Central processing unit configuration method, configuration device, storage medium, electronic equipment and computer program product

Abstract

The application discloses a central processing unit configuration method and device, a storage medium, an electronic device and a computer program product, and relates to the technical field of parameter configuration. The method comprises the following steps: receiving a configuration trigger instruction of a central processing unit; in response to the configuration trigger instruction, reading target configuration information of the central processing unit from an external memory, wherein the target configuration information is within a preset allowed configuration range and is stored in the external memory; and configuring the central processing unit according to the target configuration information. The method reads the target configuration information of the central processing unit from the external memory to configure the central processing unit under the condition that the configuration trigger instruction is received, so that different target application scenarios are met, and the matching degree of CPU configuration and application scenarios is improved. Therefore, the problem that the matching degree of CPU configuration and application scenarios of a server is low in the prior art can be solved, and the effect of realizing reasonable resource utilization without changing the CPU hardware is achieved.

Description

Technical Field

[0001] This application relates to the field of parameter configuration technology, and in particular to a method for configuring a central processing unit, a device for configuring a central processing unit, a computer-readable storage medium, an electronic device, and a computer program product. Background Technology

[0002] With the rise of AI (Artificial Intelligence) technology and cloud services, the requirements for servers are becoming increasingly demanding.

[0003] In related technologies, during the production process, each server's CPU (Central Processing Unit) parameters are configured according to the hardware assembly. During the application process, technicians select the appropriate server based on the application scenario's requirements. However, due to the limitations of server types, the matching degree with the application scenario's needs is low. Users often choose servers with CPU configurations exceeding the application requirements, leading to increased power consumption, resource waste, and increased application costs. Summary of the Invention

[0004] This application provides a method for configuring a central processing unit, a configuration device, a storage medium, an electronic device, and a computer program product, in order to at least solve the problem in the related art that the CPU configuration of servers is not well matched with the application scenario, which easily leads to resource waste and increased application costs.

[0005] This application provides a method for configuring a central processing unit (CPU), comprising the following steps: receiving a configuration trigger instruction for the CPU; in response to the configuration trigger instruction, reading target configuration information of the CPU from an external memory, wherein the target configuration information is within a preset allowed configuration range and is stored in the external memory; and configuring the CPU according to the target configuration information.

[0006] This application also provides a central processing unit (CPU) configuration device, comprising: a receiving module for receiving a CPU configuration trigger instruction; an acquisition module for reading target configuration information of the CPU from an external memory in response to the configuration trigger instruction, wherein the target configuration information is within a preset allowed configuration range and is stored in the external memory; and a configuration module for configuring the CPU according to the target configuration information.

[0007] This application also provides a computer-readable storage medium storing a configuration program for a central processing unit (CPU), which, when executed by a processor, implements the aforementioned CPU configuration method.

[0008] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for implementing the configuration method of any of the above-described central processing units when executing the computer program.

[0009] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described central processing unit configuration methods.

[0010] By means of this application, when a configuration trigger instruction is received, the target configuration information of the central processing unit is read from the external memory to configure the parameters of the central processing unit in order to meet different application scenarios, thereby improving the matching between the configuration of the central processing unit and the needs of the application scenarios. Therefore, the problem of low matching degree between the CPU configuration of the server and the application scenario in related technologies can be solved, and the effect of rational resource utilization, power consumption and application cost reduction can be achieved without changing the CPU hardware. Attached Figure Description

[0011] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart illustrating a central processing unit configuration method provided in an embodiment of this application;

[0013] Figure 2 A schematic diagram of the system architecture provided for a specific embodiment of this application;

[0014] Figure 3 A flowchart illustrating a central processing unit configuration method provided in a specific embodiment of this application;

[0015] Figure 4 A connection diagram of the configuration device for the central processing unit provided in the embodiments of this application;

[0016] Figure 5 This is a block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0018] It should be noted that, in the description of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0019] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0020] With the rise of AI technology and cloud services, the use of servers is increasing daily. Among these issues, server power consumption is a critical problem that urgently needs to be addressed. It is important in many ways, and will be analyzed from the following aspects:

[0021] (1) Operating costs: Power consumption directly determines the power consumption of the server during operation. Data centers usually have a large number of servers, and power costs are an important part of their operating costs. The higher the power consumption of the server, the more electricity costs need to be paid. High power consumption servers usually require a more powerful heat dissipation system to ensure their stable operation, which will increase the procurement and installation costs of hardware.

[0022] (2) Performance and Stability: Power consumption is closely related to server performance. To a certain extent, improving server performance often requires increasing power consumption, but if the power consumption is too high, it may cause the server to overheat, thereby leading to performance degradation. Excessive power consumption will keep the server hardware in a high-temperature environment for a long time, accelerating hardware aging and damage, and reducing the server's lifespan and stability. For example, high temperature can cause the metal interconnect structure of electronic components to migrate, leading to short circuits or open circuits, increasing the probability of server failure.

[0023] (3) Business Expansion and Planning: Servers with lower power consumption generate less heat, allowing for denser server deployment in data centers with limited space, thus improving space utilization. This allows some space-constrained data centers to expand their business scale and increase the number of servers deployed to meet business growth needs without incurring excessive site costs.

