US 12,450,408 B2
Machine learning for selecting initial source shapes for source mask optimization
William A. Stanton, Meridian, ID (US); Sylvain Berthiaume, Gatineau (CA); Hans-Jürgen Stock, Dachau (DE); and Jay A. Hiserote, Hillsboro, OH (US)
Assigned to Synopsys, Inc., Sunnyvale, CA (US)
Filed by Synopsys, Inc., Mountain View, CA (US)
Filed on Jun. 1, 2022, as Appl. No. 17/829,714.
Application 17/829,714 is a continuation of application No. PCT/US2022/030384, filed on May 20, 2022.
Claims priority of provisional application 63/191,493, filed on May 21, 2021.
Prior Publication US 2022/0382144 A1, Dec. 1, 2022
Int. Cl. G06F 30/27 (2020.01); G03F 1/70 (2012.01); G03F 7/00 (2006.01); G06F 30/30 (2020.01); G06F 30/398 (2020.01); G06N 3/08 (2023.01)
CPC G06F 30/27 (2020.01) [G03F 1/70 (2013.01); G03F 7/705 (2013.01); G03F 7/706841 (2023.05); G06F 30/398 (2020.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a layout of a lithographic mask;
applying, by a processor, a machine learning model to infer source shapes from the layout of the lithographic mask; and
providing the inferred source shapes as initial source shapes that are used as a starting point for a source mask optimization process.