Methods for training machine learning model for computation lithography
US-2020380362-A1 · Dec 3, 2020 · US
US12287567B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12287567-B2 |
| Application number | US-202418427577-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jan 30, 2024 |
| Priority date | Jan 28, 2022 |
| Publication date | Apr 29, 2025 |
| Grant date | Apr 29, 2025 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
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.
Opening claim text (preview).
What is claimed: 1. A method for reticle enhancement technology (RET) for transferring a pattern to a substrate, the method comprising: inputting a mask exposure information; determining a mask 3D (M3D) effect, wherein the determining the M3D effect includes determining a variable side wall angle (VSA); calculating a calculated pattern on the substrate using the M3D effect; and modifying the mask exposure information based on the calculated pattern on the substrate. 2. The method of claim 1 , wherein the determining the M3D effect uses a neural network. 3. The method of claim 2 , wherein the determining the M3D effect uses a transfer function. 4. The method of claim 1 , wherein the calculating the calculated pattern on the substrate includes lithography simulation. 5. The method of claim 1 , further comprising calculating a mask 2D (M2D) effect from the mask exposure information, wherein the determining the M3D effect is inferenced from the M2D effect. 6. The method of claim 5 , further comprising iterating: 1) the calculating the M2D effect, 2) the determining the M3D effect, 3) the calculating the calculated pattern and 4) the modifying the mask exposure information. 7. The method of claim 5 , wherein the M2D effect further comprises optical proximity correction (OPC). 8. The method of claim 1 , further comprising: inputting a target substrate pattern; and calculating the mask exposure information from the target substrate pattern using reticle enhancement technology (RET) prior to inputting the mask exposure information. 9. The method of claim 8 , wherein the RET comprises inverse lithography technology (ILT). 10. The method of claim 1 , wherein the calculating of the calculated pattern on the substrate comprises extreme ultraviolet (EUV) simulation. 11. The method of claim 1 , wherein the determining the M3D effect includes calculating a dose margin from the mask exposure information. 12. The method of claim 1 , wherein the mask exposure information is for a multi-beam exposure system. 13. A method for calculating a pattern to be formed on a substrate using optical lithography with a mask, the method comprising: inputting a mask exposure information that will form a mask pattern on the mask; calculating a variable side wall angle (VSA); calculating the pattern on the substrate using the VSA, wherein the calculating the pattern on the substrate includes a mask 3D (M3D) effect; and modifying the mask exposure information based on the calculated pattern on the substrate. 14. The method of claim 13 , wherein the variable side wall angle is calculated using a neural network. 15. The method of claim 13 , wherein the calculating the pattern on the substrate comprises lithography simulation. 16. The method of claim 13 , wherein the calculating the pattern on the substrate comprises extreme ultraviolet (EUV) simulation. 17. The method of claim 13 , wherein the pattern on the substrate is for a semiconductor device. 18. The method of claim 13 , further comprising calculating the mask pattern from the mask exposure information, wherein the calculating the pattern on the substrate uses the mask pattern. 19. The method of claim 13 , further comprising determining a dose margin from the mask exposure information, wherein the calculating the VSA uses the dose margin. 20. A system for reticle enhancement technology (RET) comprising: a. a device configured to receive a mask exposure information; b. a device configured to determine a mask 3D (M3D) effect, wherein the determining the M3D effect includes determining a variable side wall angle (VSA); and c. a device configured to calculate a calculated pattern on a substrate using the M3D effect. 21. The system of claim 20 , further comprising a device configured to calculate a mask 2D (M2D) effect from the mask exposure information, wherein the determining the M3D effect uses the M2D effect. 22. The system of claim 20 , wherein the device configured to determine the M3D effect uses a neural network.
Modelling or simulating from physical phenomena up to complete wafer processes or whole workflow in wafer productions · CPC title
Optical proximity correction [OPC] · CPC title
Masks or mask blanks for imaging by radiation of 100nm or shorter wavelength, e.g. X-ray masks, extreme ultraviolet [EUV] masks; Preparation thereof · CPC title
Adapting basic layout or design of masks to lithographic process requirements, e.g., second iteration correction of mask patterns for imaging · CPC title
Masks having proximity correction features; Preparation thereof, e.g. optical proximity correction [OPC] design processes · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.