting in smaller model size. Besides, across-height information sharing results in better model accuracy and generalization capability. Our experimental results demonstrate that TEMPO can obtain up to 1170x speedup compared with rigorous simulation while achieving satisfactory accuracy.

[1]  Ronald L. Gordon,et al.  Mask topography simulation for EUV lithography , 1999, Advanced Lithography.

[2]  Shoji Mimotogi,et al.  Mask topography effects of hole patterns on hyper-NA lithography , 2007, Photomask Japan.

[3]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[4]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[5]  Yu Cao,et al.  Fast and accurate 3D mask model for full-chip OPC and verification , 2007, SPIE Advanced Lithography.

[6]  Xuejiao Zhao,et al.  Fast lithography aerial image calculation method based on machine learning. , 2017, Applied optics.

[7]  Seong-woon Choi,et al.  Study of the mask topography effect on the OPC modeling of hole patterns , 2008, SPIE Advanced Lithography.

[8]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[9]  Thomas K. Gaylord,et al.  Stable implementation of the rigorous coupled-wave analysis for surface-relief gratings: enhanced transmittance matrix approach , 1995 .

[10]  Luc Van Gool,et al.  ComboGAN: Unrestrained Scalability for Image Domain Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[11]  Wei Ye,et al.  LithoGAN : End-to-End Lithography Modeling with Generative Adversarial Networks , 2019 .

[12]  Shigeki Nojima,et al.  Data Efficient Lithography Modeling With Transfer Learning and Active Data Selection , 2018, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[13]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[15]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[16]  Andreas Erdmann,et al.  Application of artificial neural networks to compact mask models in optical lithography simulation , 2013, Advanced Lithography.

[17]  David Z. Pan,et al.  Generative Learning in VLSI Design for Manufacturability: Current Status and Future Directions , 2019, Journal of Microelectronic Manufacturing.

[18]  Chris A. Mack Understanding focus effects in submicrometer optical lithography: a review , 1993 .

[19]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[20]  A. Neureuther,et al.  Domain decomposition methods for the rapid electromagnetic simulation of photomask scattering , 2002 .

[21]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  David Z. Pan,et al.  Machine Learning for Yield Learning and Optimization , 2018, 2018 IEEE International Test Conference (ITC).

[23]  A. Neureuther,et al.  Mask topography effects in projection printing of phase-shifting masks , 1994 .

[24]  Johannes Ruoff Impact of mask topography and multilayer stack on high NA imaging of EUV masks , 2010, Photomask Technology.

[25]  Eli Yablonovitch,et al.  Boundary layer model to account for thick mask effects in photolithography , 2003, SPIE Advanced Lithography.

[26]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[27]  C. Mack Fundamental principles of optical lithography : the science of microfabrication , 2007 .