[0024] (4) Power Capacity Planning: Lower server power consumption means relatively lower capacity requirements for the power supply system during data center construction and operation. This can reduce investment and upgrade costs for power infrastructure and alleviate pressure on power supply. Reasonably assessing server power consumption during data center planning helps to accurately plan power capacity and avoid limiting business development due to insufficient power supply.

[0025] (5) Environment and sustainability: With the rapid development of information technology, the number of servers is constantly increasing, and their energy consumption is also rising. Reducing server power consumption can improve the efficiency of energy resource utilization.

[0026] Therefore, it is particularly important to find a way to meet the needs of server operations while minimizing power consumption.

[0027] To address at least one of the aforementioned technical problems, embodiments of this application propose a configuration method for a Central Processing Unit (CPU). This method adjusts the CPU configuration without altering the CPU entity, thereby optimizing CPU power consumption and reducing application costs while meeting business requirements. The method is described in detail below, following the execution flow of the CPU configuration method.

[0028] Figure 1 A flowchart illustrating a central processing unit configuration method provided in an embodiment of this application.

[0029] like Figure 1 As shown, the configuration method of the central processing unit in this application embodiment includes the following steps:

[0030] S1 receives the configuration trigger instruction from the central processing unit;

[0031] S2, in response to the configuration trigger instruction, reads the target configuration information of the central processing unit from the external memory, wherein the target configuration information is within the preset allowed configuration range and is stored in the external memory;

[0032] S3 configures the central processing unit based on the target configuration information.

[0033] Specifically, the Central Processing Unit (CPU) is the core of a computer's computation and control system. It is primarily responsible for interpreting and executing computer instructions, processing data, and controlling the operation of other hardware devices. The CPU's configuration trigger instructions can be triggered upon power-on or by user-sent configuration commands, among others; there are no specific limitations.

[0034] External memory is a storage unit that stores the received target configuration information. For example, combined with... Figure 2As shown, after the BMC (Baseboard Management Controller) receives the target configuration information, it compares the target configuration information with the preset allowed configuration range. If the configuration data of the target configuration information is within the preset allowed configuration range, the target configuration information is sent to external memory for storage, to be retrieved when a configuration trigger command is received subsequently. The preset allowed configuration range can be set according to the hardware parameters of the central processing unit to ensure that the central processing unit can be used normally after configuration. The external memory can be Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), etc., and can be defined according to actual needs.

[0035] Upon receiving a configuration trigger command, this embodiment retrieves target configuration information from external memory and sends it to the central processing unit (CPU). The CPU can then configure parameters based on this information, enabling customized CPU configuration according to customer needs. This achieves reduced power consumption and application costs while meeting application requirements. Furthermore, storing the target configuration information received by the BMC in external memory further enhances data stability and security.

[0036] In one embodiment of this application, the target configuration information includes target power and / or target number of cores.

[0037] Specifically, the power consumption and number of cores of a central processing unit (CPU) are two closely related concepts that jointly determine the CPU's performance and power consumption. CPU power consumption typically refers to its Thermal Design Power (TDP). TDP is the power consumption of a CPU under standard operating conditions at maximum load, usually measured in watts (W). CPU cores refer to the physical processing units within the CPU. Each core can execute tasks independently. Multi-core CPUs have multiple cores, which can process multiple tasks in parallel, thereby improving overall processing power. The number of cores directly affects the CPU's multitasking capability. Multi-core CPUs typically have 4, 6, 8, or even more cores, enabling them to handle complex tasks and multi-threaded applications more efficiently. The number of cores is also a significant factor affecting CPU power consumption; more cores mean more processing units working simultaneously, leading to higher power consumption.

[0038] During the configuration of the central processing unit (CPU), the CPU power consumption can be configured separately, in which case the target configuration information may only include the target power; the number of CPU cores can also be configured separately, in which case the target configuration information may only include the target number of cores; or both CPU power consumption and the number of CPU cores can be configured simultaneously, in which case the target configuration information may include both the target power and the target number of cores, to meet the needs of different application scenarios.

[0039] When the target configuration information includes target power, the target power can limit the total power limit of the CPU operation, or it can be matched to the operating power of each CPU core, thereby limiting the power limit of each CPU core. In multi-core CPUs, multiple processor cores are integrated onto a single chip, and each core is an independent processing unit capable of executing different tasks simultaneously. Therefore, the workload of each CPU core varies. Consequently, the target power can also be used to specifically limit the operating power of a particular CPU core. For example, the power limit of a CPU core with higher computational demands can be increased based on the application scenario, or the power limit of a CPU core with lower computational demands can be decreased based on the application scenario. Furthermore, power settings can be differentiated based on the relative position of each CPU core and the heat sink. That is, CPU cores closer to the heat sink (i.e., areas with better heat dissipation) can be given a higher power limit, while CPU cores farther away (i.e., areas with poorer heat dissipation) can be given a lower power limit to prevent localized overheating.

[0040] When the target configuration information includes the target number of cores, the central processing unit can determine the number of CPU cores in operation based on the target number of cores, thereby controlling the CPU cores and planning reasonable application paths and function implementation.

