Kla Tencor Corporation

Kla Corporation

Arpit Yati

Jagdish Chandra Saraswatula

Arun Lobo

Arpit Jain

Martin Plihal

Saravanan Paramasivam

Andrew Cross

Thirupurasundari Jayaraman

Vidyasagar Anantha

Hari Pathangi

Raghavan Konuru

Olivier Moreau

Shivam Agarwal

Jincheng Lin

Raj Kuppa

Hema Prasad

Saiyashwanth Momula

Hemanta Kumar Roy

Chandrashekaran Gurumurthy

Hari Sriraman Pathangi

An image of a portion of a semiconductor die is obtained that shows one or more structures in a first process layer and one or more structures in a second process layer. Using machine learning, a first region is defined on the image that at least partially includes the one or more structures in the first process layer. Also using machine learning, a second region is defined on the image that at least partially includes the one or more structures in the second process layer. An overlay offset between the one or more structures in the first process layer and the one or more structures in the second process layer is calculated using the first region and the second region.

Semiconductor overlay measurements using machine learning

A system for characterizing a specimen is disclosed. In one embodiment, the system includes a characterization sub-system configured to acquire one or more images a specimen, and a controller communicatively coupled to the characterization sub-system. The controller may be configured to: receive training images of one or more features of a specimen from the characterization sub-system; receive training three-dimensional (3D) design images corresponding to the one or more features of the specimen; generate a deep learning predictive model based on the training images and the training 3D design images; receive product 3D design images of one or more features of a specimen; generate simulated images of the one or more features of the specimen based on the product 3D design images with the deep learning predictive model; and determine one or more characteristics of the specimen based on the one or more simulated images.

System and method for rendering SEM images and predicting defect imaging conditions of substrates using 3D design

An initial inspection or critical dimension measurement can be made at various sites on a wafer. The location, design clips, process tool parameters, or other parameters can be used to train a deep learning model. The deep learning model can be validated and these results can be used to retrain the deep learning model. This process can be repeated until the predictions meet a detection accuracy threshold. The deep learning model can be used to predict new probable defect location or critical dimension failure sites.

Systems and methods for predicting defects and critical dimension using deep learning in the semiconductor manufacturing process

A metrology system is disclosed. In one embodiment, the system includes a characterization sub-system configured to acquire one or more images of a specimen. In another embodiment, the system includes a controller configured to: receive one or more training images of a specimen from the characterization sub-system; receive one or more training region-of-interest (ROI) selections within the one or more training images; generate a machine learning classifier based on the one or more training images and the one or more training ROI selections; receive one or more product images of a specimen from the characterization sub-system; generate one or more classified regions of interest with the machine learning classifier; and determine one or more measurements of the specimen within the one or more classified regions of interest.

Deep learning based adaptive regions of interest for critical dimension measurements of semiconductor substrates

Systems and methods for determining location of critical dimension (CD) measurement or inspection are disclosed. Real-time selection of locations to take critical dimension measurements based on potential impact of critical dimension variations at the locations can be performed. The design of a semiconductor device also can be used to predict locations that may be impacted by critical dimension variations. Based on an ordered location list, which can include ranking or criticality, critical dimension can be measured at selected locations. Results can be used to refine a critical dimension location prediction model.

Inspection-guided critical site selection for critical dimension measurement

A deep learning algorithm is used for defect discovery, such as for semiconductor wafers. A care area is inspected with the wafer inspection tool. The deep learning algorithm is used to identify and classify defects in the care area. This can be repeated for remaining care areas, but similar care areas may be skipped to increase throughput.

Defect discovery using electron beam inspection and deep learning with real-time intelligence to reduce nuisance

A wafer topography measurement system can be paired with a scanning electron microscope. A topography threshold can be applied to wafer topography data about the wafer, which was obtained with the wafer topography measurement system. A metrology sampling plan can be generated for the wafer. This metrology sampling plan can include locations in the wafer topography data above the topography threshold. The scanning electron microscope can scan the wafer using the metrology sampling plan and identify defects.

Guided scanning electron microscopy metrology based on wafer topography

Use of care areas in scanning electron microscopes or other review tools can provide improved sensitivity and throughput. A care area is received at a controller of a scanning electron microscope from, for example, an inspector tool. The inspector tool may be a broad band plasma tool. The care area is applied to a field of view of a scanning electron microscope image to identify at least one area of interest. Defects are detected only within the area of interest using the scanning electron microscope. The care areas can be design-based or some other type of care area. Use of care areas in SEM tools can provide improved sensitivity and throughput.

Care areas for improved electron beam defect detection

Deskew for image review, such as SEM review, aligns inspection and review coordinate systems. Deskew can be automated using design files or inspection images. A controller that communicates with a review tool can align a file of the wafer, such as a design file or an inspection image, to an image of the wafer from the review tool; compare alignment sites of the file to alignment sites of the image from the review tool; and generate a deskew transform of coordinates of the alignment sites of the file and coordinates of alignment sites of the image from the review tool. The image of the wafer may not contain defects.

Automatic deskew using design files or inspection images

A technique to identify non-visual defects, such as SEM non-visual defects (SNVs), includes generating an image of a layer of a wafer, evaluating at least one attribute of the image using a classifier, and identifying the non-visual defects on the layer of the wafer. A controller can be configured to identify the non-visual defects using the classifier. This controller can communicate with a defect review tool, such as a scanning electron microscope (SEM).

Range-based real-time scanning electron microscope non-visual binner

A system and method to image a layer of a wafer based on a coordinate of a defect in a pre-layer of the wafer are disclosed. A design file for the current layer can be aligned to the wafer using an image of the current layer. A design file for a previous layer can be aligned to the design file for the current layer.

Growing community of inventors

Lucknow, India

Arpit Yati