Rapid layout pattern classification

Authors:
Jen-Yi Wuu;Fedor G. Pikus;Andres Torres;Malgorzata Marek-Sadowska
Affiliations:
University of California, Santa Barbara, CA;Mentor Graphics Corporation, Wilsonville, OR;Mentor Graphics Corporation, Wilsonville, OR;University of California, Santa Barbara, CA
Venue:
Proceedings of the 16th Asia and South Pacific Design Automation Conference
Year:
2011

Citing 6
Cited 4

Support-Vector Networks

Machine Learning
Layout Printability Optimization Using a Silicon Simulation Methodology

ISQED '04 Proceedings of the 5th International Symposium on Quality Electronic Design
Predicting variability in nanoscale lithography processes

Proceedings of the 46th Annual Design Automation Conference
ELIAD: efficient lithography aware detailed routing algorithm with compact and macro post-OPC printability prediction

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
LIBSVM: A library for support vector machines

ACM Transactions on Intelligent Systems and Technology (TIST)
Fast Dual-Graph-Based Hotspot Filtering

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

Accurate process-hotspot detection using critical design rule extraction

Proceedings of the 49th Annual Design Automation Conference
Dealing with IC manufacturability in extreme scaling

Proceedings of the International Conference on Computer-Aided Design
Machine-learning-based hotspot detection using topological classification and critical feature extraction

Proceedings of the 50th Annual Design Automation Conference
A novel fuzzy matching model for lithography hotspot detection

Proceedings of the 50th Annual Design Automation Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

Printability of layout objects becomes increasingly dependent on neighboring shapes within a larger and larger context window. In this paper, we propose a two-level hotspot pattern classification methodology that examines both central and peripheral patterns. Accuracy and runtime enhancement techniques are proposed, making our detection methodology robust and efficient as a fast physical verification tool that can be applied during early design stages to large-scale designs. We position our method as an approximate detection solution, similar to pattern matching-based tools widely adopted by the industry. In addition, our analyses of classification results reveal that the majority of non-hotspots falsely predicted as hotspots have printed CD barely over the minimum allowable CD threshold. Our method is verified on several 45nm and 32nm industrial designs.