[0041] Therefore, this embodiment can flexibly set the target power and / or target number of cores based on application requirements, so as to match the application scenario without changing the CPU entity, improve the rationality of resource utilization, and reduce the CPU's operating power consumption.

[0042] In one embodiment of this application, the external memory is a general-purpose flash memory storage area of ​​a programmable logic device.

[0043] Specifically, a programmable logic device (PLD) is a general-purpose integrated circuit whose logic function is defined by user programming. It is suitable for the design and implementation of various digital systems, including programmable array logic (PAL), complex programmable logic device (CPLD), and field-programmable gate array (FPGA).

[0044] by Figure 2 For example, the target configuration information is received through the BMC. To prevent this critical setting from failing due to BMC malfunction during operation, the target configuration information is no longer transmitted to the BIOS (Basic Input Output System) every time via the BMC. Instead, the CPLD (Complex Programmable Logic Device) transmits the configuration information to the BIOS. That is, the BMC sends the target configuration information and stores it in the CPLD's UFM (Universal Flash Storage) area. The BMC, acting as the server's management controller, can manage and control the server, including power consumption management.

[0045] Since the values ​​in the UFM region of the CPLD do not disappear or change under AC (Alternating Current), DC (Direct Current), and firmware upgrades, the data is very stable and not lost, ensuring that the target configuration information can be successfully retrieved when a configuration trigger command is received.

[0046] In one embodiment of this application, before receiving the configuration trigger instruction from the central processing unit, the method further includes: obtaining initial configuration information and target configuration information of the central processing unit; and storing the target configuration information to an external memory if the target configuration information is different from the initial configuration information and the target configuration information is within a preset allowed configuration range.

[0047] Specifically, the initial configuration information of the central processing unit (CPU) can be either general configuration information defined based on the CPU's production line or custom-defined factory-defined general configuration information. The preset allowed configuration range is the range of configurable parameters determined based on the CPU's hardware configuration.

[0048] by Figure 2For example, each time the BIOS starts up, it sends the number of CPU cores currently running and the power consumption of the CPU to the BMC, which is the initial configuration information, as well as the range of the number of cores and power consumption that the CPU can be set, which is the preset allowed configuration range.

[0049] During engineering shipment, the package setup tool is used to set the CPU power consumption and number of CPU cores specified by the customer for the package to the BMC, i.e., the target configuration information. The BMC then compares the received target configuration information with the initial configuration information. If the target configuration information is the same as the initial configuration information, it can be ignored to avoid repeating the configuration process. If the target configuration information is different from the initial configuration information, it is further compared with a preset allowed configuration range. If the target configuration information is within the preset allowed configuration range, the CPU hardware configuration is considered suitable for the target configuration information, and the target configuration information is sent to the CPLD's UFM area for storage, so that it can be retrieved when a configuration trigger command is received later. If the target configuration information is not within the preset allowed configuration range, the CPU hardware configuration is considered unable to meet the customer's customized requirements, an alarm is issued, and the target configuration information is not sent to the CPLD's UFM area.

[0050] When receiving target configuration information, this embodiment filters the target configuration information using the initial configuration information of the central processing unit and the preset allowed configuration range. On the one hand, it can avoid repeated configuration, and on the other hand, it can ensure that the hardware architecture of the central processing unit is compatible with the target configuration information, thereby improving the success rate of subsequent configuration and the actual application effect of the central processing unit after configuration.

[0051] Furthermore, when the target configuration information is the same as the initial configuration information, a synchronous reminder can be issued to notify the technicians that the configuration has been completed, thus avoiding repetitive operations by the technicians.

[0052] In one embodiment of this application, the configuration method of the central processing unit further includes: displaying a preset allowed configuration range and initial configuration information in response to a viewing instruction from the central processing unit.

[0053] Specifically, the viewing command can be received through the interactive screen. Thus, before the technicians input the target configuration information, they can view the preset allowed configuration range and initial configuration information of the central processing unit in advance through the display screen. This allows them to input the target configuration information based on the preset allowed configuration range and initial configuration information, thereby speeding up the input process of the target configuration information that meets the configuration operation requirements and accelerating the configuration progress.

[0054] For example, technicians can review the preset allowed configuration range and initial configuration information. If the customer-customized target configuration information is the same as the initial configuration information, no further input of the target configuration information is required, and a "configured" button can be triggered to mark the current CPU as configured. If one aspect of the customer-customized target configuration information is the same as the initial configuration information, such as the number of CPU cores, only the target power can be entered as the target configuration information, thus speeding up the configuration process. Furthermore, if the target configuration information differs from the initial configuration information, the data can be pre-adjusted by referring to the preset allowed configuration range. For instance, if the customer-customized target configuration information is outside the preset allowed configuration range, no input of the target configuration information is required. In this case, other servers can be selected based on the user-customized target configuration information to choose a CPU that supports the target configuration information, enabling autonomous configuration. Alternatively, other adjustment strategies can be sought to adjust the target configuration information to the preset allowed configuration range while meeting the needs of the customized application scenario, thereby avoiding the input of invalid target configuration information and data processing.

