Managing the operation of a computing device by determining performance-power states

Patent metadata

Field	Value
Publication number	US-9524009-B2
Application number	US-201213976789-A
Country	US
Kind code	B2
Filing date	May 14, 2012
Priority date	May 14, 2012
Publication date	Dec 20, 2016
Grant date	Dec 20, 2016

Abstract

A method and system for managing the operation of a computing system are described herein. The method includes determining a number of workloads on the computing system. The method also includes determining a number of performance-power states for each workload and a corresponding performance range and power consumption range for each performance-power state. The method further includes managing performance and power consumption of the computing system based on the performance-power states.

First claim

What is claimed is:

1. A method for managing operation of a computing system, comprising:
determining a number of workloads on the computing system;
determining a number of performance-power states for each workload and a corresponding performance range and power consumption range for each performance-power state, wherein determining the number of performance-power states comprises determining a plurality of architectural features utilized by each workload, disabling one or more of the architectural features, and operating an input/output communication link at a lower bandwidth; and
managing performance and power consumption of the computing system based on the performance-power states.

2. The method of claim 1 , comprising determining parameters corresponding to each workload by specifying a definition of performance for each workload.

3. The method of claim 2 , wherein the definition of performance is based on architectural features of the computing system.

4. The method of claim 2 , comprising receiving the definition of the performance for each workload from a user via a user interface.

5. The method of claim 1 , wherein determining the number of performance-power states for each workload comprises:
running each workload in each system operational state;
measuring a performance of the computing system for each workload in each system operational state; and
measuring a power consumption of the computing system for each workload in each system operational state.

6. The method of claim 1 , comprising managing operation of the computing system in response to input from a system management agent.

7. The method of claim 6 , wherein managing operation of the computing system comprises:
maintaining the power consumption below a predefined power limit; and
maintaining the performance at a predefined performance level.

8. The method of claim 1 , wherein each performance-power state is separated from a previous performance-power state and a next performance-power state by a minimum power consumption and a minimum performance.

9. The method of claim 1 , comprising:
determining a number of workloads corresponding to a plurality of computing systems and parameters corresponding to each workload;
determining a number of performance-power states for each workload and a corresponding performance range and power range for each performance-power state; and
managing performance and power consumption of the plurality of computing systems based on the performance-power states.

10. The method of claim 9 , comprising managing operation of the plurality of computing systems in response to input from a datacenter manager located outside of the plurality of computing systems.

11. The method of claim 9 , wherein managing the performance and the power consumption of the plurality of computing systems comprises maintaining an overall power consumption of the plurality of computing systems below a power limit while maintaining the performance of the plurality of computing systems at a uniform performance level.

12. The method of claim 1 , wherein determining the number of performance-power states comprises varying a display refresh rate, and reducing a number of instructions executed by a vector processing unit in a period of time.

13. A computing system, comprising:
a processor that is adapted to execute stored instructions; and
a storage device that stores instructions, the storage device comprising processor executable code that, when executed by the processor, is adapted to:
determine a number of workloads of the computing system;
determine a number of performance-power states for each workload, wherein determining a performance-power state comprises defining a performance level range and a power level range for the performance-power state and wherein determining the number of performance-power states comprises determining a plurality of architectural features utilized by each workload, disabling one or more of the architectural features, and operating an input/output communication link at a lower bandwidth; and
manage performance and power consumption of the computing system based on the performance-power states.

14. The computing system of claim 13 , wherein a system operational state comprises a state in which the computing system is capable of running a specific workload by varying configurable parameters.

15. The computing system of claim 13 , wherein the performance-power state comprises a state in which the computing system is capable of running a specific workload within the performance level range and the power level range.

16. The computing system of claim 13 , wherein the processor executable code is executed by the processor during an initial system boot.

17. The computing system of claim 13 , wherein the processor executable code is executed by the processor by an operating system on demand.

18. The computing system of claim 13 , wherein the processor executable code is executed by the processor as a response to a request by a user of another computing system.

19. The computing system of claim 13 , wherein the processor executable code is adapted to use the performance-power states to achieve a balance between the performance and the power consumption of the computing system.

20. The computing system of claim 13 , wherein each performance-power state is separated from a previous performance-power state and a next performance-power state by a minimum power consumption and a minimum performance.

21. At least one non-transitory machine readable medium having instructions stored therein that, in response to being executed on a computing system, cause the computing system to:
determine a number of workloads of the computing system;
determine a number of performance-power states for each workload and a corresponding performance range and power range for each performance-power state, wherein determining the number of performance-power states comprises determining a plurality of architectural features utilized by each workload, disabling one or more of the architectural features and operating an input/output communication link at a lower bandwidth; and
control performance and power consumption of the computing system based on the performance-power states.

22. The at least one non-transitory machine readable medium of claim 21 , wherein a system operational state comprises a state in which the computing system is capable of running a specific workload by varying configurable parameters.

23. The at least one non-transitory machine readable medium of claim 21 , wherein a performance-power state comprises a state in which the computing system is capable of running a specific workload within a specified performance level range and a specified power level range.

24. The at least one non-transitory machine readable medium of claim 21 , wherein the instructions cause the computing system to determine parameters corresponding to each workload by specifying a definition of performance for each workload based on any of a plurality of architectural features of the computing system.

25. The at least one non-transitory machine readable medium of claim 21 , wherein controlling the performance and the power consumption of the computing system comprises maintaining a highest performance of the computing system at a given rate of power usage.

Assignees

• Bodas Devadatta V
• Crawford John H
• Intel Corp

Inventors

• Bodas Devadatta V
• Crawford John H

Classifications

• G06F1/3203 Primary

  Power management, i.e. event-based initiation of a power-saving mode · CPC title

• G06F9/5094

  where the allocation takes into account power or heat criteria (power management in computers in general G06F1/3203; thermal management in computers in general G06F1/206) · CPC title

• G06F1/3206 Primary

  Monitoring of events, devices or parameters that trigger a change in power modality · CPC title

• Y02B60/142

  Cross-Sectional Technologies · mapped topic

• G06F1/26

  Power supply means, e.g. regulation thereof (for memories G11C) · CPC title