Author(s)

Arjun Mehta, Neha Sharma, Ramesh Kumar^*

Affiliation(s)

Department of Civil Engineering, Indian Institute of Technology Bombay, India.

Corresponding Author

Ramesh Kumar

ABSTRACT

The semiconductor manufacturing industry faces increasing challenges due to the growing complexity of integrated circuit designs and the limitations of traditional hotspot detection methods. Lithographic hotspots—areas on chip layouts susceptible to manufacturing defects—pose significant risks to yield and performance. Traditional detection techniques, primarily rule-based and statistical methods, often fail to accurately identify these hotspots, leading to high rates of false positives and negatives. In response to these challenges, this paper proposes a multi-task deep learning framework designed to optimize lithographic hotspot detection.

By leveraging the capabilities of convolutional neural networks, the framework simultaneously addresses multiple related tasks, including hotspot detection, design rule violation prediction, and critical area estimation. This multi-task learning approach enhances the model's ability to capture intricate relationships within IC layouts, resulting in improved accuracy and efficiency compared to conventional methods. The proposed framework was trained on a comprehensive dataset, ensuring robust performance across diverse IC designs. Experimental results indicate that the model achieves an impressive accuracy of 92%, significantly outperforming traditional detection systems. Furthermore, the integration of multi-task learning facilitates the sharing of representations across tasks, leading to enhanced generalization and reduced overfitting. The findings underscore the potential of deep learning techniques to revolutionize hotspot detection in semiconductor manufacturing, ultimately contributing to higher yields and better-performing devices. This research not only highlights the advantages of adopting advanced machine learning methodologies but also sets the stage for future explorations into hybrid models that incorporate domain-specific knowledge and advanced architectures.

KEYWORDS

Lithographic hotspot detection; Multi-Task learning; Deep learning

CITE THIS PAPER

Arjun Mehta, Neha Sharma, Ramesh Kumar. Optimized lithographic hotspot detection with multi-task deep learning. AI and Data Science Journal. 2024, 1(1): 37-45. DOI: https://doi.org/10.61784/adsj3005.

REFERENCES

[1] Alawieh, M B, Pan, D Z. ADAPT: An adaptive machine learning framework with application to lithography hotspot detection. In 2021 ACM/IEEE 3rd Workshop on Machine Learning for CAD (MLCAD), Raleigh, NC, USA, 2021, 1-6. DOI: 10.1109/MLCAD52597.2021.9531210.

[2] Wang, X, Wu, Y C, Zhou, M, et al. Beyond surveillance: privacy, ethics, and regulations in face recognition technology. Frontiers in big data, 2024, 7, 1337465.

[3] Kataoka, G, Yamamoto, M, Inagi, M, et al. Feature Vectors Based on Wire Width and Distance for Lithography Hotspot Detection. IPSJ Transactions on System and LSI Design Methodology, 2023, 16, 2-11.

[4] Lu, K, Zhang, X, Zhai, T, et al. Adaptive Sharding for UAV Networks: A Deep Reinforcement Learning Approach to Blockchain Optimization. Sensors, 2024, 24(22): 7279.

[5] Ismail, M T, Sharara, H, Madkour, K, et al. Autoencoder-based data sampling for machine learning-based lithography hotspot detection. In Proceedings of the 2022 ACM/IEEE Workshop on Machine Learning for CAD(MLCAD), UT, USA, 2022, 91-96. DOI: 10.1109/MLCAD55463.2022.9900096.

[6] Kabeel, A, ElManhawy, W, Kwan, J, et al. Machine Learning using retarget data to improve accuracy of fast lithographic hotspot detection. In Design-Process-Technology Co-optimization for Manufacturability XIV. SPIE. 2020, 11328, 1132803.

[7] Wang, X, Wu, Y C, Ji, X, et al. Algorithmic discrimination: examining its types and regulatory measures with emphasis on US legal practices. Frontiers in Artificial Intelligence, 2024, 7, 1320277.

[8] Kim, J, Lim, J, Lee, J, et al. Hotspot Prediction: SEM Image Generation With Potential Lithography Hotspots. IEEE Transactions on Semiconductor Manufacturing, 2023, 37(1): 103-114. DOI: 10.1109/TSM.2023.3327784.

