Multi-controller inspection system

Patent metadata

Field	Value
Publication number	US-11415526-B2
Application number	US-202017136919-A
Country	US
Kind code	B2
Filing date	Dec 29, 2020
Priority date	May 6, 2020
Publication date	Aug 16, 2022
Grant date	Aug 16, 2022

Abstract

An inspection system is disclosed. The inspection system includes a shared memory configured to receive image data from a defect inspection tool and a controller communicatively coupled to the shared memory. The controller includes a host image module configured to apply one or more general-purpose defect-inspection algorithms to the image data using central-processing unit (CPU) architectures, a results module configured to generate inspection data for defects identified by the host image module, and secondary image module(s) configured to apply one or more targeted defect-inspection algorithms to the image data. The secondary image module(s) employ flexible sampling of the image data to match a data processing rate of the host image module within a selected tolerance. The flexible sampling of the image data is adjusted responsive to the inspection data generated by the results module and the host image module.

First claim

What is claimed:

1. An inspection system comprising:
a shared memory communicatively coupled to a defect inspection tool, wherein the shared memory is configured to receive image data generated by the defect inspection tool; and
a controller communicatively coupled to the shared memory including:
a host image module, wherein the host image module comprises program instructions maintained in memory and configured to cause one or more processors to apply one or more general-purpose defect-inspection algorithms to the image data, wherein the one or more general-purpose defect-inspection algorithms are configured to identify a plurality of defect types in the image data using central-processing unit (CPU) architectures, wherein the host image module fully samples the image data;
one or more secondary image modules, wherein the one or more secondary image modules comprise program instructions maintained in memory and configured to cause one or more processors to apply one or more targeted defect-inspection algorithms to the image data, wherein at least some of the one or more targeted defect-inspection algorithms are tailored to identify a targeted subset of the plurality of defect types in the image data, wherein the one or more secondary image modules employ flexible sampling of the image data to match a data processing rate of the host image module within a selected tolerance; and
a results module, wherein the results module comprises program instructions maintained in memory and configured to cause one or more processors to generate inspection data for defects identified by the host image module or the one or more secondary image modules.

2. The inspection system of claim 1 , wherein at least some of the one or more secondary image modules utilize CPU architectures to implement at least some of the one or more targeted defect-inspection algorithms.

3. The inspection system of claim 1 , wherein at least some of the one or more secondary image modules utilize graphical-processing unit (GPU) architectures to implement at least some of the one or more targeted defect-inspection algorithms.

4. The inspection system of claim 1 , wherein at least some of the one or more secondary image modules utilize non-CPU math accelerators to implement at least some of the one or more targeted defect-inspection algorithms.

5. The inspection system of claim 1 , wherein at least some of the one or more secondary image modules utilize a neural network to implement at least some of the one or more targeted defect-inspection algorithms.

6. The inspection system of claim 1 , wherein at least some of the one or more secondary image modules utilize deep-learning to implement at least some of the one or more targeted defect-inspection algorithms.

7. The inspection system of claim 1 , wherein at least one of the one or more secondary image modules is configured to identify one or more known defect types of the plurality of defect types and is further configured to employ flexible sampling of the image data to sample one or more care areas in the image data.

8. The inspection system of claim 7 , wherein the one or more care areas include portions of the image data associated with locations susceptible to the one or more known defect types.

9. The inspection system of claim 1 , wherein the controller further includes a sample plan module configured to generate a plurality of inspection jobs based on the image data.

10. The inspection system of claim 9 , wherein at least one of the one or more secondary image modules is configured to employ flexible sampling of the image data by disregarding one or more inspection jobs to match the data processing rate of the host image module within the selected tolerance.

11. The inspection system of claim 1 , wherein the inspection data includes pixel-level data.

12. The inspection system of claim 1 , wherein the inspection data includes separate datasets for at least some of the one or more general-purpose defect-inspection algorithms or at least some of the one or more targeted defect-inspection algorithms.

13. The inspection system of claim 1 , wherein the inspection data includes a common dataset for the one or more general-purpose defect-inspection algorithms and the one or more targeted defect-inspection algorithms.

14. The inspection system of claim 13 , wherein the inspection data for an identified defect includes an indication of which of the one or more general-purpose defect-inspection algorithms or the one or more targeted defect-inspection algorithms identified the identified defect.

15. An inspection system comprising:
a shared memory communicatively coupled to a defect inspection tool, wherein the shared memory is configured to receive image data generated by the defect inspection tool; and
a controller communicatively coupled to the shared memory including:
a host image module, wherein the host image module comprises program instructions maintained in memory and configured to cause one or more processors to apply one or more general-purpose defect-inspection algorithms to the image data, wherein the one or more general-purpose defect-inspection algorithms are configured to identify a plurality of defect types in the image data using central-processing unit (CPU) architectures, wherein the host image module fully samples the image data;
a results module, wherein the results module comprises program instructions maintained in memory and configured to cause one or more processors to generate inspection data for defects identified by the host image module; and
one or more secondary image modules, wherein the one or more secondary image modules comprise program instructions maintained in memory and configured to cause one or more processors to apply one or more targeted defect-inspection algorithms to the image data, wherein at least some of the one or more targeted defect-inspection algorithms are tailored to identify a targeted subset of the plurality of defect types in the image data, wherein the one or more secondary image modules employ flexible sampling of the image data to match a data processing rate of the host image module within a selected tolerance,
wherein the flexible sampling of the image data is adjusted responsive to the inspection data generated by the results module and the host image module,
wherein the results module is further configured to generate inspection data for defects identified by the one or more secondary image modules.

16. The inspection system of claim 15 , wherein at least one of the one or more secondary image modules is configured to identify one or more known defect types of the plurality of defect types and is further configured to employ the flexible sampling of the image data to sample one or more care areas in the image data.

17. The inspection system of claim 16 , wherein the one or more care areas include portions of the image data associated with locations susceptible to the one or more known defect types.

18. The inspection system of claim 16 , wherein inspection data generated by the results module indicates zero or no defects in the one or more care areas inspected by the one or more general-purpose defect-inspection algorithms,
wherein the one or more care areas are flexibly sampled from the image data for the one or more targeted defect-inspection algorithms based on the indication of zero or no defects in the one or more care areas inspected by the one or more general-purpose defect-inspection algorithms,
wherein the one or more targeted defect-inspection algorithms verify the indication of

Assignees

• Kla Corp

Inventors

• Duffy Brian
• Roulo Mark
• Mathew Ashok
• Zhang Jing
• Bhaskar Kris

Classifications

• G06T2207/30148

  Semiconductor; IC; Wafer · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/10061

  from scanning electron microscope · CPC title

• G06T7/0004 Primary

  Industrial image inspection · CPC title

• G01N21/9501 Primary

  Semiconductor wafers (manufacturing processes per se of semiconductor devices implementing a measuring step H10P74/20) · CPC title