Selective GPU throttling

Patent metadata

Field	Value
Publication number	US-9530174-B2
Application number	US-201414503311-A
Country	US
Kind code	B2
Filing date	Sep 30, 2014
Priority date	May 30, 2014
Publication date	Dec 27, 2016
Grant date	Dec 27, 2016

Abstract

A method and apparatus of a device that manages a thermal profile of a device by selectively throttling graphics processing unit operations of the device is described. In an exemplary embodiment, the device monitors the thermal profile of the device, where the device executes a plurality of processes that utilizes a graphics processing unit of the device. In addition, the plurality of processes include a high priority process and a low priority process. If the thermal profile of the device exceeds a thermal threshold, the device decreases a first GPU utilization for the low priority process and maintains a second GPU utilization for the high priority process. The device further executes the low priority process using the first GPU utilization with the GPU and executes the high priority process using the second GPU utilization with the GPU.

First claim

What is claimed is:

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 data of the thermal profile of the device, the device is executing a plurality of processes that utilize a graphics processing unit (GPU) of the device, the plurality of processes including a high priority process and a low priority process;
if the thermal data of the device exceeds a first thermal threshold,
decreasing a first GPU utilization for the low priority process, and
maintaining a second GPU utilization for the high priority process;

executing the low priority process using the first GPU utilization with the GPU; and
executing the high priority process using the second GPU utilization with the GPU, wherein the first GPU utilization is different from the second GPU utilization after the thermal data of the device exceeds a first thermal threshold and the first and second GPU utilizations are each a different percentage of a maximum GPU frequency.

2. The non-transitory machine-readable medium of claim 1 , wherein a GPU utilization sets the amount of GPU resources are used for a process when that process is executed by the GPU.

3. The non-transitory machine-readable medium of claim 2 , wherein the GPU utilization can be zero.

4. The non-transitory machine-readable medium of claim 2 , wherein the GPU execution level is greater than zero and less than 100%.

5. The non-transitory machine-readable medium of claim 1 , wherein the first GPU utilization is less than 100% and the second GPU utilization is 100%.

6. The non-transitory machine-readable medium of claim 1 , if the thermal data of the device exceeds a second thermal threshold,
further increasing the first GPU utilization; and
decreasing the second GPU utilization, wherein the second GPU utilization is less than 100%.

7. The non-transitory machine-readable medium of claim 6 , if the thermal data falls below the second thermal threshold,
restoring the first and second GPU utilization to previous values.

8. The non-transitory machine-readable medium of claim 1 , wherein the thermal data is selected from the group consisting of device temperature and audible fan noise.

9. The non-transitory machine-readable medium of claim 1 , wherein the high priority process is visual process and the low priority is a batch process.

10. The non-transitory machine-readable medium of claim 1 , wherein the monitoring of the thermal data comprises:
recording the device temperature.

11. A method to manage a thermal profile of a device, the method comprising:
monitoring thermal data of the thermal profile of the device, the device is executing a plurality of processes that utilize a graphics processing unit (GPU) of the device, the plurality of processes including a high priority process and a low priority process;
if the thermal data of the device exceeds a first thermal threshold,
decreasing a first GPU utilization for the low priority process, and
maintaining a second GPU utilization for the high priority process;

executing the low priority process using the first GPU utilization with the GPU; and
executing the high priority process using the second GPU utilization with the GPU, wherein the first GPU utilization is different from the second GPU utilization after the thermal data of the device exceeds a first thermal threshold and the first and second GPU utilizations are each a different percentage of a maximum GPU frequency.

12. The method of claim 11 , wherein a GPU utilization sets the amount of GPU resources are used for a process when that process is executed by the GPU.

13. The method of claim 11 , if the thermal data of the device exceeds a second thermal threshold,
further increasing the first GPU utilization; and
decreasing the second GPU utilization, wherein the second GPU utilization is less than 100%.

14. The method of claim 13 , if the thermal data falls below the second thermal threshold,
restoring the first and second GPU utilization to previous values.

15. The method of claim 11 , wherein the thermal data is selected from the group consisting of device temperature and audible fan noise.

16. The method of claim 11 , wherein the high priority process is visual process and the low priority is a batch process.

17. A device to manage a thermal profile of the device, the device comprising:
a processor;
a memory coupled to the processor though a bus; and
a process executed from the memory by the processor that causes the processor to monitor thermal data of the thermal profile of the device, the device is executing a plurality of processes that utilize a graphics processing unit (GPU) of the device, the plurality of processes including a high priority process and a low priority process, if the thermal data of the device exceeds a first thermal threshold, decrease a first GPU utilization for the low priority process, and maintain a second GPU utilization for the high priority process, execute the low priority process using the first GPU utilization with the GPU, and execute the high priority process using the second GPU utilization with the GPU, wherein the first GPU utilization is different from the second GPU utilization after the thermal data of the device exceeds a first thermal threshold and the first and second GPU utilizations are each a different percentage of a maximum GPU frequency.

18. The device of claim 17 , wherein a GPU utilization sets the amount of GPU resources are used for a process when that process is executed by the GPU.

19. The device of claim 17 , if the thermal data of the device exceeds a second thermal threshold, the process further causes the processor to further increase the first GPU utilization and decrease the second GPU utilization, wherein the second GPU utilization is less than 100%.

20. The device of claim 19 , if the thermal data falls below the second thermal threshold, the process further causes the processor to restore the first and second GPU utilization to previous values.

Assignees

• Apple Inc

Inventors

• Vaishampayan Umesh Suresh
• Kumar Derek R
• Foret Cecile Marie
• Sumpter Anthony Graham
• Gopalakrishnan Harshavardhan P
• Damon Iii William E

Classifications

• G06F1/206 Primary

  comprising thermal management · CPC title

• G06F9/4893

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

• G06T2200/28

  involving image processing hardware · CPC title

• G06T1/20 Primary

  Processor architectures; Processor configuration, e.g. pipelining · CPC title

• G09G5/363

  Graphics controllers · CPC title