Control method and apparatus for electronic device, server, medium, and program product
By adjusting the target operating frequency and status level on the configuration interface, the problem of processor frequency adjustment under different manufacturers and scenarios is solved, achieving optimal energy consumption and efficient resource utilization.
Patent Information
- Application Number
- CN202511222019.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-28
- Publication Date
- 2025-12-12
- Estimated Expiration
- 2045-08-28
AI Technical Summary
Existing technologies struggle to effectively adjust processor operating frequencies to achieve the lowest energy consumption across different manufacturers and application scenarios, leading to resource waste and high energy costs.
By using the configuration controls on the display configuration interface, users can adjust the target operating frequency of the electronic device, and display matching configuration information based on the status level configuration operation. The target operating frequency is determined and confirmed to control the operating frequency of the electronic device, and the frequency is dynamically adjusted using intelligent frequency reduction technology to adapt to different loads.
It enables flexible adjustment of processor frequency according to load demand, reduces energy consumption, improves resource utilization efficiency, and avoids equipment aging and energy waste caused by fixed frequency strategy.
Smart Images

Figure CN120723129B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of servers, and more particularly to a control method and device of an electronic device, a server, a medium and a program product. BACKGROUND
[0002] The processor of a server, such as a Central Processing Unit (CPU), is the operation and control core of the server, like the brain of the human body, and its importance is self-evident. The CPU is also the most important energy-consuming component in the server, and the frequency of the CPU is generally adjusted by an Operating System (OS) to improve the energy efficiency ratio. It is difficult to cope with different application scenarios by using a general frequency adjustment method, which leads to resource waste. SUMMARY
[0003] In view of the above problems, the present application provides a control method and device of an electronic device, a server, a medium and a program product.
[0004] According to a first aspect of the present application, a control method of an electronic device is provided, comprising: displaying a first configuration interface, wherein the first configuration interface displays a configuration control, the configuration control is used to adjust a target working frequency of the electronic device, and the target working frequency indicates a highest working frequency that can be supported by the electronic device; in response to a state level configuration operation on the configuration control, displaying configuration information matched with the state level configuration operation in the first configuration interface, wherein the configuration information represents a target state level of a performance state of the electronic device, and there is a mapping relationship between the target state level and the target working frequency; and in response to receiving a confirmation instruction on the configuration information, determining the target working frequency of the electronic device represented by the configuration information, so as to control the working frequency of the electronic device not to exceed the target working frequency during the operation of the electronic device.
[0005] The second aspect of the present application provides a control device of an electronic device, comprising: an interface display module configured to display a first configuration interface, wherein the first configuration interface displays a configuration control, and the configuration control is configured to adjust a target working frequency of the electronic device, and the target working frequency indicates a highest working frequency that can be supported by the electronic device; a level configuration module configured to, in response to a state level configuration operation on the configuration control, display configuration information matched with the state level configuration operation on the first configuration interface, wherein the configuration information represents a target state level of a performance state of the electronic device, and the target state level and the target working frequency have a mapping relationship; and an information determination module configured to, in response to receiving a confirmation instruction on the configuration information, determine the target working frequency of the electronic device corresponding to the configuration information, so that the working frequency of the electronic device does not exceed the target working frequency during running of the electronic device.
[0006] The third aspect of the present application provides a server, comprising: one or more processors; a memory configured to store one or more computer programs, wherein the one or more processors execute the one or more computer programs to implement steps of the control method.
[0007] The fourth aspect of the present application further provides a computer readable storage medium, which stores a computer program or instructions, and the computer program or instructions are executed by a processor to implement steps of the control method.
[0008] The fifth aspect of the present application further provides a computer program product, comprising a computer program or instructions, and the computer program or instructions are executed by a processor to implement steps of the control method. BRIEF DESCRIPTION OF DRAWINGS
[0009] The above content and other purposes, features and advantages of the present application will be more apparent through the following description of the embodiments of the present application with reference to the accompanying drawings, in which:
[0010] Figure 1 A block diagram of a server according to an embodiment of the present application is shown;
[0011] Figure 2 A flowchart of a control method of an electronic device according to an embodiment of the present application is shown;
[0012] Figure 3 A schematic diagram of a configuration control according to an embodiment of the present application is shown;
[0013] Figure 4A A display schematic diagram of a slider configuration control according to an embodiment of the present application is shown;
[0014] Figure 4BAn operation diagram of a slider configuration control according to another embodiment of the present application is shown;
[0015] Figure 4C An operation diagram of a confirmation control according to an embodiment of the present application is shown;
[0016] Figure 5A An operation diagram of an activation control of a second configuration interface according to an embodiment of the present application is shown;
[0017] Figure 5B A block diagram of configuration information activation according to an embodiment of the present application is shown;
[0018] Figure 6A An operation diagram of a task configuration operation according to an embodiment of the present application is shown;
[0019] Figure 6B An operation diagram of a health assessment operation according to an embodiment of the present application is shown;
[0020] Figure 6C An operation diagram of a level state optimization according to an embodiment of the present application is shown;
[0021] Figure 7 An operation diagram of a heterogeneous graph according to an embodiment of the present application is shown;
[0022] Figure 8 An operation diagram of a deep learning model according to an embodiment of the present application is shown;
[0023] Figure 9 A structural block diagram of a control device of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION
[0024] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. It should be understood, however, that the description which follows is merely exemplary and is not intended to limit the scope of the application. In the following detailed description of embodiments of the present application, numerous specific details are set forth in order to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that one or more embodiments of the present application can be practiced without these specific details. In other instances, well-known structures and functions have not been described in detail in order to avoid obscuring aspects of the present application.
[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used herein, the term "includes" and tautological expressions thereof, such as "including," "includes," "include," "contains," "containing," and so forth, shall be read expansively and without limitation. The terms "comprising," "comprise" and / or "comprises" and tautological expressions thereof (for example, "comprising a," "comprises an," etc.) shall be interpreted open as taking their broadest possible interpretation in light of the prior art to encompass the performance of avoidance of any additional feature, step, operation, identifier, and / or component.
[0026] All terms used herein, including technical and scientific terms, have the meanings as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of the specification, and should not be interpreted in an idealized or overly formal way.
[0027] In the case of using expressions such as "at least one of A, B, and C, etc.", it should generally be interpreted that the meaning of the expression is at least one of A, B, and C (for example, "a system having at least one of A, B, and C" should include but not be limited to a system having A alone, a system having B alone, a system having C alone, a system having both A and B, a system having both A and C, a system having both B and C, and / or a system having A, B, and C, etc.).
[0028] In the current wave of digitization sweeping the world, the demand for fine and intelligent server performance management in various industries is growing explosively. As the "computing heart" of the digital economy, data centers are facing the dual challenges of business load diversification and soaring energy costs. On the one hand, with the popularization of emerging technologies such as 5G, the Internet of Things, and artificial intelligence, the types of businesses carried by data centers are becoming increasingly diverse, from the instant surge in transaction traffic on e-commerce platforms to the continuous high demand for computing power in AI training clusters. Servers need to quickly switch performance modes in different scenarios; for example, during e-commerce promotions, transaction peaks can cause server CPU load to jump from 30% to more than 90% within a few minutes. On the other hand, high energy costs have become a heavy burden for data center operations. According to statistics, the annual power consumption of global data centers is as high as 200 terawatt-hours, accounting for about 3% of the world's total electricity consumption, of which the processor power consumption of servers accounts for a significant proportion.
[0029] The prior art can dynamically adjust the running energy consumption of the processor by adjusting the working frequency of the processor. However, different manufacturers' processors have different models, heat dissipation capabilities, and running power consumptions, and in addition, different application scenarios are adapted to different working frequencies. Using the same frequency adjustment strategy, it is difficult to ensure that the working frequency of each processor can be adjusted to the optimal parameter to achieve the lowest energy consumption.
[0030] Therefore, the embodiments of the present application provide a control method of an electronic device, comprising: displaying a first configuration interface, wherein the first configuration interface displays a configuration control, and the configuration control is used to adjust a target working frequency of the electronic device; in response to a state level configuration operation on the configuration control, displaying configuration information matched with the state level configuration operation in the first configuration interface, wherein the configuration information comprises a target state level representing a performance state of the electronic device; and in response to receiving a confirmation instruction on the configuration information, determining a target working frequency of the electronic device corresponding to the configuration information, so as to control the electronic device to run based on the target working frequency during the running of the electronic device.
[0031] By means of the control method of the electronic device provided in the embodiments of the present application, the configuration control can be set on the first configuration interface, so as to flexibly configure the target state level representing the performance state of the electronic device by means of the configuration control in an interactive manner, and then the target working frequency of the electronic device is determined based on the configuration information, so as to control the operation of the electronic device by means of the target working frequency, so that the frequency adjustment strategy is flexibly adjusted based on the target working frequency, and the energy consumption is reduced.
[0032] Figure 1 A block diagram of a server according to an embodiment of the present application is shown.
[0033] As shown in Figure 1 , the server 100 of the embodiment can include a processor 110, a baseboard management controller (BMC) 120, a basic input / output system (BIOS) 130 and the like. Those skilled in the art can understand that the structure of the server shown in Figure 1 does not constitute a limitation on the server, and the server provided in the embodiments of the present application can include more or less components than the diagram, or combine certain components, or different component arrangements.
[0034] The following will be specifically introduced in combination with Figure 1 the components of the server 100:
[0035] The processor 110 can include one or more processing units 111, which can be a central processing unit, a graphics processing unit (GPU), a digital signal processor, an application-specific integrated circuit, a field-programmable gate array (FPGA) or other programmable logic device, without limitation. The processor 110 can also include a first storage unit 112. The processing unit 111 can connect various components by means of various interfaces and lines, execute instructions of an operating system 113 stored in the first storage unit 112, and call data stored in the first storage unit 112, so as to execute various functions and process data of the server 100, thereby realizing various services based on the server 100.
[0036] Exemplarily, the operating system 113 can be Linux, Windows or vxWorks, etc., which can be run on the processor 110.
[0037] BMC120 is used to monitor the hardware of server 100, such as processor 110. For example, it can monitor the temperature, voltage, and other information of various components of server 100 and make corresponding adjustments to ensure normal operation. Optionally, BMC120 may be configured with a first configuration interface 121, on which configuration controls can be displayed so that the user can configure processor 110 as the target operating frequency of the electronic device and store the target operating frequency in the second storage unit 122 of BMC120.
[0038] BIOS 130 is firmware within server 100, responsible for hardware initialization and self-test during server 100 startup, and providing basic input / output functions. BIOS 130 resides on the motherboard of server 100. Optionally, BIOS 130 may include a second configuration interface 131 and a third storage unit 132. BIOS 130 may also send a target operating frequency read from the second storage unit 122 to the operating system 113 running on processor 110, causing operating system 113 to adjust the maximum supported operating frequency of processor 110 to the target operating frequency.
[0039] It should be noted that the first storage unit 112, the second storage unit 122, and the third storage unit 132 are all used to store data, including but not limited to random access memory (RAM), read-only memory (ROM), flash memory, or optical memory.
[0040] like Figure 1 As shown, the target operating frequency or configuration information can be stored in the first storage unit 112 so that the target operating frequency can be read from the first storage unit 112 during the operation of the operating system 113, so that the processor 110 can adjust the operating frequency according to the working state, thereby reducing energy consumption.
