Litho-GPA: Gaussian Process Assurance for Lithography Hotspot Detection

Lithography hotspot detection is one of the fundamental steps in physical verification. Due to the increasingly complicated design patterns, early and quick feedback for lithography hotspots is desired to guide design closure in early stages. Machine learning approaches have been successfully applied to hotspot detection while demonstrating a remarkable capability of generalization to unseen hotspot patterns. However, most of the proposed machine learning approaches are not yet able to answer one critical question: how much a hotspot predicted from a trained model can be trusted? In this work, we present Litho-GPA, a lithography hotspot detection framework, with Gaussian Process assurance to provide confidence in each prediction. The framework also incorporates a data selection scheme with a sequence of weak classifiers to sample representative data and eventually reduce the amount of training data and lithography simulations needed. Experimental results demonstrate that our Litho-GPA is able to achieve the state-of-the-art accuracy while obtaining on average 28% reduction in false alarms.

[1]  Frank Liu,et al.  Predicting variability in nanoscale lithography processes , 2009, 2009 46th ACM/IEEE Design Automation Conference.

[2]  Toshiya Kotani,et al.  Automatic layout feature extraction for lithography hotspot detection based on deep neural network , 2016, SPIE Advanced Lithography.

[3]  Jingyu Xu,et al.  Accurate detection for process-hotspots with vias and incomplete specification , 2007, 2007 IEEE/ACM International Conference on Computer-Aided Design.

[4]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[5]  J. Andres Torres,et al.  High Performance Lithography Hotspot Detection With Successively Refined Pattern Identifications and Machine Learning , 2011, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[6]  Philippe Hurat,et al.  Automated full-chip hotspot detection and removal flow for interconnect layers of cell-based designs , 2007, SPIE Advanced Lithography.

[7]  Chikaaki Kodama,et al.  Lithography hotspot detection by two-stage cascade classifier using histogram of oriented light propagation , 2017, 2017 22nd Asia and South Pacific Design Automation Conference (ASP-DAC).

[8]  Wan-Yu Wen,et al.  A novel fuzzy matching model for lithography hotspot detection , 2013, 2013 50th ACM/EDAC/IEEE Design Automation Conference (DAC).

[9]  Iris Hui-Ru Jiang,et al.  Machine-Learning-Based Hotspot Detection Using Topological Classification and Critical Feature Extraction , 2015, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[10]  Evangeline F. Y. Young,et al.  Enabling online learning in lithography hotspot detection with information-theoretic feature optimization , 2016, 2016 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[11]  Wan-Yu Wen,et al.  A Fuzzy-Matching Model With Grid Reduction for Lithography Hotspot Detection , 2014, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[12]  Qiang Liu,et al.  LithoROC: lithography hotspot detection with explicit ROC optimization , 2019, ASP-DAC.

[13]  Jee-Hyong Lee,et al.  Accurate lithography hotspot detection using deep convolutional neural networks , 2016 .

[14]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[15]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[16]  Evangeline F. Y. Young,et al.  Bilinear Lithography Hotspot Detection , 2017, ISPD.

[17]  Xiaoyu Song,et al.  Litho-Aware Machine Learning for Hotspot Detection , 2018, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[18]  J. Andres Torres,et al.  ICCAD-2012 CAD contest in fuzzy pattern matching for physical verification and benchmark suite , 2012, 2012 IEEE/ACM International Conference on Computer-Aided Design (ICCAD).

[19]  Iris Hui-Ru Jiang,et al.  Accurate process-hotspot detection using critical design rule extraction , 2012, DAC Design Automation Conference 2012.

[20]  David Z. Pan,et al.  EPIC: Efficient prediction of IC manufacturing hotspots with a unified meta-classification formulation , 2012, 17th Asia and South Pacific Design Automation Conference.

[21]  Juhwan Kim,et al.  Hotspot detection on post-OPC layout using full-chip simulation-based verification tool: a case study with aerial image simulation , 2003, SPIE Photomask Technology.

[22]  David Z. Pan,et al.  A new lithography hotspot detection framework based on AdaBoost classifier and simplified feature extraction , 2015, Advanced Lithography.

[23]  Chris A. Mack.  Thirty years of lithography simulation , 2004, SPIE Advanced Lithography.

[24]  Chenxi Lin,et al.  Imbalance aware lithography hotspot detection: a deep learning approach , 2017, Advanced Lithography.

[25]  David Z. Pan,et al.  Machine Learning for Yield Learning and Optimization , 2018, 2018 IEEE International Test Conference (ITC).

[26]  Evangeline F. Y. Young,et al.  Layout Hotspot Detection With Feature Tensor Generation and Deep Biased Learning , 2019, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[27]  Ying Chen,et al.  Semi-supervised hotspot detection with self-paced multi-task learning , 2019, ASP-DAC.

[28]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[29]  Kibok Lee,et al.  Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples , 2017, ICLR.