Voltage regulating method and electronic equipment

Abstract

The present application provides a voltage regulation method and electronic equipment, which relate to the technical field of electronic equipment. The method includes: obtaining the operation status information of each subsystem, determining the load analysis results of each subsystem according to the operation status information, and determining the following voltage regulation strategy according to the load analysis results, obtaining the first voltage regulation instruction, and determining the second voltage regulation instruction according to the following voltage regulation strategy and the first voltage regulation instruction, the first voltage regulation instruction is used to instruct the voltage of each subsystem to be adjusted to the target value, the second voltage regulation instruction is used to instruct the voltage of each subsystem to be adjusted to the actual value, and the voltage provided to each subsystem is adjusted according to the second voltage regulation instruction. It is intended to improve the problem of being unable to balance the contradiction between the performance and power consumption of electronic equipment.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of electronic equipment, and in particular to a voltage regulation method and electronic equipment. Background Art

[0002] As electronic devices become increasingly versatile, users spend more time and more frequently using them. In the process of using electronic devices, processor performance is improved to ensure that the electronic devices are in an efficient operating state. However, improving processor performance will cause electronic devices to have higher power consumption. Therefore, how to balance the contradiction between electronic device performance and power consumption is an issue that needs to be considered. Summary of the invention

[0003] The embodiments of the present application provide a voltage regulation method and an electronic device, which are used to improve the problem of being unable to balance the contradiction between the performance and power consumption of an electronic device.

[0004] To achieve the above objectives, the embodiments of the present application adopt the following technical solutions:

[0005] In a first aspect, an embodiment of the present application provides a voltage regulation method, the method comprising: obtaining operating status information of each subsystem, determining a load analysis result of each subsystem based on the operating status information, and determining a follow-up voltage regulation strategy based on the load analysis result, obtaining a first voltage regulation instruction, and determining a second voltage regulation instruction based on the follow-up voltage regulation strategy and the first voltage regulation instruction, the first voltage regulation instruction being used to instruct the voltage of each subsystem to be adjusted to a preset target value, the second voltage regulation instruction being used to instruct the voltage of each subsystem to be adjusted to an actual target value, and adjusting the voltage provided to each subsystem according to the second voltage regulation instruction.

[0006] The voltage regulation method provided by the present application can realize differentiated voltage regulation of different subsystems by taking the operating status information of each subsystem as the basic basis for voltage regulation, so that each subsystem can match the best voltage regulation strategy under different working conditions. The voltage of each subsystem of the electronic device can more accurately follow the load change, improve the accuracy of voltage regulation, reduce unnecessary power consumption, and balance the contradiction between the performance and power consumption of the electronic device.

[0007] In one possible implementation, based on the operating status information, the load analysis results of each subsystem are determined, and based on the load analysis results, a following voltage regulation strategy is determined, including: obtaining the operating status information of each subsystem in a first operating cycle, based on the operating status information of each subsystem in the first operating cycle, determining the load analysis results of each subsystem in the first operating cycle, and determining the following voltage regulation strategy for the first operating cycle based on the load analysis results of each subsystem in the first operating cycle.

[0008] In one possible implementation, based on the operating status information of each subsystem in the first operating cycle, the load analysis result of each subsystem in the first operating cycle is determined, including: inputting the operating status information of each subsystem in the first operating cycle as input features into a first preset model, and using the output of the first preset model as the load analysis result of each subsystem in the first operating cycle, wherein the first preset model is trained based on the historical operating status information of each subsystem.

[0009] The voltage regulation method provided in the present application can ensure the accuracy and reliability of the prediction results by using the preset model obtained by training with historical data, and can realize the dynamic update of the follow-up voltage regulation strategy.

[0010] In one possible implementation, a load analysis result of each subsystem is determined based on operating status information, and a following voltage regulation strategy is determined based on the load analysis result, including: obtaining operating status information of each subsystem in a first operating cycle, and determining a predicted load analysis result of each subsystem in a second operating cycle based on the operating status information of each subsystem in the first operating cycle, the second operating cycle being an operating cycle after the first operating cycle, and determining a following voltage regulation strategy for the second operating cycle based on the load analysis result of each subsystem in the second operating cycle.

[0011] In one possible implementation, based on the operating status information of each subsystem in the first operating cycle, the load analysis results of each subsystem in the first operating cycle are determined, including: inputting the operating status information of each subsystem in the second operating cycle as input features into a second preset model, and using the output of the second preset model as the predicted load analysis results of each subsystem in the second operating cycle, wherein the second preset model is trained based on the historical operating status information of each subsystem.

[0012] In a possible implementation, the load analysis results include load status and temperature status, the following voltage regulation strategy includes voltage amplitude adjustment strategy and power channel adjustment strategy, and the following voltage regulation strategy is determined according to the load analysis results, including: determining the power channel adjustment strategy of each subsystem according to the load status of each subsystem, and determining the voltage amplitude adjustment strategy of each subsystem according to the temperature status of each subsystem.

[0013] In a possible implementation, the voltage regulation instruction includes a power channel adjustment instruction and a voltage amplitude adjustment instruction. According to the following voltage regulation strategy and the first voltage regulation instruction, the second voltage regulation instruction is determined, including: according to the matching result between the power channel adjustment instruction in the first voltage regulation instruction and the power channel adjustment strategy, the power channel adjustment instruction of the second voltage regulation instruction is determined; according to the matching result between the voltage amplitude adjustment instruction in the second voltage regulation instruction and the voltage amplitude adjustment strategy, the voltage amplitude adjustment instruction of the second voltage regulation instruction is determined.

[0014] In a possible implementation, determining a power channel adjustment strategy for each subsystem according to a load state of each subsystem includes:

[0015] The load state includes influencing factors of multiple dimensions. According to the influencing factors of each dimension in at least one dimension, an evaluation score of each dimension is obtained. According to the evaluation score of each dimension and the weight coefficient corresponding to the dimension, the power channel priority score of each subsystem is determined, wherein the power channel priority score is equal to the cumulative value of the product of the evaluation score corresponding to each dimension in at least one dimension and the corresponding weight coefficient. According to the power channel priority score, the voltage regulation priority of the power channel of each subsystem is determined.

