Novel End-to-End Production-Ready Machine Learning Flow for Nanolithography Modeling and Correction (2401.02536v1)
Abstract: Optical lithography is the main enabler to semiconductor manufacturing. It requires extensive processing to perform the Resolution Enhancement Techniques (RETs) required to transfer the design data to a working Integrated Circuits (ICs). The processing power and computational runtime for RETs tasks is ever increasing due to the continuous reduction of the feature size and the expansion of the chip area. State-of-the-art research sought Machine Learning (ML) technologies to reduce runtime and computational power, however they are still not used in production yet. In this study, we analyze the reasons holding back ML computational lithography from being production ready and present a novel highly scalable end-to-end flow that enables production ready ML-RET correction.
- Model based mask process correction and verification for advanced process nodes, in: H. J. Levinson, M. V. Dusa (Eds.), SPIE Advanced Lithography, San Jose, California, USA, 2009, p. 72742A. doi:10.1117/12.814362.
- GAN-OPC: Mask Optimization with Lithography-guided Generative Adversarial Nets, in: 2018 55th ACM/ESDA/IEEE Design Automation Conference (DAC), IEEE, San Francisco, CA, 2018, pp. 1–6. doi:10.1109/DAC.2018.8465816.
- DevelSet: Deep Neural Level Set for Instant Mask Optimization, in: 2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD), IEEE, Munich, Germany, 2021, pp. 1–9. doi:10.1109/ICCAD51958.2021.9643464.
- Neural-ILT 2.0: Migrating ILT to Domain-Specific and Multitask-Enabled Neural Network, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 41 (2022) 2671–2684.
- Machine learning OPC with generative adversarial networks, in: N. V. Lafferty, R.-H. Kim (Eds.), DTCO and Computational Patterning, SPIE, San Jose, United States, 2022, p. 27. doi:10.1117/12.2606715.
- DAMO: Deep Agile Mask Optimization for Full-Chip Scale, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 41 (2022) 3118–3131.
- GAN-SRAF: Subresolution Assist Feature Generation Using Generative Adversarial Networks, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 40 (2021) 373–385.
- SRAF placement with generative adversarial network, in: S. Owa, M. C. Phillips (Eds.), Optical Microlithography XXXIV, SPIE, Online Only, United States, 2021, p. 3. doi:10.1117/12.2581334.
- Optical proximity correction with hierarchical Bayes model, Journal of Micro/Nanolithography, MEMS, and MOEMS 15 (2016) 021009.
- Optical proximity correction using bidirectional recurrent neural network (BRNN), in: J. P. Cain, C.-M. Yuan (Eds.), Design-Process-Technology Co-optimization for Manufacturability XIII, SPIE, San Jose, United States, 2019, p. 12. doi:10.1117/12.2515159.
- SRAF Insertion via Supervised Dictionary Learning, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 39 (2020) 2849–2859.
- S. Shim, Y. Shin, Etch proximity correction through machine-learning-driven etch bias model, in: Q. Lin, S. U. Engelmann (Eds.), SPIE Advanced Lithography, San Jose, California, United States, 2016, p. 97820O. doi:10.1117/12.2219057.
- Machine Learning Models for Edge Placement Error Based Etch Bias, IEEE Transactions on Semiconductor Manufacturing 34 (2021) 42–48.
- Machine learning guided curvilinear MPC, in: J. H. Rankin, M. E. Preil (Eds.), Photomask Technology 2019, SPIE, Monterey, United States, 2019, p. 24. doi:10.1117/12.2538646.
- L. L. Pang, Inverse lithography technology: 30 years from concept to practical, full-chip reality, Journal of Micro/Nanopatterning, Materials, and Metrology 20 (2021).
- Fast pixel-based optical proximity correction based on nonparametric kernel regression, Journal of Micro/Nanolithography, MEMS, and MOEMS 13 (2014) 043007.