[0055] In one embodiment of this application, when the target configuration information is different from the initial configuration information and the target configuration information is within a preset allowed configuration range, the method further includes: sending and storing the target configuration information to a backup storage device, so as to call the target configuration information stored in the backup storage device when a configuration data call instruction is received.

[0056] Specifically, the backup memory is used to back up the target configuration information sent to the external storage for subsequent data retrieval. The backup memory can be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), electrically erasable programmable read-only memory (EPROM), etc.

[0057] Continue with Figure 2For example, using EEPROM (Electrically Erasable Programmable Read-Only Memory) as backup storage ensures that data is not lost after power failure. After the BMC receives the target configuration information, it compares the target configuration information with the initial configuration information and the preset allowed configuration range. If it determines that the target configuration information is different from the initial configuration information and is within the allowed configuration range, it determines that parameter configuration operations for the central processing unit can be performed based on the target configuration information. At this time, the BMC stores the set target configuration information in EEPROM for backup to prevent the BMC from losing it when power fails. On the other hand, it sends the set target configuration information to the CPLD, which stores it in the UFM area for subsequent configuration of the central processing unit.

[0058] The configuration data retrieval instruction is used to retrieve target configuration information that meets configuration requirements. This instruction applies the target configuration information to tasks other than central processing unit (CPU) configuration, such as configuration data comparison and data viewing. Therefore, this embodiment sets the data retrieval path of the target configuration information and the path of the target configuration information configuring the CPU separately. That is, the data is used for applications other than CPU configuration through backup storage, and data reading and CPU configuration are performed through external storage. This avoids mutual interference between data application scenarios and improves the stability of the data retrieval and configuration process.

[0059] In this embodiment, after storing the target configuration information in the backup memory and the external memory, if a configuration data retrieval instruction is received, the target configuration information is retrieved from the backup memory; if a configuration trigger instruction is received, the target configuration information is read from the external memory. This improves the stability and security of data storage, distinguishes data application paths, enhances the application stability of the target configuration information, and ensures the stable implementation of the central processing unit's configuration process.

[0060] In one embodiment of this application, after configuring the central processing unit based on the target configuration information, the configuration method of the central processing unit further includes: obtaining the actual configuration information of the central processing unit and retrieving the target configuration information from the backup memory; when the actual configuration information is inconsistent with the target configuration information, generating a first alarm signal and alerting the user based on the first alarm signal.

[0061] Specifically, in combination Figure 2As shown, the actual configuration information can be obtained through the BIOS and sent to the BMC application. After receiving the data sent by the BIOS, the BMC compares it with the data in the EEPROM. If they match, it proves that the setting is successful and sends an SEL (System Event Log) log for recording. If the setting is unsuccessful, an SEL log is also recorded. At the same time, the system health light will be turned on and the fan speed will be increased to 80% to notify the maintenance and production line setup personnel that the current setting has failed and needs to be intercepted and analyzed.

[0062] In the aforementioned cases of configuration inconsistency, an alarm is triggered by illuminating the system health indicator and increasing the fan speed to 80%. Besides these alarm methods, alarms can also be differentiated based on discrepancies between the actual and target configuration information. The first alarm signal can be generated accordingly based on these discrepancies, allowing for different alarm methods to alert the user. For example, if the target configuration information includes target power and target number of cores, and the actual configuration information includes actual CPU power and actual number of CPU cores, and the comparison confirms that the target power and actual CPU power are the same, but the target number of cores differs, the first alarm signal generated is a CPU core configuration failure alarm signal. This can control the first warning light to illuminate, the first fault code to be displayed, and the fan speed to be increased to 80%. If the comparison confirms that the target number of cores and actual CPU cores are the same, but the target power differs, the first alarm signal generated is a CPU core configuration failure alarm signal. The U-power configuration failure alarm signal can control the second warning light to illuminate, the second fault code to be displayed, and the fan speed to be increased to 80%. If, after information comparison, it is confirmed that the target number of cores and the actual number of CPU cores, as well as the target power and the actual CPU power, are inconsistent, the first alarm signal generated at this time is the CPU core count and CPU power configuration failure alarm signal. This can control both the first alarm light and the second warning light to illuminate, the third fault code to be displayed, and the fan speed to be increased to 80%, thereby differentiating the alarm for technicians so that they can promptly find the configuration fault area and facilitate subsequent fault diagnosis and handling.

[0063] In addition, the acquisition of the above-mentioned actual configuration information can be confirmed according to the type of target configuration information. For example, if the target configuration information only includes the target power, then only the actual CPU power is acquired for subsequent information comparison and judgment; if the target configuration information only includes the target number of cores, then only the actual number of CPU cores is acquired for subsequent information comparison and judgment; if the target configuration information includes both the target power and the target number of cores, then both the actual CPU power and the actual number of CPU cores are acquired, thereby reducing the workload of data collection and data comparison and speeding up the work progress.

