Methods and apparatuses for determining throttle settings to satisfy a system power constraint

• US 9,274,574 B2
• Filed: 05/01/2014
• Issued: 03/01/2016
• Est. Priority Date: 08/25/2005
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Conroy, David G., Culbert, Michael, Cox, Keith A.
• Primary Examiner(s): Phan, Raymond
• Application Number:
  US14/267,237
• Publication Number:
  US 20140351621A1
• Time in Patent Office: 670 Days
• Field of Search: 713300-340
• US Class Current: 1/1
• CPC Class Codes: G05D 23/19 characterised by the use of electric means G05D23/1393 takes precedence
• CPC Class Codes: G06F 1/26 Power supply means, e.g. regulation thereof for memories G11C
• CPC Class Codes: G06F 1/28 Supervision thereof, e.g. detecting power-supply failure by out of limits supervision
• CPC Class Codes: G06F 1/30 Means for acting in the event of power-supply failure or interruption, e.g. power-supply fluctuations for resetting only G06F1/24
• CPC Class Codes: G06F 1/3203 Power management, i.e. event-based initiation of a power-saving mode
• CPC Class Codes: G06F 1/324 by lowering clock frequency
• CPC Class Codes: G06F 1/3287 by switching off individual functional units in the computer system
• CPC Class Codes: G06F 1/3296 by lowering the supply or operating voltage
• CPC Class Codes: Y02B 70/10 Technologies improving the efficiency by using switched-mode power supplies [SMPS], i.e. efficient power electronics conversion e.g. power factor correction or reduction of losses in power supplies or efficient standby modes
• CPC Class Codes: Y02B 70/30 Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Exemplary embodiments of methods and apparatuses to manage a power of a system that leverage intermediate power margins are described. One or more subsystems of the system are operated at one or more performance points. A power consumed by the one or more subsystems at each of the one or more performance points is measured. An operational power of the one or more subsystems at the one or more performance points is determined. The one or more subsystems are operated at well-known conditions at the one or more performance points. The operational power may be adjusted based on data associated with the one or more subsystems. The operational power is provided to a power lookup table. The power is distributed among the one or more subsystems based on the operational power.

Claims

1. A data processing system, comprising:

a plurality of components including a set of non-throttled components and a set of throttled components, wherein each throttled component is capable of being actively controlled to one or more corresponding throttle settings, and wherein each throttle setting includes a different combination of one or more operating settings for the corresponding throttled component;

a plurality of sensors configured to determine information on power usage of the plurality of components during a first time period; and

a processor configured to;

estimate power usage of the set of non-throttled components during a second time period, and

determine, according to a target goal level, one or more global throttle settings, wherein each global throttle setting corresponds to a set of throttle settings, and wherein the set of throttle settings includes a different combination of throttle settings for the throttled components such that power usage of the plurality of components during the second time period satisfies a system constraint.

2. The data processing system of claim 1, wherein one or more non-throttled components are configured to provide respective state signals corresponding to respective global states, and wherein the processor is configured to estimate power usage of the one or more non-throttled components during the second time period based on the respective state signals.

3. The data processing system of claim 1, wherein the target goal level is a function of a current state of the data processing system, and wherein the function is based at least in part on respective current workloads of one or more throttled components.

4. The data processing system of claim 1, wherein the target goal level is based on a combination of required performance levels, and wherein the combination of required performance levels includes at least one of a required computing power level or a required energy consumption level.

5. The data processing system of claim 1, wherein the processor is further configured to:

sort the one or more global throttle settings in an order of priority according to the target goal level, and

select a highest priority global throttle setting such that power usage of the plurality of components during the second time period satisfies the system constraint.

6. The data processing system of claim 2, wherein the processor is configured to estimate, when a non-throttled component does not provide a respective state signal, that the power usage of the non-throttled component during the second time period is a maximum power usage for the non-throttled component.

7. The data processing system of claim 3, wherein the processor is configured to estimate the respective current workloads of the one or more throttled components based on the information on power usage of the plurality of components during the first time period.

8. The data processing system of claim 5, wherein the system constraint includes a limit on at least one of power usage, battery discharge current, thermal/heat dissipation, or heat generation.

