Author(s)

Carlos Silva, Felipe Rocha^*

Affiliation(s)

Department of Energy Engineering, University of Sao Paulo, Brazil. 

Corresponding Author

Felipe Rocha

ABSTRACT

The semiconductor manufacturing industry is vital to modern technology, powering devices from smartphones to supercomputers. A critical challenge within this industry is the detection of lithographic hotspots—areas in integrated circuit designs that are prone to manufacturing defects. Traditional methods for hotspot detection, primarily rule-based and statistical approaches, often struggle to address the complexities of contemporary IC designs, leading to potential yield losses and compromised device performance.

This paper proposes a deep learning-based framework for lithographic hotspot detection, leveraging convolutional neural networks to analyze design data more effectively than conventional methods. By integrating both simulated and real-world datasets, the proposed model significantly enhances detection accuracy and generalization capabilities across various design scenarios. Furthermore, this research explores multi-task learning, allowing the model to not only identify hotspots but also predict design rule violations, thereby streamlining the design process. The findings indicate that deep learning techniques can revolutionize hotspot detection, providing a robust solution that meets the increasing demands for smaller and more efficient semiconductor devices. This work contributes to the field by offering a comprehensive framework that enhances the efficiency and effectiveness of semiconductor design and manufacturing processes, paving the way for future advancements in the industry.

KEYWORDS

Deep learning; Lithographic hotspot detection; Semiconductor manufacturing

CITE THIS PAPER

Carlos Silva, Felipe Rocha. Deep learning-based lithographic hotspot detection for enhanced semiconductor design. World Journal of Engineering Research. 2024, 2(3): 18-26. DOI: https://doi.org/10.61784/wjer3010.

REFERENCES

[1] Hsiao, H H, Wang, K J. HotspotFusion: A Generative AI Approach to Predicting CMP Hotspot in Semiconductor Manufacturing. IEEE Transactions on Semiconductor Manufacturing, 2024. DOI: 10.1109/TSM.2024.3510376.

[2] 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.

[3] Kim, I, Mun, J, Baek, K M, et al. Cascade domino lithography for extreme photon squeezing. Materials Today, 2020, 39, 89-97.

[4] 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.

[5] Francisco, L. Machine Learning for Design Rule Checking, Multilayer CMP Hotspot Detection, and PPA Modeling, with Transfer Learning and Synthetic Training. Doctoral dissertation, North Carolina State University. 2021.

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

[7] Falch, B J, Hu, T, Hsuan, T, et al. Rule-based hotspot correction using a pattern matching flow. In Design-Process-Technology Co-optimization XV. SPIE. 2021, 11614, 26-35.

[8] 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.

[9] Yang, X, Su, D, Yu, X, et al. Hot spot engineering in hierarchical plasmonic nanostructures. Small, 2023, 19(22): 2205659.

[10] 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.

[11] Sim, J H, Lee, S H, Yang, J Y, et al. Plasmonic hotspot engineering of Ag-coated polymer substrates with high reproducibility and photothermal stability. Sensors and Actuators B: Chemical, 2022, 354, 131110.

[12] 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.

[13] Paul, O, Abrar, S, Mu, R, et al. Deep Image Segmentation for Defect Detection in Photo-lithography Fabrication. In 2023 24th International Symposium on Quality Electronic Design (ISQED), San Francisco, CA, USA, 2023, 1-7. DOI: 10.1109/ISQED57927.2023.10129372.

[14] 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.

[15] 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. 

[16] Fryer, D, Moskalenko, I, Fenger, G, et al. Fast rigorous modeling of photoresist in lithography. In Optical Microlithography XXXIV. SPIE. 2021, 11613, 82.

[17] Kareem, P, Shin, Y. Synthesis of lithography test patterns using machine learning model. IEEE Transactions on Semiconductor Manufacturing, 2021, 34(1): 49-57.

[18] 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.

[19] Chirumamilla, A, Moise, I M, Cai, Z, et al. Lithography-free fabrication of scalable 3D nanopillars as ultrasensitive SERS substrates. Applied Materials Today, 2023, 31, 101763.

[20] Kumar, P, Joshi, T, Joglekar, R, et al. ComputLitho–An Indigenous Optical Lithography Simulator with Novel Features. In 2024 8th IEEE Electron Devices Technology & Manufacturing Conference (EDTM), Bangalore, India, 2024, 1-3. DOI: 10.1109/EDTM58488.2024.10511904.

[21] Chockalingam, A, Naveen, S, Sanjay, S, et al. Sensor based hotspot detection and isolation in solar array system using IOT. In 2023 9th International Conference on Electrical Energy Systems (ICEES), Chennai, India, 2023, 371-376. DOI: 10.1109/ICEES57979.2023.10110240.

[22] Ismail, M, Bahnas, M, Reimann, T, et al. A quantified approach of dataset selection for training ML models on hard-to-classify patterns. In Design-Process-Technology Co-optimization XV. SPIE. 2021, 11614, 43-50.

[23] Wu, L, Ren, Y, Zhou, H, et al. Fabrication of wafer-scale ordered micro/nanostructures for SERS substrates using rotational symmetry cantilever-based probe lithography. Applied Surface Science, 2023, 626, 157220.

[24] Shreyanth, S, Harshitha, D S, Niveditha, S. Implementation of machine learning in VLSI integrated circuit design. SN Computer Science, 2023, 4(2): 137.