Defense control system and method, storage medium, electronic equipment and chip
By evaluating and controlling the power integrity defense risk of mobile phone system-level chip loads, the defense control signal is generated, and the problem of transient changes in power caused by sudden load changes is solved, and the safety performance and stability of the load are improved.
Patent Information
- Application Number
- CN202510399754.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-31
- Publication Date
- 2025-07-18
AI Technical Summary
In mobile phone system-level chips, load changes lead to transient changes in the power supply, causing logical timing violations, which in turn causes functional problems. The existing technology cannot respond to sudden changes in load power supply demand in a timely manner.
The defense judgment unit conducts power integrity defense risk assessment on load characteristics information and power fluctuation information, generates defense control signals, and controls the load through the defense control unit, including frequency regulation, energy consumption scheduling and power supply voltage regulation.
Active defense against load is achieved, power mutations caused by load mutations are avoided, the safety performance of load is improved, and functional problems are prevented.
Smart Images

Figure CN120335589A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of chip technology, and in particular, to a defense control system, method, storage medium, electronic device, and chip. Background Art
[0002] There are a large number of high-performance processing units in the load of a mobile system-on-a-chip (SOC), such as a central processing unit (CPU), a graphics processing unit (GPU), a neural processing unit (NPU), and so on.
[0003] Currently, during the actual operation of the load, a load mutation may occur. If the power supply cannot respond in time to the sudden change in power supply demand brought about by the load mutation, then the transient change of the power supply may cause a timing violation in the logic, thereby triggering a functional problem. Summary of the Invention
[0004] In view of this, the present disclosure provides a defense control system, method, storage medium, electronic device, and chip to solve the related technical problems.
[0005] In a first aspect, the present disclosure provides a defense control system, including: a defense judgment unit, a defense control unit, and a load, where the defense control unit is respectively connected to the defense judgment unit and the load;
[0006] The defense judgment unit is configured to perform a power integrity defense risk assessment on the load according to the load characteristic information and power supply fluctuation information corresponding to the load, and generate a defense control signal according to the assessment result;
[0007] The defense control unit is configured to perform defense control on the load based on the defense control signal.
[0008] Optionally, the defense judgment unit includes: an energy efficiency-aware scheduling module, a performance monitoring module, an on-chip power supply noise sensing module, and a defense control management module;
[0009] The energy efficiency-aware scheduling module, the performance monitoring module, and the on-chip power supply noise sensing module are respectively connected to the defense control management module;
[0010] The energy efficiency-aware scheduling module is configured to obtain the load behavior information in the load characteristic information;
[0011] The performance monitoring module is configured to obtain the load power consumption information in the load characteristic information;
[0012] The on-chip power noise sensing module is used to obtain power noise information and power fluctuation information to be corrected, determine the characteristics of the power noise based on the power noise information, correct the power fluctuation information to be corrected based on the characteristics of the power noise to obtain the power fluctuation information, and perform threshold judgment and behavior prediction on the power fluctuation situation of the load based on the power fluctuation information.
[0013] Optionally, the defense control management module is used to monitor the power fluctuation of the load based on the threshold judgment result and the behavior prediction result, generate a first defense control signal when a power drop is detected, and generate a second defense control signal when a power overshoot is detected;
[0014] The defense control management module is also used to predict the instantaneous power consumption change situation of the load based on the load behavior information and the load power consumption information, and generate a third defense control signal when an instantaneous power consumption mutation is predicted;
[0015] The defense control management module is also used to perform a correlation analysis on the behavior prediction result and the load power consumption information, predict the instantaneous power consumption change situation of the load based on the correlation analysis result, judge the power consumption mutation trend when an instantaneous power consumption mutation is predicted, generate the first defense control signal or the fourth defense control signal when it is determined that the power consumption mutation trend is a power consumption surge, and generate the second defense control signal or the third defense control signal when it is determined that the power consumption mutation trend is a power consumption plunge.
