IP Library Granted Patent US 12,299,951
Granted Patent B2
US 12,299,951 · App. 17/823,352 · Granted May 13, 2025

Edge center point-based characterization of semiconductor layout designs

Inventors: Hazem Hegazy (Cairo, EG); Ahmed Hamed-Fatehy (Giza, EG); Sara Khalaf (Cairo, EG); Omar ElSewefy (Giza, EG)
Assignee: Siemens Industry Software Inc.
G06V10/44G06T7/70G06T2207/30148
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,299,951
App. No.
17/823,352
Granted
May 13, 2025
Kind
B2
Abstract

A computing system implementing a physical verification tool can identify edges of a geometric pattern located within a search area surrounding a point of interest in a semiconductor layout design, characterize the edges of the geometric pattern based on locations of center points of the edges from the point of interest within the search area, and generate geometrical feature vectors for the point of interest in the semiconductor layout design based on the characterization of the edges of the geometric pattern. The computing system can reconstruct the semiconductor layout design corresponding to the search area surrounding the point of interest using the geometrical feature vectors for the point of interest in the semiconductor layout design.

Claims (40)

1. A method comprising:

identifying, by a computing system, edges of a geometric pattern located within a search area surrounding a point of interest in a semiconductor layout design;

measuring, by the computing system, lengths of the identified edges to determine locations of center points of the edges that correspond to an equal bifurcation of the measured lengths of the edges;

determining, by the computing system, directionalities of the locations of the center points of the edges relative to the point of interest within the search area and determining distances between the locations of the center points of the edges and the point of interest;

characterizing, by the computing system, the edges of the geometric pattern based, at least in part, on the directionalities of the locations of the center points of the edges relative to the point of interest within the search area and the distances between the locations of the center points of the edges and the point of interest; and

generating, by the computing system, geometrical feature vectors for the point of interest in the semiconductor layout design based on the characterization of the edges of the geometric pattern, wherein the geometrical feature vectors are configured to allow reconstruction of the semiconductor layout design corresponding to the search area.

2. The method of claim 1 , further comprising:

determining, by the computing system, an orientation of the edges relative to the point of interest; and

characterizing, by the computing system, the center points of the edges with the orientation of the edges relative to the point of interest.

3. The method of claim 2 , wherein the geometrical feature vectors for the point of interest in the semiconductor layout design include the orientation of the edges relative to the point of interest.

4. The method of claim 1 , wherein characterizing the edges further comprises dividing the search area surround the point of interest into a plurality of measurement regions, and wherein the location of the center points of the edges from the point of interest corresponds to at least one of a set of coordinates or an angle and a distance relative to the measurement regions.

5. The method of claim 1 , further comprising reconstructing, by the computing system, the semiconductor layout design corresponding to the search area surrounding the point of interest using the geometrical feature vectors for the point of interest in the semiconductor layout design.

6. The method of claim 5 , wherein the reconstruction of the semiconductor layout design using the geometrical feature vectors for the point of interest is lossless.

7. A system comprising:

a memory system configured to store computer-executable instructions; and

a computing system, in response to execution of the computer-executable instructions, is configured to:

identify edges of at least one geometric pattern located within a search area surrounding a point of interest in a semiconductor layout design;

measure lengths of the identified edges to determine locations of center points of the edges that correspond to an equal bifurcation of the measured lengths of the edges;

determine directionalities of the locations of the center points of the edges relative to the point of interest within the search area and determining distances between the locations of the center points of the edges and the point of interest;

characterize the edges of the geometric pattern based, at least in part, on the directionalities of the locations of the center points of the edges relative to the point of interest within the search area and the distances between the locations of the center points of the edges and the point of interest; and

generate geometrical feature vectors for the point of interest in the semiconductor layout design based on the characterization of the edges of the geometric pattern, wherein the geometrical feature vectors are configured to allow reconstruction of the semiconductor layout design corresponding to the search area.

8. The system of claim 7 , wherein the computing system, in response to execution of the computer-executable instructions, is further configured to:

determine an orientation of the edges relative to the point of interest; and

characterize the center points of the edges with the orientation of the edges relative to the point of interest.

9. The system of claim 8 , wherein the geometrical feature vectors for the point of interest in the semiconductor layout design include the orientation of the edges relative to the point of interest.

10. The system of claim 7 , wherein the computing system, in response to execution of the computer-executable instructions, is further configured to characterize the edges by dividing the search area surround the point of interest into a plurality of measurement regions, and wherein the locations of the center points of the edges from the point of interest corresponds to at least one of a set of coordinates or an angle and a distance relative to the measurement regions.

11. The system of claim 7 , wherein the computing system, in response to execution of the computer-executable instructions, is further configured to reconstruct the semiconductor layout design corresponding to the search area surrounding the point of interest using the geometrical feature vectors for the point of interest in the semiconductor layout design, wherein the reconstruction of the semiconductor layout design using the geometrical feature vectors for the point of interest is lossless.

