SegNet-OPC: A Mask Optimization Framework in VLSI Design Flow Based on Semantic Segmentation Network

With the continuous decrease in the critical dimensions of integrated circuits, mask optimization has become the main challenge in VISI design. In recent years, thriving machine learning has been gradually introduced in the field of optical proximity correction (OPC). Currently, advanced learning-based frameworks have been limited by low mask printability or large computational overhead. To address these limitations, this paper proposes a learning-based framework named the SegNet-OPC, which can generate optimized masks from the target layout at shorter training and turn-around time with higher mask printability. The proposed framework consists of a backbone network and loss terms suitable for mask optimization tasks, followed by a fine-tuning network. The quantitative results demonstrate that compared with the conventional methods, the proposed improved framework can achieve tens of times better turn-around time and higher mask printability and manufacturability with only 1.25 hours of training time while maintaining comparable mask complexity. The results indicate that the proposed framework can achieve at least a 3% improvement in mask printability and a 16.7% improvement in mask manufacturability compared with the state-of-the-art methods.