IP Library › Granted Patent US 11,861,286
Granted Patent B2
US 11,861,286 · App. 17/362,085 · Granted Jan 2, 2024

Segregating defects based on computer-aided design (CAD) identifiers associated with the defects

Inventors: Ankush B. Oberai (Fremont, CA); Kiran U. Agashe (Mumbai, IN)
Assignee: Synopsys, Inc.
G06F30/398G06F30/27G06F30/392G06F30/394G06F2119/02
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 11,861,286
App. No.
17/362,085
Granted
Jan 2, 2024
Kind
B2
Abstract

For each defect in a set of defects, the defect may be associated with a defect attribute constructed from a set of computer-aided design (CAD) identifiers associated with polygons in an integrated circuit (IC) design that overlap with a defect area of the defect. Next, the set of defects may be segregated into defect groups based on the associated defect attributes. The defect groups may be used to perform additional processing on the set of defects.

Claims (33)

1. A method, comprising:

for each defect in a set of defects, associating the defect with a defect attribute constructed from a set of computer-aided design (CAD) identifiers associated with polygons in an integrated circuit (IC) design that overlap with a defect area of the defect;

segregating, by a processor, the set of defects into defect groups based on the associated defect attributes, wherein segregating the set of defects into defect groups based on the associated defect attributes comprises using a machine learning (ML) clustering technique; and

using the defect groups to perform additional processing on the set of defects, wherein the additional processing comprises analyzing defects in a given defect group to identify a root cause for the defects in the given defect group.

2. The method of claim 1 , wherein the set of CAD identifiers includes a set of cell identifiers that include polygons that overlap with the defect area.

3. The method of claim 1 , wherein the set of CAD identifiers includes one or more cell identifiers in conjunction with one or more region identifiers that include polygons that overlap with the defect area.

4. The method of claim 1 , wherein the set of CAD identifiers includes a set of net identifiers that include polygons that overlap with the defect area.

5. The method of claim 1 , wherein the set of CAD identifiers includes one or more net identifiers in conjunction with one or more region identifiers that include polygons that overlap with the defect area.

6. The method of claim 1 , wherein using the defect groups to perform additional processing on the set of defects comprises sampling defects for further review based on defect groups.

7. The method of claim 1 , wherein using the defect groups to perform additional processing on the set of defects comprises identifying a hotspot pattern associated with a defect group.

8. The method of claim 7 , further comprising using the hotspot pattern to identify additional hotspot locations in the IC design.

9. The method of claim 7 , further comprising using the hotspot pattern to filter defects.

10. A non-transitory computer-readable storage medium comprising stored instructions, which when executed by a processor, cause the processor to:

for each defect in a set of defects, associate the defect with a defect attribute constructed from a set of computer-aided design (CAD) identifiers associated with polygons in an integrated circuit (IC) design that overlap with a defect area of the defect;

segregate the set of defects into defect groups based on the associated defect attributes, wherein segregating the set of defects into defect groups based on the associated defect attributes comprises using a machine learning (ML) clustering technique; and

use the defect groups to perform additional processing on the set of defects.

11. The non-transitory computer-readable storage medium of claim 10 , wherein the set of CAD identifiers includes a set of cell identifiers that include polygons that overlap with the defect area.

12. The non-transitory computer-readable storage medium of claim 11 , wherein the set of CAD identifiers includes one or more cell identifiers in conjunction with one or more region identifiers that include polygons that overlap with the defect area.

13. The non-transitory computer-readable storage medium of claim 11 , wherein the set of CAD identifiers includes a set of net identifiers that include polygons that overlap with the defect area.

14. The non-transitory computer-readable storage medium of claim 11 , wherein the set of CAD identifiers includes one or more net identifiers in conjunction with one or more region identifiers that include polygons that overlap with the defect area.

15. The non-transitory computer-readable storage medium of claim 11 , wherein using the defect groups to perform additional processing on the set of defects comprises sampling defects for further review based on defect groups.

16. The non-transitory computer-readable storage medium of claim 11 , wherein using the defect groups to perform additional processing on the set of defects comprises analyzing defects in a given defect group to identify a root cause for the defects in the given defect group.

17. The non-transitory computer-readable storage medium of claim 11 , wherein using the defect groups to perform additional processing on the set of defects comprises identifying a hotspot pattern associated with a defect group.

18. A system comprising:

a memory storing instructions; and

a processor, coupled with the memory and to execute the instructions, the instructions when executed cause the processor to:

for each defect in a set of defects,

detect polygons in an integrated circuit (IC) design that overlap with a defect area of the defect,

extract a set of computer-aided design (CAD) identifiers associated with the polygons,

construct a defect attribute based on the CAD identifiers, and

associate the defect with the defect attribute;

use a machine learning (ML) clustering technique to segregate the set of defects into defect groups based on the associated defect attributes; and

use the defect groups to perform additional processing on the set of defects.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 15, 2021
From: OBERAI, ANKUSH B.; AGASHE, KIRAN U.
To: SYNOPSYS, INC.
Reel/Frame 056866/0525 →
Continuity (2)
Provisional Application 63046425 · Jun 30, 2020
Related Publication 20210406441A1 · Dec 30, 2021