EAAUnet-ILT: A Lightweight and Iterative Mask Optimization Resolution with SRAF Constraint Scheme

With the continuous scaling-down of integrated circuit feature sizes, inverse lithography technology (ILT), as the most groundbreaking resolution enhancement technique (RET), has become crucial in advanced semiconductor manufacturing. By directly optimizing mask patterns through inverse computation rather than rule-based local corrections, ILT can more accurately approximate target design patterns while extending the process window. However, current mainstream ILT approaches—whether machine learning-based or gradient descent-based—all face the challenge of balancing mask optimization quality and computational time. Moreover, ILT often faces a trade-off between imaging fidelity and manufacturability; fidelity-prioritized optimization leads to explosive growth in mask complexity, whereas manufacturability constraints require compromising fidelity. To address these challenges, we propose an iterative deep learning-based ILT framework incorporating a lightweight model, ghost and adaptive attention U-net (EAAUnet) to accelerate runtime and reduce computational overhead while progressively improving mask quality through multiple iterations based on the pre-trained network model. Compared to recent state-of-the-art (SOTA) ILT solutions, our approach achieves up to a 39% improvement in mask quality metrics. Additionally, we introduce a mask constraint scheme to regulate complex SRAF (sub-resolution assist feature) patterns on the mask, effectively reducing manufacturing complexity.