Method of post optical proximity correction (OPC) printing verification by machine learning

1. A method of fabricating an integrated circuit (IC), comprising:

receiving an IC design layout;

performing an optical proximity correction (OPC) process to the IC design layout to produce a corrected IC design layout;

verifying the corrected IC design layout using a machine learning algorithm, wherein verifying the corrected IC design layout comprises:

using the machine learning algorithm to identify one or more features of the corrected IC design layout,

comparing the one or more identified features to a database comprising a plurality of features, and

verifying the corrected IC design layout based on labels in the database associated with the plurality of features;

generating the database, wherein generating the database comprises:

generating a plurality of IC design layouts,

performing a printing simulation for each IC design layout to determine a probability of whether the corrected IC design will print-out successfully on a wafer or print with defects on the wafer, and

storing a label associated with each IC design layout in the database, wherein the label indicates the probability; and

verifying the corrected IC design layout using a compact OPC model by performing a plurality of printing simulations for each IC at a plurality of exposure doses to determine the probability.

2. The method of claim 1 , wherein the labels correspond to a probability of whether the corrected IC design will print-out successfully on a wafer or print with defects on the wafer.

3. The method of claim 1 , wherein receiving the IC design layout comprises receiving a graphic design system (GDS) file, and wherein the corrected IC design layout comprises an adjusted GDS file.

4. The method of claim 1 , wherein the machine learning algorithm comprises at least one of: a convolutional neural network algorithm, a recursive neural network algorithm, a support vector machine algorithm, or a deep learning artificial intelligence algorithm.

5. A system of fabricating an integrated circuit (IC), comprising:

at least memory storing a database;

a mask making module configured to receive an IC design layout, wherein the mask making module comprises:

a data preparation module configured to:

perform an optical proximity correction (OPC) process to the IC design layout to produce a corrected IC design layout,

verify the corrected IC design layout using a machine learning algorithm to identify one or more features of the corrected IC design layout; and

compare the one or more identified features to the database comprising a plurality of features,

verify the corrected IC design layout based on labels in the database associated with the plurality of features, and

verify the corrected IC design layout using a compact OPC model by performing a plurality of printing simulations for each IC at a plurality of exposure doses to determine the probability;

a mask tooling module configured to print the mask layout design;

a fabrication module configured to fabricate the IC using the mask;

a data training module configured to generate the database by:

generating a plurality of IC design layouts;

performing a printing simulation for each IC design layout to determine a probability of whether the corrected IC design will print-out successfully on a wafer or print with defects on the wafer, and

storing a label associated with each IC design layout in the database, wherein the label indicates the probability.

6. The system of claim 5 , wherein the labels correspond to a probability of whether the corrected IC design will print-out successfully on a wafer or print with defects on the wafer.

7. The system of claim 5 , wherein receiving the IC design layout comprises receiving a graphic design system (GDS) file, and wherein the corrected IC design layout comprises an adjusted GDS file.

8. The system of claim 5 , wherein the machine learning algorithm comprises at least one of: a convolutional neural network algorithm, a recursive neural network algorithm, a support vector machine algorithm, or a deep learning artificial intelligence algorithm.

9. A computer readable medium having computer executable code stored thereon, comprising:

code for receiving an integrated circuit (IC) design layout;

code for performing an optical proximity correction (OPC) process to the IC design layout to produce a corrected IC design layout;

code for generating a database, comprising:

code for generating a plurality of IC design layouts,

code for performing a printing simulation for each IC design layout to determine a probability of whether the corrected IC design will print-out successfully on a wafer or print with defects on the wafer, and

code for storing a label associated with each IC design layout in the database, wherein the label indicates the probability; and

code for verifying the corrected IC design layout comprises:

code for using a machine learning algorithm to identify one or more features of the corrected IC design layout,

code for comparing the one or more identified features to the database comprising a plurality of features, and

code for verifying the corrected IC design layout based on labels in the database associated with the plurality of features.

10. The computer readable medium of claim 9 , wherein the labels correspond to a probability of whether the corrected IC design will print-out successfully on a wafer or print with defects on the wafer.

11. The computer readable medium of claim 9 , wherein code for receiving the IC design layout comprises code for receiving a graphic design system (GDS) file, and wherein the corrected IC design layout comprises an adjusted GDS file.

12. The computer readable medium of claim 9 , wherein the machine learning algorithm comprises at least one of: a convolutional neural network algorithm, a recursive neural network algorithm, a support vector machine algorithm, or a deep learning artificial intelligence algorithm.