With the continuous decrease in the critical dimensions of integrated circuits, mask optimization has become the main challenge in VLSI 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 SegNet-OPC, which can generate optimized masks from the target layout at shorter training and turnaround 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 framework yields remarkable improvements over conventional methods, delivering significantly faster turnaround time and superior mask printability and manufacturability. With just 1.25 hours of training, the framework achieves comparable mask complexity while surpassing the state-of-the-art methods, achieving a minimum 3% enhancement in mask printability and an impressive 16.7% improvement in mask manufacturability.

There is a sharp decline in the network performance when the wireless link fails as a data path in the Wireless Network-on-Chip (WiNoC). To counteract this problem, we propose a fault-tolerance mechanism for the efficient retransmission of data in the WiNoC. When an error is detected in the data transmission process, this mechanism works to feed back the fault information to the source node in real time via fault signal lines. In the source node, the highest transmission priority is assigned to the backup retransmitted data, and the corresponding direct link is positioned to enable the data packet for its efficient retransmission to the destination node, thereby ensuring efficiency in fault tolerance. Additionally, we have improved the receiving port of the wireless router, added the corresponding redundant buffers and mux, and dynamically selected the retransmitted non-faulty data packets to be written to the local router in order to avoid the disorderly retransmission of the data packets. The evaluation results of this paper demonstrate that compared with the methods which are under different fault conditions, this fault-tolerant method drastically improves the data throughput rate, reduces the delay, effectively guarantees the reliability of the network, and improves the system performance.