[0016] In a possible implementation, determining a voltage amplitude adjustment strategy for each subsystem according to a temperature state of each subsystem includes:

[0017] The voltage adjustment range of each subsystem is determined according to the matching result between the temperature state of each subsystem and the preset value.

[0018] In a second aspect, the present application provides an electronic device, comprising: a memory and a processor; the processor is coupled to the memory; wherein the memory is used to store computer program code, and the computer program code comprises computer instructions; when the computer instructions are executed by the processor, the electronic device executes the method of the first aspect.

[0019] In a third aspect, the present application provides a computer-readable storage medium, comprising computer instructions; when the computer instructions are executed on an electronic device, the electronic device executes the method of the first aspect.

[0020] In a fourth aspect, the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes the method in any possible design manner as in the first aspect.

[0021] In a fifth aspect, the present application provides a chip system, which includes one or more interface circuits and one or more processors. The interface circuit and the processor are interconnected by lines. The above chip system can be applied to an electronic device including a communication module and a memory. The interface circuit is used to receive a signal from the memory of the electronic device and send the received signal to the processor, the signal including a computer instruction stored in the memory. When the processor executes the computer instruction, the electronic device can execute the method of the first aspect.

[0022] Among them, the technical effects of the second to fifth aspects refer to the technical effects of the first aspect and any of its embodiments, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of a voltage adjustment process of an electronic device provided in an embodiment of the present application;

[0025] Figure 3 A schematic diagram of a voltage regulation waveform provided in an embodiment of the present application;

[0026] Figure 4 A schematic diagram of the steps of the voltage regulation method provided in the embodiment of the present application;

[0027] Figure 5 A functional block diagram of a voltage regulation method provided in an embodiment of the present application;

[0028] Figure 6 A schematic diagram of a model training process provided in an embodiment of the present application;

[0029] Figure 7 A schematic diagram of another model training process provided for an embodiment of the present application;

[0030] Figure 8 A schematic diagram of a process for determining a voltage regulation strategy provided in an embodiment of the present application;

[0031] Fig. 9 A schematic diagram of a process for determining another voltage regulation strategy provided in an embodiment of the present application;

[0032] Fig.10 A schematic diagram of a process for determining another voltage regulation strategy provided in an embodiment of the present application;

[0033] Fig.11 A schematic diagram of a voltage adjustment process of another electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0034] The terms used in the following embodiments are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include, for example, "one or more" such expressions, unless there is an explicit contrary indication in the context. It should also be understood that in the following embodiments of the present application, "at least one", "one or more" refer to one or more than two (including two). The character " / " generally represents that the front and back associated objects are a kind of "or" relationship.

[0035] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0036] In the following, the terms "first", "second", etc. are used only for convenience of description and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more. For example, a plurality of processing units refers to two or more processing units.

[0037] In addition, in the embodiments of the present application, "upper", "lower", "left" and "right" are not limited to being defined relative to the orientation of the components schematically placed in the drawings. It should be understood that these directional terms can be relative concepts, which are used for description and clarification relative to the components, and can change accordingly according to the change in the orientation of the components placed in the drawings. In the drawings, for the sake of clarity, the thickness of the layers and regions is exaggerated, and the size ratio relationship between the parts in the drawings does not reflect the actual size ratio relationship.

[0038] In the embodiments of the present application, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium. In addition, the term "electrical connection" can be a direct electrical connection or an indirect electrical connection through an intermediate medium.

[0039] In the embodiments of the present application, the term "module" is generally a functional structure divided according to logic, and the "module" can be implemented by pure hardware, or by a combination of software and hardware. In the embodiments of the present application, "and / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, B exists alone, and A and B exist at the same time.

[0040] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0041] An embodiment of the present application provides an electronic device, Figure 1 A structural diagram of an electronic device 100 is shown.

[0042] The electronic device 100 may include at least one of a mobile phone, a foldable electronic device, a tablet computer, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a personal digital assistant (PDA), an augmented reality (AR) device, a virtual reality (VR) device, an artificial intelligence (AI) device, a wearable device, an in-vehicle device, a smart home device, or a smart city device. The embodiment of the present application does not impose any special restrictions on the specific type of the electronic device 100.

[0043] The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) connector 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera module 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0044] The processor 110 may be a system on chip (SOC), which may include multiple subsystems. The subsystems of the SOC may include but are not limited to a central processing unit (CPU) subsystem, a graphics processing unit (GPU) subsystem, and a neural processing unit (NPU) subsystem.

[0045] It is to be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0046] Taking a mobile phone as an example, during the operation of the mobile phone, the processor performance can be improved to ensure efficient operation of the mobile phone. Improving processor performance usually means increasing processing speed, executing more instructions, higher clock frequency and more complex computing capabilities. These improvements usually require more power supply, resulting in higher power consumption.

[0047] The embodiment of the present application provides an implementation method that can use a voltage and frequency adjustment strategy to solve the contradiction between processor performance and power consumption. The dynamic voltage and frequency strategy refers to reducing the frequency and voltage of the processor when the processor is in a light-load working state, and increasing the frequency and voltage of the processor when the processor is in a heavy-load working state, thereby achieving a balance between power consumption and performance of electronic equipment.

[0048] See also Figure 2 , the voltage adjustment process of the electronic device is described. The components involved in the voltage adjustment process may include SOC, power management unit (PMU) and voltage adjustment execution unit. SOC communicates with PMU through system power management interface (SPMI) bus. PMU adjusts the voltage provided to SOC through the power channel.

