Reliability and performance of a system-on-a-chip by predictive wear-out based activation of functional components

• US 8,549,363 B2
• Filed: 03/19/2010
• Issued: 10/01/2013
• Est. Priority Date: 01/08/2010
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cher, Chen-Yong, Coteus, Paul W., Gara, Alan, Kursun, Eren, Paulsen, David P., Schuelke, Brian A., Sheets, John E. II, Tian, Shurong
• Primary Examiner(s): KO, CHAE M
• Application Number:
  US12/727,967
• Publication Number:
  US 20110173432A1
• Time in Patent Office: 1,292 Days
• Field of Search: 714/47.3
• US Class Current: 714/47.3
• CPC Class Codes: G01R 31/31725 Timing aspects, e.g. clock distribution, skew, propagation delay for tester hardware G01R31/31937
• CPC Class Codes: G06F 30/30 Circuit design

Abstract

A processor-implemented method for determining aging of a processing unit in a processor the method comprising: calculating an effective aging profile for the processing unit wherein the effective aging profile quantifies the effects of aging on the processing unit; combining the effective aging profile with process variation data, actual workload data and operating conditions data for the processing unit; and determining aging through an aging sensor of the processing unit using the effective aging profile, the process variation data, the actual workload data, architectural characteristics and redundancy data, and the operating conditions data for the processing unit.

Claims

1. A processor-implemented method for determining aging of a processing unit in a processor, the method comprising:

calculating an effective aging profile for the processing unit, wherein the effective aging profile quantifies the effects of aging on the processing unit, wherein the effective aging profile is based at least in part upon at least one aging profile coefficient, and wherein the aging profile coefficient has an initial value;

combining the effective aging profile with process variation data, actual workload data and operating conditions data for the processing unit;

determining aging through an aging sensor of the processing unit using the effective aging profile, the process variation data, the actual workload data, architectural characteristics and redundancy data, and the operating conditions data for the processing unit;

recalibrating the aging profile coefficient based at least in part upon the determined aging to generate a modified value for the aging profile coefficient; and

recalculating the effective aging profile, wherein the recalculated effective aging profile is based at least in part upon the aging profile coefficient modified value.

2. The method of claim 1, further comprising matching the aging sensor configuration to an effective aging profile.

3. The method of claim 2, further comprising commencing a corrective reaction to prolong the processor'"'"'s operational lifetime.

4. The method of claim 3, wherein the corrective reaction includes at least one of the following:

adjusting supply voltage, adjusting frequency, reducing a workload, selectively shutting down a processing unit, scheduling a workload, executing task migration, matching a workload to a processing unit.

5. The method of claim 1, wherein the effective aging profile for the processing unit is calculated using an aging model, the aging model using circuit characteristics data, architecture characteristics, redundancy and criticality data, assumed workload data and assumed operating conditions data.

6. The method of claim 5, wherein process variation is factored in the calculation of effective aging profile using the aging model.

7. The method of claim 1, wherein the step of calculating the effective aging profile of the processing unit using the effective aging data, the process variation data, the actual workload data and the operating conditions data is performed using an aging model.

8. A processor-implemented method for determining aging of a processing unit in a processor, the method comprising:

calculating an effective aging profile for the processing unit wherein the effective aging profile quantifies the effects of aging on the processing unit;

exposing an aging analyzer to analogous workload factors as the processing unit wherein the aging analyzer mimics a critical timing path of the processing unit the aging analyzer measures;

combining the effective aging profile, process variation data and aging analyzer data; and

determining aging through the aging analyzer of the processing unit using the effective aging profile, the process variation data and the aging sensor data.

9. The method of claim 8, further comprising matching the aging analyzer configuration to an effective aging profile.

10. The method of claim 9, further comprising commencing a corrective reaction to prolong the processor'"'"'s operational lifetime.

11. The method of claim 10, wherein the corrective reaction includes at least one of the following:

adjusting supply voltage, adjusting frequency, reducing a workload, selectively shutting down a processing unit, scheduling a workload, executing task migration, matching a workload to a processing unit.

12. The method of claim 8, wherein the effective aging profile for the processor unit is calculated using an aging model, the aging model using circuit/macro characteristics data and architecture redundancy data.

13. The method of claim 12, wherein process variation is factored in the calculation of effective aging profile using the aging model.

14. The method of claim 8, wherein the step of calculating the effective aging profile of the processing unit using the effective aging profile, the process variation data and the aging sensor data is performed using an aging model.