[0041] The processor 110, BMC120, and BIOS130 can communicate with each other via IPMI or Redfish.
[0042] Specifically, IPMI (Intelligent Platform Management Interface) is an industry standard specification for remotely monitoring and managing system-level events, particularly suitable for servers and other computing devices.
[0043] Redfish: "Redfish" protocol is a standardized management interface for unified management of servers, storages and network devices in modern data centers. It provides a Representational State Transfer (REST) Application Programming Interface (API) to make the management of hardware devices more flexible and efficient.
[0044] It should be noted that, Figure 1 The server in this embodiment is only an example, and the number and form of components included in the server are not limited in this embodiment.
[0045] The control method of the electronic device according to the embodiments of the present application will be described in detail below based on the server architecture described above. Figure 1 The control method of the electronic device according to the embodiments of the present application will be described in detail below based on the server architecture described above.
[0046] Figure 2 A flowchart of the control method of the electronic device according to the embodiments of the present application is shown.
[0047] As Figure 2 shown, the control method of the electronic device of this embodiment includes operations S210-S230.
[0048] In operation S210, a first configuration interface is displayed. The first configuration interface displays a configuration control, which is used to adjust the target operating frequency of the electronic device, indicating the highest operating frequency that the electronic device can support.
[0049] In operation S220, in response to a state level configuration operation on the configuration control, configuration information matching the state level configuration operation is displayed on the first configuration interface. The configuration information represents the target state level of the performance state of the electronic device, and there is a mapping relationship between the target state level and the target operating frequency.
[0050] In operation S230, in response to receiving a confirmation instruction on the configuration information, the target operating frequency of the electronic device corresponding to the configuration information is determined. In order to control the operating frequency of the electronic device not to exceed the target operating frequency during the operation of the electronic device.
[0051] The electronic device can include a central processing unit, a graphics processing unit, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic devices in the server, which are not limited here.
[0052] The first configuration interface can be displayed on a display device inside the server or on a display device connected to the server, but is not limited thereto. The first configuration interface can be a display interface (also referred to as an interactive interface) of a controller of the server.
[0053] The timing of displaying the first configuration interface can be various, and can be one of the following possibilities: when the server is first installed or after a major hardware upgrade, the controller automatically loads and presents the first configuration interface, allowing the user to configure the target operating frequency of the electronic device according to the intended use of the server, such as high-performance computing, data center energy-saving operation or balanced mode. In the regular operation of the server, when the user needs to adjust the performance or power consumption of the electronic device, the target operating frequency of the electronic device can be accessed and adjusted by re-entering the first configuration interface of the controller of the server. The controller of the server can also automatically pop up the first configuration interface when the user requests performance optimization or energy-saving strategy change, and guide the user to confirm or adjust the target operating frequency of the electronic device to ensure the best balance between performance and efficiency of the electronic device.
[0054] The first configuration interface can display a configuration control or an application guide of the configuration control. The application guide is used to indicate the correspondence between the state level and the operating frequency.
[0055] The Enhanced Intel Speed Step Technology (EIST) can be used to automatically adjust the voltage and frequency according to the load of the electronic device to reduce power consumption and heat generation. For example, when the load of the electronic device is large and the AI model training task is executed, the operating frequency of the electronic device can be automatically adjusted to the maximum operating frequency that can be supported. When the electronic device is idle, the operating frequency of the electronic device can be automatically adjusted to a lower operating frequency.
[0056] The operating frequency can be adjusted by adjusting the state level representing the performance state (P-state) of the electronic device. For example, a mapping relationship between the state level and the operating frequency is established, and the operating frequency is dynamically adjusted according to the load of the electronic device and the mapping relationship. For example, the operating frequency can be adjusted to a frequency matched with the active state level in the active state of the electronic device, and the operating frequency can be adjusted to a frequency matched with the inactive state level in the inactive state of the electronic device. Generally, P0 is the highest performance level, and P1, …, Pn levels are successively lowered. Correspondingly, the operating frequency matched with the state level is also successively lowered. The lower the operating frequency of the processor, the lower the power consumption.
[0057] Optionally, the target state level representing the performance state of the electronic device can be adjusted by operating the configuration control provided on the first configuration interface, and then the highest workable frequency can be determined.
[0058] In response to the confirmation instruction for the configuration information, the target work frequency of the electronic device corresponding to the configuration information can be determined. Thus, the electronic device can be controlled based on the target work frequency during the operation of the electronic device. For example, in the case that the load of the electronic device is high, the highest workable frequency of the electronic device can be controlled to be raised to the target work frequency. Thus, the flexible adaptation of the electronic device can be achieved.
[0059] For example, for an AI training task, the target state level representing the performance state of the electronic device can be configured as P1, and the highest workable frequency of the electronic device during the operation can be the target work frequency matched with P1.
[0060] For example, for a retrieval task in an idle state, the target state level representing the performance state of the electronic device can be configured as P3, and the highest workable frequency of the electronic device during the operation can be the target work frequency matched with P3.
[0061] According to the embodiments of the present application, the configuration control can be provided on the first configuration interface, so that the target state level representing the performance state of the electronic device can be flexibly configured by the configuration control in an interactive manner. Then, based on the configuration information, the target work frequency of the electronic device can be determined, and thus the operation of the electronic device can be controlled by the target work frequency. Thus, the capped maximum work frequency can be flexibly adjusted based on the configured target work frequency, and thus the energy consumption can be reduced.
[0062] Optionally, the first configuration interface can be an interactive interface of a controller of the electronic device. The controller of the electronic device can be but not limited to a kind of controller device that can be used for management and monitoring of the electronic device. Similarly, the controller can be but not limited to an out-of-band system. Specifically, the controller can be but not limited to a BMC or a complex programmable logic device (CPLD) and the like. The BMC hardware implementation can be a separate board card installed on the mainboard, or can be integrated on the mainboard. The BMC is not limited by the management mode based on the user operating system, such as: the user operating system does not respond or is not loaded, and the BMC can still be used to switch the device, extract the device related information and the like.
[0063] According to the system configuration, the highest performance state level of the electronic device is P0, and the target working frequency corresponding to P0 is W0. After being configured through the first configuration interface, the highest performance state level of the electronic device is P1, and the target working frequency corresponding to P1 is W1. Wherein, P1 is less than P0, and W1 is less than W0.
[0064] The BIOS system can send a request for obtaining the current load of the electronic device to the controller, for example, the BMC, and the BMC sends the current load of the electronic device to the BIOS. The BIOS determines the current state level of the performance state of the electronic device according to the current load of the electronic device. The BIOS sends the current state level to the operating system, for example, the OS, so that the OS can adjust the working frequency of the electronic device to the working frequency suitable for the current state level.
[0065] Optionally, when the BIOS determines that the current state level P' is the target state level P1, the working frequency of the electronic device can be adjusted to the target working frequency W1 by using the OS. When the BIOS determines that the current state level P' is greater than the target state level P1, the working frequency of the electronic device is still adjusted to the target working frequency W1 by using the OS.
[0066] Therefore, the target working frequency of the electronic device can be flexibly configured through the first configuration interface, and the flexibility of the target working frequency adjustment is improved, and the energy consumption is reduced.
[0067] According to the related examples of the present application, the intelligent frequency reduction technology can be used to adjust the frequency of each electronic device according to the fixed working frequency as the maximum working frequency.
[0068] However, the fixed working frequency is difficult to adapt to electronic devices of different models and different manufacturers, and it is very likely that the electronic device will run under the condition of exceeding the maximum supportable working frequency, thereby causing aging or damage of the electronic device.
[0069] According to another related example of the present application, the intelligent frequency reduction technology can be used to adjust the running frequency of each electronic device according to the working frequency corresponding to P0 as the maximum working frequency.
[0070] Using the working frequency corresponding to P0 as the maximum working frequency can adapt to the frequency requirement of performing an AI training task, but for the search demand with less request amount, the working frequency corresponding to P0 is still used as the maximum working frequency for adjustment, which causes waste of energy consumption.
[0071] According to the embodiment of the present application, the configuration control can be set in the first configuration interface, and the target state level representing the performance state of the electronic device is reasonably configured through the interactive mode. The target working frequency matched with the target state level is taken as the maximum supportable working frequency, thereby improving the adaptability of the target working frequency to the electronic device and the adaptability of the target working frequency to the task to be executed by the electronic device, and avoiding the waste of resources and energy consumption.
[0072] The above describes how to set the target working frequency of the electronic device through the embodiment shown in Figure 2 The configuration control of the first configuration interface will be described in detail below.
[0073] According to the embodiment of the present application, for the operation S210 shown in Figure 2 The display of the first configuration interface can include at least one of the following display forms of the configuration control in the first configuration interface: slider type, list type, drop-down menu type, input box type, label type, scroll type and disc pointer type.
[0074] Figure 3 The schematic diagram of the configuration control according to the embodiment of the present application is shown.
[0075] As shown in Figure 3 The type of the configuration control can include option type or random type. The option type can include slider type 310, list type 320, drop-down menu type 330, label type 340, scroll type 350 or disc pointer type 360.
[0076] Optionally, the option type has provided multiple options, and the configuration information can be determined by clicking any option or the like, thereby simplifying the configuration operation.
[0077] Another option is that the random type can include input box type 370, and the corresponding configuration information can be determined by randomly inputting the option value, thereby improving the flexibility of the configuration.
[0078] According to the optional embodiment of the present application, the display form of the slider type is adopted in the first configuration interface to display the configuration control, which can include: displaying the track type component of the configuration control and the selector capable of sliding on the track type component. A plurality of mark points, also called nodes, are arranged on the track type component. A plurality of identifiers corresponding to the plurality of mark points are displayed on the first configuration interface, and the state levels represented by the plurality of identifiers are different.
[0079] Figure 4A The display schematic diagram of the slider type configuration control according to the embodiment of the present application is shown.
[0080] As shown in Figure 4AAs shown, multiple marker points 420 can be set on the track-type component 410 of the configuration control 400. The marker points can be set to squares or circles. Optionally, in order to clearly distinguish them from the square selector 430, the marker points can be set to circles.
[0081] like Figure 4A As shown, identifiers 440, such as P0, ..., P15, can be set around the marker 420, for example, above or below it, to characterize the performance state level (P-state) of the electronic device. P15 represents the lowest P-state performance state currently supported by the electronic device, with the lowest target operating frequency. P0 represents the highest P-state performance state currently supported, with the highest target operating frequency. At P1, P2, ..., P15, the highest operating frequency of the electronic device decreases sequentially, and power consumption and performance also decrease accordingly.
[0082] According to embodiments of this application, a slider-type configuration control is used, which can display all available options on the first configuration interface through identifiers, improving information readability. Furthermore, the operation of the configuration control is enhanced by using a selector slider.
[0083] According to embodiments of this application, for example, Figure 2 The operation S220 shown, in response to a state level configuration operation for a configuration control, displays configuration information matching the state level configuration operation on the first configuration interface. This may include: in response to a sliding operation of the selector on the track component, determining a target marker point specified by the selector on the track component; updating the color of a portion of the track component based on the selector's movement trajectory; and displaying the identifier corresponding to the target marker point as configuration information in a pop-up window.