[0064] Furthermore, when the target configuration information only includes the target power or the target number of cores, the actual CPU power and the actual number of CPU cores can also be acquired synchronously. The actual signal of the unconfigured information type is compared with the initial configuration information, and the actual signal of the configured signal type is compared with the target configuration information to verify the final central processing unit configuration. Furthermore, based on the comparison results, corresponding alarm signals are generated to trigger alarm reminders. For example, when the target configuration information only includes the target power, the actual CPU power is compared with the target power, and the actual number of CPU cores is compared with the initial number of CPU cores. If both are consistent, the configuration is considered successful. If one or both are inconsistent, the configuration is considered to have failed, and a first alarm signal is generated to remind the user. For instance, if the actual CPU power is consistent with the target power but the actual number of CPU cores is inconsistent with the initial number of CPU cores, it is considered that the power configuration process has affected the number of CPU cores in the central processing unit, and the generated first alarm signal is a CPU core misconfiguration alarm. Based on the first alarm signal, corresponding warning lights and fault codes can be triggered to remind the user. If the actual CPU power is inconsistent with the target power but the actual number of CPU cores is consistent with the initial number of CPU cores, the power configuration is considered to have failed, and the generated first alarm signal is a CPU power configuration failure alarm signal. Based on the first alarm signal, a second warning light can be activated, a second fault code can be displayed, and the fan speed can be increased to 80%.

[0065] This embodiment can generate a first alarm signal when the actual configuration information is inconsistent with the target configuration information, and remind the user of configuration failure based on the first alarm signal so that the user can perform subsequent processing in a timely manner.

[0066] In one embodiment of this application, obtaining the actual configuration information of the central processing unit includes: obtaining the current configuration information of the central processing unit; and when the current configuration information of the central processing unit is different from the initial configuration information, using the current configuration information of the central processing unit as the actual configuration information of the central processing unit.

[0067] Specifically, in combination Figure 2 As shown, upon receiving the configuration trigger command after the next power-on, the CPLD reads the preset target configuration information from the UFM area. The target configuration information includes the target power consumption, which is transmitted to the CPU via the eSPI (Enhanced Serial Peripheral Interface) bus for power consumption setting.

[0068] Then, the current CPU power consumption of the central processing unit is monitored in real time. When it is determined that the current CPU power consumption is different from the initial CPU power consumption, the power consumption is considered to be effective and the power consumption configuration is completed. Then, the current CPU power consumption is used as the actual CPU power consumption, and the current number of CPU cores is used as the actual number of CPU cores. These are sent to the BMC for information comparison to determine whether the configuration is successful, thereby improving the configuration evaluation speed.

[0069] When the target configuration information includes target power consumption and target number of cores, the system can determine whether the configuration is complete based solely on whether the current CPU power consumption or the current number of CPU cores differs from the initial configuration. Alternatively, it can compare both the current CPU power consumption and the current number of CPU cores with the initial configuration to determine whether the configuration is complete, and then obtain the actual configuration information after the configuration is complete.

[0070] In addition, to ensure the configuration progress, the configuration period needs to be preset. During the configuration of the central processing unit based on the target configuration information, if the current configuration information obtained within the preset configuration period remains consistent with the initial configuration information, the configuration is considered to have failed, and an alarm is issued to the user. This is to avoid wasting time due to the central processing unit's configuration information remaining unchanged due to a fault, and to improve the rationality of configuration control.

[0071] In one embodiment of this application, after configuring the central processing unit according to the target configuration information, the method further includes: receiving a reconfiguration instruction for the central processing unit; and in response to the reconfiguration instruction, clearing the configuration information in the backup memory and the external memory.

[0072] Specifically, the configuration change command is a command to change the package settings received after the central processing unit has been configured according to the target configuration information. At this time, according to the configuration change command, the EEPROM area of ​​the motherboard and the UFM area of ​​the CPLD are cleared through the BMC, restoring everything to an unconfigured state for use by other packages. These other packages include target configuration information customized by the user.

[0073] Then, after receiving the target configuration information again, the target configuration information received again is compared with the initial configuration information and the preset allowed configuration range. The target configuration information that meets the requirements is stored in the EEPROM area on the one hand and in the UFM area of ​​the CPLD on the other hand, so that the configuration process can be executed when the configuration trigger command is received.

[0074] When this embodiment receives a configuration change instruction, it clears the configuration information in the backup storage and external storage so that it can be used by other packages.

[0075] In one embodiment of this application, the configuration method of the central processing unit further includes: generating a second alarm signal when the target configuration information is outside the preset allowed configuration range, and alerting the user based on the second alarm signal.

[0076] In other words, the preset allowed configuration range is the range of parameter configurations supported by the central processing unit (CPU), which can be set based on the CPU's hardware architecture. For example, during engineering shipment, the package setting tool is used to set the CPU power consumption specified by the customer for the package to the BMC, i.e., the target configuration information. When the user-customized target configuration information is within the preset allowed configuration range, the CPU configuration based on the target configuration information is allowed. At this time, the target configuration information is stored in external memory for subsequent configuration retrieval applications. When the user-customized target configuration information is outside the preset allowed configuration range, i.e., the set target power value is not a power consumption number supported by the preset allowed configuration range, a second alarm signal will be generated to indicate that the package setting has failed.

