Scheduling method, scheduling apparatus and storage medium

Patent metadata

Field	Value
Publication number	US-12443441-B2
Application number	US-202217877844-A
Country	US
Kind code	B2
Filing date	Jul 29, 2022
Priority date	Mar 21, 2022
Publication date	Oct 14, 2025
Grant date	Oct 14, 2025

Abstract

The present disclosure relates to a scheduling method, a scheduling apparatus and a storage medium. The method includes: acquiring, by a terminal device, temperatures of the terminal device in two adjacent monitoring periods; determining a temperature change level based on a first temperature difference between the adjacent monitoring periods; and determining and executing a corresponding CPU scheduling strategy based on the temperature change level, to maintain the temperature of the terminal device below a temperature warning value.

First claim

What is claimed is:

1. A scheduling method, performed by a terminal device having a multi-core CPU architecture, a temperature sensor, an Energy Aware Scheduling (EAS) scheduler, and a graphics processing unit (GPU), comprising:
acquiring, by the temperature sensor, temperatures of the terminal device in two adjacent monitoring periods;
determining, by the EAS scheduler, a temperature change level based on a first temperature difference between the adjacent monitoring periods, wherein the temperature change level comprises a first level, a second level, and a third level; and
adjusting dynamically, by the EAS scheduler, a corresponding CPU scheduling strategy based on the temperature change level, to maintain a temperature of the terminal device below a temperature warning value, wherein the CPU scheduling strategy comprises at least one of following:
disabling a large core cluster in the CPU, restricting a frequency of a medium core cluster in the CPU, restricting a frequency of the GPU, and clearing preset applications run in a background, in response to that the temperature change level is the first level;
restricting frequencies of a large core cluster and a medium core cluster in the CPU, and reducing a CPU occupancy rate of applications run in a background, in response to that the temperature change level is the second level; or
maintaining a current running state of a CPU core cluster, in response to that the temperature change level is the third level.

2. The scheduling method according to claim 1 , wherein the first temperature difference is configured to indicate a temperature difference between a current monitoring period and a previous monitoring period; and
wherein determining the temperature change level based on the first temperature difference between the adjacent monitoring periods comprises:
determining the temperature change level being the first level in response to that the first temperature difference is not smaller than a change amount threshold; and
determining the temperature change level being the second level or the third level based on temperature changes of a plurality of consecutive monitoring periods, in response to that the first temperature difference is smaller than the change amount threshold.

3. The scheduling method according to claim 2 , wherein determining the temperature change level being the second level or the third level based on temperature changes of a plurality of consecutive monitoring periods comprises:
successively determining a plurality of second temperature differences in the plurality of monitoring periods based on temperatures of the plurality of consecutive monitoring periods comprising the current monitoring period, wherein the second temperature difference is configured to indicate a temperature difference between a latter monitoring period and a former monitoring period in every two adjacent monitoring periods of the plurality of consecutive monitoring periods; and
determining a corresponding temperature change level based on the plurality of second temperature differences.

4. The scheduling method according to claim 3 , wherein determining the corresponding temperature change level based on the plurality of second temperature differences comprises:
determining the temperature change level being the second level in response to that the plurality of second temperature differences are all greater than 0 and increase successively; and
determining the temperature change level being the third level in response to that a part of temperature differences among the plurality of second temperature differences is not greater than 0.

5. The scheduling method according to claim 1 , further comprising:
acquiring a temperature of a preset monitoring period after executing the scheduling strategy; and
determining and executing a corresponding performance optimization strategy based on the temperature of the preset monitoring period.

6. The scheduling method according to claim 5 , wherein determining and executing the corresponding performance optimization strategy based on the temperature of the preset monitoring period comprises:
determining and executing at least one of following performance optimization strategies in response to that the temperature of the preset monitoring period is smaller than a temperature threshold: stopping a measure of disabling or restricting a large core cluster and a medium core cluster in the CPU, stopping a measure of restricting a GPU, or increasing frequencies of the large core cluster and the medium core cluster in the CPU; and
determining and executing at least one of following performance optimization strategies in response to that the temperature of the preset monitoring period is not smaller than the temperature threshold and temperatures of a plurality of successive monitoring periods comprising the preset monitoring period gradually decrease: stopping a measure of disabling the large core cluster in the CPU, or restoring a frequency of the GPU,
wherein, the temperature threshold is smaller than the temperature warning value.

7. A scheduling apparatus, applied to a terminal device having a multi-core CPU architecture, a temperature sensor, an Energy Aware Scheduling (EAS) scheduler, and a graphics processing unit (GPU), and comprising:
a processor; and
a memory, for storing instructions executable by the processor,
wherein the processor is configured to:
acquire temperatures of the terminal device in two adjacent monitoring periods;
determine a temperature change level based on a first temperature difference between the adjacent monitoring periods, wherein the temperature change level comprises a first level, a second level, and a third level; and
adjust dynamically a corresponding CPU scheduling strategy based on the temperature change level, to maintain a temperature of the terminal device below a temperature warning value, wherein the CPU scheduling strategy comprises at least one of following:
disabling a large core cluster in the CPU, restricting a frequency of a medium core cluster in the CPU, restricting a frequency of the GPU, and clearing preset applications run in a background, in response to that the temperature change level is the first level;
restricting frequencies of a large core cluster and a medium core cluster in the CPU, and reducing a CPU occupancy rate of applications run in a background, in response to that the temperature change level is the second level; or
maintaining a current running state of a CPU core cluster, in response to that the temperature change level is the third level.

8. The scheduling apparatus according to claim 7 , wherein the first temperature difference is configured to indicate a temperature difference between a current monitoring period and a previous monitoring period; and
the processor is further configured to:
determine the temperature change level being the first level in response to that the first temperature difference is not smaller than a change amount threshold; and
determine the temperature change level being the second level or the third level based on temperature changes of a plurality of consecutive monitoring periods, in response to that the first temperature difference is smaller than the change amount threshold.

9. The scheduling apparatus according to claim 8 , wherein the processor is further configured to:
successively determine a plurality of second temperature differences in the plurality of monitoring periods based on temperatures of the plurality of consecutive monitoring periods comprising the current monitoring period, wherein the second temperature difference is configured to indicate a temperature difference between a latter monitoring period and a f

Assignees

• Beijing Xiaomi Mobile Software Co Ltd

Inventors

• Gu Chao
• He Shuai

Classifications

• Y02D10/00

  Energy efficient computing, e.g. low power processors, power management or thermal management · CPC title

• G06F9/4893 Primary

  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

• G06F1/329

  by task scheduling · CPC title

• G06F1/206 Primary

  comprising thermal management · CPC title

• G06F9/5027 Primary

  the resource being a machine, e.g. CPUs, Servers, Terminals · CPC title