[0084] Users can select a selector by clicking and dragging it on the track component. However, this is not the only option. The selector can also be controlled via touchscreen.
[0085] Because of human operation, the selector may not be fixed in a position that perfectly matches the marker point. Optionally, if the selector approaches the marker point or is within a preset range of the marker point and stops for a predetermined period of time, then the selector is determined to specify that marker point. This marker point can be used as the target marker point.
[0086] The color of a portion of the track-like component can be updated based on a target marker point, thus distinguishing it from unspecified marker points. However, this is not the only limitation. The color of a portion of the track-like component can also be updated along the selector's movement trajectory, allowing the user to determine whether the displayed content satisfies their operational intent.
[0087] In addition, the identifier corresponding to the target marker point is displayed in the form of a pop-up window, further prompting the configuration information of the user, so that the user is clear whether the operation intention is met, and the experience of the interaction is improved.
[0088] Figure 4B An operation schematic diagram of the slider configuration control according to another embodiment of the present application is shown.
[0089] As shown in Figure 4B , in response to the user control selector 430 sliding to the third marker point of the track component 410, corresponding to P2, the marker point P2 is taken as the target marker point. The area on the track component 410 where the selector 430 slides is marked in blue with a diagonal line, and the area where the selector 430 does not slide is marked in light gray. The identifier P2 corresponding to the target marker point is displayed in the form of a pop-up window 450.
[0090] The operation mode of the configuration control is described above, and the display form of the marker point of the configuration control will be described below.
[0091] According to an embodiment of the present application, before performing the operation S210 as shown in Figure 2 , the control method of the electronic device can further include determining the number of initial state levels that the electronic device can support based on the device attribute of the electronic device. In the case where the number of initial state levels of the electronic device is less than or equal to the predetermined number of state levels, the number of initial state levels is taken as the number of state levels. In the case where the number of initial state levels of the electronic device is greater than the predetermined number of state levels, the predetermined number of state levels is taken as the number of state levels.
[0092] Optionally, the predetermined number of state levels can include 16, which is set according to the Advanced Configuration and Power Management Interface (ACPI) specification.
[0093] If the number of initial state levels of each electronic device is greater than 16, the number is updated to 16, so that the number of P state levels does not exceed 16. In this way, the effectiveness of the identifier of the configuration control on the first configuration interface and the adaptability to the specification are improved, and the problem of invalid configuration caused by configuration not meeting the standard is avoided.
[0094] According to an embodiment of the present application, the track component for displaying the configuration control can include displaying a plurality of marker points on the track component, which are matched with the number of state levels of the electronic device.
[0095] In another optional embodiment, the track component displaying the configuration control can further include: updating the display state of the adjustable area on the track component to a state representing that the selector is slidable. The adjustable area includes a plurality of marker points corresponding to the number of state levels.
[0096] Optionally, the state levels of the optional P state displayed on the first configuration interface dynamically change with the number of state levels supported by different electronic devices. The number of state levels of the electronic device is determined according to the device attribute of the electronic device.
[0097] Optionally, the device attribute of the electronic device can include, but is not limited to, the model, the manufacturer, the maximum supported working frequency, the maximum supported state level, and the like.
[0098] Referring to FIGS. 1-3, the track component can display a plurality of marker points corresponding to the number of state levels, each of which is a selected state, for example, a state in which the selector is slidable on the track component corresponding to the marker point. Figure 4A Figure 4B Referring to FIGS. 1-3, the track component can display a plurality of marker points corresponding to the number of state levels, each of which is a selected state, for example, a state in which the selector is slidable on the track component corresponding to the marker point.
[0099] The track component can also display a plurality of excess marker points corresponding to the number of excess state levels, but the display state of the excess marker points is different from that of the marker points of the adjustable area. The excess marker points correspond to the area on the track component that the selector cannot slide to, while the marker points of the adjustable area correspond to the area on the track component that the selector can slide to and position the selection.
[0100] According to the device attribute of the electronic device, the adjustable range of the state levels representing the performance state is flexibly adjusted, thereby improving the flexibility of the state level configuration while ensuring the effectiveness of the adjustment from the optional perspective.
[0101] According to an embodiment of the present application, before performing the operation S230 as shown in FIG. 2, the control method of the electronic device further includes: in response to the confirmation control on the first configuration interface being triggered, determining that the confirmation instruction on the configuration information is received, wherein the confirmation control is used to indicate that the configuration is completed. Figure 2 In response to the waiting time being longer than the preset time, it is determined that the confirmation instruction on the configuration information is received, wherein the waiting time includes the time length between the current time and the operation time of the state level configuration operation.
[0102] In an embodiment of the present application, the confirmation control can be triggered in response to the click operation on the determination control of the first configuration interface. In response to the confirmation control being triggered, it is determined that the confirmation instruction on the configuration information is received, and the first configuration information is saved.
[0103]
[0104] Figure 4C An operation schematic diagram of the confirmation control according to an embodiment of the present application is shown.
[0105] As shown in Figure 4C , the confirmation control 460 can include a button with a "save" label. The confirmation instruction for the configuration information can be determined by a click operation on the confirmation control 460.
[0106] In another embodiment of the present application, the confirmation instruction can also but not limited to include a series of instructions for automatic script execution; the condition can be preset in advance (for example, the continuous waiting time length reaches the preset time length) through the automatic script, and the automatic script automatically generates the confirmation instruction.
[0107] Optionally, the server can be restarted immediately after the configuration information configured on the first configuration interface is saved. Or the server can be closed and wait for the next normal start of the server.
[0108] According to the embodiments of the present application, in response to the confirmation control being triggered, it is determined again that the confirmation instruction for the configuration information is received, or in response to the waiting time length exceeding the preset time length, it is determined again that the confirmation instruction is received, which can avoid the problem that the configuration information is configured due to the user's misoperation, and improve the effectiveness of the configuration information.
[0109] The display form of the configuration control is described above. However, the configuration control can not be configured at any time, and needs to be in an activated state. How to activate the configuration control will be described below.
[0110] According to the embodiments of the present application, when the operation S220 shown in Figure 2 is performed, the control method of the electronic device further includes: in response to the state level configuration operation for the configuration control, determining whether the configuration control is in an activated state. In response to the configuration control being in a non-activated state, refreshing the first configuration interface to display the configuration control representing the non-activated state.
[0111] Optionally, the first configuration interface can be configured with a tab representing whether the configuration control is in the activated state. Whether the activated state is represented by the option value of the tab. For example, the option value of 1 represents the activated state, and the option value of 0 represents the non-activated state.
[0112] When it is determined that the configuration control is in the non-activated state, the first configuration interface is refreshed to display the configuration control representing the non-activated state, for example, the configuration control is gray, and the selector cannot be selected, or the selector is automatically reset immediately after being selected.
[0113] According to the embodiments of the present application, the activated state can be set for the configuration control, which can be freely operated when the configuration control is in the activated state, thereby avoiding the misoperation problem of the configuration control, and further improving the effectiveness of the configuration information configuration.
[0114] Alternatively, before the end of each BIOS startup process, the current information indicating whether the configuration control is in the active state is sent to the BMC in a predetermined information format through the Redfish channel, and the BMC saves the information in a second storage unit in the BMC chip. By searching for the information, it is determined whether the configuration control is in the active state.
[0115] In another optional example, the second configuration interface is configured with a tab indicating whether the configuration control is in the active state. The option value of the tab indicates whether it is in the active state.
[0116] Optionally, the second configuration interface can be a configuration interface of a control system of the server. The control system can be, but is not limited to, a comprehensive management platform integrating software and hardware functions, which is responsible for monitoring and managing the running state of the server, including initialization, configuration, performance adjustment and fault diagnosis of hardware devices. Specifically, the control system of the server can be, but is not limited to, an out-of-band system. The out-of-band system can be, but is not limited to, a system outside the in-band system of the server, which does not depend on the operating system and can provide the most basic and direct hardware management and control for the device. The control system of the server can be, but is not limited to, BIOS. BIOS can be, but is not limited to, a ROM chip and a group of programs running thereon fixed to the motherboard of the server. The group of programs includes the most important basic input and output program of the computer, system setting information, self-checking program after startup and system self-starting program. BIOS can provide the most basic and direct hardware setting and control for the device. Currently, the functions of BIOS are mainly used for device self-checking, hardware initialization, driver loading, system booting, etc., and will automatically exit the running after booting the device into the system.
[0117] According to the embodiments of the present application, in the case where it is determined that the configuration control is in the inactive state, the configuration control in the active state can be updated through the second configuration interface configured by the control system. Specifically, the control method of the electronic device further includes: adjusting the configuration control to the active state on the second configuration interface.
[0118] Specifically, the parameter item of the active control is adjusted to the parameter item indicating that the configuration control is in the active state on the second configuration interface. The first configuration interface is refreshed to display the configuration control in the active state.
[0119] Optionally, the user can enter the second configuration interface through the first configuration interface to activate the configuration control.
[0120] Thus, the control mode of the electronic device is the "EIST, intelligent frequency reduction technology" mode, and the configuration control on the first configuration interface is activated.
[0121] By adjusting the configuration control in the above manner, the flexibility of the configuration can be improved, and the existing controls on the second configuration interface can be applied by combining the second configuration interface.
[0122] According to an optional embodiment of the present application, the activation control includes a first activation control and a second activation control. The first activation control is used to activate the frequency dynamic adjustment function of the electronic device. The second activation control is used to activate the frequency general adjustment function of the electronic device.
[0123] Optionally, the first activation control can be a control representing the frequency dynamic adjustment function, such as any of “EIST Support”, “EIST”, and “Speed Step”. The second activation control can be a control representing the frequency general adjustment function, such as “Hardware P-State”.
[0124] Adjusting the parameter items of the activation control on the second configuration interface to the active state of the configuration control includes: adjusting the parameter items of the first activation control on the second configuration interface to available items, such as “Enabled”. Adjusting the parameter items of the second activation control on the second configuration interface to unavailable items, such as “Disabled”.
[0125] Figure 5A A schematic diagram of the activation control of the second configuration interface according to an embodiment of the present application is shown.
[0126] As shown in Figure 5A The first activation control and the second activation control displayed on the second configuration interface are both drop-down menus. The parameter items of the drop-down menus both include “Enabled” and “Disabled”. By selecting the parameter items, it is determined whether the items are available.
[0127] According to an embodiment of the present application, the two activation controls work together to improve the fine granularity of the active state operation and avoid the problem of false activation.
[0128] According to another embodiment of the present application, the control method of the electronic device can further include: in response to an option configuration operation on the option configuration control displayed on the first configuration interface, generating an option configuration command for activating the configuration control. Sending the option configuration command to the control system to activate the configuration control through the control system.
[0129] The option configuration control is used to control whether to generate the option configuration command for activating the configuration control. The option configuration operation can be used to trigger the generation of the option configuration command for activating the configuration control. The option configuration control can be an option, such as an option parameter for activating or not activating the configuration control, and the option configuration operation is selected by selecting the option parameter to generate the option configuration command.
[0130] Figure 5B A block diagram of configuration information activation is shown according to an embodiment of the present application.
[0131] As Figure 5B shown, the option configuration command can be sent to the control system 520 through the first configuration interface 511 of the controller 510 to activate the configuration control through the control system 520.
