Optical proximity correction based on combining inverse lithography technology with pattern classification

Patent metadata

Field	Value
Publication number	US-12411405-B2
Application number	US-202217823679-A
Country	US
Kind code	B2
Filing date	Aug 31, 2022
Priority date	Sep 29, 2021
Publication date	Sep 9, 2025
Grant date	Sep 9, 2025

Abstract

Various aspects of the present disclosed technology relate to techniques for inverse-lithography-technology-based optical proximity correction. A layout design is received. A machine learning-based clustering process is then performed to separate layout features in the layout design into groups of layout features. For layout features in each of the groups of layout features, preliminary corrections are determined. The determination may be based on inverse lithography technology. The preliminary corrections are applied to the layout design to generate a pre-processed layout design. An inverse lithography technology process is performed on the pre-processed layout design to generate a processed layout design. Masks can be manufactured based on the processed layout design.

First claim

What is claimed is:

1. A method, executed by at least one processor of a computer, comprising:
receiving a layout design;
performing a machine learning-based clustering process to separate layout features in the layout design into groups of layout features;
determining preliminary corrections for layout features in each of the groups of layout features;
applying the preliminary corrections to the layout design to generate a pre-processed layout design;
performing an inverse lithography technology process on the pre-processed layout design to generate a processed layout design; and
storing information of the processed layout design.

2. The method recited in claim 1 , wherein the machine learning-based clustering process comprises:
extracting a feature vector for each of the layout features; and
mapping the set of feature vectors into hyperboxes of a hyperspace.

3. The method recited in claim 1 , wherein the determining preliminary corrections is based on performing another inverse lithography technology process for each of the groups of layout features.

4. The method recited in claim 3 , wherein the another inverse lithography technology process and the inverse lithography technology process employ the same inverse lithography technology model.

5. The method recited in claim 1 , wherein the performing an inverse lithography technology process comprises:
determining parameters (recipe) for the inverse lithography technology process based on layout features selected from each of the groups of layout features.

6. The method recited in claim 1 , wherein the performing inverse lithography technology process comprises:
performing a first inverse lithography technology sub-process to generate sub-resolution assist features; and
performing a second inverse lithography technology sub-process to generate the processed layout design.

7. The method recited in claim 1 , further comprising:
manufacturing masks based on the processed layout design.

8. One or more non-transitory computer-readable media storing computer-executable instructions for causing one or more processors to perform a method, the method comprising:
receiving a layout design;
performing a machine learning-based clustering process to separate layout features in the layout design into groups of layout features;
determining preliminary corrections for layout features in each of the groups of layout features;
applying the preliminary corrections to the layout design to generate a pre-processed layout design;
performing an inverse lithography technology process on the pre-processed layout design to generate a processed layout design; and
storing information of the processed layout design.

9. The one or more non-transitory computer-readable media recited in claim 8 , wherein the machine learning-based clustering process comprises:
extracting a feature vector for each of the layout features; and
mapping the set of feature vectors into hyperboxes of a hyperspace.

10. The one or more non-transitory computer-readable media recited in claim 8 , wherein the determining preliminary corrections is based on performing another inverse lithography technology process for each of the groups of layout features.

11. The one or more non-transitory computer-readable media recited in claim 10 , wherein the another inverse lithography technology process and the inverse lithography technology process employ the same inverse lithography technology model.

12. The one or more non-transitory computer-readable media recited in claim 8 , wherein the performing an inverse lithography technology process comprises:
determining parameters (recipe) for the inverse lithography technology process based on layout features selected from each of the groups of layout features.

13. The one or more non-transitory computer-readable media recited in claim 8 , wherein the performing inverse lithography technology process comprises:
performing a first inverse lithography technology sub-process to generate sub-resolution assist features; and
performing a second inverse lithography technology sub-process to generate the processed layout design.

14. A system, comprising:
one or more processors, the one or more processors programmed to perform a method, the method comprising:
receiving a layout design;
performing a machine learning-based clustering process to separate layout features in the layout design into groups of layout features;
determining preliminary corrections for layout features in each of the groups of layout features;
applying the preliminary corrections to the layout design to generate a pre-processed layout design;
performing an inverse lithography technology process on the pre-processed layout design to generate a processed layout design; and
storing information of the processed layout design.

15. The system recited in claim 14 , wherein the machine learning-based clustering process comprises:
extracting a feature vector for each of the layout features; and
mapping the set of feature vectors into hyperboxes of a hyperspace.

16. The system recited in claim 14 , wherein the determining preliminary corrections is based on performing another inverse lithography technology process for each of the groups of layout features.

17. The system recited in claim 16 , wherein the another inverse lithography technology process and the inverse lithography technology process employ the same inverse lithography technology model.

18. The system recited in claim 14 , wherein the performing an inverse lithography technology process comprises:
determining parameters (recipe) for the inverse lithography technology process based on layout features selected from each of the groups of layout features.

19. The system recited in claim 14 , wherein the performing inverse lithography technology process comprises:
performing a first inverse lithography technology sub-process to generate sub-resolution assist features; and
performing a second inverse lithography technology sub-process to generate the processed layout design.

Assignees

• Siemens Ind Software Inc

Inventors

• Ma Yuansheng
• Hong Le
• Wu Rui
• Lei Junjiang

Classifications

• G03F1/70

  Adapting basic layout or design of masks to lithographic process requirements, e.g., second iteration correction of mask patterns for imaging · CPC title

• G06F30/27

  using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model · CPC title

• G06F30/398

  Design verification or optimisation, e.g. using design rule check [DRC], layout versus schematics [LVS] or finite element methods [FEM] (optical proximity correction [OPC] design processes G03F1/36) · CPC title

• G03F1/36 Primary

  Masks having proximity correction features; Preparation thereof, e.g. optical proximity correction [OPC] design processes · CPC title