[0016] Optionally, the defense control unit includes: a frequency control module, an energy consumption scheduling control module, a power supply module, and a buffer module;
[0017] The frequency control module, the energy consumption scheduling control module, the power supply module, and the buffer module are respectively connected to the defense control management module and the load, wherein the power supply module is also connected to the buffer module;
[0018] The frequency control module is used to receive the first defense control signal and control the load to perform fast enable clock downscaling;
[0019] The energy consumption scheduling control module is used to receive the third defense control signal, trigger pipeline suppression, and control the tasks and threads included in the load.
[0020] Optionally, the power supply module is used to receive the second defense control signal and / or the fourth defense control signal, send a buffer control signal to the buffer module when the second defense control signal is received, and perform power supply voltage regulation control on the load when the fourth defense control is received;
[0021] The buffer module is used to complete the buffer chain voltage division switching when receiving the buffer control signal.
[0022] Optionally, the load includes: a voltage sensing module;
[0023] The voltage sensing module is connected to the on-chip power supply noise sensing module;
[0024] The voltage sensing module is used to monitor the voltage of the load to obtain the power supply fluctuation information to be corrected.
[0025] In a second aspect, the present disclosure provides a chip, including the system described in the first aspect.
[0026] In a third aspect, the present disclosure provides a defense control method, including:
[0027] Performing a power integrity defense risk assessment on the load according to the load characteristic information and power supply fluctuation information corresponding to the load, and generating a defense control signal according to the assessment result;
[0028] Performing defense control on the load based on the defense control signal.
[0029] Optionally, before performing the power integrity defense risk assessment on the load according to the load characteristic information and power supply fluctuation information corresponding to the load, the method further includes:
[0030] Obtaining the load characteristic information, power supply noise information, and power supply fluctuation information to be corrected, where the load characteristic information includes load behavior information and load power consumption information, and the power supply fluctuation information to be corrected is obtained by monitoring the load;
[0031] Determining the power supply noise characteristics based on the power supply noise information, and performing correction processing on the power supply fluctuation information to be corrected based on the power supply noise characteristics to obtain the power supply fluctuation information.
[0032] Optionally, the performing a power integrity defense risk assessment on the load according to the load characteristic information and power supply fluctuation information corresponding to the load, and generating a defense control signal according to the assessment result includes:
[0033] Performing threshold judgment and behavior prediction on the power supply fluctuation condition of the load based on the power supply fluctuation information, and monitoring the power supply fluctuation of the load according to the threshold judgment result and behavior prediction result;
[0034] Generating a first defense control signal when a power supply drop is detected, and generating a second defense control signal when a power supply overshoot is detected.
[0035] Optionally, the defense control of the load based on the defense control signal includes:
[0036] In the case of detecting a power supply drop, controlling the load to perform fast enable clock downscaling based on the first defense control signal;
[0037] In the case of detecting a power supply overshoot, completing the buffer chain voltage division switching based on the second defense control signal.
[0038] Optionally, the power integrity defense risk assessment of the load based on the load characteristic information and power supply fluctuation information corresponding to the load, and generating a defense control signal according to the assessment result, further includes:
[0039] Predicting the instantaneous power consumption change of the load based on the load behavior information and the load power consumption information, and generating a third defense control signal when it is predicted that there is an instantaneous power consumption mutation;
[0040] The defense control of the load based on the defense control signal further includes:
[0041] Triggering pipeline suppression based on the third defense control signal and controlling the tasks and threads included in the load.
[0042] Optionally, the power integrity defense risk assessment of the load based on the load characteristic information and power supply fluctuation information corresponding to the load, and generating a defense control signal according to the assessment result, further includes:
[0043] Performing a correlation analysis on the behavior prediction result and the load power consumption information, and predicting the instantaneous power consumption change of the load based on the correlation analysis result;
[0044] Judging the power consumption mutation trend when it is predicted that there is an instantaneous power consumption mutation, generating the first defense control signal or the fourth defense control signal when it is determined that the power consumption mutation trend is a power consumption surge, and generating the second defense control signal or the third defense control signal when it is determined that the power consumption mutation trend is a power consumption sudden decrease.