12. An apparatus comprising at least one computer-readable memory device storing instructions configured to cause one or more processing devices to perform operations comprising:

identifying edges of at least one geometric pattern located within a search area surrounding a point of interest in a semiconductor layout design;

measuring lengths of the identified edges to determine locations of center points of the edges that correspond to an equal bifurcation of the measured lengths of the edges;

determining directionalities of the locations of the center points of the edges relative to the point of interest within the search area and determining distances between the locations of the center points of the edges and the point of interest;

characterizing the edges of the geometric pattern based, at least in part, on the directionalities of the locations of the center points of the edges relative to the point of interest within the search area and the distances between the locations of the center points of the edges and the point of interest; and

generating geometrical feature vectors for the point of interest in the semiconductor layout design based on the characterization of the edges of the geometric pattern, wherein the geometrical feature vectors are configured to allow reconstruction of the semiconductor layout design corresponding to the search area.

13. The apparatus of claim 12 , wherein the instructions are configured to cause one or more processing devices to perform operations further comprising:

determining an orientation of the edges relative to the point of interest; and

characterizing the center points of the edges with the orientation of the edges relative to the point of interest.

14. The apparatus of claim 13 , wherein the geometrical feature vectors for the point of interest in the semiconductor layout design include the orientation of the edges relative to the point of interest.

15. The apparatus of claim 12 , wherein characterizing the center points of the edges further comprises dividing the search area surround the point of interest into a plurality of measurement regions, and wherein the locations of the center points of the edges from the point of interest corresponds to at least one of a set of coordinates or an angle and a distance relative to the measurement regions.

16. The apparatus of claim 12 , wherein the instructions are configured to cause one or more processing devices to perform operations further comprising reconstructing the semiconductor layout design corresponding to the search area surrounding the point of interest using the geometrical feature vectors for the point of interest in the semiconductor layout design.

17. The apparatus of claim 16 , wherein the reconstruction of the semiconductor layout design using the geometrical feature vectors for the point of interest is lossless.

Assignments (4)
CHANGE OF NAME Recorded Apr 11, 2025
From: MENTOR GRAPHICS EGYPT
To: SIEMENS INDUSTRY SOFTWARE (A LIMITED LIABILITY COMPANY UNDER THE PRIVATE FREE ZONES REGIME
Reel/Frame 070864/0014 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 23, 2024
From: HEGAZY, HAZEM; HAMED-FATEHY, AHMED; KHALAF, SARA; ELSEWEFY, OMAR
To: SIEMENS INDUSTRY SOFTWARE INC.
Reel/Frame 068385/0460 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 23, 2024
From: SIEMENS INDUSTRY SOFTWARE (A LIMITED LIABILITY COMPANY UNDER THE PRIVATE FREE ZONES REGIME)
To: SIEMENS INDUSTRY SOFTWARE INC.
Reel/Frame 068385/0552 →
MERGER AND CHANGE OF NAME Recorded Aug 23, 2024
From: MENTOR GRAPHICS CORPORATION; SIEMENS INDUSTRY SOFTWARE INC.
To: SIEMENS INDUSTRY SOFTWARE INC.
Reel/Frame 068385/0711 →
Continuity (1)
Related Publication 20240071038A1 · Feb 29, 2024
References Cited (15)
US 8832621B1 · Gennari · 2014 [cited by examiner]
US 11017147B2 · Hegazy · 2021 [cited by examiner]
US 20070230770A1 · Kulkarni · 2007 [cited by examiner]
US 20080320421A1 · Demaris · 2008 [cited by examiner]
US 20200081352A1 · Kim · 2020 [cited by examiner]
US 20210064717A1 · Hegazy · 2021 [cited by examiner]
Yang, Haoyu, et al. “Detecting multi-layer layout hotspots with adaptive squish patterns.” Proceedings of the 24th Asia and South Pacific Design Automation Conference. Jan. 21, 2019. [cited by applicant]
Pathak, Piyush, et al. “Methodology to extract, data mine and score geometric constructs from physical design layouts for analysis and applications in semiconductor manufacturing”. Design-Process-Technology Co-optimizat… [cited by applicant]
Haoyu Yang, et al. “DeePattern: Layout Pattern Generation with Transforming Convolutional Auto-Encoder”. DAC '19—Association for Computing Machinery, Las Vegas, NV, USA, Jun. 2, 2019. [cited by applicant]
Punitha Selvam, et al., “Deep learning-based hotspot prediction of via printability in process window corners”, Proceedings vol. 11614, Design-Process-Technology Co-optimization XV, Feb. 22, 2021. [cited by applicant]
Fadi Batarseh, et al., “Pattern similarity profiling using semi-supervised learning algorithm”, Proceedings vol. 11614, Design-Process-Technology Co-optimization XV, Feb. 22, 2021. [cited by applicant]
Haoyu Yang, et al., “Hotspot Detection Using Squish-Net”, Proc. SPIE 10962, Design-Process-Technology Co-optimization for Manufacturability XIII, Mar. 20, 2019. [cited by applicant]
Jason P. Cain, Moutaz Fakhry, Piyush Pathak, Jason Sweis, Frank E. Gennari, Ya-Chieh Lai, “Pattern-based analytics to estimate and track yield risk of designs down to 7nm” Proc. SPIE 10148, Design-Process-Technology Co-… [cited by applicant]
He, Kaiming, et al. “Deep residual learning for image recognition.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. [cited by applicant]
Yang, Haoyu, et al. “Lithography hotspot detection: From shallow to deep learning.” 2017 30th IEEE International System-on-Chip Conference (SOCC). Sep. 5, 2017. [cited by applicant]