With the continuous shrinking of the semiconductor device dimensions, mask topography effects stand out among the major factors influencing the lithography process. Including these effects in the lithography optimization procedure has become necessary for advanced technology nodes. However, conventional rigorous simulation for mask topography effects is extremely computationally expensive for high accuracy. In this work, we propose TEMPO as a novel generative learning-based framework for efficient and accurate 3D aerial image prediction. At its core, TEMPO comprises a generative adversarial network capable of predicting aerial image intensity at different resist heights. Compared to the default approach of building a unique model for each desired height, TEMPO takes as one of its inputs the desired height to produce the corresponding aerial image. In this way, the global model in TEMPO can capture the shared behavior among different heights, thus, resulting in smaller model size. Besides, across-height information sharing results in better model accuracy and generalization capability. Our experimental results demonstrate that TEMPO can obtain up to 1170x speedup compared with rigorous simulation while achieving satisfactory accuracy.

Lithography simulation is one of the key steps in physical verification, enabled by the substantial optical and resist models. A resist model bridges the aerial image simulation to printed patterns. While the effectiveness of learning-based solutions for resist modeling has been demonstrated, they are considerably data-demanding. Meanwhile, a set of manufactured data for a specific lithography configuration is only valid for the training of one single model, indicating low data efficiency. Due to the complexity of the manufacturing process, obtaining enough data for acceptable accuracy becomes very expensive in terms of both time and cost, especially during the evolution of technology generations when the design space is intensively explored. In this paper, we propose a new resist modeling framework for contact layers, utilizing existing data from old technology nodes and active selection of data in a target technology node, to reduce the amount of data required from the target lithography configuration. Our framework based on transfer learning and active learning techniques is effective within a competitive range of accuracy, i.e., $3 \times -10 \times $ reduction on the amount of training data with comparable accuracy to the state-of-the-art learning approach.

Lithography simulation is one of the key steps in physical verification, enabled by the substantial optical and resist models. A resist model bridges the aerial image simulation to printed patterns. While the effectiveness of learning-based solutions for resist modeling has been demonstrated, they are considerably data-demanding. Meanwhile, a set of manufactured data for a specific lithography configuration is only valid for the training of one single model, indicating low data efficiency. Due to the complexity of the manufacturing process, obtaining enough data for acceptable accuracy becomes very expensive in terms of both time and cost, especially during the evolution of technology generations when the design space is intensively explored. In this work, we propose a new resist modeling framework for contact layers that utilizes existing data from old technology nodes to reduce the amount of data required from a target lithography configuration. Our framework based on residual neural networks and transfer learning techniques is effective within a competitive range of accuracy, i.e., 2-10X reduction on the amount of training data with comparable accuracy to the state-of-the-art learning approach.

Subresolution assist feature (SRAF) generation is a very important resolution enhancement technique to improve yield in modern semiconductor manufacturing process. Model-based and rule-based approaches are widely adopted in the semiconductor industry. The model-based SRAF generation can achieve a high accuracy but it is known to be time-consuming and it is hard to obtain consistent SRAFs on the same layout pattern configurations. The rule-based SRAF generation is highly technology dependent and it is becoming extremely difficult to render high-quality results in advanced technology nodes. This paper proposes supervised data learning techniques for fast yet consistent SRAF generation with high-quality results. We first propose the constrained concentric circle with area sampling scheme for feature extraction. Illumination source symmetry-based feature compaction technique is further invented to reduce the training data set size and achieve consistent SRAF predictions. Using accurate model-based SRAFs as training data, classification models based on logistic regression (LGR) and support vector machine are calibrated for SRAF predictions. Moreover, the probability maximum prediction is proposed to generate manufacturing-friendly SRAFs with a greedy simplification scheme. We compare support vector machine and LGR models by embedding into an entire mask optimization flow, where the support vector machine model obtains better lithographic performance. Experimental results demonstrate that, compared with the commercial Calibre tool, supervised data learning techniques for SRAF generation obtain significant speed up (>3X for a 100 um2layout clip) and comparable lithographic performance in terms of edge placement error and process variation band.

