System and methods for scheduling software tasks based on central processing unit power characteristics

Patent metadata

Field	Value
Publication number	US-10459517-B2
Application number	US-201715689090-A
Country	US
Kind code	B2
Filing date	Aug 29, 2017
Priority date	Mar 31, 2017
Publication date	Oct 29, 2019
Grant date	Oct 29, 2019

Abstract

Methods and devices for scheduling processing tasks in a computing device configured with a group of low-power processor cores and at least one high-performance processor core may include identifying multiple application streams related to communication with a wireless local area network (WLAN), computing a total WLAN throughput requirement for the application streams, and determining whether the total WLAN throughput requirement is less than a first threshold value. The first threshold value may be based on power characteristics of the low-power processor cores. In response to determining that the total WLAN throughput requirement is less than the first threshold value, the computing device may schedule all processing tasks for the multiple application streams on one of the low-power processor cores.

First claim

What is claimed is:

1. A method of scheduling processing tasks in a computing device having a group of low-power processor cores and other processor cores, the method comprising:
identifying multiple application streams related to communication with a wireless local area network (WLAN);
computing a total WLAN throughput requirement for the multiple application streams;
determining whether the total WLAN throughput requirement is less than a first threshold value, wherein the first threshold value is based on power characteristics of the low-power processor cores; and
in response to determining that the total WLAN throughput requirement is not less than the first threshold value:
determining whether the total WLAN throughput requirement is less than a second threshold value, wherein the second threshold value corresponds to a change in a power profile curve measuring power consumption as a function of workload for the low-power processor cores; and
scheduling processing tasks for the multiple application streams by distributing the tasks across all of the low-power processor cores in response to determining that the total WLAN throughput requirement is not less than the second threshold value.

2. The method of claim 1 , further comprising scheduling all processing tasks for the multiple application streams on at least one of the low-power processor cores in response to determining that the total WLAN throughput requirement is less than the second threshold value.

3. The method of claim 1 , further comprising scheduling all processing tasks for the multiple application streams on one of the low-power processor cores in response to determining that the total WLAN throughput requirement is less than the first threshold value.

4. The method of claim 1 , wherein distributing the tasks across all of the low-power processor cores reduces an average frequency among the low-power processor cores, wherein reducing the average frequency among the low-power processor cores provides a power advantage based on a slower rate of increase in performance than power consumption.

5. The method of claim 1 , wherein the processing tasks for the multiple application streams comprise at least WLAN driver software and internet protocol (IP) stack software.

6. The method of claim 1 , wherein a performance core is turned off during the scheduling.

7. A computing device, comprising:
a processing device having a group of low-power processor cores and at least one high-performance processor core, wherein the processing device is configured with processor-executable instructions to:
identify multiple application streams related to communication with a wireless local area network (WLAN);
compute a total WLAN throughput requirement for the multiple application streams;
determine whether the total WLAN throughput requirement is less than a first threshold value, wherein the first threshold value is based on power characteristics of the low-power processor cores; and
in response to determining that the total WLAN throughput requirement is not less than the first threshold value:
determine whether the total WLAN throughput requirement is less than a second threshold value, wherein the second threshold value corresponds to a change in a power profile curve measuring power consumption as a function of workload for the low-power processor cores; and
schedule processing tasks for the multiple application streams by distributing the tasks across all of the low-power processor cores in response to determining that the total WLAN throughput requirement is not less than the second threshold value.

8. The computing device of claim 7 , wherein the processing device is further configured with processor-executable instructions to schedule all processing tasks for the multiple application streams on at least one of the low-power processor cores in response to determining that the total WLAN throughput requirement is less than the second threshold value.

9. The computing device of claim 7 , wherein the processing device is further configured with processor-executable instructions to schedule processing tasks for the multiple application streams on one of the low-power processor cores in response to determining that the total WLAN throughput requirement is less than the first threshold value.

10. The computing device of claim 7 , wherein distributing the tasks across all of the low-power processor cores reduces an average frequency among the low-power processor cores, wherein reducing the average frequency among the low-power processor cores provides a power advantage based on a slower rate of increase in performance than power consumption.

11. The computing device of claim 7 , wherein the processing tasks for the multiple application streams comprise at least WLAN driver software and internet protocol (IP) stack software.

12. The computing device of claim 7 , wherein a performance core is turned off during the scheduling.

13. A computing device, comprising:
a group of low-power processor cores and at least one high-performance processor core;
means for identifying multiple application streams related to communication with a wireless local area network (WLAN);
means for computing a total WLAN throughput requirement for the multiple application streams;
means for determining whether the total WLAN throughput requirement is less than a first threshold value, wherein the first threshold value is based on power characteristics of the low-power processor cores;
means for determining whether the total WLAN throughput requirement is less than a second threshold value in response to determining that the total WLAN throughput requirement is not less than the first threshold value, wherein the second threshold value corresponds to a change in a power profile curve measuring power consumption as a function of workload for the low-power processor cores; and
means for scheduling processing tasks for the multiple application streams by distributing the processing tasks across all of the low-power processor cores in response to determining that the total WLAN throughput requirement is not less than the second threshold value.

14. The computing device of claim 13 , further comprising means for scheduling all processing tasks for the multiple application streams on at least one of the low-power processor cores in response to determining that the total WLAN throughput requirement is less than the second threshold value.

15. The computing device of claim 13 , further comprising means for scheduling all processing tasks for the multiple application streams on one of the low-power processor cores in response to determining that the total WLAN throughput requirement is less than the first threshold value.

16. The computing device of claim 13 , distributing the processing tasks across all of the low-power processor cores reduces an average frequency among the low-power processor cores, wherein reducing the average frequency among the low-power processor cores provides a power advantage based on a slower rate of increase in performance than power consumption.

17. The computing device of claim 13 , wherein the processing tasks for the multiple application streams comprise at least WLAN driver software and internet protocol (IP) stack software.

18. The computing device of claim 13 , wherein a performance core is turned off during the scheduling.

19. A non-transitory processor-readable storage medium having stored thereon processor-executable instructions configured to cause a processing device having

Assignees

• Qualcomm Inc

Inventors

• He Rong
• Dutt Debashis
• Akyildiz Orhan
• Bhatia Sunit

Classifications

• 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

• 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

• G06F1/206

  comprising thermal management · CPC title

• H04L67/1029

  using data related to the state of servers by a load balancer · CPC title

• G06F1/3206

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