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.

Effective layout pattern sampling is a fundamental component for lithography process optimization, hotspot detection, and model calibration. Existing pattern sampling algorithms rely on either vector quantization or heuristic approaches. However, it is difficult to manage these methods due to the heavy demands of prior knowledges, such as high-dimensional layout features and manually tuned hypothetical model parameters. In this paper we present a self-contained layout pattern sampling framework, where no manual parameter tuning is needed. To handle high dimensionality and diverse layout feature types, we propose a nonlinear dimensionality reduction technique with kernel parameter optimization. Furthermore, we develop a Bayesian model based clustering, through which automatic sampling is realized without arbitrary setting of model parameters. The effectiveness of our framework is verified through a sampling benchmark suite and two applications, lithography hotspot detection and optical proximity correction.

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.

Machine learning (ML) and pattern matching (PM) are powerful computer science techniques which can derive knowledge from big data, and provide prediction and matching. Since nanometer VLSI design and manufacturing have extremely high complexity and gigantic data, there has been a surge recently in applying and adapting machine learning and pattern matching techniques in VLSI physical design (including physical verification), e.g., lithography hotspot detection and data/pattern-driven physical design, as ML and PM can raise the level of abstraction from detailed physics-based simulations and provide reasonably good quality-of-result. In this paper, we will discuss key techniques and recent results of machine learning and pattern matching, with their applications in physical design.