摘要:
Described herein is a method of determining assist features for a mask pattern. The method includes obtaining (i) a target pattern comprising a plurality of target features, wherein each of the plurality of target features comprises a plurality of target edges, and (ii) a trained sequence-to-sequence machine leaning (ML) model (e.g., long short term memory, Gated Recurrent Units, etc.) configured to determine sub-resolution assist features (SRAFs) for the target pattern. For a target edge of the plurality of target edges, geometric information (e.g., length, width, distances between features, etc.) of a subset of target features surrounding the target edge is determined. Using the geometric information as input, the ML model generates SRAFs to be placed around the target edge.
摘要:
A method including: obtaining a thin-mask transmission function of a patterning device and a M3D model for a lithographic process, wherein the thin-mask transmission function represents a continuous transmission mask and the M3D model at least represents a portion of M3D attributable to multiple edges of structures on the patterning device; determining a M3D mask transmission function of the patterning device by using the thin-mask transmission function and the M3D model; and determining an aerial image produced by the patterning device and the lithographic process, by using the M3D mask transmission function.
摘要:
A method for determining an image of a mask pattern in a resist coated on a substrate, the method including determining an aerial image of the mask pattern at substrate level; and convolving the aerial image with at least two orthogonal convolution kernels to determine a resist image that is representative of the mask pattern in the resist.
摘要:
Methods of generating a characteristic pattern for a patterning process and training a machine learning model. A method of training a machine learning model configured to generate a characteristic pattern for a mask pattern includes obtaining (i) a reference characteristic pattern that meets a satisfactory threshold related to manufacturing of the mask pattern, and (ii) a continuous transmission mask (CTM) for use in generating the mask pattern; and training, based on the reference characteristic pattern and the CTM, the machine learning model such that a first metric between the characteristic pattern and the CTM, and a second metric between the characteristic pattern and the reference characteristic pattern is reduced.
摘要:
The present disclosure relates to lithographic apparatuses and processes, and more particularly to tools for optimizing illumination sources and masks for use in lithographic apparatuses and processes. According to certain aspects, the present disclosure significantly speeds up the convergence of the optimization by allowing direct computation of gradient of the cost function. According to other aspects, the present disclosure allows for simultaneous optimization of both source and mask, thereby significantly speeding the overall convergence. According to still further aspects, the present disclosure allows for free-form optimization, without the constraints required by conventional optimization techniques.
摘要:
A method including: obtaining a characteristic of a portion of a design layout; determining a characteristic of M3D of a patterning device including or forming the portion; and training, by a computer, a neural network using training data including a sample whose feature vector includes the characteristic of the portion and whose supervisory signal includes the characteristic of the M3D. Also disclosed is a method including: obtaining a characteristic of a portion of a design layout; obtaining a characteristic of a lithographic process that uses a patterning device including or forming the portion; determining a characteristic of a result of the lithographic process; training, by a computer, a neural network using training data including a sample whose feature vector includes the characteristic of the portion and the characteristic of the lithographic process, and whose supervisory signal includes the characteristic of the result.
摘要:
Methods according to the present invention provide computationally efficient techniques for designing gauge patterns for calibrating a model for use in a simulation process. More specifically, the present invention relates to methods of designing gauge patterns that achieve complete coverage of parameter variations with minimum number of gauges and corresponding measurements in the calibration of a lithographic process utilized to image a target design having a plurality of features. According to some aspects, a method according to the invention includes transforming the space of model parametric space (based on CD sensitivity or Delta TCCs), then iteratively identifying the direction that is most orthogonal to existing gauges' CD sensitivities in this new space, and determining most sensitive line width/pitch combination with optimal assist feature placement which leads to most sensitive CD changes along that direction in model parametric space.
摘要:
Systems and methods for tuning photolithographic processes are described. A model of a target scanner is maintained defining sensitivity of the target scanner with reference to a set of tunable parameters. A differential model represents deviations of the target scanner from the reference. The target scanner may be tuned based on the settings of the reference scanner and the differential model. Performance of a family of related scanners may be characterized relative to the performance of a reference scanner. Differential models may include information such as parametric offsets and other differences that may be used to simulate the difference in imaging behavior.
摘要:
A method for calibrating a process model and training an inverse process model of a patterning process. The training method includes obtaining a first patterning device pattern from simulation of an inverse lithographic process that predicts a patterning device pattern based on a wafer target layout, receiving wafer data corresponding to a wafer exposed using the first patterning device pattern, and training an inverse process model configured to predict a second patterning device pattern using the wafer data related to the exposed wafer and the first patterning device pattern.
摘要:
The present invention provides a number of innovations in the area of computational process control (CPC). CPC offers unique diagnostic capability during chip manufacturing cycle by analyzing temporal drift of a lithography apparatus/ process, and provides a solution towards achieving performance stability of the lithography apparatus/process. Embodiments of the present invention enable optimized process windows and higher yields by keeping performance of a lithography apparatus and/or parameters of a lithography process substantially close to a pre-defined baseline condition. This is done by comparing the measured temporal drift to a baseline performance using a lithography process simulation model. Once in manufacturing, CPC optimizes a scanner for specific patterns or reticles by leveraging wafer metrology techniques and feedback loop, and monitors and controls, among other things, overlay and/or CD uniformity (CDU) performance over time to continuously maintain the system close to the baseline condition.