Predicting die susceptible to early lifetime failure
Semiconductor yield is modeled at the die level to predict die that are susceptible to early lifetime failure (ELF). A first die yield calculation is made from parametric data obtained from wafer testing in a semiconductor manufacturing process. A second die yield calculation is made from die location only. The difference between the first die yield calculation and the second die yield calculation is a prediction delta. Based on an evaluation of the first die yield calculation and the prediction delta, the likelihood of early lifetime failure can be identified and an acceptable level of die loss can be established to remove die from further processing.
1. A method, comprising:
predicting a first yield value for each of a first plurality of die in a first identified parameter group using a first machine learning model configured to predict the first yield value using data values obtained from parametric testing of a semiconductor wafer on which the first plurality of die are formed, each of the first plurality of die having data values for each of a plurality of parameters in the first identified parameter group;
assigning each of the first predicted yield values to respective ones of the first plurality of die;
predicting a second yield value for each of the first plurality of die in the first parameter group using a second machine learning model configured to predict respective second yield values using a location of corresponding ones of the first plurality of die;
determining a prediction delta for each of the first plurality of die by subtracting respective predicted second yield values from respective predicted first yield values;
establishing a threshold for acceptable die loss based on a relationship between the respective predicted first yield values and respective prediction deltas; and
removing a portion of the first plurality of die from further processing in accordance with the threshold for acceptable die loss.
2. The method of claim 1 , further comprising:
predicting the first yield value for additional pluralities of die, each additional plurality of die organized into one of a plurality respective parameter groups, each of the additional pluralities of die having data values for each of a plurality of parameters in each of the respective parameter groups; and
predicting the second yield value for each of the additional pluralities of die in respective parameter groups using a location of each die.
3. The method of claim 1 , further comprising:
identifying a plurality of parameter groups, each identified parameter group including a respective plurality of die each having data values for each of a plurality of parameters in the identified parameter group;
predicting the first yield value for each of the respective plurality of die in each identified parameter group; and
predicting the second yield value for each of the respective plurality of die in each identified parameter group using a location of each die.
4. The method of claim 1 , further comprising:
estimating a maximum limit, respectively, for each of the plurality of parameters;
for each die, comparing each of the plurality of parameters to the respective maximum limit;
removing die having a parameter that exceeds the respective maximum limit.
5. The method of claim 1 , further comprising:
evaluating the relationship between respective predicted first yield values and respective prediction deltas in order to establish the threshold value.
6. The method of claim 5 , further comprising:
sorting the predicted first yield values from lowest to highest;
calculating a yield percentile of the predicted first yield value associated with each of the first plurality of die;
sorting the prediction deltas from lowest to highest;
calculating a delta percentile of respective prediction deltas associated with each of the first plurality of die; and
identifying a minimum percentile value as between the yield percentile and the delta percentile;
selecting the minimum percentile value as the threshold value.
7. The method of claim 5 , further comprising:
setting the threshold for acceptable die loss for a condition when the predicted first yield value is less than a defined limit and when the prediction delta is a negative value.
8. The method of claim 5 , further comprising:
setting the threshold for acceptable die loss for a condition when the predicted first yield value is less than a defined limit and when the prediction delta is a positive value.
9. The method of claim 1 , wherein the first machine learning model is further configured using data obtained from fabrication processing of the semiconductor wafer.
10. The method of claim 1 , wherein the first machine learning model is further configured using data obtained from packaging of the semiconductor wafer.
11. A method, comprising:
receiving a plurality of data values obtained from a semiconductor process configured to fabricate a first plurality of unique die on a semiconductor wafer;
identifying a subset of the data values that are always present in testing results for passing die;
predicting a first yield value for each one of the first plurality of die formed on the basis of the subset of data values;
predicting a second yield value for each one of the first plurality of die on the basis of a location of each one of the first plurality of die;
subtracting respective predicted second yield values from respective predicted first yield values to obtain a plurality of respective prediction deltas;
establishing a threshold for acceptable die loss based on a relationship between the respective predicted first yield values and respective prediction deltas; and
removing any of the first plurality of die that exceed the threshold from further processing.
12. The method of claim 11 , further comprising:
establishing the threshold to avoid a low predicted first yield or a large negative prediction delta.
13. The method of claim 11 , further comprising:
establishing the threshold to avoid a low predicted first yield and a large negative prediction delta.
14. The method of claim 11 , further comprising:
establishing a maximum limit for each of the subset of data values;
for each die, each of the subset of data values to the respective maximum limit; and
removing any die having a data value that exceeds the respective maximum limit.
15. A predictive model, comprising at least one processor configured to:
predict a first yield value for each of a first plurality of die in a first identified parameter group using a first machine learning model configured to predict the first yield value using data values obtained from parametric testing of a semiconductor wafer on which the first plurality of die are formed, each of the first plurality of die having data values for each of a plurality of parameters in the first identified parameter group;
assign each of the first predicted yield values to respective ones of the first plurality of die;
predict a second yield value for each of the first plurality of die in the first parameter group using a second machine learning model configured to predict respective second yield values using a location of corresponding ones of the first plurality of die;
determine a prediction delta for each of the first plurality of die by subtracting respective predicted second yield values from respective predicted first yield values;
establish a threshold for acceptable die loss based on a relationship between the respective predicted first yield values and respective prediction deltas; and
remove a portion of the first plurality of die from further processing in accordance with the threshold for acceptable die loss.