[0132] Exemplarily, the parameter item of the first activated control can be automatically adjusted to the available item and the parameter item of the second activated control can be automatically adjusted to the non-available item on the second configuration interface 521 through the control system 520.
[0133] Therefore, the second configuration interface can be opened without manual operation, the second configuration interface can be automatically switched and the activated operation of the configuration control can be performed through the option configuration operation of the first configuration interface, thereby realizing the front-end non-sensing back-end processing and improving the user experience.
[0134] Optionally, as Figure 5B shown, after the configuration control is in the activated state of the configuration state, the electronic device 530 can be restarted to activate the configuration control to be in the configurable state, thereby improving the accuracy and stability of the target working frequency configuration of the electronic device 530.
[0135] According to an embodiment of the present application, after the operation S230 as Figure 2 shown is performed, the control method of the electronic device can further include: writing the configuration information into a target register of the electronic device.
[0136] As Figure 5B shown, the configuration information can be written into the target register 531 of the electronic device 530 through the controller 510. During the running process of the operating system OS 532 running on the electronic device 530, the control system 520 can send a request for obtaining the current load of the electronic device 530 and obtaining the target working frequency matched with the target state level to the controller 510, the controller 510 sends the current load of the electronic device 530 to the control system 520 and sends the configuration information such as the target state level read from the target register 531 to the control system 520, the control system 520 determines the current state level of the performance state of the electronic device 530 according to the current load of the electronic device 530 and the target state level, and sends the working frequency matched with the current state level to the operating system OS 532, so that the operating system OS 532 can adjust the working frequency of the electronic device 530 to the working frequency matched with the current state level.
[0137] Optionally, when the control system 520 determines that the current state level P' is the target state level P1, the operating system OS 532 can be used to adjust the working frequency of the electronic device 530 to the target working frequency W1. When the control system 520 determines that the current state level P' is greater than the target state level P1, the operating system OS 532 is still used to adjust the working frequency of the electronic device 530 to the target working frequency W1.
[0138] Optionally, the target register can include a first register and a second register. The target state level stored in the first register is used to control the running of a thread executed by the electronic device. The target state level stored in the second register is used to control the running of a process executed by the electronic device.
[0139] By using both registers as target registers and for controlling the running of different tasks executed by the electronic device, flexibility of configuration is improved, and subsequent operation capability in combination with actual hardware is improved, thereby improving power consumption adjustment performance of the electronic device.
[0140] According to embodiments of the present application, after performing the operation S230 as shown in Figure 2 The control method of the electronic device can further include: generating a target data packet based on the target state level of the electronic device and the check sequence; sending the target data packet to the electronic device, so that the electronic device decompresses the target data packet, checks the target data packet using the check sequence, and receives feedback information from the electronic device. In the case that the feedback information represents that the target data packet passes the check, it is determined that the target state level has been stored in the target register of the electronic device, so that the operating system controls the electronic device to run based on the target state level stored in the target register.
[0141] When the target state level is written into the data packet, an assured write frame check sequence (AWFCS) is included therein. Exemplarily, the target data packet can be sent to the electronic device, so that the electronic device decompresses the target data packet. If the AWFCS does not match the target check sequence, the electronic device aborts storing the target state level into the target register. And feedback information representing that the check fails is displayed on the first configuration interface, so that the target data packet is regenerated and sent.
[0142] If the AWFCS matches the target check sequence, the electronic device stores the target state level into the target register. And feedback information representing that the check passes is displayed on the first configuration interface, so that the operating system controls the electronic device to run based on the target state level stored in the target register, using the target working frequency matching the target state level.
[0143] Thus, the security and effectiveness of the target state level in the configuration information are improved. The problem of unsuccessful configuration due to storage failure is avoided.
[0144] Alternatively, the target state level of the electronic device can be configured by a configuration operation as shown in Figure 2 However, the application is not limited thereto. After the operating system of the electronic device is started, the state identifier representing the performance state level can be manually written in the target register of the electronic device. The state identifier is different from the performance state level represented by the displayed configuration information of the first configuration interface.
[0145] In order to avoid the problem of being arbitrarily tampered, the stability check can be performed in the following manner.
[0146] According to the embodiment of the application, the control method of the electronic device further comprises: reading the current state level stored in the target register of the electronic device at a predetermined period. In the case that the current state level does not match the target state level, determining that the target register is abnormal. In the case that the target register is abnormal, sending the configuration information to the electronic device so as to update the data stored in the target register.
[0147] The current state level stored in the target register of the electronic device is read at a predetermined period, for example, once every 1 hour or once every 30 minutes. So that the BIOS informs the operating system of the configurable working frequency based on the current load state of the electronic device and the target state level stored in the target register. So that the operating system controls the electronic device to run according to the current configurable working frequency.
[0148] The data in the target register is checked by the embodiment of the application, thereby improving the correctness of the data in the target register, and preventing the problem of conflict between the data written in the target register and the configured data after a certain P target state level is selected.
[0149] According to the embodiment of the application, the target register comprises a first register and a second register. The target state level stored in the first register is used to control the running of the thread executed by the electronic device. The target state level stored in the second register is used to control the running of the process executed by the electronic device.
[0150] In the case that the current state level does not match the target state level, it is determined that the target register is abnormal. Specifically, it can include: in the case that any one of the current state level stored in the first register and the current state level stored in the second register does not match the target state level, it is determined that the target register is abnormal.
[0151] The first register type can be 0x199, and the second register type can be 0x64C. The first register and the second register can both write a target state level, but are not limited thereto, and can also write a target operating frequency. When the two registers are simultaneously set and take effect, the configuration accuracy and effectiveness of the target operating frequency of each scope are improved by using the different scopes of the two registers.
[0152] The above describes the configuration control, and the following describes how to determine the target operating frequency based on the configuration information.
[0153] According to an embodiment of the present application, for the operation S230 as shown in FIG. 2, determining the target operating frequency of the electronic device corresponding to the configuration information can include: determining the target operating frequency corresponding to the configuration information from the plurality of operating frequencies based on a level mapping relationship. Figure 2
[0154] The level mapping relationship represents the corresponding relationship between the state levels and the operating frequencies of the electronic device. For example, the level mapping relationship can include that the state level P0 corresponds to the operating frequency W0, the state level P1 corresponds to the operating frequency W1,..., and the state level Pn corresponds to the operating frequency Wn.
[0155] The target operating frequency can be determined as W1 based on the identifier P1 indicated in the user configuration information.
[0156] According to an embodiment of the present application, the target operating frequency is determined by using the mapping relationship, which can improve the processing efficiency and simplify the determination operation.
[0157] According to an embodiment of the present application, the level mapping relationship can be determined by the following operation: obtaining the frequency threshold of the electronic device from the register of the electronic device. Based on the frequency threshold and the number of state levels of the electronic device, the operating frequency corresponding to each state level is determined to generate the level mapping relationship.
[0158] The frequency threshold includes a maximum frequency value and a minimum frequency value . The difference between the maximum frequency value and the minimum frequency value may be divided into N equal parts based on the number of state levels N, and the number interval includes , which is N-1.
[0159] The operating frequency corresponding to each state level can be determined by referring to the following formula (1).
[0160] ; formula (1)
[0161] wherein i is 0 to N-1, represents the working frequency corresponding to the i-th P state level.
[0162] The level mapping relationship is determined in the above manner, so that the working frequency corresponding to the performance state level P0 is the largest, and the working frequency corresponding to P(N-1) is the smallest. By using the above mapping manner, the identifier of the configuration control displayed on the first configuration interface can be corresponded to the general knowledge of the user, so as to reduce the understanding difficulty of the user and improve the configuration efficiency of the user.
[0163] According to a preferred embodiment of the present application, based on the frequency threshold and the number of state levels of the electronic device, the working frequency corresponding to each state level is determined, which can further include: determining the initial working frequency corresponding to each state level from the frequency threshold in a uniform manner. In the case that the initial working frequency is a decimal number, the initial working frequency is fine-tuned to determine the working frequency corresponding to the state level, so that the level mapping relationship is in a quasi-linear distribution.
[0164] The fine-tuning of the initial working frequency can include rounding offset. For example, the working frequency corresponding to each state level can be determined by referring to the following formula (2).
[0165] ; formula (2)
[0166] wherein i is 0 to N-1, for offset rounding, to ensure that the multiple working frequencies are more evenly distributed.
[0167] According to an embodiment of the present application, the number of state levels can change with different electronic devices, so the selectable state levels displayed on the first configuration interface are dynamically changed with the number of state levels supported by different electronic devices. The BIOS obtains the maximum frequency value and the minimum frequency value of the current electronic device by reading the register during the startup process. If the Turbo Mode is turned on, the frequency corresponding to P0 can be set as the maximum Turbo frequency value, and if the Turbo Mode is turned off, the P0 frequency is set as the maximum Non-Turbo frequency value. After determining the number of state levels, the working frequency corresponding to each level state is calculated, which can use (i * RatioRange + M) / NumGaps to achieve a quasi-linear distribution, and M is used for offset rounding to ensure that the distribution is more uniform.
[0168] Whether the configuration information is suitable for the task to be executed and other hardware can be further confirmed by the following manner.
[0169] According to an optional embodiment of the present application, for example, Figure 2After the operation S230 shown, the control method of the electronic device can further include: in response to a task configuration operation on the task control displayed in the first configuration interface, displaying task information matched with the task configuration operation in the first configuration interface. Displaying prompt information indicating whether the configuration information is qualified in the first configuration interface.
[0170] The task information is used to indicate a task performed by the electronic device. The prompt information is determined by checking the target working frequency corresponding to the configuration information based on the frequency reference information, and the frequency reference information is determined by the task information.
[0171] Figure 6A A schematic diagram of a task configuration operation according to an embodiment of the present application is shown.
[0172] The task control can be displayed in the first configuration interface. The task control can be any one of a slider, a list, a drop-down menu, and an input box. As shown in Figure 6A The task control 611 can be a drop-down menu, thereby avoiding the user to type, and improving the recognition ability of the controller, such as the BMC, to the task information.
[0173] As shown in Figure 6A In response to a selection operation on the multiple candidate task information in the drop-down menu 612, the task information 613, such as the task n displayed in the display box, is determined. In response to a confirmation operation on the task information 613, such as a click operation on the "confirm" identification control 614, it is determined that the task configuration operation of the user selecting the task information 613 is completed.
[0174] Based on the frequency reference information and the target frequency information configured by the user, the prompt information indicating whether the configuration information is qualified is determined. And as shown in Figure 6A the prompt information is displayed in the first configuration interface. For example, the prompt information 615 is displayed in the form of a pop-up window.
[0175] Optionally, in the case that the target frequency information is less than the frequency reference information, it can be determined that the configuration information is unqualified, and prompt information indicating the unqualification can be fed back. In the case that the target frequency information is greater than or equal to the frequency reference information, it can be determined that the configuration information is qualified, and prompt information indicating the qualification can be fed back.
[0176] According to the embodiments of the present application, in the case that the target frequency information is configured by the user, the task control is used to determine the task to be performed, so as to determine whether the configuration information and the task to be performed are adapted, thereby improving the effectiveness and qualification of the configuration information, avoiding the waste of resources, and the low efficiency of task execution and the problem of affecting user experience caused by the too low highest working frequency that can be supported.