9. A non-transitory machine readable medium storing instructions which, when executed by a data processing system, cause the data processing system to perform a method to manage power usage in the data processing system, the method comprising:

determining information on power usage of a plurality of components during a first time period, the plurality of components including a set of non-throttled components and a set of throttled components, wherein each throttled component is capable of being actively controlled to one or more corresponding throttle settings, and wherein each throttle setting includes a different combination of one or more operating settings for the corresponding throttled component;

estimating power usage of the set of non-throttled components during a second time period; and

determining, according to a target goal level, one or more global throttle settings, wherein each global throttle setting corresponds to a set of throttle settings, and wherein the set of throttle settings includes a different combination of throttle settings for the throttled components such that power usage of the plurality of components during the second time period satisfies a system constraint.

10. The non-transitory machine readable medium of claim 9, the method further comprising:

providing, by one or more non-throttled components, respective state signals corresponding to respective global states; and

wherein estimating power usage of the one or more non-throttled components during the second time period is based on the respective state signals.

11. The non-transitory machine readable medium of claim 9, wherein the target goal level is a function of a current state of the data processing system, and wherein the function is based at least in part on respective current workloads of one or more throttled components.

12. The non-transitory machine readable medium of claim 9, wherein the target goal level is based on a combination of required performance levels, and wherein the combination of required performance levels includes at least one of a required computing power level or a required energy consumption level.

13. The non-transitory machine readable medium of claim 9, the method further comprising:

sorting the one or more global throttle settings in an order of priority according to the target goal level; and

selecting a highest priority global throttle setting such that power usage of the plurality of components during the second time period satisfies the system constraint.

14. The non-transitory machine readable medium of claim 10, the method further comprising:

estimating, when a non-throttled component does not provide a respective state signal, that the power usage of the non-throttled component during the second time period is a maximum power usage for the non-throttled component.

15. The non-transitory machine readable medium of claim 11, the method further comprising:

estimating the respective current workloads of the one or more throttled components based on the information on power usage of the plurality of components during the first time period.

16. The non-transitory machine readable medium of claim 13, wherein the system constraint includes a limit on at least one of power usage, battery discharge current, thermal/heat dissipation, or heat generation.

17. A method comprising:

determining information on power usage of a plurality of components during a first time period, the plurality of components including a set of non-throttled components and a set of throttled components, wherein each throttled component is capable of being actively controlled to one or more corresponding throttle settings, and wherein each throttle setting includes a different combination of one or more operating settings for the corresponding throttled component;

estimating power usage of the set of non-throttled components during a second time period; and

determining, according to a target goal level, one or more global throttle settings, wherein each global throttle setting corresponds to a set of throttle settings, and wherein the set of throttle settings includes a different combination of throttle settings for the throttled components such that power usage of the plurality of components during the second time period satisfies a system constraint.

18. The method of claim 17 further comprising:

providing, by one or more non-throttled components, respective state signals corresponding to respective global states; and

wherein estimating power usage of the one or more non-throttled components during the second time period is based on the respective state signals.

19. The method of claim 17, wherein the target goal level is a function of a current state of the data processing system, and wherein the function is based at least in part on respective current workloads of one or more throttled components.

20. The method of claim 17, wherein the target goal level is based on a combination of required performance levels, and wherein the combination of required performance levels includes at least one of a required computing power level or a required energy consumption level.

21. The method of claim 17, further comprising:

sorting the one or more global throttle settings in an order of priority according to the target goal level; and

selecting a highest priority global throttle setting such that power usage of the plurality of components during the second time period satisfies the system constraint.

22. The method of claim 18 further comprising:

estimating, when a non-throttled component does not provide a respective state signal, that the power usage of the non-throttled component during the second time period is a maximum power usage for the non-throttled component.

23. The method of claim 19, further comprising:

estimating the respective current workloads of the one or more throttled components based on the information on power usage of the plurality of components during the first time period.

24. The method of claim 21, wherein the system constraint includes a limit on at least one of power usage, battery discharge current, thermal/heat dissipation, or heat generation.