[0049] In the process of executing the voltage and frequency adjustment strategy, the SOC generates a first voltage regulation instruction according to the needs of the subsystem and sends it to the SPMI bus. The first voltage regulation instruction is then sent to the power management unit through the SPMI bus. The SPMI bus acts as a communication bridge in this process to ensure efficient information transmission between the SOC and the PMU. The voltage regulation execution unit will continuously monitor the SPMI bus to detect whether the first voltage regulation instruction exists. When the voltage regulation execution unit detects that the first voltage regulation instruction does exist on the SPMI bus, it will further process the first voltage regulation instruction. The voltage regulation execution unit will correct and adjust the first voltage regulation instruction to ensure the accuracy and stability of the voltage regulation operation. When making these corrections and adjustments, the voltage regulation execution unit will generate the final second voltage regulation instruction based on the pre-set compensation value. Finally, after receiving the second voltage regulation instruction, the PMU will make corresponding voltage adjustments to each subsystem of the SOC according to the requirements in the instruction.

[0050] As an example, when the CPU subsystem increases the operating frequency to a preset value, the voltage of the CPU subsystem needs to be increased to a corresponding value at the same time to ensure the stable operation and performance of the system. At this time, the SOC generates a first voltage regulation instruction and sends the first voltage regulation instruction to the SPMI bus. The voltage value indicated by the first voltage regulation instruction can be 1.22V. After the voltage regulation execution unit detects the existence of the first voltage regulation instruction on the SPMI bus, it will correct the first voltage regulation instruction, that is, compensate the voltage value 1.22V indicated by the first voltage regulation instruction. The compensation value can be -0.01V, thereby generating a second voltage regulation instruction. The voltage value indicated by the second voltage regulation instruction can be 1.21V, and then the voltage regulation execution unit sends the second voltage regulation instruction to the SPMI bus. When the PMU receives the second voltage regulation instruction, it adjusts the current voltage of the CPU subsystem to 1.21V through the CPU power channel.

[0051] In the above implementation, the voltage regulation command generated by the SOC is corrected to compensate for voltage errors caused by various factors such as device aging, operating temperature changes, parameter measurement errors, etc. These factors will have a significant impact on the accuracy of the voltage.

[0052] However, there are several problems in the above implementation. The first problem is that when the SOC sends the voltage regulation instruction to the SPMI bus, it does not send it in time, but needs to send the voltage regulation instruction when the SPMI bus is idle. Since there are many power supply channels for the SOC, and all power supply channels are regulated by one SPMI bus, when there are voltage regulation instructions for multiple subsystems at the same time, they will be sent according to the preset priority. Therefore, for some subsystems with lower priority, there is a lag in the voltage regulation process.

[0053] As an example, at time T0, the load rate of the CPU subsystem is 20%, the temperature is 50°C, the CPU subsystem has a voltage regulation demand, and the first voltage regulation instruction of the CPU subsystem is generated. At time T0, the load rate of the GPU subsystem is 80%, and the temperature is 70°C. The GPU subsystem also has a voltage regulation demand, and the first voltage regulation instruction of the GPU subsystem is generated. Since the CPU subsystem and the GPU subsystem generate voltage regulation instructions at the same time, but the preset priority of the CPU subsystem is higher than the preset priority of the GPU subsystem, the voltage regulation operation of the CPU subsystem needs to be executed first, and the GPU subsystem operation can be executed at time T1. At time T2, if both the CPU subsystem and the GPU subsystem have voltage regulation requirements, and since the preset priority of the CPU subsystem is higher than the preset priority of the GPU subsystem, the voltage regulation operation of the CPU subsystem needs to be executed first, and the GPU subsystem operation can be executed at time T3. The voltage regulation operation of the CPU subsystem always takes precedence over the voltage regulation operation of the GPU subsystem, but the voltage regulation benefit of the GPU subsystem is significantly higher than the voltage regulation benefit of the CPU subsystem.

[0054] The following will be combined Figure 3 , for an explanation of the voltage regulation hysteresis of the above GPU subsystem, see Figure 3 , the voltage regulation process of the GPU subsystem includes two stages, the first voltage adjustment stage is from T0 to T2, and the second voltage adjustment stage is from T2 to T4. In the first voltage adjustment stage, the GPU subsystem generates the first voltage regulation instruction at T0, and because the voltage regulation operation of the CPU subsystem needs to be executed first, the voltage regulation execution unit can only modify the first voltage regulation instruction at T1 to generate the second voltage regulation instruction. It can be seen that the voltage waveform corresponding to the second voltage regulation instruction will not be different from the voltage waveform corresponding to the first voltage regulation instruction until T1, that is, there will be a voltage regulation benefit only after T1. In the second voltage adjustment stage, the GPU subsystem generates the first voltage regulation instruction at T2, and because the voltage regulation operation of the CPU subsystem needs to be executed first, the voltage regulation execution unit can only modify the first voltage regulation instruction at T3 to generate the second voltage regulation instruction. It can be seen that the voltage waveform corresponding to the second voltage regulation instruction will not be different from the voltage waveform corresponding to the first voltage regulation instruction until T3, that is, there will be a voltage regulation benefit only after T3. And in Figure 3 The voltage waveform corresponding to the second voltage regulation instruction is not an ideal voltage waveform. The ideal voltage waveform should have a voltage regulation benefit at time T0 in the first voltage regulation stage and a voltage regulation benefit at time T2 in the second voltage regulation stage.

[0055] It can be seen that when multiple subsystems have voltage adjustment requirements at the same time, the voltage adjustment process of the subsystem with a lower preset voltage adjustment priority has a higher lag. Therefore, for subsystems with a lower voltage adjustment priority but with poor working conditions (high load rate, high temperature), the above voltage adjustment scheme has a poor effect.

[0056] The second problem is that when setting the compensation value for the SOC voltage regulation command, the compensation value of each subsystem is often set to the maximum value, that is, the compensation value that meets the requirements of the worst working condition.

