Thermally adaptive quality-of-service
A method and apparatus of a device that manages a thermal profile of a device by selectively throttling central processing unit operations of the device is described. The device manages a thermal profile of the device by adjusting a throttling a central processing unit execution of a historically high energy consuming task. In this embodiment, the device monitors thermal level of the thermal profile of the device, the device is executing a plurality of tasks that utilize a plurality of processing cores of the device. If the thermal level of the device exceeds a thermal threshold, the device identifies one of the plurality of tasks as a historically high energy consuming task, and throttles this historically high energy consuming task by setting a force idle execution time for the historically high energy consuming task. The device further executes the plurality of tasks.
1. A non-transitory machine-readable medium having executable instructions to cause one or more processing units to perform a method to manage a thermal profile of a device, the method comprising:
monitoring thermal level of the thermal profile of the device, wherein the device is executing a plurality of tasks that utilize a plurality of processing cores of the device;
if the thermal level of the device exceeds a thermal threshold,
identifying one of the plurality of tasks as a historically high energy consuming task, wherein the identifying is based on at least information about historical energy consumption from a database that tracks energy consumption from previously running tasks, and
throttling the historically high energy consuming task by setting a force idle execution time for the historically high energy consuming task, wherein the force idle time is a percentage greater than zero and less than a hundred, wherein the force idle time percentage is set by the system according to the threshold exceeded; and
executing the plurality of tasks.
2. The non-transitory machine-readable medium of claim 1 , wherein a selective forced idle is an amount of time during an execution window that a task is not being executed.
3. The non-transitory machine-readable medium of claim 2 , further comprising:
putting a first processing core in a low power state during the selective forced idle.
4. The non-transitory machine-readable medium of claim 2 , further comprising:
overlapping the selective forced idle execution time with another one of the plurality of task that has a corresponding selective forced idle execution time.
5. The non-transitory machine-readable medium of claim 1 , wherein a historically high energy consuming task is a task that consumes more energy than an average of the plurality of tasks.
6. The non-transitory machine-readable medium of claim 1 , further comprising:
capturing energy consumption data for the plurality of tasks.
7. The non-transitory machine-readable medium of claim 6 , wherein the energy consumption data for one of the plurality of tasks is the amount of energy that is used by the device to execute that task.
8. The non-transitory machine-readable medium of claim 1 , wherein the executing the tasks comprises executing the plurality of tasks on a plurality of processing cores of the device.
9. The non-transitory machine-readable medium of claim 1 , wherein the thermal level is selected from the group consisting of device temperature and audible fan noise.
10. The non-transitory machine-readable medium of claim 1 , wherein the monitoring of the thermal level comprises:
recording the device temperature.
11. The non-transitory machine-readable medium of claim 1 , wherein the historically high energy consuming task is a foreground task.
12. A method to manage a thermal profile of a device, the method comprising:
monitoring thermal level of the thermal profile of the device, wherein the device is executing a plurality of tasks that utilize a plurality of processing cores of the device;
if the thermal level of the device exceeds a thermal threshold,
identifying one of the plurality of tasks as a historically high energy consuming task, wherein the identifying is based on at least information about historical energy consumption from a database that tracks energy consumption from previously running tasks, and
throttling the historically high energy consuming task by setting a force idle execution time for the historically high energy consuming task, wherein the force idle time is a percentage greater than zero and less than a hundred, wherein the force idle time percentage is set by the system according to the threshold exceeded; and
executing the plurality of tasks.
13. The method of claim 12 , wherein a selective forced idle is an amount of time during an execution window that a task is not being executed.
14. The method of claim 13 , further comprising:
overlapping the selective forced idle execution time with another one of the plurality of task that has a corresponding selective forced idle execution time.
15. The method of claim 13 , wherein a historically high energy consuming task is a task that consumes more energy than an average of the plurality of tasks.