Abstract:
Described herein is a method of determining candidate patterns from a set of patterns of a patterning process. The method includes obtaining (i) a set of patterns of a patterning process, (ii) a search pattern having a first feature and a second feature, and (iii) a first search condition comprising a relative position between the first feature and the second feature of the search pattern; and determining a first set of candidate patterns from the set of patterns that satisfies the first search condition associated with the first feature and the second feature of the search pattern.
Abstract:
Provided is a process, including: obtaining data specifying a layout of a lithographic pattern; obtaining performance metrics of a computational analysis of the layout, the performance metrics indicating performance of one or more computer processes performing respective portions of the computational analysis; correlating the performance metrics to portions of the layout being processed during measurement of the respective performance metrics; and generating a three or higher dimensional visualization based on a result of correlating the performance metrics to portions of the layout being processed during measurement, wherein at least some of the visualization dimensions indicate relative positions of portions of the layout and at least some of the visualization dimensions indicate a performance metric correlated to the respective portions.
Abstract:
A method of generating a characteristic pattern for a patterning process and training a machine learning model. The method for generating the characteristic pattern includes obtaining a trained generator model configured to generate a characteristic pattern (e.g., hot spot pattern), and an input pattern; and generating, via simulation of the trained generator model (e.g., CNN), the characteristic pattern based on the input pattern, wherein the input pattern is at least one of a random vector, a class of pattern.