[0077] The second alarm signal can be differentiated and determined based on the relative relationship between the target configuration information and the preset allowed configuration range. For example, if the target configuration information includes target power and target number of cores, and the target power is within the preset allowed configuration range but the target number of cores is outside the preset allowed configuration range, the generated second alarm signal is a target number of cores setting failure alarm, which can trigger the corresponding first package setting failure reminder; if the target number of cores is within the preset allowed configuration range but the target power is outside the preset allowed configuration range, the generated second alarm signal is a target power setting failure alarm, which can trigger the corresponding second package setting failure reminder.

[0078] Furthermore, the second alarm signal can be further categorized and alerted based on the numerical difference between the target configuration information and the preset allowable configuration range. For example, when the target power differs significantly from the preset allowable configuration range, the second alarm signal can be at its highest level, such as increasing the flashing frequency of the warning light for the corresponding target power setting failure alarm and changing the warning code color to red. Based on this alarm alert, the user can determine that it is difficult to meet the preset allowable configuration range of the central processing unit by adjusting the data of the target configuration information, and it is necessary to select another central processing unit, thereby avoiding unnecessary subsequent configuration work. When the target power differs slightly from the preset allowable configuration range, the second alarm signal can be at a lower level, such as keeping the warning light for the corresponding target power setting failure alarm constantly lit and changing the warning code color to yellow. Based on this alarm alert, the user can determine that the preset allowable configuration range of the central processing unit can be met by fine-tuning the data of the target configuration information, and subsequent configuration adjustment work can be carried out based on this alarm alert.

[0079] This embodiment can use a second alarm signal to differentiate between different setup failure scenarios, so that users can accurately identify the root cause of the package setup failure based on the alarm type, and promptly handle the fault, thereby improving the setup progress.

[0080] In one embodiment of this application, the configuration method of the central processing unit further includes: clearing the target configuration information stored in the external memory in response to an initialization instruction; and restoring the central processing unit to the initial configuration information based on the cleared external memory.

[0081] Specifically, initialization refers to the process in computer science and software development of setting a system, variable, object, or other available component to its initial state or initial value.

[0082] Continue with Figure 2 For example, after configuring the central processing unit according to the target configuration information, if an initialization instruction is received, the target configuration information in the UFM area of ​​the CPLD is cleared according to the initialization instruction. This eliminates the need for customized configuration of the number of CPU cores and / or power consumption, restoring the central processing unit to the default value, i.e., the initial configuration information, thus simplifying the initialization operation steps.

[0083] As a specific embodiment of this application, the system architecture for executing the central processing unit configuration method is as follows: Figure 2 As shown, the configuration method of this central processing unit is as follows: Figure 3 As shown, it includes the following steps:

[0084] S101: After the BIOS starts, it sends the CPU's initial configuration information and preset allowed configuration range to the BMC.

[0085] The initial configuration information of the CPU includes the number of CPU cores currently running and the power consumption. The preset allowed configuration range of the CPU includes the number of cores and power consumption that the current CPU can support.

[0086] S102, during engineering shipment, the package setup tool is used to set the target configuration information specified by the customer for the package to the BMC. The target configuration information may include target power consumption and / or target number of cores.

[0087] S103, determine whether the target configuration information is different from the initial configuration information. If yes, proceed to step S104; otherwise, proceed to step S116.

[0088] S104. Determine whether the target configuration information is within the preset allowed range. If yes, proceed to step S105; otherwise, proceed to step S106.

[0089] S105, the BMC stores the target configuration information in the EEPROM for backup, and simultaneously sends the target configuration information to the CPLD, which stores it in the UFM area. Proceed to step S107.

[0090] In this step, to prevent this critical setting from failing due to BMC malfunction during operation, the setting information is no longer transmitted to the BIOS via the BMC each time. Instead, the CPLD transmits the setting information to the BIOS. The values ​​AC and DC in the UFM area, as well as the firmware updates for the upgraded CPLD, will not disappear or change, so the data is stable and not lost.

[0091] In addition, the BMC provides instructions to set and query the current number of CPU cores and power consumption data to the EEPROM for backup.

[0092] S106, generate a second alarm signal and send an alarm to the user based on the second alarm signal. This allows the user to check the target configuration information based on the second alarm signal.

[0093] S107, upon the next power-on, confirm that the configuration trigger command has been received.

[0094] S108, in response to the configuration trigger command, the CPLD reads the target configuration information from the UFM area.

[0095] S109 transmits the target configuration information to the CPU via the eSPI bus for the configuration to take effect.

[0096] The BIOS can synchronize the target configuration information to the setup option Package PL1 Power Limit and execute the Package RAPL limit Lock action to prevent configuration modifications to the central processing unit under the OS (Operating System).

[0097] S110, obtain the current configuration information of the central processing unit;

[0098] S111, determine whether the current configuration information is different from the initial configuration information. If yes, proceed to step S113; otherwise, proceed to step S112.

[0099] S112, determine whether the actual configuration time has reached the preset configuration time. If yes, proceed to step S117; otherwise, proceed to step S110.

[0100] S113 uses the current configuration information as the actual configuration information of the central processing unit.

[0101] S114, the BMC receives the actual configuration information and retrieves the target configuration information from the backup storage.