[0045] Optionally, the defense control of the load based on the defense control signal further includes:
[0046] In the case of determining that the power consumption mutation trend is a power consumption surge, controlling the load to perform fast enable clock downscaling based on the first defense control signal, or performing power supply voltage regulation control on the load based on the fourth defense control signal;
[0047] In the case where it is determined that the power consumption mutation trend is a sudden decrease in power consumption, complete the buffer chain voltage division switching based on the second defense control signal, or trigger pipeline suppression based on the third defense control signal and control the tasks and threads included in the load.
[0048] Fourthly, the present disclosure provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the defense control method described in the third aspect is implemented.
[0049] Fifthly, the present disclosure provides an electronic device including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor. The feature is that when the processor executes the computer program, the defense control method described in the third aspect is implemented.
[0050] With the above technical solutions, compared with the current existing technologies, the defense control system, method, storage medium, electronic device, and chip provided by the present disclosure perform a power integrity defense risk assessment on the load based on the load characteristic information and power fluctuation information corresponding to the load to generate a defense control signal, and then control the load based on the defense control signal. It can fit the real-time change of the load performance through the load characteristic information and power fluctuation information, realize the prediction of the load behavior and energy consumption demand, and can also avoid the defense delay caused by inaccurate information; performing a power integrity defense risk assessment on the load can predict the change of the load before the load mutation, and generate a defense control signal according to the predicted change, and then perform defense control on the load, so that the present disclosure can take active defense on the load, avoid the problem of further power mutation in the case of load mutation, and further avoid causing functional problems, and can also improve the safety performance of the load.
[0051] The above description is only an overview of the technical solutions of the present disclosure. In order to be able to understand the technical means of the present disclosure more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of the present disclosure more obvious and understandable, the specific embodiments of the present disclosure are specifically given below. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] The accompanying drawings here are incorporated into the specification and form a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure.
[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.
[0054] Figure 1 shows a schematic structural diagram of a defense control system provided by an embodiment of the present disclosure;
[0055] Figure 2 shows a schematic flow diagram of a defense control method provided by an embodiment of the present disclosure;
[0056] Figure 3 shows a schematic diagram of an example provided by an embodiment of the present disclosure;
[0057] Figure 1 in:
[0058] 1 - Defense judgment unit, 11 - Energy efficiency perception scheduling module, 12 - Performance monitoring module, 13 - On - chip power noise perception module, 14 - Defense control management module;
[0059] 2 - Defense control unit, 21 - Frequency control module, 22 - Energy consumption scheduling control module, 23 - Power supply module, 24 - Buffer module;
[0060] 3 - Load, 31 - Voltage perception module. Detailed implementation manners
[0061] In the description of the present disclosure, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present disclosure and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present disclosure.
[0062] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present disclosure, "a plurality" means two or more unless otherwise specifically defined.
[0063] In the present disclosure, unless otherwise clearly specified and defined, terms such as "install", "connect", "link", "fix", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present disclosure can be understood according to specific circumstances.
[0064] The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that, without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.
[0065] The following Figure 1 describes a defense control system according to some embodiments of the present disclosure.
[0066] A defense control system provided by the present disclosure, as Figure 1 shown, includes: a defense judgment unit 1, a defense control unit 2, and a load 3. The defense control unit 2 is respectively connected to the defense judgment unit 1 and the load 3. The defense judgment unit 1 is configured to perform a power integrity defense risk assessment on the load 3 according to the load characteristic information and power fluctuation information corresponding to the load 3, and generate a defense control signal according to the assessment result. The defense control unit 2 is configured to perform defense control on the load 3 based on the defense control signal.