In advanced semiconductor-process technology, the ability to detect and repair lithography hotspots, which can affect printability, is essential. In this paper, we propose a two-stage cascade classifier for accurate hotspot detection. Our classifier uses a novel layout feature based on the propagation of light passing through a photomask. We performed experiments to evaluate our cascade classifier by applying it to the ICCAD-2012 CAD contest problem. The hotspot detection performance was evaluated according to two indices: (I1) the number of correctly detected hotspots over the number of actual hotspots and (I2) the number of correctly detected hotspots over the number of false hotspots. The results showed that the proposed method gained a 1.15% improvement in I1 and 24.4 times improvement in I2 on average compared to existing state-of-the-art methods, even the one with the best I1.

Sub-Resolution Assist Feature (SRAF) generation is a very important resolution enhancement technique to improve yield in modern semiconductor manufacturing process. Model- based SRAF generation has been widely used to achieve high accuracy but it is known to be time consuming and it is hard to obtain consistent SRAFs on the same layout pattern configurations. This paper proposes the first ma- chine learning based framework for fast yet consistent SRAF generation with high quality of results. Our technical con- tributions include robust feature extraction, novel feature compaction, model training for SRAF classification and pre- diction, and the final SRAF generation with consideration of practical mask manufacturing constraints. Experimental re- sults demonstrate that, compared with commercial Calibre tool, our machine learning based SRAF generation obtains 10X speed up and comparable performance in terms of edge placement error (EPE) and process variation (PV) band.

One of the most promising techniques in the 14 nm logic node and beyond is triple patterning lithography (TPL). Recently, LELECUT type TPL technology, where the third mask is used to cut the patterns, is discussed to alleviate native conflict and overlay problems in LELELE type TPL. In this paper, we formulate LELECUT mask assignment problem which maximizes the compliance to the lithography and apply a positive semidefinite relaxation. In our proposed method, the positive semidefinite relaxation is defined by extracting cut candidates from the layout, and a mask assignment is obtained from an optimum solution of the relaxation by randomized rounding technique.

Although self-aligned double and quadruple patterning (SADP, SAQP) have promising processes for sub-20 nm node advanced technologies and beyond, not all layouts are compatible with them. In advanced technologies, feasible wafer image should be generated effectively by utilizing SADP and SAQP where a wafer image is determined by a selected mandrel pattern. However, predicting a mandrel pattern is not easy since it is different from the wafer image (or target pattern). In this paper, we propose new routing methods for spacer-is-dielectric (SID)-type SADP, SID-type SAQP, and spacer-is-metal (SIM)-type SADP to generate a feasible layout satisfying the connection requirements. Routing algorithms comprising simple connecting and cutting rules are performed on a new grid structure where two (SID-type SADP) or three colors (SID-type SAQP and SIM-type SADP) are assigned alternately to grid-nodes. Then a mandrel pattern is selected without complex coloring or decomposition methods. Also, we try to reduce hotspots (potentially defective regions) by the proposed dummy pattern flipping for SID-type SADP. In experiments, feasible layouts meeting the connection requirements are generated and the effectiveness of the proposed framework is confirmed.

Although Self-Aligned Double and Quadruple Patterning (SADP, SAQP) have become the most promising processes for sub-20 nm and sub-14 nm node advanced technologies, not all wafer images are realized by them. In advanced technologies, feasible wafer images should be generated effectively by utilizing SADP and SAQP where a wafer image is uniquely determined by a selected mandrel pattern. However, predicting the wafer image of a mandrel pattern is not easy. In this paper, we propose a routing method of generating a feasible wafer image satisfying the connection requirements. Routing algorithms comprising simple connecting and cutting rules are performed on a new grid structure where two (SADP) or three colors (SAQP) are assigned alternately to grid-nodes. Then a mandrel pattern is selected without complex coloring or decomposition methods. Also, hotspot reduction by dummy pattern flipping is proposed. In experiments, feasible wafer images meeting the connection requirements are generated and the effectiveness of the proposed framework is confirmed.

Design shrinking beyond the resolution limits of 193 nm optical lithography requires the introduction of double patterning technology (DPT) for the semiconductor industry. Two consecutive lithography and etching process (LELE; Litho-Etch-Litho-Etch) and self aligned double patterning (SADP) process are major two options of DPT.