Center for Deep Learning in Electronics Manufacturing, Inc.

D2s, Inc.

Ansys, Inc.

Center for Deep Learning Inelectronics Mfg., Inc.

Ajay Baranwal

Thang Nguyen

Suhas Pillai

Akira Fujimura

Michael Jude Meyer

Nagesh Shirali

Norman H Chang

Jocelyn Blair

Linyong Pang

Methods include generating a scanner aerial image using a neural network, where the scanner aerial image is generated using a mask inspection image that has been generated by a mask inspection machine. Embodiments also include training the neural network with a set of images, such as with a simulated scanner aerial image and another image selected from a simulated mask inspection image, a simulated Critical Dimension Scanning Electron Microscope (CD-SEM) image, a simulated scanner emulator image and a simulated actinic mask inspection image.

Method for computational metrology and inspection for patterns to be manufactured on a substrate

Methods incorporate variable side wall angle (VSA) into calculated patterns, using a mask 3D (M3D) effect. Embodiments include inputting a mask exposure information and determining the M3D effect. Determining the M3D effect may include determining the VSA. Embodiments may include calculating a VSA; and calculating a pattern on a substrate using the calculated VSA, wherein calculating the pattern on the substrate includes a mask 3D effect.

Method and system for reticle enhancement technology

Methods and systems for generation of shape data for a set of electronic designs include inputting a set of shape data, where the set of shape data represents a set of shapes for a device fabrication process. A convolutional neural network is used on the set of shape data to determine a set of generated shape data, where the convolutional neural network comprises a generator trained with a set of pre-determined discriminators. The set of generated shape data comprises a scanning electron microscope (SEM) image.

Methods and systems for generating shape data for electronic designs

Methods for training a convolutional neural network to register images for electronic designs include inputting a first pair of images aligned in a first modality and a second pair of images aligned in a second modality. An affine transformation is generated with a convolutional neural network, using one image from the first pair of images and one image from the second pair of images. The one image from the first pair of images is in the first modality and the one image from the second pair of images is in the second modality. Methods for registering images for electronic designs include inputting a pair of images, wherein the pair of images comprises a computer aided design (CAD) image and a scanning electron microscope (SEM) image. The CAD image is registered to the SEM image, using a trained convolutional neural network. The trained convolutional neural network further comprises an affine transformation.

Methods and systems for registering images for electronic designs

Methods incorporate variable side wall angle (VSA) into calculated patterns, using a mask 3D (M3D) effect. Embodiments include inputting a mask exposure information, calculating a mask 2D (M2D) effect from the mask exposure information, and determining the M3D effect from the M2D effect. Determining the M3D effect may include determining the VSA, such as by using a neural network. Embodiments may include determining a dose margin from mask exposure information; calculating a VSA using the dose margin; and calculating a pattern on a substrate using the calculated VSA, wherein calculating the pattern on the substrate includes a mask 3D effect.

Methods for generation of shape data for a set of electronic designs include inputting a set of shape data, where the set of shape data represents a set of shapes for a device fabrication process. A convolutional neural network is used on the set of shape data to determine a set of generated shape data, where the convolutional neural network comprises a generator trained with a pre-determined set of discriminators. The set of generated shape data comprises a scanning electron microscope (SEM) image.

Methods for compressing shape data for a set of electronic designs include inputting a set of shape data, where the shape data comprises mask designs. A convolutional autoencoder encodes the set of shape data, where the encoding compresses the set of shape data to produce a set of encoded shape data. The convolutional autoencoder is tuned for increased accuracy of the set of encoded shape data based on design rules for the set of shape data. The convolutional autoencoder comprises a set of parameters comprising weights, and the convolutional autoencoder has been trained to determine what information to keep based on the weights.

Methods and systems for compressing shape data for electronic designs

Methods for fracturing or mask data preparation are disclosed in which a set of single-beam charged particle beam shots is input; a calculated image is calculated using a neural network, from the set of single-beam charged particle beam shots; and a set of multi-beam shots is generated based on the calculated image, to convert the set of single-beam charged particle beam shots to the set of multi-beam shots which will produce a surface image on the surface. Methods for training a neural network include inputting a set of single-beam charged particle beam shots; calculating a set of calculated images using the set of single-beam charged particle beam shots; and training the neural network with the set of calculated images.

Methods and systems for forming a pattern on a surface using multi-beam charged particle beam lithography

Methods for compressing shape data for a set of electronic designs include inputting a set of shape data, where the shape data represents a set of shapes for a device fabrication process. A convolutional autoencoder is used on the set of shape data, the convolutional autoencoder having a pre-determined set of convolution layers including a kernel size and filter size for each convolution layer. The set of shape data is encoded to compress the set of shape data, using the pre-determined set of convolution layers of the convolutional autoencoder, to create a set of encoded shape data. The set of shape data comprises an SEM image, and the encoded set of shape data identifies a mask defect.

Systems and methods are provided for reducing processing time of an automated engineering design. A repository of engineering design rule violations and corresponding waiver decisions regarding the design rule violations is accessed. A clustering operation is performed on violations in the repository to form clusters of violations based on one or more characteristics of the violations. Waiver decisions associated with violations in each cluster are evaluated to assign a risk level to each cluster. A plurality of detected engineering design rule violations associated with an engineering design are identified. Each of the detected violations is iterated through to determine which cluster that detected violation belongs. Detected violations associated with low risk clusters are automatically to approve the engineering design.

Growing community of inventors

Dublin, CA, United States of America

Ajay Baranwal