[0177] The above describes the eligibility check of the configuration information by the frequency reference information matched with the task information. How to obtain the frequency reference information will be introduced below.
[0178] According to an optional embodiment of the present application, the frequency reference information can be determined from the multiple candidate frequency reference information based on the task information and the task mapping relationship. The task mapping relationship represents the corresponding relationship between the task information and the candidate frequency reference information.
[0179] According to the embodiments of the present application, the frequency reference information can be accurately and quickly determined by using the task mapping relationship, thereby improving the processing efficiency.
[0180] According to another optional embodiment of the present application, the frequency reference information can also be determined by a deep learning method. For example, the task features of the task information are input into a first deep learning model to obtain the frequency reference information.
[0181] The task information can be feature-extracted by a feature extraction network to obtain the task features. The network structure of the feature extraction network is not limited. For example, it can include at least one of a convolutional neural network, an encoder-decoder, or a long short-term memory network.
[0182] The first deep learning model can include at least one of an encoder-decoder, a fully connected layer, a graph neural network, and an XGboost network.
[0183] According to the embodiments of the present application, the frequency reference information is determined by using the deep learning model, which can be used as a technical compensation when the task information does not exist in the task mapping relationship, thereby improving the universality of the frequency reference information determination and avoiding technical gaps.
[0184] According to an optional embodiment of the present application, after the operation S230 as shown in Figure 2 The control method of the electronic device can further include: in response to a triggering operation on the health assessment control displayed in the first configuration interface, displaying multiple assessment items in the first configuration interface. In response to receiving an assessment instruction, displaying a target assessment item indicated by the assessment instruction in the first configuration interface. In response to receiving an assessment confirmation instruction on the target assessment item, displaying assessment information on the first configuration interface. The assessment information represents the influence of the target working frequency on the hardware matched with the target assessment item.
[0185] Figure 6B A schematic diagram of the health assessment operation according to an embodiment of the present application is shown.
[0186] The health assessment control can be displayed in the first configuration interface. The health assessment control can be any one of a slider type, a list type, a drop-down menu type, and an input box type. As shown in Figure 6BAs shown, the health assessment control 621 can be in the form of a drop-down menu, thereby avoiding the user from typing and improving the recognition ability of the controller, such as the BMC, on the assessment item.
[0187] As shown, the plurality of assessment items in the drop-down menu 622 can include an impact on a heat dissipation component, an impact on a memory, a wear impact on the electronic device, and the like. In response to a selection operation of any one of the plurality of assessment items by the user, such as a click operation on the assessment item, the target assessment item 623 is determined, and an assessment instruction is generated. In response to receiving the assessment confirmation instruction for the target assessment item, such as through a trigger operation of clicking the “confirm” icon control 624, it is determined that the assessment confirmation instruction is received. Figure 6B The assessment information is displayed on the first configuration interface. The assessment information represents an impact of the target working frequency on the hardware matched with the target assessment item.
[0188] As shown, the assessment information 625 is displayed on the first configuration interface. The assessment information 625 is displayed in the form of a pop-up window, for example. The assessment information can indicate that no impact is caused on the heat dissipation component. Or the setting of the target working frequency will accelerate the aging of the electronic device, and the like.
[0189] Figure 6B According to the embodiments of the present application, in the case where the user configures the target frequency information, the assessment control can be used to determine the impact of the target working frequency on the hardware of the server, so as to determine whether the configuration information will bring adverse effects on the hardware, thereby improving the effectiveness and security of the configuration information, verifying the service life and use safety of the server.
[0190] According to another optional embodiment of the present application, the assessment information can also be determined through a deep learning method. For example, the assessment item features of the target assessment item and the frequency features of the target working frequency are input into a second deep learning model to obtain the assessment information.
[0191] The feature extraction network can be used to extract features of the target assessment item to obtain the assessment item features. The network structure of the feature extraction network is not limited. For example, it can include at least one of a convolutional neural network, an encoder-decoder, or a long short-term memory network.
[0192] The second deep learning model can include at least one of an encoder-decoder, a fully connected layer, a graph neural network, an XGBoost (eXtreme Gradient Boosting) network, or a combination thereof.
[0193] According to an optional embodiment of the present application, as shown,
[0194] According to an optional embodiment of the present application, as shown, Figure 2 Following operation S230, the control method for the electronic device may further include: displaying multiple optimization items on the first configuration interface in response to a trigger operation on an optimization control displayed on the first configuration interface; displaying the target optimization item indicated by the optimization instruction on the first configuration interface in response to receiving an optimization instruction; and displaying optimization information matching the target optimization item on the first configuration interface in response to receiving an optimization confirmation instruction for the target optimization item.
[0195] Figure 6C A schematic diagram of the level state optimization according to an embodiment of this application is shown.
[0196] Optimization controls can be displayed in the first configuration interface. These controls can be sliders, lists, dropdown menus, or input boxes. For example... Figure 6C As shown, the optimization control 631 can be a drop-down menu, thereby avoiding user typing and improving the controller's ability, such as BMC, to identify the target optimization item.
[0197] like Figure 6C As shown, the multiple optimization items in the drop-down menu 632 may include optimizations for heat dissipation components, memory, and the status level of electronic devices. In response to a user's selection of any of the optimization items, such as a click on an optimization item, the target optimization item 633 is determined, and an optimization instruction is generated. In response to receiving an optimization confirmation instruction for the target optimization item, such as a click on the "Confirm" indicator control 634, it is determined that an optimization confirmation instruction has been received.
[0198] The optimization information is displayed on the first configuration interface. The optimization information represents the optimization information that matches the target optimization item.
[0199] like Figure 6C As shown, optimization information 635 is displayed on the first configuration interface. For example, the optimization information may be displayed as a pop-up window. The optimization information may indicate: reducing the operating frequency of heat dissipation components or lowering the target state level of electronic devices to reduce power consumption.
[0200] Optionally, the target optimization item can be determined based on the evaluation information. For example, if the evaluation information determines that the target operating frequency affects the operation of target hardware, such as a power supply, the target optimization item can be determined as an optimization related to the target hardware based on the hardware indicated by the evaluation information. This combines the evaluation information with the optimization information, improving the relevance and accuracy of the optimization information.
[0201] According to embodiments of this application, when the user configures target frequency information, the optimization control can be used to determine the target optimization item, thereby performing further optimization configuration, thereby improving the server's operating performance, stability, security, and reducing the server's energy consumption.
[0202] According to another optional embodiment of the present application, the optimization information can also be determined by a deep learning method. For example, the optimization item features of the target optimization item and the frequency features of the target working frequency are input into a third deep learning model to obtain the optimization information.
[0203] The target optimization item can be subjected to feature extraction by a feature extraction network to obtain the optimization item features. The network structure of the feature extraction network is not limited. For example, it can include at least one of a convolutional neural network, an encoder-decoder, or a long short-term memory network.
[0204] The third deep learning model can include at least one of an encoder-decoder, a fully connected layer, a graph neural network, an XGboost network, or a combination thereof.
[0205] Optionally, the first deep learning model, the second deep learning model, and the third deep learning model can adopt the same model structure and be trained by different training samples. However, it is not limited thereto. Different model structures can also be adopted and be trained by different training samples.
[0206] A deep learning model combining the same main network structure and multiple expert networks can be constructed to adapt to different processing tasks, such as an expert network for generating frequency reference information, an expert network for generating optimization information, and an expert network for generating evaluation information.
[0207] Another optional example, the graph features of the heterogeneous graph can also be collectively used as input data to perform the processing tasks introduced above. The heterogeneous graph provided by the embodiments of the present application will be described below. Figure 7
[0208] Figure 7 A schematic diagram of the heterogeneous graph according to the embodiments of the present application is shown.
[0209] As shown in Figure 7 , the heterogeneous graph 700 can include different types of first nodes 710 represented by blocks, second nodes 720 represented by triangles, and third nodes 730 represented by circles, as well as different types of first edges 740 and second edges 750. The first nodes 710 represent tasks, the second nodes 720 represent hardware, and the third nodes 730 represent state levels. The first edges 740 with arrows are used to connect two nodes having a causal relationship, and the second edges 750 without arrows are used to connect two nodes having a correlation. The first nodes 710, the second nodes 720, and the third nodes 730 all have their own node attributes.
[0210] Optionally, the first node 710 can specifically represent, for example, but not limited to, query service or AI training service, and can also be AI inference task, etc. The node attribute corresponding to the first node 710 can include: service type, processing time length, type of data to be processed, etc.
[0211] Optionally, the second node 720 can specifically represent, for example, but not limited to, CPU, GPU, memory, power supply, etc. The node attribute corresponding to the second node 720 can include: dynamic attribute, for example, temperature (℃), running frequency (GHz), power consumption (W), load rate (%), cumulative running time (hours), and static attribute, such as model, process technology (nm), power consumption (W), identification, etc.
[0212] Optionally, the third node 730 can specifically represent, for example, but not limited to, state level of capping (P0-P7). The node attribute corresponding to the third node 730 can include: effective range (such as single node, rack, cluster), trigger condition (such as "temperature ≥ 85℃"), associated action (such as synchronously adjusting fan speed to 80%), etc.
[0213] The first edge 740 is used to connect two nodes with causal relationship, for example, the second node 720 representing hardware and the third node 730 representing state level have causal relationship. Specifically, a directed edge with arrow can be used to represent. For example, "CPU temperature rises" → "trigger P state capping", and the edge attribute can be the influence degree of temperature change rate on state level. For another example, the third node 730 representing state level and the first node 710 representing service have causal relationship. Specifically, "maximum P state is set to P2" → "response time of A service is prolonged by 10%", and the edge attribute can be the historical average influence value.
[0214] The second edge 750 is used to connect two nodes with correlation. The correlation can include that the two nodes are associated with each other, but is not limited to this, and can also include that the two nodes depend on each other. A non-directed edge can be used to represent. For example, the second node 720 representing hardware and the first node 710 representing service have correlation, specifically, for example, "AI training task" ↔ "high GPU memory bandwidth demand", and the edge attribute can include resource occupation threshold.
[0215] By using the heterogeneous graph provided in the present application, various information of different types such as hardware, service, state level, etc. can be included, the data to be analyzed can be enriched, and the application range can be expanded.
[0216] According to the embodiment of the present application, the processing of the heterogeneous graph and the obtaining of the graph feature can be performed by the following operations: performing graph isomorphism representation on the heterogeneous graph to obtain a first graph feature; performing graph heteromorphism representation on the heterogeneous graph to obtain a second graph feature; and fusing the first graph feature and the second graph feature to obtain the graph feature.
[0217] Optionally, the graph global representation of the heterogeneous graph can be performed by using a graph convolution neural network (GCN). For example, for each node, the features of the neighbor nodes and the weights of the relationship edges are aggregated, so that the first graph feature represents the correlation feature between each node and the adjacent nodes and edges.
[0218] Optionally, the graph attention neural network (GAT) can also be used to calculate the attention coefficient between the nodes to highlight the key relationship features.