[0067] In the embodiments of the present disclosure, the load may specifically be a load in a system-on-a-chip (SoC). Specifically, the load refers to the amount of resources consumed by each component or module inside the SoC when performing a specific task, especially electrical energy and computing power.
[0068] In some examples, the main components of the load may include: 1. Central Processing Unit (CPU) cores: Execute the main computing tasks, such as application logic, data processing, etc. Modern System-on-Chip (SoC) usually contains multiple CPU cores, which may include high-performance cores and low-power cores to adapt to different workload requirements. 2. Graphics Processing Unit (GPU): Specifically used to accelerate graphics rendering and complex mathematical operations, widely used in games, video decoding, and other multimedia applications. 3. Digital Signal Processor (DSP): Process real-time data streams such as audio, images, and videos, commonly used in fields such as communication and speech recognition. 4. Neural Network Processing Unit (NPU): Accelerate neural network inference and training in machine learning algorithms, especially suitable for AI-related applications. 5. Specialized hardware accelerators: Hardware modules designed for specific tasks, such as video encoders / decoders, security engines, etc., aiming to improve efficiency and reduce power consumption. 6. Memory subsystem: Includes caches, Random Access Memory (RAM), and related controllers, responsible for data storage and fast access, directly affecting the overall performance. 7. Peripheral interfaces: Connection modules such as USB, Wi-Fi, Bluetooth, etc., supporting communication with external devices. 8. Sensor fusion module: Integrate data from multiple sensors to provide more accurate environmental perception, commonly found in smart devices and Internet of Things applications.
[0069] For this embodiment, the defense judgment unit and the defense control unit can also be one or more unit modules in the SoC. Specifically, the defense judgment unit can perform a power integrity defense risk assessment on the load characteristic information and power fluctuation information of the load, and generate a defense control signal; correspondingly, the defense control unit can control the load based on the defense control signal.
[0070] As an alternative, the load characteristic information can be a set of data describing how a device or system consumes electrical energy, processes data, responds to requests, etc. under different working conditions. It not only covers energy consumption and power consumption, but also includes multiple dimensions such as performance, stability, and response time.
[0071] In some examples, the power fluctuation information of the load can be the situation of the electrical energy and power consumed by the load changing over time within a certain period. These fluctuations may be caused by the dynamic characteristics of the load itself, external environmental factors, or the transient response of the power supply system.
[0072] In some examples, Power Integrity (PI) defense risk assessment is a crucial step to ensure the stable and reliable operation of an electronic system in the face of various power-related threats. This assessment not only involves the analysis of the existing design but also includes the prediction of potential future problems and the formulation of preventive measures. Through comprehensive risk assessment, factors that may lead to power failures can be identified, and corresponding countermeasures can be taken to reduce these risks.
[0073] Compared with the current existing technologies, in this embodiment, based on the load characteristic information and power fluctuation information corresponding to the load, a power integrity defense risk assessment is performed on the load to generate a defense control signal, and then the load is controlled based on the defense control signal. The real-time change of the load performance can be fitted through the load characteristic information and power fluctuation information to realize the prediction of the load behavior and energy consumption demand, and the defense lag caused by inaccurate information can also be avoided; furthermore, performing a power integrity defense risk assessment on the load can predict the change of the load before the load mutation, and generate a defense control signal according to the predicted change, and then perform defense control on the load, so that this embodiment can take active defense against the load, avoid the problem of further power mutation in the case of load mutation, and thus avoid causing functional problems, and can also improve the safety performance of the load.
[0074] Optionally, the defense judgment unit includes: an energy efficiency perception scheduling module 11, a performance monitoring module 12, an on-chip power noise perception module 13, and a defense control management module 14; the energy efficiency perception scheduling module 11, the performance monitoring module 12, and the on-chip power noise perception module 13 are respectively connected to the defense control management module 14; the energy efficiency perception scheduling module 11 is used to obtain the load behavior information in the load characteristic information; the performance monitoring module 12 is used to obtain the load power consumption information in the load characteristic information; the on-chip power noise perception module 13 is used to obtain the power noise information and the power fluctuation information to be corrected, determine the power noise characteristics based on the power noise information, and perform correction processing on the power fluctuation information to be corrected based on the power noise characteristics to obtain the power fluctuation information, and perform threshold judgment and behavior prediction on the power fluctuation situation of the load based on the power fluctuation information.
