Abstract: A calibrated lithographic model may be used to generate a lithographic model output based on an integrated circuit (IC) design layout. Next, at least a chemical parameter may be extracted from the lithographic model output. A calibrated defect rate model may then be used to predict a defect rate for the IC design layout based on the chemical parameter.

Abstract: A method of generating a mask used in fabrication of a semiconductor device includes, in part, selecting a source candidate, generating a process simulation model that includes a defect rate in response to the selected source candidate, performing a first optical proximity correction (OPC) on the data associated with the mask in response to the process simulation model, assessing one or more lithographic evaluation metrics in response to the OPC mask data, computing a cost in response to the assessed one or more lithographic evaluation metrics, and determining whether the computed cost satisfies a threshold condition. In response to the determination that the computed cost does not satisfy the threshold condition, a different source candidate may be selected.

Abstract: A computational lithography process uses machine learning models. An aerial image produced by a lithographic mask is first calculated using a two-dimensional model of the lithographic mask. This first aerial image is applied to a first machine learning model, which infers a second aerial image. The first machine learning model was trained using a training set that includes aerial images calculated using a more accurate three-dimensional model of lithographic masks. The two-dimensional model is faster to compute than the three-dimensional model but it is less accurate. The first machine learning model mitigates this inaccuracy.

Abstract: Initial source shapes for source mask optimization are determined based on a layout of the lithographic mask. In one approach, a layout of a lithographic mask is received. Different sections of the lithographic mask, referred to as clips, are selected. These clips are applied to a machine learning model which infers source shapes from the clips. The inferred source shapes are used as the initial source shapes for source mask optimization.

Abstract: A method of generating a mask used in fabrication of a semiconductor device includes, in part, selecting a source candidate, generating a process simulation model that includes a defect rate in response to the selected source candidate, performing a first optical proximity correction (OPC) on the data associated with the mask in response to the process simulation model, assessing one or more lithographic evaluation metrics in response to the OPC mask data, computing a cost in response to the assessed one or more lithographic evaluation metrics, and determining whether the computed cost satisfies a threshold condition. In response to the determination that the computed cost does not satisfy the threshold condition, a different source candidate may be selected.

Abstract: A calibrated lithographic model may be used to generate a lithographic model output based on an integrated circuit (IC) design layout. Next, at least a chemical parameter may be extracted from the lithographic model output. A calibrated defect rate model may then be used to predict a defect rate for the IC design layout based on the chemical parameter.