[0057] As an example, under the first working condition, the load rate of the CPU subsystem is 20%, the temperature is 50°C, and the voltage regulation instruction compensation value of the CPU subsystem under the first working condition is 0.1V. Under the second working condition, the load rate of the CPU subsystem is 80%, the temperature is 60°C, and the voltage regulation instruction compensation value of the CPU subsystem under the second working condition is also 0.1V.

[0058] It can be seen that under different working conditions, the voltage adjustment compensation value for the CPU subsystem is exactly the same, and under the first working condition, the actual compensation voltage required by the CPU subsystem may be 0.05V, and there is a voltage waste of 0.05V. Continuing to refer to Table 1, Table 1 shows the excess compensation value of the working voltage of the CPU subsystem at different working frequencies. It can be seen that the set compensation value can meet the needs of the worst working conditions, but under milder working conditions, such a compensation value may appear too high, resulting in voltage waste and increased power consumption. Therefore, although the above voltage regulation scheme can ensure the stability of the system under various working conditions, it does not take into account the actual needs under specific working conditions, which may lead to a decrease in energy efficiency.

[0059] Table 1

[0060]

[0061] Based on the improvement of the above scheme, the present application can realize differentiated voltage adjustment for different subsystems by taking the operating status information of each subsystem as the basic basis for voltage adjustment, so that each subsystem can match the best voltage adjustment strategy under different working conditions.

[0062] See also Figure 4 , the present application embodiment also provides a voltage regulation method, such as Figure 4 As shown, the voltage regulation method includes:

[0063] S401: Obtaining the operating status information of each subsystem.

[0064] The subsystems of SOC may include but are not limited to CPU subsystem, GPU subsystem and NPU subsystem, etc., which can be selected independently according to the modules actually included in the product or the modules that actually need to be adjusted. The operating status information of the subsystem may include but is not limited to the temperature, load rate, frequency, power supply voltage, operating temperature and other parameters of each subsystem chip, and can also be adjusted and selected according to actual needs. This application does not limit this. By obtaining the operating status information of each subsystem, it is used as the basis for judging the load characteristics of each subsystem, thereby realizing accurate identification of the load characteristics of each subsystem. The load characteristic analysis module determines the operating status information of each subsystem by obtaining the key operating events of the SOC.

[0065] As an example, at time T1, the load characteristic analysis module obtains the key operating events of the SOC and determines that the load rate of the CPU subsystem is 20%, the temperature is 50°C, the load rate of the GPU subsystem is 40%, the temperature is 60°C, and the load rate of the NPU subsystem is 80%, and the temperature is 80°C.

[0066] S402: Determine the load analysis results of each subsystem according to the operation status information, and determine the following voltage regulation strategy according to the load analysis results.

[0067] After obtaining the operating status information of the current operating cycle of each subsystem, the load analysis results of each subsystem can be determined based on the operating status information of the current operating cycle of each subsystem. As an example, the load analysis results include but are not limited to the load level, temperature level and load current of each subsystem. The load level may include light load, medium load and heavy load, and the temperature level may include low temperature, normal temperature and high temperature. The load current cannot be obtained directly and needs to be determined through other operating status information of the subsystem. After obtaining the load analysis results of each subsystem, the follow-up voltage regulation strategy of each subsystem can be determined based on the load analysis results.

[0068] See also Figure 5 When determining the load analysis results of each subsystem, the voltage regulation control module can input a first preset model based on the operating status information of the current operating cycle of each subsystem, such as the operating status information of the CPU subsystem, the operating status information of the GPU subsystem, the operating status information of the NPU subsystem, and the operating status information of the power subsystem. To determine the load analysis results of the first operating cycle of each subsystem. It is also possible to input a second preset model based on the operating status information of the current operating cycle of each subsystem to determine the load analysis results of the second operating cycle of each subsystem.

[0069] When determining the load analysis results of each subsystem, the load characteristic analysis module may determine the load analysis results of the current operation cycle of each subsystem based on the operation status information of the current operation cycle of each subsystem. It may also determine the load analysis results of the next operation cycle of each subsystem based on the operation status information of the current operation cycle of each subsystem.

[0070] In a possible implementation, based on the operation status information, the load analysis results of each subsystem are determined, and based on the load analysis results, the following voltage regulation strategy of the current operation cycle is determined, including:

[0071] S4021: Acquire the operation status information of each subsystem in the first operation cycle;

[0072] S4022: Determine a load analysis result of each subsystem in the first operation cycle according to the operation status information of each subsystem in the first operation cycle;

[0073] S4023: Determine a following voltage regulation strategy for the first operation cycle according to the load analysis results of each subsystem in the first operation cycle.

[0074] Based on the operating status information of the current operating cycle of each subsystem, the load analysis result of the current operating cycle is determined to focus on the feedback mechanism and real-time performance, and can quickly respond and adjust the voltage.

[0075] As an example, first, the load analysis module will monitor and collect the operating status information of each subsystem in the current operating cycle in real time. Determine that the load rate of the CPU subsystem is 20%, the temperature is 50°C, the load rate of the GPU subsystem is 40%, the temperature is 60°C, and the load rate of the NPU subsystem is 80%, and the temperature is 80°C. Then, based on the above-obtained operating status information, the load analysis of each subsystem is performed through the first preset model to obtain their respective load levels and temperature levels.

[0076] CPU load analysis results: Load level: light load, temperature level: normal temperature. Then, based on other operating status information of the CPU subsystem, the load current of the CPU subsystem is determined.

[0077] GPU load analysis results: load level: medium load, temperature level: normal temperature, and then determine the load current of the GPU subsystem based on other operating status information of the GPU subsystem.

[0078] NPU load analysis results: load level: heavy load, temperature level: high temperature, and then determine the load current of the NPU subsystem based on other operating status information of the NPU subsystem.

[0079] Then, based on the above load analysis results, the following voltage regulation strategy for the current operation cycle is determined.