[0102] S115, determine whether the actual configuration information is consistent with the target configuration information. If yes, proceed to step S116; otherwise, proceed to step S117.

[0103] In one embodiment, after the AC operation, the ipmitool (Intelligent Platform Management Interface Tool) is used to check whether the BMC has recorded any abnormal alarms, including other configuration abnormalities in the package and RPAL (Robotic Process Automation) setting abnormal alarms. If the verification passes, the process ends; otherwise, the configuration information is checked to ensure it is normal.

[0104] S116, the BMC confirms that the central processing unit is configured successfully and sends a SEL log message for recording.

[0105] In addition, after successful configuration, upon receiving the initialization command, the CPLD UFM region can be cleared, thus eliminating the need for custom settings of the number of CPU cores and power consumption, and restoring them to their default values.

[0106] S117, the BMC determines that the central processing unit configuration has failed, records the SEL log, and simultaneously illuminates the system health indicator and increases the fan speed to 80% to alert the user.

[0107] In other words, after the BIOS starts up, it sends the current effective number of CPU cores and power consumption to the BMC. The BMC compares and confirms the data. If the data is inconsistent with the settings, it issues an alarm and increases the fan speed to inform the maintenance personnel that there is a configuration problem.

[0108] Therefore, this embodiment allows the number of CPU cores and power consumption to be set during engineering shipment without changing the CPU entity, so that the CPU does not need to be customized and replaced again when it is shipped for application, and it is convenient for modification and maintenance, which has objective economic significance.

[0109] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0110] In summary, the central processing unit (CPU) configuration method according to the embodiments of this application, upon receiving a CPU configuration trigger instruction, reads target configuration information of the CPU from external memory in response to the configuration trigger instruction. This target configuration information is stored in external memory and falls within a preset allowed configuration range. Then, the CPU is configured according to the target configuration information. Therefore, this method, upon receiving a configuration trigger instruction, reads the target configuration information of the CPU from external memory to configure the CPU parameters to meet different application scenarios, ensuring that the CPU configuration matches the application scenario. This solves the problem of low matching degree between server CPU configuration and application scenario in related technologies, achieving the effect of rational resource utilization and reduced power consumption and application costs without changing the CPU hardware.

[0111] Embodiments of this application also provide a configuration device for a central processing unit, such as... Figure 4 As shown, the configuration device of the central processing unit includes: a receiving module 10, an acquisition module 20, and a configuration module 30.

[0112] The receiving module 10 is used to receive the configuration trigger instruction of the central processing unit; the acquiring module 20 is used to read the target configuration information of the central processing unit from the external memory in response to the configuration trigger instruction, wherein the target configuration information is within the preset allowed configuration range and is stored in the external memory; the configuration module 30 is used to configure the central processing unit according to the target configuration information.

[0113] According to one embodiment of this application, the external memory is a general-purpose flash memory storage area of ​​a programmable logic device.

[0114] According to one embodiment of this application, before receiving the configuration trigger instruction from the central processing unit, the acquisition module 20 is further configured to: acquire the initial configuration information and the target configuration information of the central processing unit; and store the target configuration information in an external memory if the target configuration information is different from the initial configuration information and the target configuration information is within a preset allowed configuration range.

[0115] According to one embodiment of this application, the acquisition module 20 is further configured to: display the preset allowed configuration range and initial configuration information in response to the viewing instruction of the central processing unit.

[0116] According to one embodiment of this application, when the target configuration information is different from the initial configuration information and the target configuration information is within a preset allowed configuration range, the acquisition module 20 is further configured to: send and store the target configuration information to a backup storage device, so as to call the target configuration information stored in the backup storage device when a configuration data call instruction is received.

[0117] According to one embodiment of this application, after configuring the central processing unit based on the target configuration information, the acquisition module 20 is further configured to: acquire the actual configuration information of the central processing unit and retrieve the target configuration information from the backup memory; when the actual configuration information is inconsistent with the target configuration information, generate a first alarm signal and alert the user based on the first alarm signal.

[0118] According to one embodiment of this application, the acquisition module 20 acquires the actual configuration information of the central processing unit, specifically for: acquiring the current configuration information of the central processing unit; and when the current configuration information of the central processing unit is different from the initial configuration information, using the current configuration information of the central processing unit as the actual configuration information of the central processing unit.

[0119] According to one embodiment of this application, after configuring the central processing unit according to the target configuration information, the receiving module 10 is further configured to: receive a reconfiguration instruction for the central processing unit; the obtaining module 20 is further configured to clear the configuration information in the backup memory and the external memory in response to the reconfiguration instruction.

[0120] According to one embodiment of this application, the acquisition module 20 is further configured to: generate a second alarm signal when the target configuration information is outside the preset allowed configuration range, and alert the user based on the second alarm signal.

[0121] According to one embodiment of this application, the target configuration information includes target power and / or target number of cores.

[0122] According to one embodiment of this application, the acquisition module 20 is further configured to: clear the target configuration information stored in the external memory in response to an initialization instruction; and restore the central processing unit to the initial configuration information based on the cleared external memory.

[0123] For a description of the features in the embodiment corresponding to the configuration device of the central processing unit, please refer to the relevant description of the embodiment corresponding to the configuration method of the central processing unit, which will not be repeated here.

