Electronic device controlling CPU clock, method for operating same, and storage medium
According to an embodiment, an electronic device may include at least one communication processor comprising at least one central processing unit (CPU). According to an embodiment, the at least one communication processor may be configured to enter an RRC_Connected state. According to an embodiment, the at least one communication processor may be configured to control a clock level for the at least one CPU to be a first CPU clock level corresponding to the RRC_Connected state. According to an embodiment, the at least one communication processor may be configured to identify workload information comprising at least one of utilization information of the at least one CPU and traffic information of at least one bus of the at least one communication processor. According to an embodiment, the at least one communication processor may be configured provide the workload information as an input to an artificial intelligence (AI) model, wherein the AI model is trained using training data comprising at least one of CPU utilization information and bus traffic information as input values and CPU clock levels as output values. According to an embodiment, the at least one communication processor may be configured to identify, based on the providing the workload information as the input to the AI model, a second CPU clock level as an output of the AI model. Various other embodiments may be possible.
1. An electronic device comprising:
memory storing one or more computer programs; and
at least one communication processor comprising at least one central processing unit (CPU),
wherein the one or more computer programs include computer-executable instructions that, when executed by the at least one communication processor individually or collectively, cause the electronic device to:
enter an RRC_Connected state;
select an artificial intelligence (AI) model based on whether the AI model satisfies a first condition related to an application;
control a clock level for the at least one CPU to be a first CPU clock level based on a state of the at least one communication processor or the AI model;
identify workload information comprising at least one of utilization information of the at least one CPU and traffic information of at least one bus of the at least one communication processor;
identify a maximum workload based on the first CPU clock level and whether a second condition related to an increase in a throughput is satisfied;
generate the workload information comprising the maximum workload and the first CPU clock level;
provide the workload information as an input to the AI model, wherein the AI model is trained using training data comprising at least one of CPU utilization information and bus traffic information as input values and CPU clock levels as output values;
identify, based on the providing the workload information as the input to the AI model, a second CPU clock level as an output of the AI model; and
change the clock level for the at least one CPU from the first CPU clock level to the second CPU clock level.
2. The electronic device of claim 1 , wherein the utilization information of the at least one CPU comprises utilization information of a first part of the at least one CPU.
3. The electronic device of claim 2 , wherein the first part of the at least one CPU comprises a CPU configured to be consistently turned on independent of an operation of the at least one communication processor.
4. The electronic device of claim 1 , wherein the traffic information of the at least one bus of the at least one communication processor comprises at least one of traffic information of a CPU bus of the at least one communication processor, traffic information of a data bus of the at least one communication processor, and traffic information of a DMA bus of the at least one communication processor.
5. The electronic device of claim 1 ,
wherein the one or more computer programs include computer-executable instructions that, when executed by the at least one communication processor individually or collectively, cause the electronic device to:
identify the throughput of the electronic device, and
identify the first CPU clock level based on the throughput.
6. The electronic device of claim 1 , wherein the AI model is selected further based on at least one of the state of the at least one communication processor and a state of the electronic device.
7. The electronic device of claim 1 , wherein the second CPU clock level is identified as the output of the AI model further based on the state of the at least one communication processor or a state of the electronic device satisfying the first condition.
8. The electronic device of claim 7 , wherein the first condition is associated with at least one of a measurement value of at least one piece of hardware of the electronic device and execution of the application by the electronic device.
9. A method of operating an electronic device, the method comprising:
entering an RRC_Connected state;
selecting an artificial intelligence (AI) model based on whether the AI model satisfies a first condition related to an application;
controlling a clock level for at least one central processing unit (CPU) included in at least one communication processor of the electronic device to be a first CPU clock level based on a state of the at least one communication processor or the AI model;
identifying workload information comprising at least one of utilization information of the at least one CPU and traffic information of at least one bus of the at least one communication processor;
identifying a maximum workload based on the first CPU clock level and whether a second condition related to an increase in a throughput is satisfied;
generating the workload information comprising the maximum workload and the first CPU clock level;
providing the workload information as an input to the AI model, wherein the AI model is trained using training data comprising at least one of CPU utilization information and bus traffic information as input values and CPU clock levels as output values;
identifying, based on the providing the workload information as the input to the AI model, a second CPU clock level as an output of the AI model; and
changing the clock level for the at least one CPU from the first CPU clock level to the second CPU clock level.
10. The method of claim 9 , wherein the utilization information of the at least one CPU comprises utilization information of a first part of the at least one CPU.
11. The method of claim 10 , wherein the first part of the at least one CPU comprises a CPU configured to be consistently turned on independent of an operation of the at least one communication processor.
12. The method of claim 9 , wherein the traffic information of the at least one bus of the at least one communication processor comprises traffic information of a CPU bus of the at least one communication processor, traffic information of a data bus of the at least one communication processor, and traffic information of a DMA bus of the at least one communication processor.
13. The method of claim 9 , further comprising:
identifying the throughput of the electronic device; and
identifying the first CPU clock level based on the throughput.
14. The method of claim 9 , wherein the AI model is selected further based on at least one of the state of the at least one communication processor and a state of the electronic device.
15. The method of claim 9 , wherein the second CPU clock level is identified as the output of the AI model-based on the state of the at least one communication processor or a state of the electronic device satisfying the first condition.
16. The method of claim 15 , wherein the first condition comprises a measurement value of at least one piece of hardware of the electronic device and execution of the application by the electronic device.
17. A non-transitory computer readable medium having instructions stored therein, which when executed by at least one communication processor of an electronic device, cause the electronic device to execute a method of operating the electronic device, the method comprising:
entering an RRC_Connected state;
selecting an artificial intelligence (AI) model based on whether the AI model satisfies a first condition related to an application;
controlling a clock level for at least one central processing unit (CPU) included in at least one communication processor of the electronic device to be a first CPU clock level based on a state of the at least one communication processor or the AI model;
identifying workload information comprising at least one of utilization information of the at least one CPU and traffic information of at least one bus of the at least one communication processor;
identifying a maximum workload based on the first CPU clock level and whether a second condition related to an increase in a throughput is satisfied;
generating the workload information comprising the maximum workload and the first CPU clock level;
providing the workload information as an input to the AI model, wherein the AI model is trained using training data comprising at least one of CPU utilization information and bus traffic information as input values and CPU clock levels as output values;
identifying, based on the providing the workload information as the input to the AI model, a second CPU clock level as an output of the AI model; and
changing the clock level for the at least one CPU from the first CPU clock level to the second CPU clock level.
18. The non-transitory computer readable medium of claim 17 , wherein the utilization information of the at least one CPU comprises utilization information of a first part of the at least one CPU.