ABSTRACT
Technology scaling has increased the complexity of integrated circuit design. It has also led to more challenges in the field of Design for Manufacturing (DFM). One of these challenges is lithography hotspot detection. Hotspots (HS) are design patterns that negatively affect the output yield. Identifying these patterns early in the design phase is crucial for high yield fabrication. Machine Learning-based (ML) hotspot detection techniques are promising since they have shown superior results to other methods such as pattern matching. Training ML models is a challenging task due three main reasons. First, industrial training designs contain millions of unique patterns. It is impractical to train models using this large number of patterns due to limited computational and memory resources. Second, the HS detection problem has an imbalanced nature; datasets typically have a limited number of HS and a large number of non-hotspots. Lastly, hotspot and non-hotspot patterns can have very similar geometries causing models to be susceptible to high false positive rates. Due to these reasons, the use of data sampling techniques is needed to choose the best representative dataset for training. In this paper, a dataset sampling technique based on autoencoders is introduced. The autoencoders are used to identify latent data features that can reconstruct the input patterns. These features are used to group the patterns using Density-based spatial clustering of applications with noise (DBSCAN). Then, the clustered patterns are sampled to reduce the training set size. Experiments on the ICCAD-2019 dataset show that the proposed data sampling approach can reduce the dataset size while maintaining the levels of recall and precision that were obtained using the full dataset.
- Vadim Borisov and Jurgen Scheible. 2018. Lithography Hotspots Detection Using Deep Learning. In 2018 15th International Conference on Synthesis, Modeling, Analysis and Simulation Methods and Applications to Circuit Design (SMACD). IEEE, Prague, 145--148. https://doi.org/10.1109/SMACD.2018.8434561Google Scholar
- Gangmin Cho, Yonghwi Kwon, Pervaiz Kareem, Sungho Kim, and Youngsoo Shin. 2021. Test pattern extraction for lithography modeling under design rule revisions. In Optical Microlithography XXXIV, Soichi Owa and Mark C. Phillips (Eds.). SPIE, Online Only, United States, 23. https://doi.org/10.1117/12.2583916Google Scholar
- Martin Ester, Hans-Peter Kriegel, Jörg Sander, and Xiaowei Xu. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. AAAI Press, 226--231.Google ScholarDigital Library
- Tianyang Gai, Ying Chen, Pengzheng Gao, Xiaojing Su, Lisong Dong, Yajuan Su, Yayi Wei, and Tianchun Ye. 2019. Sample patterns extraction from layout automatically based on hierarchical cluster algorithm for lithography process optimization. In Design-Process-Technology Co-optimization for Manufacturability XIII, Jason P. Cain and Chi-Min Yuan (Eds.). SPIE, San Jose, United States, 32. https://doi.org/10.1117/12.2514177Google Scholar
- Jhih-Rong Gao, Bei Yu, and David Z. Pan. 2014. Accurate lithography hotspot detection based on PCA-SVM classifier with hierarchical data clustering, John L. Sturtevant and Luigi Capodieci (Eds.). San Jose, California, USA, 90530E. https://doi.org/10.1117/12.2045888Google Scholar
- Xavier Glorot, Antoine Bordes, and Yoshua Bengio. 2011. Deep Sparse Rectifier Neural Networks. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 15), Geoffrey Gordon, David Dunson, and Miroslav Dudík (Eds.). PMLR, Fort Lauderdale, FL, USA, 315--323. https://proceedings.mlr.press/v15/glorot11a.htmlGoogle Scholar
- Geoffrey E. Hinton and Richard S. Zemel. 1993. Autoencoders, Minimum Description Length and Helmholtz Free Energy. In Proceedings of the 6th International Conference on Neural Information Processing Systems (Denver, Colorado) (NIPS'93). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 3--10.Google Scholar
- Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv:1704.04861 [cs] (April 2017). http://arxiv.org/abs/1704.04861 arXiv: 1704.04861.Google Scholar
- Xuanyu Huang, Rui Zhang, Yu Huang, Peiyao Wang, and Mei Li. 2021. Enhancements of Model and Method in Lithography Hotspot Identification. In 2021 Design, Automation & Test in Europe Conference & Exhibition (DATE). IEEE, Grenoble, France, 102--107. https://doi.org/10.23919/DATE51398.2021.9473963Google Scholar