[0075] In the embodiment of the present disclosure, Energy-Aware Scheduling (EAS) is an advanced task scheduling strategy that can optimize the usage efficiency of computing resources while minimizing energy consumption. It achieves the best balance between performance and energy efficiency by intelligently allocating tasks to different processing units and adjusting the execution manner of these tasks according to the real-time workload and system state.
[0076] In some examples, the energy efficiency aware scheduling module 11 may obtain load characteristic information, where the load characteristic information includes load behavior information and load power consumption information, and the load behavior information and load power consumption information are key data for evaluating the performance and energy efficiency of an electronic device or system under different working conditions.
[0077] Specifically, the load behavior information describes the behavioral characteristics of a device or system when performing tasks. Correspondingly, the load power consumption information focuses on the power consumption of the device under different load conditions.
[0078] As an alternative, during the operation of Load 3, the energy efficiency aware scheduling module 11 may analyze load behavior, task allocation, thread information, Performance Monitoring Unit (PMU) events, etc., and feed back the power supply requirements for program execution to the defense control and management module 14. It may also monitor and count the key signal flips that can characterize power consumption changes during the operation of Load 3, and send the statistical information to the defense control and management module 14.
[0079] Preferably, the performance monitoring module 12 can specifically detect related events such as the number of instruction executions of the processor, branch instruction executions, data buffer hits or misses, pipeline stall cycles, the number of integer and floating-point operation instructions executed, and so on.
[0080] For this embodiment, the on-die power noise awareness module 13 can monitor the power noise information of Load 3 and determine the power noise characteristics based on the power noise information. Specifically, the power noise characteristics may include noise type, noise intensity assessment, noise source location, and so on.
[0081] Furthermore, the on-die power noise awareness (ODNA) technology is a highly integrated solution designed to monitor and manage the power noise inside an integrated circuit (IC) in real time. The ODNA technology not only helps designers understand the behavior of the power network inside the chip, but also provides the ability to dynamically adjust and optimize power management to ensure the stability and performance of the system.
[0082] In the embodiment of the present disclosure, the on-die power noise awareness module 13 can also obtain the power supply fluctuation information to be corrected monitored by the voltage monitoring module, and perform correction processing on the power supply fluctuation information to be corrected based on the obtained noise characteristics to obtain the corrected power supply fluctuation information.
[0083] It should be noted that the power fluctuation information detected by the voltage monitoring module needs to be corrected based on the noise characteristics to ensure the accuracy and reliability of the monitoring data. This correction process typically involves identifying and quantifying the noise components, and then applying appropriate algorithms or techniques to eliminate or reduce the impact of these noises on the measurement results.
[0084] In some examples, the on-chip power noise sensing module 13 also needs to perform threshold judgment and behavior monitoring on the corrected power fluctuation information. Specifically, performing threshold judgment and behavior monitoring on the power fluctuation information is an important means to ensure the stability and reliability of the electronic system. By setting reasonable thresholds to detect abnormal situations and monitoring the power behavior in real time, problems that may cause system failures or performance degradation can be discovered and processed in a timely manner.