15. A computer system for determining aging of a processing unit in a processor, the system comprising:

a memory;

a processor in communications with the computer memory, wherein the computer system is capable of performing a method comprising;

calculating an effective aging profile for the processing unit wherein the effective aging profile quantifies the effects of aging on the processing unit, wherein the effective aging profile is based at least in part upon at least one aging profile coefficient, and wherein the aging profile coefficient has an initial value;

combining the effective aging profile with process variation data, actual workload data and operating conditions data for the processing unit; and

determining aging through an aging sensor of the processing unit using the effective aging profile, the process variation data, the actual workload data, architectural characteristics and redundancy data, and the operating conditions data for the processing unit;

recalibrating the aging profile coefficient based at least in part upon the determined aging to generate a modified value for the aging profile coefficient; and

recalculating the effective aging profile, wherein the recalculated effective aging profile is based at least in part upon the aging profile coefficient modified value.

16. The computer system of claim 15, further comprising matching the effective aging profile to a predetermined aging requirement and commencing a corrective reaction to prolong the processor'"'"'s operational lifetime.

17. The computer system of claim 16, wherein the corrective reaction includes at least one of the following:

adjusting supply voltage, adjusting frequency, reducing a workload, selectively shutting down a processing unit, scheduling a workload, executing task migration, matching a workload to a processing unit.

18. The computer system of claim 15, wherein the effective aging profile for the processing unit is calculated using an aging model, the aging model using circuit characteristics data, architecture characteristics, redundancy and criticality data, assumed workload data and assumed operating conditions data, and the combination of the effective aging profile with process variation data, actual workload data and operating conditions data for the processing unit is performed using the aging model, and the step of determining aging through aging analyzer of the processing unit using the effective aging profile, the process variation data, the actual workload data, architectural characteristics and redundancy data, and the operating conditions data for the processing unit is performed using the aging model.

19. A computer readable storage device having computer readable program code logic tangibly embodied therein to execute at least one machine instruction in a processing circuit, the at least one machine instruction being for determining aging of a processing unit in a processor, the at least one machine instruction performing a method comprising:

calculating an effective aging profile for the processing unit wherein the effective aging profile quantifies the effects of aging on the processing unit, wherein the effective aging profile is based at least in part upon at least one aging profile coefficient, and wherein the aging profile coefficient has an initial value;

combining the effective aging profile with process variation data, actual workload data and operating conditions data for the processing unit; and

determining aging through an aging sensor of the processing unit using the effective aging profile, the process variation data, the actual workload data, architectural characteristics and redundancy data, and the operating conditions data for the processing unit;

recalibrating the aging profile coefficient based at least in part upon the determined aging to generate a modified value for the aging profile coefficient; and

recalculating the effective aging profile, wherein the recalculated effective aging profile is based at least in part upon the aging profile coefficient modified value.

20. A computer system for determining aging of a processing unit in a processor, the system comprising:

a memory;

a processor in communications with the computer memory, wherein the computer system is capable of performing a method comprising;

calculating an effective aging profile for the processing unit wherein the effective aging profile quantifies the effects of aging on the processing unit;

exposing an aging analyzer to analogous workload factors as the processing unit wherein the aging analyzer mimics a critical timing path of the processing unit the aging analyzer measures;

combining the effective aging profile, process variation data and aging analyzer data; and

determining aging through the aging analyzer of the processing unit using the effective aging profile, the process variation data and the aging sensor data.

21. The computer system of claim 20, further comprising matching the effective aging profile to a predetermined aging requirement and commencing a corrective reaction to prolong the processor'"'"'s operational lifetime.

22. The computer system of claim 21, wherein the corrective reaction includes at least one of the following:

adjusting supply voltage, adjusting frequency, reducing a workload, selectively shutting down a processing unit, scheduling a workload, executing task migration, matching a workload to a processing unit.

23. The computer system of claim 20, wherein the effective aging profile for the processing unit is calculated using an aging model, the aging model using circuit/macro characteristics data and architecture redundancy data, and the combination of the effective aging profile, process variation data and aging sensor data is performed using the aging model, and the step of determining aging through aging analyzer of the processing unit using the effective aging profile, the process variation data and the aging sensor data is performed using the aging model.

24. A computer readable storage device having computer readable program code logic tangibly embodied therein to execute at least one machine instruction in a processing circuit, the at least one machine instruction being for determining aging of a processing unit in a processor, the at least one machine instruction performing a method comprising:

calculating an effective aging profile for the processing unit wherein the effective aging profile quantifies the effects of aging on the processing unit;

exposing an aging analyzer to analogous workload factors as the processing unit wherein the aging analyzer mimics a critical timing path of the processing unit the aging analyzer measures;

combining the effective aging profile, process variation data and aging analyzer data; and

determining aging through the aging analyzer of the processing unit using the effective aging profile, the process variation data and the aging sensor data.