Fast detection of novel problematic patterns based on dictionary learning and boundary detection of failure regions
Détails
ID Serval
serval:BIB_AF50844DE2F7
Type
Actes de conférence (partie): contribution originale à la littérature scientifique, publiée à l'occasion de conférences scientifiques, dans un ouvrage de compte-rendu (proceedings), ou dans l'édition spéciale d'un journal reconnu (conference proceedings).
Collection
Publications
Institution
Titre
Fast detection of novel problematic patterns based on dictionary learning and boundary detection of failure regions
Titre de la conférence
SPIE Advanced Lithography 2014
Adresse
San Jose, California, USA, February 23-27, 2014
Statut éditorial
Publié
Date de publication
2014
Langue
anglais
Résumé
Assessing pattern printability in new large layouts
faces important challenges of runtime and false
detection. Lithographic simulation tools and
classification techniques do not scale well. We propose a
fast pattern detection method by learning an overcomplete
basis representing each reference pattern. A pattern from
a new design is detected âeurooenovelâeuro˝ if its reconstruction
error, when coded in the learned basis, is large. We show
high speedup (1000x) compared to nearest neighbor search.
A new boundary detection technique selects the minimal
set of the novel patterns to predict problematic
patterns; 14.93% of the novel patterns suffice to
predict ORC hotspots, while 53.77% are needed using
traditional methods.
faces important challenges of runtime and false
detection. Lithographic simulation tools and
classification techniques do not scale well. We propose a
fast pattern detection method by learning an overcomplete
basis representing each reference pattern. A pattern from
a new design is detected âeurooenovelâeuro˝ if its reconstruction
error, when coded in the learned basis, is large. We show
high speedup (1000x) compared to nearest neighbor search.
A new boundary detection technique selects the minimal
set of the novel patterns to predict problematic
patterns; 14.93% of the novel patterns suffice to
predict ORC hotspots, while 53.77% are needed using
traditional methods.
Mots-clé
Large scale pattern selection and sampling, hotspots, , failure regions, boundary detection, lithographic, difficulty, LTS5
Création de la notice
06/01/2014 19:40
Dernière modification de la notice
20/08/2019 16:18
Données d'usage