[0219] The graph convolution operation in the GCN can be used to aggregate the neighbor node features in the heterogeneous graph, which solves the representation problem of the graph structure data, but it is difficult to process the difference representation of different types of nodes and multi-element relationships in the heterogeneous graph. The GAT introduces an attention mechanism, which can effectively improve the representation ability of different types of nodes and edges in the heterogeneous graph by adaptively learning the correlation between the nodes, and assign different attention weights. Therefore, by combining the GCN and the GAT, the representation can be performed comprehensively from the isomorphism and the heteromorphism, so that the obtained graph feature is rich and complete in information.
[0220] The frequency reference information can be obtained by combining the graph feature of the obtained heterogeneous graph and the task feature of the task information. For example, the task feature of the task information and the graph feature of the heterogeneous graph are input into a first target model to obtain the frequency reference information.
[0221] The deep learning model as shown in Figure 8 can also be used to process the task information and the heterogeneous graph to obtain the frequency reference information.
[0222] Figure 8 The schematic diagram of the deep learning model according to the embodiment of the present application is shown.
[0223] As shown in Figure 8 , the deep learning model can include a GCN M810, a GAT M820, a feature extraction layer M830, and a set of expert networks M840.
[0224] As shown in Figure 8As shown, the heterogeneous graph 810 can be input into the GCN M810 and the GAT M820 respectively to obtain first graph feature 820 and second graph feature 830. The first graph feature 820 and the second graph feature 830 are fused to obtain the graph feature 840.
[0225] As shown, the task information 850 can be input into the feature extraction layer M830 to obtain the task feature 860. Figure 8
[0226] As shown, the task feature 860 and the graph feature 840 are jointly input into the target expert network to obtain the frequency reference information 870. Figure 8
[0227] By using the deep learning model provided in the present application, different to-be-processed tasks can be adapted through the constructed multiple expert networks, thereby improving the universality of application.
[0228] As shown, the target evaluation item can also be input into the feature extraction layer M830 to obtain the evaluation feature of the target evaluation item. The target working frequency is input into the feature extraction layer M830 to obtain the frequency feature. The evaluation feature of the target evaluation item, the frequency feature of the target working frequency, and the graph feature of the heterogeneous graph are input into the second target network to obtain the evaluation information, as shown in the dashed line content. Figure 8 Figure 9
[0229] Optionally, the second target network is determined from the expert network set based on the evaluation feature and the frequency feature.
[0230] According to the evaluation information determination method provided in the embodiments of the present application, the health condition of the hardware can be evaluated, the configuration flexibility is improved, the comprehensive analysis capability is realized, and the configuration information is adapted to the health of the hardware. In addition, the frequency feature, the evaluation feature, and the heterogeneous graph are combined, so that the information to be considered is comprehensive and effective. In addition, the second target network matched with the evaluation task is determined from the expert network set, and the expertise is strong.
[0231] As shown, the target optimization item can also be input into the feature extraction layer to obtain the optimization feature. The optimization feature of the target optimization item, the frequency feature of the target working frequency, and the graph feature of the heterogeneous graph are input into the third target model to obtain the optimization information.
[0232] Optionally, the third target network is determined from the expert network set based on the optimization feature and the frequency feature.
[0233] According to the optimization information determination method provided in the embodiments of the present application, the analysis can be performed from the optimization perspective, the configuration flexibility can be improved, the optimization capability of hardware and state level and the like information can be realized, and thus the optimization capability of the configuration information can be ensured. In addition, the combination of the frequency feature, the optimization feature and the heterogeneous atlas makes the information to be considered comprehensive and effective. In addition, the second target network matched with the optimization task is determined from the expert network set, the expertise is strong, and the optimization information obtained finally is comprehensive and effective.
[0234] According to the embodiments of the present application, the determination of the first target network, the second target network and the third target network from the expert network set can be the same or similar.
[0235] Optionally, the intention information can be determined based on the task information. Based on the intention information, the first target network is determined from the plurality of expert networks.
[0236] However, it is not limited thereto. The task feature can also be input to the gating layer, and based on the classification result output by the gating layer, the first target network is determined from the plurality of expert networks. The gating layer can include a fully connected layer and an activation function.
[0237] Optionally, the frequency feature and the evaluation feature can also be input to the gating layer, and based on the classification result output by the gating layer, the second target network is determined from the plurality of expert networks.
[0238] Optionally, the frequency feature and the optimization feature can also be input to the gating layer, and based on the classification result output by the gating layer, the third target network is determined from the plurality of expert networks.
[0239] Based on the control method of the electronic device, the present application further provides a control device of the electronic device. The control device of the electronic device according to the embodiments of the present application will be described in detail below. Figure 9 The control device will be described in detail.
[0240] Figure 9 The structure block diagram of the control device of the electronic device according to the embodiments of the present application is shown.
[0241] As shown in The control device 900 of the electronic device according to the embodiments includes an interface display module 910, a level configuration module 920 and an information determination module 930.
[0242] The interface display module 910 is configured to display a first configuration interface. The first configuration interface displays a configuration control. The configuration control is configured to adjust a target working frequency of the electronic device. The target working frequency indicates a highest working frequency that can be supported by the electronic device. In an embodiment, the interface display module 910 can be configured to perform the operation S210 described above, and thus the description will not be repeated here.
[0243] The level configuration module 920 is used to respond to a status level configuration operation on the configuration control by displaying configuration information matching the status level configuration operation on the first configuration interface. The configuration information represents the target status level of the electronic device's performance state, and there is a mapping relationship between the target status level and the target operating frequency. In one embodiment, the level configuration module 920 can be used to perform the operation S220 described above, which will not be repeated here.
[0244] The information determination module 930 is used to determine the target operating frequency of the electronic device corresponding to the configuration information in response to receiving a confirmation command for the configuration information, so as to control the operating frequency of the electronic device to not exceed the target operating frequency during operation. In one embodiment, the information determination module 930 can be used to perform the operation S230 described above, which will not be repeated here.
[0245] According to an embodiment of this application, the interface display module includes an interface display submodule.
[0246] The interface display submodule is used to display configuration controls in the first configuration interface using at least one of the following display formats: slider, list, drop-down menu, input box, label, scroll, or circular pointer.
[0247] According to an embodiment of this application, the interface display submodule includes: an interface display unit.
[0248] The interface display unit is used to display the track-shaped component of the configuration control and the selector that can slide on the track-shaped component. Multiple markers are set on the track-shaped component, and multiple identifiers corresponding to the multiple markers are displayed on the first configuration interface. The multiple identifiers represent different state levels.
[0249] According to an embodiment of this application, the level configuration module includes: a sliding submodule and an update submodule.
[0250] The sliding submodule is used to determine the target marker point specified by the selector on the track component in response to the sliding operation of the control selector on the track component.
[0251] The update submodule is used to update the color of a portion of the track-type component based on the motion trajectory of the selector, and display the identifier corresponding to the target marker point as configuration information in a pop-up window.
[0252] According to an embodiment of this application, the interface display unit includes: a first marker display subunit or a second marker display subunit.
[0253] The first marker display subunit is used to display multiple markers on the track-type assembly that match the number of status levels of the electronic device.
[0254] The second mark point display sub-unit is configured to update the display state of the adjustable area on the track assembly to a state indicating that the selector is slidable, wherein the adjustable area includes a plurality of mark point areas corresponding to the number of state levels.
[0255] The number of state levels of the electronic device is determined according to the device attribute of the electronic device.
[0256] According to an embodiment of the present application, the control device of the electronic device further includes a first level number determination module, a second level number determination module and a third level number determination module.
[0257] The first level number determination module is configured to determine the initial number of state levels that can be supported by the electronic device based on the device attribute of the electronic device.
[0258] The second level number determination module is configured to, in a case where the initial number of state levels of the electronic device is less than or equal to a predetermined number of state levels, take the initial number of state levels as the number of state levels.
[0259] The third level number determination module is configured to, in a case where the initial number of state levels of the electronic device is greater than the predetermined number of state levels, take the predetermined number of state levels as the number of state levels.
[0260] According to an embodiment of the present application, the control device of the electronic device further includes an activation determination module and a first refreshing module.
[0261] The activation determination module is configured to, in response to a state level configuration operation on the configuration control, determine whether the configuration control is in an activated state.
[0262] The first refreshing module is configured to, in response to the configuration control being in an inactivated state, refresh the first configuration interface to display the configuration control in the inactivated state.
[0263] According to an embodiment of the present application, the control device of the electronic device further includes an activation module and a second refreshing module.
[0264] The activation module is configured to adjust a parameter item of the activation control on the second configuration interface to indicate that the configuration control is in the activated state.
[0265] The second refreshing module is configured to refresh the first configuration interface to display the configuration control in the activated state.
[0266] According to an embodiment of the present application, the activation control includes a first activation control and a second activation control, wherein the first activation control is configured to activate a frequency dynamic adjustment function of the electronic device, and the second activation control is configured to activate a frequency general adjustment function of the electronic device.
[0267] According to an embodiment of the present application, the activating module comprises a first activating submodule and a second activating submodule.
[0268] The first activating submodule is configured to adjust the parameter item of the first activating control to an available item on the second configuration interface.
[0269] The second activating submodule is configured to adjust the parameter item of the second activating control to a non-available item on the second configuration interface.
[0270] According to an embodiment of the present application, the control device of the electronic device further comprises an option configuration module and a command sending module.
[0271] The option configuration module is configured to generate an option configuration command for activating the configuration control in response to an option configuration operation on the option configuration control displayed on the first configuration interface.
[0272] The command sending module is configured to send the option configuration command to the control system to activate the configuration control through the control system.
[0273] According to an embodiment of the present application, the control device of the electronic device further comprises a restart module.
[0274] The restart module is configured to restart the electronic device to activate the configuration control.
[0275] According to an embodiment of the present application, the control device of the electronic device further comprises a first confirmation instruction determination module or a second confirmation instruction determination module.
[0276] The first confirmation instruction determination module is configured to determine that a confirmation instruction for the configuration information is received in response to the confirmation control on the first configuration interface being triggered, wherein the confirmation control is used to indicate that the configuration is completed.
[0277] The second confirmation instruction determination module is configured to determine that a confirmation instruction for the configuration information is received in response to a waiting time length being longer than a preset time length, wherein the waiting time length comprises a time length between a current time and an operation time of the state level configuration operation.
[0278] According to an embodiment of the present application, the information determination module comprises an information determination submodule.
[0279] The information determination submodule is configured to determine a target working frequency corresponding to the configuration information from a plurality of working frequencies based on a level mapping relationship, wherein the level mapping relationship represents a corresponding relationship between a state level and a working frequency of the electronic device.
[0280] According to an embodiment of the present application, the level mapping relationship is determined by the following module operation.
[0281] The threshold obtaining unit is configured to obtain a frequency threshold of the electronic device from a register of the electronic device, wherein the frequency threshold comprises a maximum frequency value and a minimum frequency value.
[0282] The grade mapping unit is configured to determine a working frequency corresponding to each state grade based on the frequency threshold and a number of state grades of the electronic device, and generate a grade mapping relationship.
[0283] According to an embodiment of the present application, the grade mapping unit comprises a division subunit and a fine-tuning subunit.
[0284] The division subunit is configured to determine an initial working frequency corresponding to each state grade from the frequency threshold in a division manner.
[0285] The fine-tuning subunit is configured to fine-tune the initial working frequency in a case where the initial working frequency is a decimal number, and determine a working frequency corresponding to the state grade, so that the grade mapping relationship is in a quasi-linear distribution.
