ABSTRACT
With the continuous shrinking of technology nodes, lithography hotspot detection and elimination in the physical verification phase is of great value. Recently machine learning and pattern matching based methods have been extensively studied to overcome runtime overhead problem of expensive full-chip lithography simulation. However, there is still much room for improvement in terms of accuracy and Overall Detection and Simulation Time (ODST). In this paper, we propose a unified machine learning based hotspot detection framework, where feature extraction and optimization is guided by an information-theoretic approach and solved by a dynamic programming model. More importantly, our framework can be naturally extended to online learning scenario, where some newly detected and verified layout patterns are integrated into the learning model. Experimental results show that the proposed batch detection model outperforms all state-of-the-art methods with 3.47% of accuracy improvement and 58.88% of ODST reduction on ICCAD-2012 contest benchmark suite. More importantly, equipped with online learning, our framework can further improve both accuracy and ODST.
- [1]. . Design for manufacturing with emerging nanolithography. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 32 (10):1453–1472, 2013.Google ScholarDigital Library
- [2]. . Hotspot prevention and detection method using an image-recognition technique based on higher-order local autocorrelation. Journal of Micra/Nanotithoqrapluy, MEMS, and MOEMS (JM3), 13 (1):011007, 2014.Google Scholar
- [3]. . Hotspot detection on Post-OPC layout using full chip simulation based verification tool: A case study with aerial image simulation. In Proceedings of SPIE, volume 5256, 2003.Google Scholar
- [4]. . Automated full-chip hotspot detection and removal flow for interconnect layers of cell-based designs. In Proceedings of SPIE, volume 6521, 2007.Google Scholar
- [5]. . Accurate detection for process-hotspots with vias and incomplete specification. In IEEEI/ACM InternationalConference on Computer-Aided Design (ICCAD), pages 839–846, 2007.Google Scholar
- [6]. . Accurate process-hotspot detection using critical design rule extraction. In ACM/IEEE Design Automation Conference (DAC), pages 1167–1172, 2012.Google Scholar
- [7]. . A novel fuzzy matching model for lithography hotspot detection. In ACM/IEEE Design Automation Conference (DAC), pages 68:1–68:6, 2013.Google Scholar
- [8]. . A fuzzy-matching model with grid reduction for lithography hotspot detection. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 33 (11):1671–1680, 2014.Google ScholarCross Ref
- [9]. . Predicting variability in nanoscale lithography processes. In ACM/IEEE Design Automation Conference (DAC), pages 545–550, 2009.Google Scholar
- [10]. . High performance lithography hotspot detection with successively refined pattern identifications and machine learning. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 30 (11):1621–1634, 2011.Google Scholar
- [11]. . EPIC: Efficient prediction of IC manufacturing hotspots with a unified meta-classification formulation. In IEEE/ACM Asia and South Pacific Design Automation Conference (ASPDAC), pages 263–270, 2012.Google Scholar
- [12]. . Machine-learning-based hotspot detection using topological classification and critical feature extraction. In ACM/IEEE Design Automation Conference (DAC), pages 671–676, 2013.Google Scholar
- [13]. . A new lithography hotspot detection framework based on AdaBoost classifier and simplified feature extraction. In Proceedings of SPIE, volume 9427, 2015.Google Scholar
- [14]. . Machine-learning-based hotspot detection using topological classification and critical feature extraction. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 34 (3):460–470, 2015.Google ScholarDigital Library
- [15]. . Fundamental Principles of Optical Lithography: The Science of Microfabrication. John Wiley& Sons, 2008.Google Scholar
- [16]. . ICCAD-2012 CAD contest in fuzzy pattern matching for physical verification and benchmark suite. In IEEE/ACM InternationalConference on Computer-Aided Design (ICCAD), pages 349–350, 2012.Google Scholar
- [17]. . Optical proximity correction with hierarchical bayes model. In Proceedings of SPIE, volume 9426, 2015.Google Scholar
- [18]. . Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27 (8):1226–1238, 2005.Google ScholarDigital Library
- [19]. . Optical proximity correction with linear regression. IEEE Transactions on Semiconductor Manufacturing (TSM), 21 (2):263–271, 2008.Google ScholarCross Ref
- [20]. Additive logistic regression: a statistical view of boosting (with discussion and a rejoinder by the authors). Annals of Statistics, 28 (2):337–407, 2000.Google ScholarCross Ref
- [21]. . Classification and Regression Trees. CRC press 1984.Google Scholar
- [22]. . Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT press, 2001.Google Scholar
- [23]. . Neural network design for engineering applications. Computers & Structures, 79 (17):1541–1552, 2001.Google ScholarCross Ref
- [24]. . The elements of statistical learning: data mining, inference and prediction. The Mathematical Intelligencer, 27 (2):83–85, 2005.Google ScholarCross Ref
- [25]. . Smooth boosting and learning with malicious noise. Journal of Machine Learning Research, 4: 633–648, 2003.Google ScholarDigital Library
- [26]. . Online bagging and boosting. In IEEE InternationalConference on Systems, Man, and Cybernetics (ICSMC), volume 3, pages 2340–2345, 2005.Google Scholar
- [27]. . ICCAD-2013 CAD contest in mask optimization and benchmark suite. In IEEEI/ACM InternationalConference on Computer-Aided Design (ICCAD), pages 271–274, 2013.Google Scholar
Index Terms
- Enabling online learning in lithography hotspot detection with information-theoretic feature optimization
Recommendations
Bilinear Lithography Hotspot Detection
ISPD '17: Proceedings of the 2017 ACM on International Symposium on Physical DesignAdvanced semiconductor process technologies are producing various circuit layout patterns, and it is essential to detect and eliminate problematic ones, which are called lithography hotspots. These hotspots are formed due to light diffraction and ...
Layout Hotspot Detection with Feature Tensor Generation and Deep Biased Learning
DAC '17: Proceedings of the 54th Annual Design Automation Conference 2017Detecting layout hotspots is one of the key problems in physical verification flow. Although machine learning solutions show benefits over lithography simulation and pattern matching based methods, it is still hard to select a proper model for large ...
Lithography Hotspot Detection with FFT-based Feature Extraction and Imbalanced Learning Rate
With the increasing gap between transistor feature size and lithography manufacturing capability, the detection of lithography hotspots becomes a key stage of physical verification flow to enhance manufacturing yield. Although machine learning ...
Comments