[0080] In a possible implementation, determining a following voltage regulation strategy for the first operation cycle according to a load analysis result of each subsystem in the first operation cycle includes:

[0081] S40231: Input the operating status information of each subsystem in the first operating cycle as input features into the first preset model, and use the output of the first preset model as the load analysis result of each subsystem in the first operating cycle.

[0082] First, the collected operating status information is preprocessed, which may include data cleaning, normalization, feature extraction, etc., to ensure the data quality and format of the input model are correct. The preprocessed operating status information is input into the first preset model. Then, the first preset model processes the input features through the trained parameters and algorithms, and outputs the load analysis results of the current operating cycle.

[0083] The function of the first preset model is to integrate and process the operating status information of each subsystem, so as to obtain the load analysis results of each subsystem that cannot be directly obtained. These load analysis results include information such as the current load level and temperature status of each subsystem. By integrating data from multiple dimensions, the first preset model can provide a more comprehensive and accurate subsystem status assessment than a single data source. It should be noted that the first preset model does not have a predictive function. It only analyzes and processes the actual operating status information collected during the current operating cycle, and provides load analysis results within the current cycle, rather than predicting future operating status.

[0084] In a possible implementation, based on the operation status information, the load analysis results of each subsystem are determined, and based on the load analysis results, the current operation cycle following voltage regulation strategy is determined, including:

[0085] S4024: Acquire the operation status information of each subsystem in the first operation cycle;

[0086] S4025: Determine a predicted load analysis result of each subsystem in a second operation cycle according to the operation status information of each subsystem in the first operation cycle;

[0087] S4026: Determine a follow-up voltage regulation strategy for the second operation cycle according to the load analysis results of each subsystem in the second operation cycle.

[0088] First, based on the operating status information of the current operating cycle of each subsystem, the operating status information of the next operating cycle of each subsystem is predicted, and then based on the operating status information of the next operating cycle of each subsystem, the load analysis results of the next operating cycle of each subsystem are determined. The load analysis results of the next operating cycle are determined with emphasis on foresight and pre-regulation. By predicting and adjusting in advance, the response speed of the voltage regulation strategy can be improved.

[0089] As an example, first, the load analysis module will monitor and collect the operating status information of each subsystem in the current operation cycle in real time. Determine that the load rate of the CPU subsystem is 20%, the temperature is 50°C, the load rate of the GPU subsystem is 40%, the temperature is 60°C, and the load rate of the NPU subsystem is 80%, and the temperature is 80°C. Then, it is predicted that the load rate of the CPU subsystem in the next operation cycle will be 45%, the temperature will be 62°C, the load rate of the GPU subsystem will be 44%, the temperature will be 64°C, and the load rate of the NPU subsystem will be 75%, and the temperature will be 78°C.

[0090] Based on the operation status information of the next operation cycle as input, the load analysis of each subsystem is performed through the second preset model to obtain the respective load level and temperature level.

[0091] CPU load analysis results: load level: medium load, temperature level: normal temperature.

[0092] GPU load analysis results: load level: medium load, temperature level: normal temperature.

[0093] NPU load analysis results: load level: heavy load, temperature level: high temperature.

[0094] Then, based on the above load analysis results, the following voltage regulation strategy for the current operation cycle is determined.

[0095] In a possible implementation, based on the operation status information, a load analysis result of each subsystem is determined, and based on the load analysis result, a voltage regulation strategy for the next operation cycle is determined, including:

[0096] The operating status information of each subsystem in the second operating cycle is input into the second preset model as an input feature, and the output of the second preset model is used as the predicted load analysis result of each subsystem in the second operating cycle.

[0097] First, the collected operating status information is preprocessed, including data cleaning, normalization, feature extraction and other operations to ensure the data quality and format of the input model are correct. The preprocessed operating status information is input into the second preset model. The second preset model calculates and analyzes the input operating status information. Then, the second preset model processes the input features through the trained parameters and algorithms, and outputs the load analysis results of the next operating cycle.

[0098] The second preset model not only includes the functions of the first preset model, but also has the function of data prediction, and infers the operating status information of the second operating cycle based on the operating status information of the first operating cycle of each subsystem. The second preset model can predict the operating status of each subsystem in the future cycle by learning historical data, and make corresponding voltage adjustments based on the prediction results.

[0099] The second preset model can be trained based on the historical operating status information of each subsystem, and the operating status of each subsystem in the past period of time can be learned. The second preset model is trained using the historical operating status information of each subsystem, so that the trained second preset model can be used to predict the operating status information of each subsystem in the second operating cycle, that is, the operating status information of the second operating cycle is inferred based on the operating status information of the first operating cycle of each subsystem.

[0100] Exemplarily, before using the second preset model to infer the operating status information of the second operating cycle, the second preset model needs to be trained. Figure 6 The training of the second preset model includes: obtaining the historical operation status information of each subsystem of the user, and training the initial model according to the historical operation status information of each subsystem to obtain a trained second preset model.

[0101] Among them, the historical operating status information of each subsystem can be the historical operating status information of each subsystem stored in the electronic device. After obtaining the historical operating status information of each subsystem, the initial model is trained according to the historical operating status information of each subsystem, wherein the initial model can be a reference initial model, or a model obtained according to default model parameters. In a possible implementation method, the initial model can be a model determined based on a transformer neural network (transformer) or a model determined based on a recurrent neural network (RNN). For example, the initial model can also be a Bayesian model, etc.

[0102] The initial model is trained using training sample data, i.e., the historical operating status information of each subsystem mentioned above. The converged initial model obtained can be used as the trained second preset model. The operating status information of each subsystem in the second operating cycle is determined using the trained second preset model based on the operating status information of each subsystem in the first operating cycle.

