Abstract: Embodiments of the invention provide a system, media, and method for deep learning applications in physical design verification. Generally, the approach includes maintaining a pattern library for use in training machine learning model(s). The pattern library being generated adaptively and supplemented with new patterns after review of new patterns. In some embodiments, multiple types of information may be included in the pattern library, including validation data, and parameter and anchoring data used to generate the patterns. In some embodiments, the machine learning processes are combined with traditional design rule analysis. The patterns being generated and adapted using a lossless process that encodes the information of a corresponding area of a circuit layout.

Abstract: Methodologies and a device for assessing integrated circuit and pattern for yield risk based on 3D simulation of semiconductor patterns are provided. Embodiments include generating, with a processor, a 3D simulation of semiconductor patterns; obtaining critical dimensions of distances between layers or within a layer of the 3D simulation of semiconductor patterns; comparing the set of critical dimensions with predefined minimum dimensions; and yield scoring each of the semiconductor patterns of the 3D simulation based on the comparing step.

Abstract: Disclosed is a method and corresponding system and program product that includes providing integrated circuit design layout(s), deconstructing the integrated circuit design layout(s) into unit-level geometric constructs, identifying anomalies in the unit-level geometric constructs, and storing anomaly data in a database.

Abstract: Disclosed is a method and corresponding system and program product that includes providing integrated circuit design layout(s), deconstructing the integrated circuit design layout(s) into unit-level geometric constructs, identifying anomalies in the unit-level geometric constructs, and storing anomaly data in a database.

Abstract: Methodologies and a device for assessing integrated circuit and pattern for yield risk based on 3D simulation of semiconductor patterns are provided. Embodiments include generating, with a processor, a 3D simulation of semiconductor patterns; obtaining critical dimensions of distances between layers or within a layer of the 3D simulation of semiconductor patterns; comparing the set of critical dimensions with predefined minimum dimensions; and yield scoring each of the semiconductor patterns of the 3D simulation based on the comparing step.

Abstract: A mechanism is provided in a data processing system for detecting lithographic hotspots. The mechanism receives a design layout. The mechanism generates spatial pattern clips from the design layout. The mechanism performs a transform on the spatial pattern clips to form frequency domain pattern clips. The mechanism performs feature extraction on the frequency domain pattern clips to form frequency domain features. The mechanism utilizes the extracted features on a set of training samples to train a machine learning classifier model. The mechanism classifies a set of previously unseen patterns, based on frequency domain features of the previously unseen patterns using the trained machine learning classifier model, into hotspots and non-hotspots.

Abstract: A mechanism is provided in a data processing system for detecting lithographic hotspots. The mechanism receives a design layout. The mechanism generates spatial pattern clips from the design layout. The mechanism performs a transform on the spatial pattern clips to form frequency domain pattern clips. The mechanism performs feature extraction on the frequency domain pattern clips to form frequency domain features. The mechanism utilizes the extracted features on a set of training samples to train a machine learning classifier model. The mechanism classifies a set of previously unseen patterns, based on frequency domain features of the previously unseen patterns using the trained machine learning classifier model, into hotspots and non-hotspots.

Abstract: A process and apparatus are provided for automated pattern-based semiconductor design layout correction. Embodiments include: determining a portion of a layout of an IC design, the portion comprising a first pattern of a plurality of routes connecting a plurality of design connections; determining one or more sets of the plurality of design connections based on the plurality of routes; and determining, by a processor, a second pattern of a plurality of routes connecting the plurality of design connections within the portion based on the one or more sets.

Abstract: Methods for modifying a physical design of an electrical circuit used in the manufacture of a semiconductor device, and methods for fabricating an integrated circuit, are provided. In an embodiment, a method includes providing a circuit design layout that has a plurality of element patterns. A first library of problematic sections is provided. An initial circuit section and an additional circuit section within the circuit design layout are determined to match problematic sections in the first library, and the initial and additional circuit sections have overlapping peripheral boundaries. A second library of replacement sections is provided. The replacement sections correspond to the problematic sections. The circuit sections that match the problematic sections are replaced with a replacement section that corresponds to the respective problematic sections to form the final circuit layout. Boundary characteristics of the replacement sections are substantially the same as the circuit sections replaced thereby.

Abstract: A method includes receiving a design layout file for an integrated circuit device in a computing apparatus. The design layout file specifies dimensions of a plurality of features. Outer markers are generated in the computing apparatus for at least a subset of the features based on the proximity of the features to one another and spacing requirements. Features are identified in the computing apparatus where the associated outer marker has at least one dimension greater than the dimensions specified for the feature.

Abstract: A method includes receiving a design layout file for an integrated circuit device in a computing apparatus. The design layout file specifies dimensions of a plurality of features. Outer markers are generated in the computing apparatus for at least a subset of the features based on the proximity of the features to one another and spacing requirements. Features are identified in the computing apparatus where the associated outer marker has at least one dimension greater than the dimensions specified for the feature.