IP Library › Granted Patent US 9,256,274
Granted Patent B2
US 9,256,274 · App. 14/135,577 · Granted Feb 9, 2016

Dynamic low power states characterization

Inventors: Nicole Chalhoub (Antibes, FR); Damien Ramonda (Mougins, FR); François Lacoste (Roquefort les Pins, FR); Karine Bartolo (Le Rouret, FR); Vincent Bour (Antibes, FR)
Assignee: TEXAS INSTRUMENTS INCORPORATED
G06F1/3234
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,256,274
App. No.
14/135,577
Granted
Feb 9, 2016
Kind
B2
Abstract

An optimal idle state of a processor is selected using dynamically derived parameters. For example, the idle state is selected from a group of possible idle power states. A current detector is arranged to perform power measurements of the processor and to report a total power consumption of the processor for each time value of a range of discrete values for each possible idle power state. A calibration unit is arranged to communicate with the current detector and the processor, and to automatically activate a calibration sequence that is used to produce data from which idle power state is optimal for the processor for an estimated idle period.

Claims (29)

1. A computing device, comprising:

a processor that is arranged to enter an idle state that is selected from a group of characterized idle states, wherein the selected idle state is an optimal idle state that is selected from the group of the characterized idle states in response to an estimated idle period in which the processor is estimated to remain in the selected idle state;

a detector that is arranged to provide processor power indications that are used to determine an amount of power consumed by the processor while the processor is in any of the idle states of the group of characterized idle states; and

a calibration unit that is arranged to characterize each idle state of the group of characterized idle states in response to the provided processor power indications, wherein each idle state is characterized by determining an aggregate amount of power consumed by the processor during each iteration of the processor operating in the idle state for a different idle period.

2. The device of claim 1 , wherein the calibration unit is arranged to compare an aggregate power consumption for each different idle period of a plurality of characterized idle states of the group of idle states and select an idle state having the least aggregate amount of power that is associated with the estimated idle period.

3. The device of claim 2 , wherein the calibration unit is arranged to compare each aggregate power consumption for each different idle period of a first characterized idle state with each aggregate power consumption for each respective different idle period of a second characterized idle state and determine a threshold where one of the aggregate power consumption for each different idle period of either the first or second characterized idle states transitions to a power consumption that is lower than a respective aggregate power consumption of the second or first, respectively, characterized idle state.

4. The device of claim 3 , wherein the calibration unit is arranged to store the determined threshold information in association with an indication of the idle state having the transitioned-to lower power consumption, wherein the indication of the idle state identifies the idle state having the transitioned-to lower power consumption as being the optimal idle power state.

5. The device of claim 4 , wherein the estimated idle period is compared with the stored threshold information to determine the associated idle state having the lower power consumption.

6. The device of claim 4 , wherein the indication of the idle state identifies the idle state having the transitioned-to lower power consumption as being the optimal idle power state.

7. The device of claim 6 , wherein the optimal idle power state is subsequently characterized in response to the identification of being the optimal idle power state.

8. The device of claim 1 , wherein the characterization is performed after the deployment of the computing device.

9. The device of claim 8 , wherein the characterization is initiated within the computing device.

10. The device of claim 1 , wherein the stored threshold information is updated to reflect newer threshold information derived from the processor power indications provided by the detector.

11. The device of claim 1 , wherein the characterization is performed at periodic intervals.

12. The device of claim 1 , wherein the characterization is performed in response to a change in operating temperature of the computing device.

13. The device of claim 4 , wherein estimation of idle time is determined in response to a comparison between performance requirements and performance capabilities of the computing device.

14. The device of claim 1 , wherein the idle period includes the quiescent idle period and one or more of the entry transition period and the exit transition period of the idle state.

15. A low power states characterization system, comprising:

a processor coupled to a power supply, the processor including a plurality of idle power states, each idle power state associated with an idle period;

a current detector that is arranged to perform power measurements of the processor and to report a total power consumption of the processor for each possible idle power state over a plurality of different durations for each possible idle power state; and

a calibration unit that is arranged to communicate with the current detector and the processor, and to store the reported total power consumption data from the detector, and wherein the calibration unit activates a calibration sequence to select an optimal idle power state of the processor in response to comparisons of the received total power consumption data with the stored total power consumption data for each idle power state, repeating the calibration sequence for different idle periods over each idle power state, and selecting an optimal idle power state for a given idle period in response to the total power consumption data reported by the current detector.

16. The system of claim 15 , wherein the current detector is arranged in a common substrate the processor.

17. The system of claim 15 wherein the calibration unit is at least partially embodied as a software application of the processor.

18. A method, comprising:

selecting an idle state as an optimal idle state from a group of the characterized idle states in response to an estimated idle period in which a processor is estimated to remain in the selected idle state;

providing processor power indications that are used to determine an amount of power consumed by the processor while the processor is in any of the idle states of the group of characterized idle states; and

characterizing each idle state of the group of characterized idle states in response to the provided processor power indications, wherein each idle state is characterized by determining an aggregate amount of power consumed by the processor during each iteration of the processor operating in the idle state for a different idle period.

19. The method of claim 18 , comprising updating a list of selected idle power states in response to a parsable list of possible idle power states that is received after deployment of a system that includes the processor.

20. The method of claim 18 , wherein each idle state of the group of characterized idle states is characterized after deployment of a system that includes the processor.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 8, 2014
From: TEXAS INSTRUMENTS FRANCE; CHALHOUB, NICOLE; RAMONDA, DAMIEN; LACOSTE, FRANCOIS; BARTOLO, KARINE; BOUR, VINCENT
To: TEXAS INSTRUMENTS INCORPORATED
Reel/Frame 032202/0413 →
Priority Claims (1)
EP 13290183 · Aug 1, 2013 · regional
Continuity (1)
Related Publication 20150039922A1 · Feb 5, 2015