[0286] According to an embodiment of the present application, the control device of the electronic device further comprises a configuration information writing module.
[0287] The configuration information writing module is configured to write configuration information into a target register configured by the electronic device.
[0288] According to an embodiment of the present application, the control device of the electronic device further comprises a manual modification module.
[0289] The manual modification module is configured to manually write a state identifier representing a performance state grade into the target register configured by the electronic device after starting an operating system of the electronic device.
[0290] The configuration information displayed on the first configuration interface is different from the state identifier.
[0291] According to an embodiment of the present application, the target register comprises a first register and a second register, a target state grade stored in the first register is used to control running of a thread executed by the electronic device, and a target state grade stored in the second register is used to control running of a process executed by the electronic device.
[0292] According to an embodiment of the present application, the configuration information writing module comprises a first data packet generation sub-module, a verification sub-module, a feedback sub-module and a storage sub-module.
[0293] The first data packet generation sub-module is configured to generate a target data packet based on a target state grade of the electronic device and a verification sequence.
[0294] The verification sub-module is configured to send the target data packet to the electronic device, so that the electronic device decompresses the target data packet and verifies the target data packet by using the verification sequence.
[0295] a feedback submodule, configured to receive feedback information from the electronic device.
[0296] a storage submodule, configured to determine that the target state level has been stored in a target register of the electronic device in a case where the feedback information indicates that the target data packet passes the verification, so that the operating system controls the electronic device to operate based on the target state level stored in the target register.
[0297] According to an embodiment of the present application, the configuration information writing module further includes a second data packet generating submodule.
[0298] The second data packet generating submodule is configured to display the feedback information on the first configuration interface in a case where the feedback information indicates that the target data packet fails the verification, so as to re-generate and send the target data packet.
[0299] According to an embodiment of the present application, the control device of the electronic device further includes a reading module, a matching module and an exception determining module.
[0300] The reading module is configured to read a current state level stored in a target register of the electronic device according to a predetermined period.
[0301] The matching module is configured to determine that the target register is abnormal in a case where the current state level does not match the target state level.
[0302] The first exception determining module is configured to send configuration information to the electronic device in a case where the target register is abnormal, so that the electronic device updates data stored in the target register.
[0303] According to an embodiment of the present application, the target register includes a first register and a second register, the target state level stored in the first register is used to control the running of a thread executed by the electronic device, and the target state level stored in the second register is used to control the running of a process executed by the electronic device.
[0304] According to an embodiment of the present application, the control device of the electronic device further includes a second exception determining module.
[0305] The second exception determining module is configured to determine that the target register is abnormal in a case where any one of the current state level stored in the first register and the current state level stored in the second register does not match the target state level.
[0306] According to an embodiment of the present application, the control device of the electronic device further includes a task configuration module and a prompt module.
[0307] The task configuration module is configured to display, in response to a task configuration operation on a task control displayed in the first configuration interface, task information matched with the task configuration operation in the first configuration interface, wherein the task information is used to indicate a task performed by the electronic device.
[0308] The prompt module is configured to display, in the first configuration interface, prompt information indicating whether the configuration information is qualified.
[0309] The prompt information is determined based on a verification of a target operating frequency corresponding to the configuration information by frequency reference information determined by the task information.
[0310] According to an embodiment of the present application, the control device of the electronic device further comprises a health evaluation module, an evaluation determination module and an evaluation display module.
[0311] The health evaluation module is configured to display, in response to a trigger operation on a health evaluation control displayed in the first configuration interface, a plurality of evaluation items in the first configuration interface.
[0312] The evaluation determination module is configured to display, in response to receiving an evaluation instruction, a target evaluation item indicated by the evaluation instruction in the first configuration interface.
[0313] The evaluation display module is configured to display, in response to receiving an evaluation confirmation instruction on the target evaluation item, evaluation information in the first configuration interface.
[0314] The evaluation information represents an impact of the target operating frequency on hardware matched with the target evaluation item.
[0315] According to an embodiment of the present application, the control device of the electronic device further comprises an optimization control display module, an optimization determination module and an optimization display module.
[0316] The optimization control display module is configured to display, in response to a trigger operation on an optimization control displayed in the first configuration interface, a plurality of optimization items in the first configuration interface.
[0317] The optimization determination module is configured to display, in response to receiving an optimization instruction, a target optimization item indicated by the optimization instruction in the first configuration interface.
[0318] The optimization display module is configured to display, in response to receiving an optimization confirmation instruction on the target optimization item, optimization information matched with the target optimization item in the first configuration interface.
[0319] According to an embodiment of the present application, the control device of the electronic device further comprises a first reference information determination module.
[0320] The first reference information determination module is configured to determine the frequency reference information from the plurality of candidate frequency reference information based on the task information and a task mapping relationship, where the task mapping relationship represents a corresponding relationship between the task information and the candidate frequency reference information.
[0321] According to an embodiment of the present application, the control device of the electronic device further includes a second reference information determination module.
[0322] The second reference information determination module is configured to input a task feature of the task information and a graph feature of the heterogeneous graph into a first target network to obtain the frequency reference information.
[0323] The heterogeneous graph includes different types of first nodes, second nodes and third nodes, and different types of first edges and second edges, the first nodes represent tasks, the second nodes represent hardware, the third nodes represent state levels, the first edges are used to connect two nodes having a causal relationship, the second edges are used to connect two nodes having a correlation, and the first nodes, the second nodes and the third nodes each have a respective node attribute.
[0324] According to an embodiment of the present application, the control device of the electronic device further includes an evaluation information determination module.
[0325] The evaluation information determination module is configured to input an evaluation feature of the target evaluation item, a frequency feature of the target working frequency and a graph feature of the heterogeneous graph into a second target network to obtain the evaluation information.
[0326] According to an embodiment of the present application, the control device of the electronic device further includes an optimization information determination module.
[0327] The optimization information determination module is configured to input an optimization feature of the target optimization item, a frequency feature of the target working frequency and a graph feature of the heterogeneous graph into a third target network to obtain the optimization information.
[0328] According to an embodiment of the present application, the control device of the electronic device further includes a homogeneous representation module and a heterogeneous representation module and a fusion module.
[0329] The homogeneous representation module is configured to perform graph homogeneous representation on the heterogeneous graph to obtain a first graph feature.
[0330] The heterogeneous representation module is configured to perform graph heterogeneous representation on the heterogeneous graph to obtain a second graph feature.
[0331] The fusion module is configured to fuse the first graph feature and the second graph feature to obtain the graph feature.
[0332] According to an embodiment of the present application, the control device of the electronic device further includes an intention determination module and a network determination module.
[0333] an intent determination module, configured to determine intent information based on the task information.
[0334] a network determination module, configured to determine a first target network from the plurality of expert networks based on the intent information.
[0335] According to embodiments of the present application, any of the interface display module 910, the level configuration module 920, and the information determination module 930 can be combined in one module, or any of them can be split into multiple modules. Alternatively, at least part of the function of one or more of these modules can be combined with at least part of the function of other modules, and implemented in one module. According to embodiments of the present application, at least one of the interface display module 910, the level configuration module 920, and the information determination module 930 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system on package, an application specific integrated circuit (ASIC), or any other reasonable way of hardware or firmware that can be integrated or packaged with a circuit, or implemented in any one of software, hardware, and firmware or in a proper combination of any of them. Alternatively, at least one of the interface display module 910, the level configuration module 920, and the information determination module 930 can be at least partially implemented as a computer program module that can perform corresponding functions when the computer program module is run.
[0336] The present application also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments, or can exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, which, when executed, implement the control method according to the embodiments of the present application.
[0337] According to embodiments of the present application, the computer readable storage medium can be a non-volatile computer readable storage medium, which can include but is not limited to a portable computer diskette, a hard disk, a random access memory (RAM), a read only memory (ROM), an erasable programmable read only memory (EPROM or flash memory), a portable compact disc read only memory (CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination thereof. In the present application, the computer readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present application, the computer readable storage medium can include one or more memories of the above-described ROM and / or RAM and / or ROM and RAM in addition to one or more memories.
[0338] Embodiments of the present application also include a computer program product, which comprises a computer program containing program codes for executing the control method shown in the flow chart. When the computer program product is run in a computer system, the program codes are used to make the computer system implement the control method of the electronic device provided by the embodiments of the present application.
[0339] The above functions defined in the system / apparatus of the embodiments of the present application are performed when the computer program is executed by the processor. According to the embodiments of the present application, the system, apparatus, module, unit, etc. described above can be implemented by computer program modules.
[0340] According to the embodiments of the present application, the program codes for executing the computer program provided by the embodiments of the present application can be written in any combination of one or more programming languages, and specifically, these computer programs can be implemented by using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. The programming languages include, but are not limited to, such as Java, C++, python, “C” language, or similar programming languages. The program codes can be executed entirely on a user computing device, partially on a user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case involving a remote computing device, the remote computing device can be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, connected to the Internet through an Internet service provider).
[0341] The flowcharts and block diagrams in the drawings illustrate the possible implementation architectures, functions, and operations of the systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowcharts or block diagrams can represent a module, a program segment, or a part of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in different orders than those noted in the drawings. For example, two blocks that are shown in succession can actually be executed substantially in parallel, and sometimes they can be executed in reverse order, depending on the involved functions. It should also be noted that each block in the block diagrams or flowcharts, and the combination of blocks in the block diagrams or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.
[0342] Those skilled in the art can understand that the features described in various embodiments of the present application can be combined and / or integrated in various combinations, even if such combinations or integrations are not expressly described in the present application. In particular, the features described in various embodiments of the present application can be combined and / or integrated in various combinations without departing from the spirit and teachings of the present application. All such combinations and / or integrations are within the scope of the present application.
[0343] The embodiments of the present application are described above. However, these embodiments are merely for illustrative purposes, and are not intended to limit the scope of the present application. Although each embodiment is described above separately, this does not mean that the measures in various embodiments cannot be used advantageously in combination. Various alternatives and modifications can be made to the embodiments of the present application without departing from the scope of the present application, and such alternatives and modifications are intended to fall within the scope of the present application.
Claims
1. A control method for an electronic device, characterized in that, The control method includes: The first configuration interface is displayed, wherein the first configuration interface displays configuration controls, the configuration controls are used to adjust the target operating frequency of the electronic device, the target operating frequency indicating the highest operating frequency that the electronic device can support; In response to a status level configuration operation on the configuration control, configuration information matching the status level configuration operation is displayed on the first configuration interface, wherein the configuration information represents a target status level of the electronic device's performance state, and a mapping relationship exists between the target status level and the target operating frequency; and In response to receiving a confirmation instruction for the configuration information, a target operating frequency of the electronic device corresponding to the configuration information is determined so that during the operation of the electronic device, the performance status level of the electronic device is determined according to the current load of the electronic device, and the operating frequency of the electronic device is adjusted according to the status level and the level mapping relationship, while controlling the operating frequency of the electronic device to not exceed the target operating frequency, wherein the level mapping relationship represents the correspondence between the status level and the operating frequency of the electronic device; The configuration information is stored in a target register; the target register includes a first register and a second register, wherein the target status level stored in the first register is used to control the execution of threads executed by the electronic device; and the target status level stored in the second register is used to control the execution of processes executed by the electronic device. The control method further includes: If either the current status level stored in the first register or the current status level stored in the second register does not match the target status level, the target register is determined to be abnormal.
