Lufeng Liao

As the designed feature size of integrated circuits (ICs) continues to shrink, the lithographic printability of the design has become one of the important issues in IC design and manufacturing. There are patterns that cause lithography hotspots in the IC layout. Hotspot detection affects the turn-around time and the yield of IC manufacturing. The precision and F1 score of available machine-learning-based hotspot-detection methods are still insufficient. In this paper, a lithography hotspot detection method based on transfer learning using pre-trained deep convolutional neural network is proposed. The proposed method uses the VGG13 network trained with the ImageNet dataset as the pre-trained model. In order to obtain a model suitable for hotspot detection, the pre-trained model is trained with some down-sampled layout pattern data and takes cross entropy as the loss function. ICCAD 2012 benchmark suite is used for model training and model verification. The proposed method performs well in accuracy, recall, precision, and F1 score. There is significant improvement in the precision and F1 score. The results show that updating the weights of partial convolutional layers has little effect on the results of this method.

Source and mask optimization (SMO) is one of the most important resolution enhancement techniques for integrated circuit manufacturing in 2X nm technology node and beyond. Nowadays full-chip SMO is alternatively realized by applying SMO to limited number of selected critical patterns instead of to full-chip area, since it is too computational expensive to be apply SMO in full-chip area directly. The critical patterns are selected by a pattern selection method which enables SMO in full-chip application by balancing the performance and computation consumption. A novel diffraction-based pattern selection method has been proposed in this paper. In this method, diffraction-signatures are sufficiently described with widths in eight selected directions. Coverage rules between the diffraction-signatures are specifically designed. Diffraction-signature grouping method and pattern selection strategy are proposed based on the diffraction-signatures and coverage rules. A series of simulations and comparisons performed using ASML’s Tachyon software, which is one of the state of the art commercial SMO platforms, verify the validity of the proposed method.