Creating knowledge base for optical proximity correction to reduce sub-resolution assist feature printing

Patent metadata

Field	Value
Publication number	US-2018196340-A1
Application number	US-201715401299-A
Country	US
Kind code	A1
Filing date	Jan 9, 2017
Priority date	Jan 9, 2017
Publication date	Jul 12, 2018
Grant date	—

Abstract

Embodiments of the present disclosure include methods, program products, and systems for creating a knowledge base for optical proximity correction (OPC). Methods according to the disclosure can include: fabricating a circuit using a proposed IC layout; identifying a plurality of features in an image of the fabricated circuit; predicting, based on the identifying and a predictive algorithm, whether the fabricated circuit includes a printed sub-resolution assist feature (SRAF) from the proposed IC layout; determining the predicting as being correct when the fabricated circuit includes the printed SRAF, or as being incorrect when the fabricated circuit does not include the printed SRAF; in response to the predicting being incorrect: adjusting the predictive algorithm, and flagging the fabricated circuit as incorrectly predicted; in response to the predicting being correct, flagging the fabricated circuit as correctly predicted; and storing the image of the fabricated circuit in a repository of training data.

First claim

What is claimed is:

1 . A method for creating a knowledge base for optical proximity correction (OPC), the method comprising:
fabricating a circuit using a proposed IC layout; identifying a plurality of features in an image of the fabricated circuit; predicting, based on the identifying and a predictive algorithm, whether the fabricated circuit includes a printed sub-resolution assist feature (SRAF) from the proposed IC layout; determining the predicting as being correct when the fabricated circuit includes the printed SRAF, or as being incorrect when the fabricated circuit does not include the printed SRAF; in response to the predicting being incorrect:
adjusting the predictive algorithm, and
flagging the fabricated circuit as incorrectly predicted;
in response to the predicting being correct, flagging the fabricated circuit as correctly predicted; and storing the image of the fabricated circuit in a repository of training data.

2 . The method of claim 1 , wherein the repository of training data includes images of fabricated circuits for different products.

3 . The method of claim 1 , wherein the predicting is further based on the repository of training data.

4 . The method of claim 3 , wherein the repository of training data includes a plurality of sample circuit images, the plurality of sample circuit images including at least one SRAF-free image and at least one SRAF-including image.

5 . The computer-implemented method of claim 1 , wherein the predictive algorithm includes a principal component analysis of the fabricated circuit.

6 . The computer-implemented method of claim 1 , wherein the predictive algorithm includes a support vector machine (SVM) analysis of the fabricated circuit.

7 . The computer-implemented method of claim 1 , wherein the predictive algorithm includes a K-nearest neighbor analysis of the fabricated circuit.

8 . A program product stored on a computer readable storage medium, the program product operative to create a knowledge base for optical proximity correction (OPC) when executed, the computer readable storage medium comprising program code for:
causing a fabricating device to fabricate a circuit using a proposed IC layout; identifying a plurality of features in an image of the fabricated circuit; predicting, based on the identifying and a predictive algorithm, whether the fabricated circuit includes a printed sub-resolution assist feature (SRAF) from the proposed IC layout; determining the predicting as being correct when the fabricated circuit includes the printed SRAF, or as being incorrect when the fabricated circuit does not include the printed SRAF; in response to the predicting being incorrect:
adjusting the predictive algorithm, and
flagging the printed circuit as incorrectly predicted;
in response to the predicting being correct, flagging the fabricated circuit as correctly predicted; and storing the image of the fabricated circuit in a repository of training data.

9 . The program product of claim 8 , wherein the repository of training data includes images of fabricated circuits for different products.

10 . The program product of claim 8 , wherein the program code for predicting is further based on the repository of training data.

11 . The program product of claim 10 , wherein the repository of training data includes a plurality of sample circuit images, the plurality of sample circuit images including at least one SRAF-free image and at least one SRAF-including image.

12 . The program product of claim 8 , wherein the predictive algorithm includes a principal component analysis of the fabricated circuit.

13 . The program product of claim 12 , wherein the predictive algorithm includes a support vector machine (SVM) analysis of the fabricated circuit.

14 . The program product of claim 12 , wherein the predictive algorithm includes a K-nearest neighbor analysis of the fabricated circuit.

15 . A system for building a knowledge base for optical proximity correction (OPC), the system comprising:
a fabricating device configured to fabricate a circuit using a proposed integrated circuit (IC) layout; and a layout analysis component configured to:
identify a plurality of features in an image of a fabricated circuit yielded from the fabricating device; and
predict, based on the identifying and a predictive algorithm, whether the fabricated circuit includes a printed sub-resolution assist feature (SRAF);
a training component configured to:
determine the prediction as being correct when the fabricated circuit includes the printed SRAF, or as being incorrect when the fabricated circuit does not include the printed SRAF;
in response to the prediction being incorrect:
adjust the predictive algorithm, and
flag the fabricated circuit as incorrectly predicted,

in response to the prediction being correct, flag the fabricated circuit as correctly predicted, and
store the image of the fabricated circuit in a repository of training data.

16 . The system of claim 15 , wherein the repository of training data includes images of fabricated circuits for different products.

17 . The system of claim 15 , wherein the layout analysis component is further configured to predict whether the image of the fabricated circuit will include the printed SRAF based on the repository of training data.

18 . The system of claim 15 , wherein the predictive algorithm includes a principal component analysis of the fabricated circuit.

19 . The system of claim 15 , wherein the predictive algorithm includes a support vector machine (SVM) analysis of the fabricated circuit.

20 . The system of claim 15 , wherein the predictive algorithm includes a K-nearest neighbor analysis of the fabricated circuit.

Assignees

• Globalfoundries Inc

Inventors

• Kohli Kriteshwar K
• Jobes Mark N
• Graur Ioana C

Classifications

• G03F1/36 Primary

  Masks having proximity correction features; Preparation thereof, e.g. optical proximity correction [OPC] design processes · CPC title

• G06F2217/12

  Physics · mapped topic

• G06F17/5081

  Physics · mapped topic