SRAF insertion with artificial neural network

1. A method comprising:

identifying a target feature in an integrated circuit (IC) layout not represented in a library, the library including a plurality of sub-resolution assist feature (SRAF) usefulness maps corresponding to a plurality of features and SRAFs in the IC layout;

generating a usefulness map for the target feature with an artificial neural network (ANN), the generating being based on the target feature and the plurality of SRAF usefulness maps in the library, wherein the usefulness map includes at least one candidate zone where an SRAF will increase printability of the target feature, and at least one excluded zone where an SRAF will decrease printability of the target feature;

translating one of the plurality of SRAF usefulness maps along at least one reference axis to yield a translated SRAF usefulness map;

adding the target feature, the translated SRAF usefulness map and the generated usefulness map to the library;

selecting a candidate zone in the generated usefulness map as an SRAF insertion site for the target feature;

inserting an SRAF for the target feature into the IC layout at the selected SRAF insertion site; and

manufacturing a circuit using the IC layout.

2. The method of claim 1 , further comprising:

training the ANN to generate the usefulness map for the target feature based on the translated SRAF usefulness map, the target feature, and the plurality of SRAF usefulness maps in the library.

3. The method of claim 2 , wherein the at least one reference axis comprises one of an x-axis and a y-axis in a plan view of the IC layout.

4. The method of claim 1 , wherein at least one SRAF usefulness map of the plurality of SRAF usefulness maps is based on a manufactured IC structure formed from the IC layout.

5. The method of claim 1 , further comprising determining a completeness of the library based on features of the IC layout represented in the library.

6. The method of claim 1 , wherein the ANN is a fully connected multilayer perceptron ANN.

7. The method of claim 1 , wherein the ANN is a convolutional ANN.

8. The method of claim 1 , wherein the library further includes SRAF usefulness maps for a plurality of distinct IC layouts, the plurality of SRAF usefulness maps includes at least one feature different from the target feature, and the target feature is not included within the plurality of distinct IC layouts.

9. A computer program product stored on a computer readable storage medium, the computer program product comprising program code, which, when being executed by at least one computing device, causes the at least one computing device to:

identify a target feature in an integrated circuit (IC) layout not represented in a library, the library including a plurality of sub-resolution assist feature (SRAF) usefulness maps corresponding to a plurality of features and SRAFs in the IC layout;

generate a usefulness map for the target feature with an artificial neural network (ANN), the generating being based on the target feature and the plurality of SRAF usefulness maps in the library, wherein the usefulness map includes at least one candidate zone where an SRAF will increase printability of the target feature, and at least one excluded zone where an SRAF will decrease printability of the target feature;

translating one of the plurality of SRAF usefulness maps along at least one reference axis to yield a translated SRAF usefulness map;

add the target feature, the translated SRAF usefulness map, and the generated usefulness map to the library;

select a candidate zone in the generated usefulness map as an SRAF insertion site for the target feature;

insert an SRAF for the target feature into the IC layout at the selected SRAF insertion site; and

instruct a manufacturing device to manufacture a circuit using the IC layout.

10. The computer program product of claim 9 , the computer program product further comprising program code for causing the at least one computing device to:

train the ANN to generate the usefulness map for the target feature based on the translated SRAF usefulness map, the target feature, and the plurality of SRAF usefulness maps in the library.

11. The computer program product of claim 10 , wherein the at least one reference axis comprises one of an x-axis and a y-axis in a plan view of the IC layout.

12. The computer program product of claim 9 , wherein at least one SRAF usefulness map of the plurality of SRAF usefulness maps is generated from a manufactured IC structure.

13. The computer program product of claim 9 , wherein the ANN is one of a fully connected multilayer perceptron ANN or a convolutional ANN.

14. The computer program product of claim 9 , the computer program product further comprising program code for causing the at least one computing device to determine a completeness of the library based on features in the IC layout represented in the library.

15. The computer program product of claim 9 , wherein the library further includes SRAF usefulness maps pertaining to a plurality of distinct IC layouts, the plurality of SRAF usefulness maps includes at least one feature different from the target feature, and the target feature is not included within the plurality of distinct IC layouts.

16. A system comprising:

at least one computing device configured to perform a method by performing actions including:

identify a target feature in an integrated circuit (IC) layout not represented in a library, the library including a plurality of sub-resolution assist feature (SRAF) usefulness maps corresponding to a plurality of features and SRAFs in the IC layout;

generate a usefulness map for the target feature with an artificial neural network (ANN), the generating being based on the target feature and the plurality of SRAF usefulness maps in the library, wherein the usefulness map includes at least one candidate zone where an SRAF will increase printability of the target feature, and at least one excluded zone where an SRAF will decrease printability of the target feature;

translate one of the plurality of SRAF usefulness maps along at least one reference axis to yield a translated SRAF usefulness map;

add the target feature, the translated SRAF usefulness map, and the generated usefulness map to the library;

select a candidate zone in the generated usefulness map as an SRAF insertion site for the target feature; and

insert an SRAF for the target feature into the IC layout at the selected SRAF insertion site; and

a fabricating device configured to manufacture a circuit using the IC layout.

17. The system of claim 16 , wherein the at least one computing device is further configured to:

train the ANN to generate the usefulness map for the target feature based on the translated SRAF usefulness map, the target feature, and the plurality of SRAF usefulness maps in the library.

18. The system of claim 17 , wherein the at least one computing device is further configured to determine a completeness of the library based on a number of features in the IC layout represented in the library.

19. The system of claim 16 , wherein the ANN comprises one of a fully connected multilayer perceptron ANN, or a convolutional ANN.

20. The system of claim 16 , wherein the plurality of SRAF usefulness maps includes at least one feature different from the target feature, and the target feature is not included within the plurality of distinct IC layouts.