Abstract: Automatically identifying defect-based test coverage gaps in semiconductor devices includes determining a plurality of apparent killer defects on one or more semiconductor devices with a plurality of semiconductor dies based on characterization measurements of the one or more semiconductor devices acquired by one or more semiconductor fabrication subsystems, determining at least one semiconductor die which passes at least one test based on test measurements acquired by one or more test tool subsystems, correlate the characterization measurements with the test measurements to determine at least one apparent killer defect on the at least one semiconductor die which passes the at least one test, and determining one or more gap areas on the one or more semiconductor devices for defect-based test coverage based on the at least one apparent killer defect on the at least one semiconductor die which passes the at least one test.

Abstract: An inspection system may include a controller communicatively coupled to one or more in-line sample analysis tools including, but not limited to, an inspection tool or a metrology tool. The controller may identify defects in a population of dies based on data received from at least one of the one or more in-line sample analysis tools, assign weights to the identified defects indicative of predicted impact of the identified defects on reliability of the dies using a weighted defectivity model, generate defectivity scores for the dies in the population by aggregating the weighted defects in the respective dies in the population, and determine a set of outlier dies based on the defectivity scores for the dies in the population, wherein at least some of the set of outlier dies are isolated from the population.

Abstract: An inspection system may include a controller communicatively coupled to one or more in-line sample analysis tools including, but not limited to, an inspection tool or a metrology tool. The controller may identify defects in a population of dies based on data received from at least one of the one or more in-line sample analysis tools, assign weights to the identified defects indicative of predicted impact of the identified defects on reliability of the dies using a weighted defectivity model, generate defectivity scores for the dies in the population by aggregating the weighted defects in the respective dies in the population, and determine a set of outlier dies based on the defectivity scores for the dies in the population, wherein at least some of the set of outlier dies are isolated from the population.

Abstract: Embodiments herein include methods, systems, and apparatuses for die screening using inline defect information. Such embodiments may include receiving a plurality of defects, receiving wafersort electrical data for a plurality of dies, classifying each of the defects as a defect-of-interest or nuisance, determining a defect-of-interest confidence for each of the defects-of-interest, determining a die return index for each of the dies containing at least one of the defects-of-interest, determining a die return index cutline, and generating an inking map. Each of the defects may be associated with a die in the plurality of dies. Each of the dies may be tagged as passing a wafersort electrical test or failing the wafersort electrical test. Classifying each of the defects as a defect-of-interest or nuisance may be accomplished using a defect classification model, which may include machine learning. The inking map may be electronically communicated to an inking system.

Abstract: Embodiments herein include methods, systems, and apparatuses for die screening using inline defect information. Such embodiments may include receiving a plurality of defects, receiving wafersort electrical data for a plurality of dies, classifying each of the defects as a defect-of-interest or nuisance, determining a defect-of-interest confidence for each of the defects-of-interest, determining a die return index for each of the dies containing at least one of the defects-of-interest, determining a die return index cutline, and generating an inking map. Each of the defects may be associated with a die in the plurality of dies. Each of the dies may be tagged as passing a wafersort electrical test or failing the wafersort electrical test. Classifying each of the defects as a defect-of-interest or nuisance may be accomplished using a defect classification model, which may include machine learning. The inking map may be electronically communicated to an inking system.