- Aliaa Kabeel, Wael ElManhawy, Joe Kwan, Asmaa Rabie, Mohamed Ismail, Ahmed Khater, and Sarah Rizk. 2020. Machine Learning using retarget data to improve accuracy of fast lithographic hotspot detection. In Design-Process-Technology Co-optimization for Manufacturability XIV, Chi-Min Yuan (Ed.), Vol. 11328. International Society for Optics and Photonics, SPIE, 1 -- 7. https://doi.org/10.1117/12.2551827Google Scholar
- Namjae Kim, KiHeung Park, Jiwon Oh, Sangwoo Jung, Sangah Lee, Jae-Hyun Kang, Seung Weon Paek, Kareem Madkour, Wael ElManhawy, Aliaa Kabeel, Ahmed ElGhoroury, Marwah Shafee, Asmaa Rabie, and Joe Kwan. 2019. Machine learning to improve accuracy of fast lithographic hotspot detection. In Design-Process-Technology Co-optimization for Manufacturability XIII, Jason P. Cain and Chi-Min Yuan (Eds.). SPIE, San Jose, United States, 41. https://doi.org/10.1117/12.2515139Google Scholar
- Diederik P. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization. arxiv: 1412.6980 [cs.LG]Google Scholar
- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2018. Focal Loss for Dense Object Detection. arXiv:1708.02002 [cs] (Feb. 2018). http://arxiv.org/abs/1708.02002 arXiv: 1708.02002.Google Scholar
- Tetsuaki Matsunawa, Shigeki Nojima, and Toshiya Kotani. 2016. Automatic layout feature extraction for lithography hotspot detection based on deep neural network, Luigi Capodieci and Jason P. Cain (Eds.). San Jose, California, United States, 97810H. https://doi.org/10.1117/12.2217746Google Scholar
- Gaurav Rajavendra Reddy, Kareem Madkour, and Yiorgos Makris. 2019. Machine Learning-Based Hotspot Detection: Fallacies, Pitfalls and Marching Orders. In 2019 IEEE/ACM International Conference on Computer-Aided Design (ICCAD). IEEE, Westminster, CO, USA, 1--8. https://doi.org/10.1109/ICCAD45719.2019.8942128Google Scholar
- Gaurav Rajavendra Reddy, Constantinos Xanthopoulos, and Yiorgos Makris. 2021. On Improving Hotspot Detection Through Synthetic Pattern-Based Database Enhancement. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (2021), 1--1. https://doi.org/10.1109/TCAD.2021.3049285Google ScholarCross Ref
- Moojoon Shin and Jee-Hyong Lee. 2016a. Accurate lithography hotspot detection using deep convolutional neural networks. Journal of Micro/Nanolithography, MEMS, and MOEMS, Vol. 15, 4 (Nov. 2016), 043507. https://doi.org/10.1117/1.JMM.15.4.043507Google ScholarCross Ref
- Moojoon Shin and Jee-Hyong Lee. 2016b. CNN Based Lithography Hotspot Detection. The International Journal of Fuzzy Logic and Intelligent Systems, Vol. 16, 3 (Sept. 2016), 208--215. https://doi.org/10.5391/IJFIS.2016.16.3.208Google ScholarCross Ref
- Bei Yu, David Z. Pan, Tetsuaki Matsunawa, and Xuan Zeng. 2015. Machine learning and pattern matching in physical design. In The 20th Asia and South Pacific Design Automation Conference. IEEE, Chiba, Japan, 286--293. https://doi.org/10.1109/ASPDAC.2015.7059020Google ScholarCross Ref
Index Terms
- Autoencoder-Based Data Sampling for Machine Learning-Based Lithography Hotspot Detection
Recommendations
Evaluating Sampling Based Hotspot Detection
ARCS '09: Proceedings of the 22nd International Conference on Architecture of Computing SystemsIn sampling based hotspot detection, performance engineers sample the running program periodically and record the Instruction Pointer (IP) addresses at the sampling. Empirically, frequently sampled IP addresses are regarded as the hotspot of the ...
Sampling-Based Winner Prediction in District-Based Elections
AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent SystemsIn a district-based election, we apply a voting rule r to decide the winners in each district, and a candidate who wins in a maximum number of districts is the winner of the election. We present efficient sampling-based algorithms to predict the winner ...
BIRCHSCAN: A sampling method for applying DBSCAN to large datasets
Highlights- A sampling-based method for running DBSCAN on large data sets.
- The BIRCH ...
AbstractThe DBSCAN algorithm is a traditional density-based clustering method. This algorithm allows to identify clusters of different shapes, with the ability to manage noisy patterns in the data. DBSCAN usually presents good results, however ...
Comments