Lithography simulation using a neural network
As integrated circuit geometries have shrunk, lithography simulation has developed to ensure that the masks used to fabricate the circuits satisfy the chip yield and fabrication turnaround time targets. To manufacture an integrated circuit (chip), an initial layout for the integrated circuit design is processed to compute a wafer image (e.g., resist material “printed” on the wafer using photomasks). Lithography simulation processes the initial layout according to optical physics to compute an estimated wafer image without actually constructing the physical masks or consuming any wafer fabrication resources and may be used to confirm manufacturability of the design layout before it is fabricated. Performing lithography simulation using a dual-band neural network produces accurate results efficiently. Dual-band refers to a dual frequency band processing whereby the input layout (mask image) is separately processed by both a first and second branch to extract low-frequency (global) features and high-frequency (local) features, respectively.
1. A computer-implemented method, comprising:
processing, according to an optical model for lithography, a mask image defining shapes for fabrication of an integrated circuit by a first branch of a neural network to extract low-frequency component features by converting the mask image into a frequency domain and performing at least a linear operation in the frequency domain;
extracting high-frequency component features from the mask image by a second branch of the neural network; and
producing an estimated fabrication image by processing the low-frequency component features and the high-frequency component features by a reconstruction portion of the neural network.
2. The computer-implemented method of claim 1 , wherein the mask image is downsampled for processing by the first branch.
3. The computer-implemented method of claim 2 , further comprising subdividing the downsampled mask image into tiles for processing by the first branch.
4. The computer-implemented method of claim 3 , wherein each one of the tiles at least partially overlaps with an adjacent tile.
5. The computer-implemented method of claim 3 , wherein the first branch extracts high-frequency component features for each processed tile and further comprising concatenating the high-frequency component features for the processed tiles for input to the reconstruction portion of the neural network.
6. The computer-implemented method of claim 1 , wherein the low-frequency component features correspond to light intensity.
7. The computer-implemented method of claim 1 , wherein the high-frequency component features correspond to contour and shape edge details.
8. The computer-implemented method of claim 1 , wherein the first branch processes the mask image by:
performing a Fourier transform on the mask image to convert the mask image into the frequency domain;
convolving the converted mask image with a channel-lifting operator;
performing the linear operation on the convolved converted mask image to extract low-frequency features in the frequency domain; and
performing an inverse Fourier transform on the extracted low-frequency features in the frequency domain to produce the low-frequency component features.
9. The computer-implemented method of claim 1 , wherein at least one of the steps of processing, extracting, and producing are performed on a server or in a data center and the estimated fabrication image is streamed to a user device.
10. The computer-implemented method of claim 1 , wherein at least one of the steps of processing, extracting, and producing are performed within a cloud computing environment.
11. The computer-implemented method of claim 1 , wherein the integrated circuit is employed in a machine, robot, or autonomous vehicle.
12. The computer-implemented method of claim 1 , wherein at least one of the steps of processing, extracting, and producing is performed on a virtual machine comprising a portion of a graphics processing unit.
13. A computer-implemented method, comprising:
processing a fabrication image defining patterns for an integrated circuit by a first branch of a neural network according to an optical model for lithography to extract low-frequency component features by converting the mask image into a frequency domain and performing at least a linear operation in the frequency domain;
extracting high-frequency component features from the fabrication image by a second branch of the neural network; and
producing an estimated mask image by processing the low-frequency component features and the high-frequency component features by a reconstruction portion of the neural network.
14. The computer-implemented method of claim 13 , wherein the low-frequency component features correspond to light intensity.
15. The computer-implemented method of claim 13 , wherein the high-frequency component features correspond to contour and shape edge details.
16. A system, comprising:
a memory that stores a mask image defining shapes for fabrication of an integrated circuit; and
a processor that is connected to the memory, wherein the processor implements a neural network comprising:
a first branch that processes the mask image to extract low-frequency component features by converting the mask image into a frequency domain and performing at least a linear operation in the frequency domain;
a second branch that extracts high-frequency component features from the mask image; and
a reconstruction portion that produces an estimated fabrication image by processing the low-frequency component features and the high-frequency component features.
17. The system of claim 16 , wherein the mask image is downsampled for processing by the first branch.
18. The system of claim 16 , wherein the low-frequency component features correspond to light intensity.
19. A non-transitory computer-readable media storing computer instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:
processing, according to an optical model for lithography, a mask image defining shapes for fabrication of an integrated circuit by a first branch of a neural network to extract low-frequency component features by converting the mask image into a frequency domain and performing at least a linear operation in the frequency domain;
extracting high-frequency component features from the mask image by a second branch of the neural network; and
producing an estimated fabrication image by processing the low-frequency component features and the high-frequency component features by a reconstruction portion of the neural network.
20. The non-transitory computer-readable media of claim 19 , wherein the low-frequency component features correspond to light intensity.