[0124] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above-described central processing unit configuration method embodiments when run.

[0125] like Figure 5 As shown, embodiments of this application also provide an electronic device 100, including a memory 110 and a processor 120. The memory 110 stores a computer program, and the processor 120 is configured to run the computer program to perform the steps in any of the above-described central processing unit configuration method embodiments.

[0126] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0127] Embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above-described central processing unit configuration method embodiments.

[0128] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above-described central processing unit configuration method embodiments.

[0129] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0130] The foregoing has provided a detailed description of a central processing unit configuration method, configuration device, storage medium, electronic device, and computer program product provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the embodiments above are merely for the purpose of helping to understand the method and core ideas of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A method for configuring a central processing unit, characterized in that, Applied to a baseboard management controller, the method includes the following steps: Receive configuration trigger commands from the central processing unit; In response to the configuration trigger command, the target configuration information of the central processing unit is read from the external memory, wherein the target configuration information is within a preset allowed configuration range and is stored in the external memory; Configure the central processing unit according to the target configuration information; Before receiving the configuration trigger instruction from the central processing unit, the following is also included: Obtain the initial configuration information and target configuration information of the central processing unit; When the target configuration information differs from the initial configuration information and the target configuration information is within a preset allowed configuration range, the target configuration information is stored in the external memory, and the target configuration information is sent and stored in the backup memory, so that the target configuration information stored in the backup memory can be called upon receiving a configuration data call instruction; the external memory is a general flash memory storage area of ​​a programmable logic device; After configuring the central processing unit based on the target configuration information, the process further includes: Obtain the actual configuration information of the central processing unit, and retrieve the target configuration information from the backup memory; When the actual configuration information is inconsistent with the target configuration information, logs are recorded and a first alarm signal is generated to alert the user based on the first alarm signal. The alarm notification to the user based on the first alarm signal includes: Based on the first alarm signal, the target warning light and the target fan speed are determined, so as to illuminate the target warning light and control the preset fan to run at the fan speed.

2. The configuration method for a central processing unit according to claim 1, characterized in that, Also includes: In response to the viewing command from the central processing unit, the preset allowed configuration range and the initial configuration information are displayed.

3. The central processing unit configuration method according to claim 1, characterized in that, The step of obtaining the actual configuration information of the central processing unit includes: Obtain the current configuration information of the central processing unit; When the current configuration information of the central processing unit differs from the initial configuration information, the current configuration information of the central processing unit shall be used as the actual configuration information of the central processing unit.

4. The method for configuring a central processing unit according to claim 1, characterized in that, After configuring the central processing unit according to the target configuration information, the process further includes: Receive the reconfiguration command from the central processing unit; In response to the reconfiguration command, the configuration information in the backup storage and the external storage is cleared.

5. The method for configuring a central processing unit according to claim 1, characterized in that, Also includes: When the target configuration information is outside the preset allowed configuration range, a second alarm signal is generated, and an alarm is sent to the user based on the second alarm signal.

6. The method for configuring a central processing unit according to claim 1, characterized in that, The target configuration information includes target power and / or target number of cores.

7. The method for configuring a central processing unit according to claim 1, characterized in that, Also includes: In response to the initialization command, the target configuration information stored in the external memory is cleared; The central processing unit is restored to the initial configuration information based on the cleared external memory.

8. A configuration device for a central processing unit, characterized in that, The device, applied to a substrate management controller, includes: The receiving module is used to receive configuration trigger commands from the central processing unit; The acquisition module is configured to read the target configuration information of the central processing unit from the external memory in response to the configuration trigger command, wherein the target configuration information is within a preset allowed configuration range and is stored in the external memory; A configuration module is used to configure the central processing unit according to the target configuration information; Before receiving the configuration trigger instruction from the central processing unit, the receiving module is further configured to: Obtain the initial configuration information and target configuration information of the central processing unit; When the target configuration information is different from the initial configuration information and the target configuration information is within a preset allowed configuration range, the target configuration information is stored in the external memory, and the target configuration information is sent and stored in the backup memory, so that when a configuration data call instruction is received, the target configuration information stored in the backup memory can be called. The external memory is a general-purpose flash memory storage area for programmable logic devices; After configuring the central processing unit based on the target configuration information, the configuration module is further configured to: Obtain the actual configuration information of the central processing unit, and retrieve the target configuration information from the backup memory; When the actual configuration information is inconsistent with the target configuration information, logs are recorded and a first alarm signal is generated to alert the user based on the first alarm signal. The configuration module sends an alarm to the user based on the first alarm signal, specifically for: Based on the first alarm signal, the target warning light and the target fan speed are determined, so as to illuminate the target warning light and control the preset fan to run at the fan speed.

9. A computer-readable storage medium, characterized in that, It stores a computer program, wherein the computer program, when executed by a processor, is the step of the configuration method of the central processing unit as described in any one of claims 1-7.

10. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for implementing the steps of the configuration method of a central processing unit as described in any one of claims 1-7 when executing the computer program.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the central processing unit configuration method as described in any one of claims 1-7.

Images