Virtual metrology for feature profile prediction in the production of memory devices
To provide more test data during the manufacture of non-volatile memories and other integrated circuits, machine learning is used to generate virtual test values. Virtual test results are interpolated for one set of tests for devices on which the test is not performed based on correlations with other sets of tests. In one example, machine learning determines a correlation study between bad block values determined at die sort and photo-limited yield (PLY) values determined inline during processing. The correlation can be applied to interpolate virtual inline PLY data for all of the memory dies, allowing for more rapid feedback on the processing parameters for manufacturing the memory dies and making the manufacturing process more efficient and accurate. In another set of embodiments, the machine learning is used to extrapolate limited metrology (e.g., critical dimension) test data to all of the memory die through interpolated virtual metrology data values.
1. A method, comprising:
receiving a first plurality of an integrated circuit as first test samples, the integrated circuit comprising a plurality of circuitry layers formed on a substrate;
performing one or more first tests on the first test samples to determine a corresponding one or more metrology data values for each of the first test samples;
performing one or more second tests on the first plurality of the integrated circuit, the one or more second tests including determining values for electrical properties of a first subset of the circuitry layers;
performing a machine learning process to determine a correlation between the metrology data values and results of the one or more second tests;
receiving a second plurality of the integrated circuit;
determining, for the second plurality of the integrated circuit, values for the electrical properties of a first plurality of the circuitry layers, the first plurality of the circuitry layers including circuitry layers other than the first subset of the circuitry layers; and
interpolating metrology data values for the first plurality of the circuitry layers of the second plurality of the integrated circuit from the correlation and results of the values for the electrical properties of the first plurality of the circuitry layers.
2. The method of claim 1 , wherein the plurality of circuitry layers include a plurality of layers of word lines and the electrical properties of the circuitry layers comprise electrical properties of the word lines.
3. The method of claim 2 , wherein the electrical properties of the word lines include resistance-capacitance (RC) values for the word lines.
4. The method of claim 3 , wherein determining the RC values for the electrical properties of the word lines of the circuitry layers comprises:
applying a voltage to each of the word lines; and
determining for each of the word lines a time for voltage level on the word line to reach a specified voltage level in response to the application of the voltage.
5. The method of claim 2 , wherein determining for the second plurality of the integrated circuit values for the electrical properties of the first plurality of the circuitry layers includes determining electrical properties of all of the word lines of all of the layers of word lines.
6. The method of claim 2 , wherein the integrated circuit further comprises a plurality of memory holes extending vertically through layers of word lines, and
wherein the interpolated metrology for the first plurality of the circuitry layers of the second plurality of the integrated circuit includes profiled for the memory holes.
7. The method of claim 1 , wherein determining for the second plurality of the integrated circuit values for the electrical properties of the first plurality of the circuitry layers is performed as part of a die sort process.
8. The method of claim 1 , wherein one or more of the first tests are performed as part of a die sort test process.
9. The method of claim 1 , wherein one or more of the first tests are performed as part of an inline test process during fabrication of the first test samples.
10. The method of claim 1 , wherein one or more of the second tests are performed as part of a die sort test process.
11. The method of claim 1 , wherein one or more of the second tests are performed as part of an inline test process during fabrication of the first test samples.
12. The method of claim 1 , further comprising:
receiving a model of the electrical properties of the integrated circuit, wherein the machine learning process uses the model in determining the correlation between the metrology data values and results of the one or more second tests.
13. The method of claim 1 , wherein one or more of the first tests include:
determining critical dimension data by an electron microscope.
14. The method of claim 1 , wherein one or more of the first tests include:
determining optical critical dimension data.
15. The method of claim 14 , wherein the integrated circuit further comprises one or more trenches extending vertically through layers of the integrated circuit and the optical critical dimension data includes critical dimension data for the trenches.
16. The method of claim 1 , wherein performing the machine learning process comprises:
selecting a machine learning model.
17. The method of claim 1 , wherein receiving the first plurality of the integrated circuit and receiving the second plurality of the integrated circuit respectively comprise fabricating the first plurality of the integrated circuit and fabricating the second plurality of the integrated circuit.
18. The method of claim 17 , wherein the first plurality of the integrated circuit and the second plurality of the integrated circuit are fabricated using a first set of processing parameters and the method further comprises:
based the interpolated metrology data values, adjusting the first set of processing parameters; and
fabricating the integrated circuit using the adjusted first set of processing parameters.
19. A method, comprising:
fabricating a plurality of an integrated circuit using a first set of processing parameters, the integrated circuit comprising a plurality of circuitry layers formed on a substrate;
selecting a first plurality of the integrated circuit as first test samples;
performing one or more first tests on the first test samples to determine a corresponding one or more metrology data values for each of the first test samples;
performing one or more second tests on the first plurality of the integrated circuit, the one or more second tests including determining values for electrical properties of a first subset of the circuitry layers;
performing a machine learning process to determine a correlation between the metrology data values and results of the one or more second tests;
selecting a second plurality of the integrated circuit;
determining, for the second plurality of the integrated circuit, values for the electrical properties of a first plurality of the circuitry layers, the first plurality of the circuitry layers including circuitry layers other than the first subset of the circuitry layers;
interpolating metrology data values for the first plurality of the circuitry layers of the second plurality of the integrated circuit from the correlation and results of the values for the electrical properties of the first plurality of the circuitry layers;
based the interpolated metrology data values, adjusting the processing parameters; and
fabricating the integrated circuit using the adjusted processing parameters.
20. A system, comprising:
one or more processors, the one or more processors configured to:
receive results of one or more first tests on a plurality of first test samples from a first plurality of an integrated circuit, the integrated circuit comprising a plurality of circuitry layers formed on a substrate;
determine from the one or more first tests a corresponding one or more metrology data values for each of the first test samples;
receive results of one or more second tests on the first test samples of the integrated circuit, the one or more second tests including determining values for electrical properties of a first subset of the circuitry layers;
perform a machine learning process to determine a correlation between the metrology data values and results of the one or more second tests;
receive, for a second plurality of the integrated circuit, values for the electrical properties of a first plurality of the circuitry layers, the first plurality of the circuitry layers including circuitry layers other than the first subset of the circuitry layers; and
interpolate metrology data values for the first plurality of the circuitry layers of the second plurality of the integrated circuit from the correlation and results of the values for the electrical properties of the first plurality of the circuitry layers.