Static voltage drop (SIR) violation prediction systems and methods

1. A static voltage (SIR) drop violation prediction system, comprising:

SIR drop violation prediction circuitry, the SIR drop violation prediction circuitry including machine learning circuitry trained based on past data to predict the presence of SIR drop violations in electronic device designs after routing has been performed, the SIR drop violation prediction circuitry configured to:

receive clock-tree synthesis (CTS) layout data associated with a CTS layout;

inspect the CTS layout data associated with the CTS layout; and

predict, by the machine learning circuitry and based on the past data, whether one or more SIR drop violations would be present in the CTS layout due to routing of the CTS layout.

2. The system of claim 1 , further comprising:

a CTS database configured to store the CTS layout data associated with the CTS layout.

3. The system of claim 2 , further comprising:

a processed region database configured to store information associated with a plurality of CTS regions which exhibit SIR drop violations, wherein the SIR drop violation prediction circuitry is configured to predict whether one or more SIR drop violations would be present in the CTS layout based at least in part on the information associated with the plurality of CTS regions which exhibit SIR drop violations.

4. The system of claim 3 , further comprising:

a SIR drop database configured to store information associating SIR drop violations with at least one of a CTS layout or a CTS layout region,

wherein the machine learning circuitry is communicatively coupled to the SIR drop database, and the machine learning circuitry is configured to generate the information associated with the plurality of CTS regions which exhibit SIR drop violations based on the information stored in the SIR drop database.

5. The system of claim 1 wherein the SIR drop violation prediction circuitry is configured to:

generate a SIR drop violation map indicating locations of predicted SIR drop violations in the CTS layout.

6. The system of claim 1 , further comprising:

a model bank which stores a plurality of machine learning models,

wherein the machine learning circuitry is communicatively coupled to the model bank, and the machine learning circuitry is configured to:

generate a first stage ensemble by selecting a first portion of the plurality of machine learning models based on a first similarity comparison between a shape and orientation of a feature space of the CTS layout and shapes and orientations of feature spaces of the plurality of machine learning models; and

generate a second stage ensemble by selecting a second portion of the plurality of machine learning models based on a second similarity comparison between the orientation of the feature space of the CTS layout and orientation of feature spaces of the first portion of the plurality of machine learning models of the first stage ensemble.

7. The system of claim 6 wherein the SIR drop violation prediction circuitry is configured to generate a SIR drop map based on a comparison of the CTS layout with the second stage ensemble, the SIR drop map indicating predicted SIR drop values in the CTS layout.

8. The system of claim 7 wherein the SIR drop violation prediction circuitry is configured to compare the predicted SIR drop values with a threshold SIR drop value, and predict whether one or more SIR drop violations would be present in the CTS layout due to routing of the CTS layout based on the comparison of the predicted SIR drop values with the threshold SIR drop value.

9. The system of claim 1 , further comprising:

clock tree cell adjustment circuitry configured to increase a spacing between clock cells of a region of the CTS layout, in response to the SIR drop violation prediction circuitry predicting that one or more SIR drop violations would be present in the region of the CTS layout due to the routing of the CTS layout.

10. A method, comprising:

receiving, by static voltage (SIR) drop violation circuitry, clock-tree synthesis (CTS) layout data associated with a CTS layout of a semiconductor device;

inspecting, by the SIR drop violation circuitry, the CTS layout data associated with the CTS layout;

generating a SIR drop map based on a comparison of the CTS layout with at least one of a plurality of machine learning models, the SIR drop map indicating predicted SIR drop values in the CTS layout; and

predicting, by the SIR drop violation circuitry, whether one or more SIR drop violations would be present in the CTS layout due to routing of the CTS layout, based on the SIR drop map.

11. The method of claim 10 , further comprising:

routing the CTS layout in response to predicting that no SIR drop violations would be present in the CTS layout due to routing of the CTS layout.

12. The method of claim 10 , further comprising:

generating a SIR drop violation map indicating locations of predicted SIR drop violations in the CTS layout.

13. The method of claim 10 wherein the predicting whether one or more SIR drop violations would be present in the CTS layout due to routing of the CTS layout includes:

comparing the predicted SIR drop values with a threshold SIR drop value; and

predicting that one or more SIR drop violations would be present in response to one or more of the predicted SIR drop values exceeding the threshold SIR drop value.

14. The method of claim 10 , further comprising:

selecting a first portion of the plurality of machine learning models based on a first similarity comparison between a shape and orientation of a feature space of the CTS layout and shapes and orientations of feature spaces of the plurality of machine learning models;

selecting a second portion of the plurality of machine learning models based on a second similarity comparison between the orientation of the feature space of the CTS layout and orientation of feature spaces of the first portion of the plurality of machine learning models,

wherein the generating the SIR drop map includes generating the SIR drop map based on a comparison of the CTS layout with the selected second portion of the plurality of machine learning models.

15. The method of claim 10 , further comprising:

adjusting the CTS layout by increasing a spacing between clock cells of at least one region of the CTS layout, in response to the SIR drop violation prediction circuitry predicting that one or more SIR drop violations would be present in the at least one region of the CTS layout due to routing of the CTS layout.

16. A method, comprising:

training a plurality of machine learning models with information indicative of static voltage (SIR) drop violations in a plurality of electronic device designs, the plurality of machine learning models trained based on past data to predict the presence of SIR drop violations in electronic device designs after routing has been performed;

storing the plurality of machine learning models in a database;

receiving, by SIR drop violation prediction circuitry, clock-tree synthesis (CTS) data associated with a CTS layout; and

predicting, by the SIR drop violation prediction circuitry, whether one or more SIR drop violations would be present in the CTS layout due to a subsequent routing of the CTS layout, based on a similarity comparison between the CTS data and the plurality of machine learning models.

17. The method of claim 16 wherein the training the machine learning circuitry includes extracting feature information associated with the plurality of electronic device designs.

18. The method of claim 17 , further comprising:

extracting feature information associated with the CTS layout for each of a plurality of regions of the CTS layout,

wherein the predicting whether one or more SIR drop violations would be present in the CTS layout includes comparing the extracted feature information associated with the CTS layout with the extracted feature information associated with the plurality of electronic device designs.

19. The method of claim 17 , further comprising:

adjusting the CTS layout by increasing a spacing between clock cells of the CTS layout, in response to predicting that one or more SIR drop violations would be present in the CTS layout; and

routing the adjusted CTS layout.

20. The method of claim 16 , further comprising:

generating a first stage ensemble by selecting a first portion of the plurality of machine learning models based on a first similarity comparison between a shape and orientation of a feature space of the CTS layout and shapes and orientations of feature spaces of the plurality of machine learning models; and

generating a second stage ensemble by selecting a second portion of the plurality of machine learning models based on a second similarity comparison between the orientation of the feature space of the CTS layout and orientation of feature spaces of the first portion of the plurality of machine learning models of the first stage ensemble,

wherein the predicting whether one or more SIR drop violations would be present in the CTS layout is based on the first similarity comparison and the second similarity comparison.