[9] Jiang, Y, Yang, F, Yu, B, et al. Efficient layout hotspot detection via neural architecture search. ACM Transactions on Design Automation of Electronic Systems (TODAES), 2022, 27(6): 1-16.

[10] Liu, Y, Hu, X, Chen, S. Multi-Material 3D Printing and Computational Design in Pharmaceutical Tablet Manufacturing. Journal of Computer Science and Artificial Intelligence. 2024.

[11] Mohammad, S N, Boese, S, Groeger, P, et al. Focus spot monitoring: design of an automatable detection, classification, and impact analysis pipeline. In Optical and EUV Nanolithography XXXVI. SPIE. 2023, 12494, 398-408.

[12] Wang, M. AI Technologies in Modern Taxation: Applications, Challenges, and Strategic Directions. International Journal of Finance and Investment, 2024, 1(1): 42-46.

[13] Darla, L R, Garawad, S, Budihal, S V. Lithography Hotspot Detection. In International Conference on Security, Privacy and Data Analytics. ISPDA 2022. Lecture Notes in Electrical Engineering, vol 1049. Springer, Singapore. 2023, 1049, 333-345. DOI: https://doi.org/10.1007/978-981-99-3569-7_24.

[14] Qiu, L. DEEP LEARNING APPROACHES FOR BUILDING ENERGY CONSUMPTION PREDICTION. Frontiers in Environmental Research, 2024, 2(3): 11-17.

[15] Zhang, X, Li, P, Han, X, et al. Enhancing Time Series Product Demand Forecasting with Hybrid Attention-Based Deep Learning Models. IEEE Access, 2024, 12, 190079-190091. DOI: 10.1109/ACCESS.2024.3516697.

[16] Li, P, Ren, S, Zhang, Q, et al. Think4SCND: Reinforcement Learning with Thinking Model for Dynamic Supply Chain Network Design. IEEE Access, 2024. DOI: 10.1109/ACCESS.2024.3521439.

[17] Rohilla, R. Exploring Vision Transformer model for detecting Lithography Hotspots. In 2022 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON), Bengaluru, India, 2022, 2, 200-205. DOI: 10.1109/CENTCON56610.2022.10051370.

[18] Garawad, S, Budihal, S V. Intelligent Hotspot Detection in Layout Patterns. In: Rao, U P, Alazab, M, Gohil, B N, Chelliah, P R. (eds) Security, Privacy and Data Analytics. ISPDA 2022. Lecture Notes in Electrical Engineering, 2022, 1049, 347-358. DOI: https://doi.org/10.1007/978-981-99-3569-7_25.

[19] Liu, Y, Ren, S, Wang, X, et al. Temporal Logical Attention Network for Log-Based Anomaly Detection in Distributed Systems. Sensors, 2024, 24(24): 7949.

[20] Bhatia, A S, Kais, S, Alam, M A. Robustness of Quantum Federated Learning (QFL) Against “Label Flipping Attacks” for Lithography Hotspot Detection in Semiconductor Manufacturing. In 2024 IEEE International Reliability Physics Symposium (IRPS). IEEE, 2024, 1-4. DOI: 10.1109/IRPS48228.2024.10529306.

[21] Panneerchelvam, P, Huard, C M, Graves, T, et al. On the origin and evolution of hotspots in multipatterning processes. Journal of Vacuum Science & Technology B, 2023, 41(4).

[22] Takahashi, H, Ogura, H, Sato, S, et al. A feature selection method for weak classifier based hotspot detection. In Design-Process-Technology Co-optimization for Manufacturability XIV. SPIE. 2020, 11328, 310-316.

[23] Selvam, P, Rezaeifakhr, P, Schroeder, U P, et al. Deep learning-based hotspot prediction of via printability in process window corners. In Design-Process-Technology Co-optimization XV. SPIE. 2021, 11614, 173-180.

[24] Shahroz, M, Ali, M, Tahir, A, et al. Hierarchical Attention Module-Based Hotspot Detection in Wafer Fabrication Using Convolutional Neural Network Model. IEEE Access, 2024, 12, 92840-92855. DOI: 10.1109/ACCESS.2024.3422616.

[25] Zhang, X, Chen, S, Shao, Z, et al. Enhanced Lithographic Hotspot Detection via Multi-Task Deep Learning with Synthetic Pattern Generation. IEEE Open Journal of the Computer Society, 2024. DOI: 10.1109/OJCS.2024.3510555.