[0103] In the above example, the second preset model provided in the embodiment of the present application is described by training the model in the electronic device according to the historical operation status information of each subsystem of the user. In some other possible implementations, the trained second preset model can also be obtained by the electronic device, for example, see Figure 7 In a possible implementation, after obtaining the historical operating status information of each subsystem, the historical operating status information of each subsystem is sent to the server. The server trains the initial model based on the historical operating status information of each subsystem to obtain a trained second preset model. Then the electronic device 100 obtains the second preset model trained by the server, and uses the obtained second preset model to determine the operating status information of the second operating cycle of each subsystem.

[0104] It should be noted that the first preset model and the second preset model can be trained in advance and deployed in the operating system of the electronic device, or they can be dynamically trained models that are continuously improved during operation.

[0105] The trained model is deployed to the operating system and used as a static model in actual operation. The first preset model and the second preset model deployed in advance have been trained and tested with a large amount of data, have high accuracy and stability, and can respond quickly in actual operation, without the need for additional computing resources for online training. The dynamic training model will continuously collect new operating data during the system operation, and use this data to further train and optimize the model.

[0106] The pre-deployed model has been trained with a large amount of data and has the advantages of high stability and fast response, which is suitable for systems that are not subject to much change in the operating environment; while the dynamically trained model can be updated and optimized in real time to adapt to changing operating conditions, which is suitable for systems that require high flexibility and adaptability. The two methods can be selected according to the specific application scenarios and needs.

[0107] The voltage regulation strategy may include voltage regulation strategies in multiple dimensions, that is, optimizing the voltage regulation strategy from multiple aspects. The voltage regulation strategy may include, but is not limited to, a power channel adjustment strategy and a voltage amplitude adjustment strategy.

[0108] For example, see Figure 8After determining the load analysis results of each subsystem, the power channel adjustment strategy is used to indicate the priority order and start / stop status of each subsystem power channel, that is, some power channels can be dynamically turned on or off according to actual needs. On the other hand, the voltage amplitude adjustment strategy is used to indicate the value of the voltage correction of each subsystem, which can finely adjust the voltage of each subsystem.

[0109] In a feasible implementation, the following voltage regulation strategy is determined according to the load analysis results, including: determining the power channel adjustment strategy of each subsystem according to the load status of each subsystem, and determining the voltage amplitude adjustment strategy of each subsystem according to the temperature status of each subsystem.

[0110] When determining the power channel adjustment strategy for each subsystem, first determine the power channel adjustment strategy for each subsystem, and then determine the voltage amplitude adjustment strategy for each subsystem. When determining the power channel adjustment strategy for each subsystem, it can be determined according to the priority score of each power channel, and the opening priority of each power channel can be determined according to the priority score from high to low or the relationship between the priority score and the threshold. And when the load rate of the subsystem is less than the threshold, the power channel corresponding to the subsystem can be turned off. This can enable subsystems with higher load rates to obtain more voltage adjustment opportunities, thereby obtaining more power consumption benefits.

[0111] For example, see Fig. 9 , the load rate of the CPU subsystem is 45%, the load rate of the GPU subsystem is 85%, and the load rate of the NPU subsystem is 5%, then the priority score of the GPU subsystem is greater than the priority score of the CPU subsystem, and the priority score of the CPU subsystem is greater than the priority score of the NPU subsystem. However, when the GPU subsystem, the GPU subsystem, and the NPU subsystem all have voltage adjustment requirements at the same time, the voltage adjustment requirements of the GPU subsystem are met first, and then the voltage adjustment requirements of the GPU subsystem are met, that is, the power channel of the GPU subsystem (first priority) and the power channel of the CPU subsystem (second priority) are turned on, and the power channel of the NPU subsystem is turned off.

[0112] In a feasible implementation, in addition to the load rate, the load status may also include load characteristic indicators in multiple dimensions. According to the load characteristic indicators of each dimension in at least one dimension, an evaluation score of each dimension is obtained. According to the evaluation score of each dimension and the weight coefficient corresponding to the dimension, the power channel priority score of each subsystem is determined, wherein the power channel priority score is equal to the cumulative value of the product of the evaluation score corresponding to each dimension in at least one dimension and the corresponding weight coefficient. According to the power channel priority score, the voltage regulation priority of the power channel of each subsystem is determined.

[0113] As an example, the load status of each subsystem includes load characteristic indicators in the following three dimensions: dimension a, dimension b, and dimension c, with weight coefficients of 0.5, 0.3, and 0.2 respectively. Then, based on the load characteristic indicators in each dimension, the evaluation score of each dimension is calculated.

[0114] For the CPU subsystem: the evaluation score of dimension a: 0.8, the evaluation score of dimension b: 0.6, the evaluation score of dimension c: 0.7, and the power channel priority score calculation: 0.8×0.5+0.6×0.3+0.7×0.2=0.72.

[0115] For the GPU subsystem: the evaluation score of dimension a: 0.9, the evaluation score of dimension b: 0.7, the evaluation score of dimension c: 0.8, and the power channel priority score calculation: 0.9×0.5+0.7×0.3+0.8×0.2==0.85.

[0116] For the NPU subsystem: the evaluation score of dimension a: 0.7, the evaluation score of dimension b: 0.5, the evaluation score of dimension c: 0.6, and the power channel priority score calculation: 0.7×0.5+0.5×0.3+0.6×0.2==0.65.

[0117] The priorities of each subsystem are sorted from high to low according to the power channel priority score. The GPU subsystem has the highest voltage regulation priority, followed by the CPU subsystem, and finally the NPU subsystem.

[0118] Through this method, the system can comprehensively consider the load characteristic indicators of multiple dimensions, accurately evaluate the load status of each subsystem, and reasonably determine the voltage regulation priority of the power supply channel, thereby achieving more efficient power management and resource allocation. This method can dynamically adapt to the load changes of different subsystems and improve the overall performance and energy efficiency of the system.

[0119] When determining the voltage amplitude adjustment strategy for each subsystem, the voltage adjustment amplitude of each subsystem may be determined according to the matching result between the temperature state of each subsystem and the preset value.