2. The control method according to claim 1, characterized in that, The first configuration interface is displayed, including: The configuration control is displayed in the first configuration interface using at least one of the following display formats: Slider, list, drop-down menu, input box, label, scrolling, and circular pointer styles.
3. The control method according to claim 2, characterized in that, The configuration controls are displayed in a slider format on the first configuration interface, including: The configuration control displays a track-like component and a selector that can slide on the track-like component. The track-like component is provided with multiple marker points, and multiple identifiers corresponding to the multiple marker points are displayed on the first configuration interface. The multiple identifiers represent different state levels.
4. The control method according to claim 3, characterized in that, The step of displaying configuration information matching the status level configuration operation on the first configuration interface in response to the status level configuration operation includes: In response to controlling the sliding operation of the selector on the track assembly, a target marker point specified by the selector on the track assembly is determined; and Based on the motion trajectory of the selector, the color of a portion of the track-type component is updated, and the identifier corresponding to the target marker point is displayed in a pop-up window as the configuration information.
5. The control method according to claim 3, characterized in that, The track-style component that displays the configuration control includes: Multiple marker points are displayed on the track-type component, matching the number of status levels of the electronic device; or Update the display state of the adjustable area on the track component to represent the state in which the selector can slide, wherein the adjustable area includes the area of multiple marker points that match the number of state levels; The number of status levels of the electronic device is determined based on the device attributes of the electronic device.
6. The control method according to claim 5, characterized in that, The control method further includes: The number of initial state levels that the electronic device can support is determined based on the device attributes of the electronic device; If the number of initial state levels of the electronic device is less than or equal to the predetermined number of state levels, the number of initial state levels shall be used as the number of state levels; and If the number of initial state levels of the electronic device is greater than the predetermined number of state levels, the predetermined number of state levels shall be used as the number of state levels.
7. The control method according to claim 1, characterized in that, The control method further includes: In response to a configuration operation for the state level of the configuration control, determine whether the configuration control is in an active state; and In response to the configuration control being inactive, the first configuration interface is refreshed to display the configuration control indicating that it is inactive.
8. The control method according to claim 7, characterized in that, The control method further includes: On the second configuration interface, adjust the parameter item of the activation control until the parameter item indicates that the configuration control is in an active state; and Refresh the first configuration interface to display the configuration control that indicates it is in an active state.
9. The control method according to claim 8, characterized in that, The activation control includes a first activation control and a second activation control, wherein the first activation control is used to activate the frequency dynamic adjustment function of the electronic device, and the second activation control is used to activate the frequency general adjustment function of the electronic device. The step of adjusting the parameter item of the activation control on the second configuration interface so that the parameter item indicates that the configuration control is in an active state includes: On the second configuration interface, adjust the parameters of the first activation control to the available items; and On the second configuration interface, adjust the parameter item of the second activation control to a non-use item.
10. The control method according to claim 7, characterized in that, The control method further includes: In response to an option configuration operation on the option configuration control displayed on the first configuration interface, an option configuration command for activating the configuration control is generated; and Send the option configuration command to the control system to activate the configuration control through the control system.
11. The control method according to claim 8 or 10, characterized in that, The control method further includes: Restart the electronic device to activate the configuration control.
12. The control method according to claim 1, characterized in that, The control method further includes: In response to the confirmation control on the first configuration interface being triggered, it is determined that a confirmation instruction for the configuration information has been received, wherein the confirmation control is used to indicate that the configuration has been completed; or In response to a waiting time exceeding a preset time, it is determined that a confirmation instruction for the configuration information has been received, wherein the waiting time includes the time between the current time and the operation time of the status level configuration operation.
13. The control method according to any one of claims 1 to 10, characterized in that, The control method further includes: The configuration information is written into the target register configured in the electronic device.
14. The control method according to any one of claims 1 to 10, characterized in that, The control method further includes: After the operating system of the electronic device is started, a status flag representing the performance status level is manually written into the target register configured in the electronic device. The configuration information displayed on the first configuration interface is different from the status identifier.
15. The control method according to claim 13, characterized in that, Writing the configuration information into the target register configured in the electronic device includes: Based on the target state level and verification sequence of the electronic device, a target data packet is generated; The target data packet is sent to the electronic device so that the electronic device can decompress the target data packet and verify the target data packet using the verification sequence; Receive feedback information from the electronic device; If the feedback information indicates that the target data packet has passed verification, it is determined that the target status level has been stored in the target register of the electronic device, so that the operating system controls the operation of the electronic device based on the target operating frequency that matches the target status level stored in the target register.
16. The control method according to claim 15, characterized in that, The step of writing the configuration information into the target register configured in the electronic device further includes: If the feedback information indicates that the target data packet verification has failed, the feedback information is displayed on the first configuration interface so that the target data packet can be regenerated and sent.
17. The control method according to any one of claims 1 to 10, characterized in that, The control method further includes: According to a predetermined cycle, read the current status level stored in the target register of the electronic device; If the current state level does not match the target state level, the target register is determined to be abnormal; and In the event of an anomaly in the target register, the configuration information is sent to the electronic device so that the electronic device can update the data stored in the target register.
18. The control method according to any one of claims 1 to 10, characterized in that, Determining the target operating frequency of the electronic device corresponding to the configuration information includes: Based on the hierarchical mapping relationship, the target operating frequency corresponding to the configuration information is determined from multiple operating frequencies.
19. The control method according to claim 18, characterized in that, The hierarchical mapping relationship is determined through the following operations: Obtain the frequency threshold of the electronic device from its registers, wherein the frequency threshold includes a maximum frequency value and a minimum frequency value; and Based on the frequency threshold and the number of state levels of the electronic device, the operating frequency corresponding to each state level is determined, and the state mapping relationship is generated.
20. The control method according to claim 19, characterized in that, The step of determining the operating frequency corresponding to each state level based on the frequency threshold and the number of state levels of the electronic device includes: The initial operating frequency corresponding to each state level is determined from the frequency thresholds according to the equal division method; When the initial operating frequency is a decimal, the initial operating frequency is fine-tuned to determine the operating frequency corresponding to the state level, so that the level mapping relationship is a near-linear distribution.
21. The control method according to any one of claims 1 to 10, characterized in that, The control method further includes: In response to a task configuration operation on a task control displayed in the first configuration interface, task information matching the task configuration operation is displayed in the first configuration interface, wherein the task information is used to indicate the task performed using the electronic device; The first configuration interface displays a prompt message indicating whether the configuration information is qualified; The prompt information is determined by verifying the target operating frequency corresponding to the configuration information based on frequency reference information, and the frequency reference information is determined through the task information.
22. The control method according to claim 21, characterized in that, The control method further includes: In response to a triggered operation on the health assessment control displayed in the first configuration interface, multiple assessment items are displayed in the first configuration interface; In response to receiving an evaluation instruction, the target evaluation item indicated by the evaluation instruction is displayed on the first configuration interface; and In response to receiving an evaluation confirmation instruction for the target evaluation item, evaluation information is displayed on the first configuration interface; The evaluation information characterizes the impact of the target operating frequency on hardware that matches the target evaluation item.
23. The control method according to claim 22, characterized in that, The control method further includes: In response to a trigger operation on the optimization controls displayed in the first configuration interface, multiple optimization items are displayed in the first configuration interface; In response to receiving an optimization instruction, the target optimization item indicated by the optimization instruction is displayed on the first configuration interface; and In response to receiving an optimization confirmation instruction for the target optimization item, optimization information matching the target optimization item is displayed on the first configuration interface.
24. The control method according to claim 21, characterized in that, The control method further includes: Based on the task information and the task mapping relationship, the frequency reference information is determined from multiple candidate frequency reference information, wherein the task mapping relationship represents the correspondence between the task information and the candidate frequency reference information.
25. The control method according to claim 23, characterized in that, The control method further includes: The task features of the task information and the spectral features of the heterogeneous graph are input into the first target network to obtain the frequency reference information; The heterogeneous graph includes different types of first nodes, second nodes, and third nodes, as well as different types of first edges and second edges. The first node represents a task, the second node represents hardware, and the third node represents a state level. The first edge is used to connect two nodes with a causal relationship, and the second edge is used to connect two nodes with a correlation. The first node, the second node, and the third node all have their own node attributes.
26. The control method according to claim 25, characterized in that, The control method further includes: The evaluation features of the target evaluation item, the frequency features of the target operating frequency, and the spectral features of the heterogeneous spectrum are input into the second target network to obtain the evaluation information.
27. The control method according to claim 26, characterized in that, The control method further includes: The optimization features of the target optimization term, the frequency features of the target operating frequency, and the spectral features of the heterogeneous spectrum are input into the third target network to obtain the optimization information.
28. The control method according to claim 27, characterized in that, The control method further includes: The heterogeneous spectra are subjected to isomorphic characterization to obtain the first spectra feature; The heterogeneous spectra are characterized to obtain second spectra features; and The first spectral feature and the second spectral feature are fused to obtain the spectral feature.
29. The control method according to claim 25, characterized in that, The control method further includes: Based on the task information, determine the intent information; and Based on the intent information, the first target network is determined from multiple expert networks.
30. A control device for an electronic device, characterized in that, The control device includes: The interface display module is used to display a first configuration interface, wherein the first configuration interface displays configuration controls, the configuration controls are used to adjust the target operating frequency of the electronic device, and the target operating frequency indicates the highest operating frequency that the electronic device can support; A level configuration module is configured to, in response to a status level configuration operation on the configuration control, display configuration information matching the status level configuration operation on the first configuration interface, wherein the configuration information represents a target status level of the electronic device's performance state, and a mapping relationship exists between the target status level and the target operating frequency; and An information determination module is used to, in response to receiving a confirmation instruction for the configuration information, determine the target operating frequency of the electronic device corresponding to the configuration information, so that during the operation of the electronic device, the performance state level of the electronic device is determined according to the current load of the electronic device, and the operating frequency of the electronic device is adjusted according to the state level and the level mapping relationship, while controlling the operating frequency of the electronic device to not exceed the target operating frequency, wherein the level mapping relationship represents the correspondence between the state level and the operating frequency of the electronic device; The configuration information is stored in a target register; the target register includes a first register and a second register, wherein the target status level stored in the first register is used to control the execution of threads executed by the electronic device; and the target status level stored in the second register is used to control the execution of processes executed by the electronic device. The control device further includes: The second anomaly determination module is used to determine that the target register is abnormal if either the current status level stored in the first register or the current status level stored in the second register does not match the target status level.
31. A server, comprising: One or more controllers; Memory, used to store one or more computer programs. The characteristic feature is that the one or more controllers execute the one or more computer programs to implement the steps of the control method according to any one of claims 1 to 29.
32. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When the computer program or instructions are executed by the processor, they implement the steps of the control method according to any one of claims 1 to 29.
33. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the control method according to any one of claims 1 to 29.
Citation Information
Patent Citations
Processor operation frequency control method and system
CN103455382A
Control method and electronic equipment
CN103677995A
Parameter setting method and device, terminal and storage medium
CN109271208A
Resource management method and device and electronic equipment
CN117149431A
System function execution method and device
CN120104200A