[0120] As an example, assume that the preset temperature threshold of the system is as follows:

[0121] Low temperature state: less than 40℃; normal temperature state: 40℃ - 70℃; first level high temperature state: 80℃-90℃; second level high temperature state: 90℃- 100℃.

[0122] In actual operation, the temperature of the CPU subsystem is 85℃, which means the CPU subsystem is in the first level of high temperature state. The temperature of the NPU subsystem is 95℃, which means the NPU subsystem is in the second level of high temperature state. The temperature of the GPU subsystem is 65℃, which means the CPU subsystem is in the normal temperature state. Fig.10 According to the preset adjustment strategy, the specific adjustment range of the first level high temperature state can be 2mV. The specific adjustment range of the second level high temperature state can be 4mV. The specific adjustment range of the normal temperature state can be 0mV.

[0123] It should be noted that different temperature states and specific values ​​of voltage adjustment ranges corresponding to different temperature states can be adjusted and calibrated according to needs, and this application does not limit this.

[0124] In this way, the voltage adjustment strategy can be dynamically adjusted according to the real-time temperature status, thereby optimizing the operating status of each subsystem and ensuring that the system can operate efficiently and reliably under different load conditions. The specific voltage adjustment range can also be more finely calculated based on historical data and preset models to achieve more precise regulation.

[0125] S403: Acquire a first voltage regulation instruction, and determine a second voltage regulation instruction according to the following voltage regulation strategy and the first voltage regulation instruction.

[0126] After the follow-up voltage regulation strategy is deployed, the voltage regulation execution unit will continuously monitor the SPMI bus to detect whether there is a first voltage regulation instruction. When the voltage regulation execution unit detects that the first voltage regulation instruction does exist on the SPMI bus, it will further process the first voltage regulation instruction, and the voltage regulation execution unit will make necessary corrections and adjustments to the first voltage regulation instruction of the follow-up voltage regulation strategy. The first voltage regulation instruction is used to instruct the PMU to adjust the voltage of each subsystem to the target value, and the second voltage regulation instruction is used to instruct the PMU to adjust the voltage of each subsystem to the actual value. The first voltage regulation instruction is used to instruct the PMU to adjust the voltage of each subsystem to the target value, which is a voltage value pre-calculated based on the system requirements and the current operating status. The second voltage regulation instruction is used to instruct the PMU to adjust the voltage of each subsystem to the actual value, which is a further adjustment made according to real-time monitoring data and feedback during the actual operation. This adjustment takes into account the voltage error that may be caused by factors such as device aging, operating temperature, and parameter measurement errors.

[0127] According to the following voltage regulation strategy and the first voltage regulation instruction, the specific steps of determining the second voltage regulation instruction may include:

[0128] S4031: Determine the power channel adjustment instruction of the second voltage adjustment instruction according to the matching result of the power channel adjustment instruction in the first voltage adjustment instruction and the power channel adjustment strategy;

[0129] S4032: Determine the voltage amplitude adjustment instruction of the second voltage regulation instruction according to the matching result between the voltage amplitude adjustment instruction in the second voltage regulation instruction and the voltage amplitude adjustment strategy.

[0130] The first voltage regulation instruction may include specific power channel adjustment instructions and voltage amplitude adjustment instructions, which are used to implement voltage adjustment for the subsystem. The voltage regulation execution unit compares the power channel adjustment instructions and voltage amplitude adjustment instructions in the first voltage regulation instruction with the pre-deployed voltage regulation strategy to determine whether to adjust the first voltage regulation instruction and how to correct the first voltage regulation instruction, thereby generating a second voltage regulation instruction.

[0131] As an example, at time T1, the load rate of the CPU subsystem is 70%, the temperature is 50°C, and the CPU subsystem has a voltage regulation requirement, and the first voltage regulation instruction of the CPU subsystem is generated. The first voltage regulation instruction of the CPU subsystem can be: turn on the power channel, and the voltage amplitude compensation is 4mV. At time T1, the load rate of the GPU subsystem is 80%, the temperature is 85°C, and the GPU subsystem has a voltage regulation requirement, and the first voltage regulation instruction of the GPU subsystem is generated. The first voltage regulation instruction of the CPU subsystem can be: turn on the power channel, and the voltage amplitude compensation is 4mV. After the voltage regulation execution unit detects the first voltage regulation instruction of the CPU subsystem and the first voltage regulation instruction of the GPU subsystem, it is corrected according to the matching result of the first voltage regulation instruction and the follow-up voltage regulation strategy to obtain the second voltage regulation instruction. The second voltage regulation instruction of the CPU subsystem can be: turn on the power channel (second priority), and the voltage amplitude compensation is 0mV. Then the second voltage regulation instruction of the GPU subsystem can be: turn on the power channel (first priority), and the voltage amplitude compensation is 2mV.

[0132] S404: adjusting the voltage provided to each subsystem according to the second voltage regulation instruction.

[0133] After determining the second voltage regulation instruction, the voltage regulation execution unit sends the second voltage regulation instruction to the PMU, and the PMU executes the corresponding voltage regulation operation.

[0134] The following will be combined Fig.11The system architecture diagram shown in the figure describes in detail the specific implementation process of the present application. First, the load characteristic analysis module obtains the operating status information of each subsystem, and determines the load analysis results of each subsystem based on the operating status information. Then, the voltage regulation control module determines the follow-up voltage regulation strategy based on the load analysis results, and sends the follow-up voltage regulation strategy to the voltage regulation execution unit through the communication bus. Then, the SPMI bus monitoring module in the voltage regulation execution unit obtains the first voltage regulation instruction by monitoring the SPMI bus, and the voltage regulation control module determines the second voltage regulation instruction based on the follow-up voltage regulation strategy and the first voltage regulation instruction. Finally, the PMU adjusts the voltage provided to each subsystem according to the second voltage regulation instruction.

[0135] The voltage regulation method provided by the present application can realize differentiated voltage regulation of different subsystems by taking the operating status information of each subsystem as the basic basis for voltage regulation, so that each subsystem can match the best voltage regulation strategy under different working conditions. The voltage of each subsystem of the electronic device can more accurately follow the load change, improve the accuracy of voltage regulation, reduce unnecessary power consumption, and balance the contradiction between the performance and power consumption of the electronic device.

[0136] The present application also provides an electronic device, which may include: a memory and one or more processors. The memory and the processor are coupled. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device can perform each function or step in the above method embodiment.

[0137] This embodiment also provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on an electronic device, the electronic device executes each function or step in the above method embodiment.

[0138] This embodiment also provides a computer program product. When the computer program product is run on a computer, it enables the computer to execute each function or step in the above method embodiment.

[0139] Among them, the electronic device, computer-readable storage medium, and computer program product provided in this embodiment are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding methods provided above, and will not be repeated here.

[0140] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0141] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0142] The unit described as a separate component may or may not be physically separated, and the component shown as a unit may be one physical unit or multiple physical units, that is, it may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

[0143] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0144] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including a number of instructions to enable an electronic device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0145] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application and are not intended to limit it. Although the present application has been described in detail with reference to the preferred embodiments, a person of ordinary skill in the art should understand that the technical solution of the present application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A voltage regulation method, characterized in that: Applied to an electronic device, the electronic device includes a plurality of subsystems, and the method includes: Obtaining the operating status information of each subsystem; Determine the load analysis results of each subsystem according to the operation status information, and determine the following voltage regulation strategy according to the load analysis results, wherein the following voltage regulation strategy includes a power channel adjustment strategy, and the power channel adjustment strategy is used to indicate the adjustment order of the power channels of each subsystem; Determining a following voltage regulation strategy according to the load analysis result includes: Determining a power channel adjustment strategy for each subsystem according to a load state of each subsystem; The load state includes load characteristic indicators of multiple dimensions, and the power channel adjustment strategy is determined by the following steps: Determine an evaluation score for each dimension according to the load characteristic index of each dimension in at least one dimension, determine a power channel priority score for each subsystem according to the evaluation score for each dimension and a corresponding weight coefficient, and determine the power channel adjustment strategy according to the power channel priority scores of each subsystem, wherein the power channel priority score is equal to the cumulative value of the product of the evaluation score corresponding to each dimension in at least one dimension and the corresponding weight coefficient; Obtaining a first voltage regulation instruction, and determining a second voltage regulation instruction according to the following voltage regulation strategy and the first voltage regulation instruction, wherein the first voltage regulation instruction is used to instruct that the voltage of each of the subsystems be adjusted to a target value, and the second voltage regulation instruction is used to instruct that the voltage of each of the subsystems be adjusted to an actual value; The voltage provided to each of the subsystems is adjusted according to the second voltage regulation instruction.

2. The method according to claim 1, characterized in that: Determining the load analysis results of each subsystem according to the operating status information, and determining the following voltage regulation strategy according to the load analysis results, includes: Obtaining operation status information of each subsystem in the first operation cycle; Determine a load analysis result of each subsystem in the first operation cycle according to the operation status information of each subsystem in the first operation cycle; A following voltage regulation strategy for the first operation cycle is determined according to the load analysis results of each subsystem in the first operation cycle.

3. The method according to claim 2, characterized in that Determining the load analysis result of each subsystem in the first operation cycle according to the operation status information of each subsystem in the first operation cycle includes: The operating status information of each subsystem in the first operating cycle is input into a first preset model as an input feature, and the output of the first preset model is used as a load analysis result of each subsystem in the first operating cycle, wherein the first preset model is trained based on the historical operating status information of each subsystem.

4. The method according to claim 1, characterized in that: Determining the load analysis results of each subsystem according to the operating status information, and determining the following voltage regulation strategy according to the load analysis results, includes: Obtaining operation status information of each subsystem in the first operation cycle; Determine, based on the operating status information of each subsystem in the first operating cycle, the predicted load analysis results of each subsystem in a second operating cycle; the second operating cycle is an operating cycle after the first operating cycle; A following voltage regulation strategy for the second operation cycle is determined according to the load analysis results of each subsystem in the second operation cycle.

5. The method according to claim 4, characterized in that Determining the load analysis result of each subsystem in the first operation cycle according to the operation status information of each subsystem in the first operation cycle includes: The operating status information of each subsystem in the second operating cycle is input into a second preset model as an input feature, and the output of the second preset model is used as a predicted load analysis result of each subsystem in the second operating cycle, wherein the second preset model is trained based on the historical operating status information of each subsystem.

6. The method according to claim 1, characterized in that The load analysis result includes a load state and a temperature state, the following voltage regulation strategy also includes a voltage amplitude adjustment strategy, and determining the following voltage regulation strategy according to the load analysis result also includes: According to the temperature status of each subsystem, a voltage amplitude adjustment strategy of each subsystem is determined.

7. The method according to claim 6, characterized in that The voltage regulation instruction includes a power channel adjustment instruction and a voltage amplitude adjustment instruction, and determining a second voltage regulation instruction according to the following voltage regulation strategy and the first voltage regulation instruction includes: Determining the power channel adjustment instruction of the second voltage adjustment instruction according to a matching result between the power channel adjustment instruction in the first voltage adjustment instruction and the power channel adjustment strategy; The voltage amplitude adjustment instruction of the second voltage regulation instruction is determined according to a matching result between the voltage amplitude adjustment instruction in the second voltage regulation instruction and the voltage amplitude adjustment strategy.

8. An electronic device, characterized in that: The electronic device comprises: a processor, a memory and a computer program stored in the memory; the memory is respectively coupled to the processor; When the electronic device is running, the processor executes the computer program to implement the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor of an electronic device, the method according to any one of claims 1 to 7 is implemented.

10. A computer program product, characterized in that The method comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images