[0085] Optionally, the defense control management module 14 is used to monitor the power fluctuations of the load based on the threshold judgment result and the behavior prediction result, and generate a first defense control signal when a power drop is detected, and generate a second defense control signal when a power overshoot is detected; the defense control management module 14 is also used to predict the instantaneous power consumption change of the load 3 based on the load behavior information and the load power consumption information, and generate a third defense control signal when an instantaneous power consumption mutation is predicted; the defense control management module 14 is also used to perform a correlation analysis on the behavior prediction result and the load power consumption information, predict the instantaneous power consumption change of the load 3 based on the correlation analysis result, and judge the power consumption mutation trend when an instantaneous power consumption mutation is predicted. When it is determined that the power consumption mutation trend is a power consumption surge, a first defense control signal or a fourth defense control signal is generated, and when it is determined that the power consumption mutation trend is a power consumption sudden drop, a second defense control signal or a third defense control signal is generated.
[0086] In the embodiments of the present disclosure, power drop and power overshoot are two common abnormal phenomena in the power system, and they can have different degrees of impact on electronic devices. Among them, a power drop can be a process in which the supply voltage suddenly drops within a short period of time and then returns to normal. This phenomenon usually lasts from a few milliseconds to several seconds, but its amplitude may be sufficient to affect the normal operation of sensitive electronic devices. Correspondingly, a power overshoot refers to a phenomenon in which the supply voltage rises sharply within a short period of time and exceeds the normal range. It can also be short-lived, but it may also be a long-term state with a high voltage exceeding the rated voltage by 10%.
[0087] In some examples, the defense control management module 14 can monitor the power fluctuation situation based on the threshold judgment result and behavior prediction result of the power fluctuation situation, and determine whether there is a power drop or power overshoot. If a power drop is detected, a first defense control signal needs to be generated to control the load 3 through the first defense control signal. Here, the first defense control signal can be the defense control signal generated by the defense control management module 14 and sent to the frequency control module. Correspondingly, if a power overshoot is detected, a second defense control signal needs to be generated to control the load 3 through the second defense control signal. Here, the second defense control signal can be the defense control signal generated by the defense control management module 14 and sent to the power supply module.
[0088] For this embodiment, the Instantaneous Power Variation can be the rapid fluctuation of the power consumption of the electronic device in an extremely short time. Correspondingly, the defense control management module 14 can also predict the instantaneous power consumption change situation of the load 3 based on the load behavior information and load power consumption information, and generate a third defense control signal to control the load 3 through the third defense control signal when it is predicted that there is an instantaneous power consumption mutation (which can be an instantaneous power consumption surge or an instantaneous power consumption sudden decrease). Here, the third defense control signal can be the defense control signal generated by the defense control management module 14 and sent to the energy consumption scheduling control module.
[0089] In some examples, the defense control management module 14 can also predict the instantaneous power consumption change situation through the correlation analysis result between the behavior prediction result of the power fluctuation and the load power consumption information. If it is predicted that there is an instantaneous power consumption surge, the defense control management module 14 needs to generate a first defense control signal or a fourth defense control signal to control the load 3 through the first defense control signal or the fourth defense control signal. Here, the fourth defense control signal is generated by the defense control management module 14 and sent to the power supply module. Correspondingly, if it is predicted that there is an instantaneous power consumption sudden decrease, the defense control management module 14 needs to generate a second defense control signal or a third defense control signal to control the load 3 through the second defense control signal or the third defense control signal.
[0090] Optionally, the defense control unit 2 includes: a frequency control module 21, an energy consumption scheduling control module 22, a power supply module 23, and a buffer module 24; the frequency control module 21, the energy consumption scheduling control module 22, the power supply module 23, and the buffer module 24 are respectively connected to the defense control management module 14 and the load 3, where the power supply module 23 is further connected to the buffer module 24; the frequency control module 21 is configured to receive a first defense control signal and control the load 3 to perform rapid enable clock downscaling; the energy consumption scheduling control module 22 is configured to receive a third defense control signal, trigger pipeline suppression, and control the tasks and threads included in the load 3.
[0091] Optionally, the power supply module 23 is configured to receive a second defense control signal and / or a fourth defense control signal, and send a buffer control signal to the buffer module 24 when receiving the second defense control signal, and perform power supply voltage regulation control on the load 3 when receiving the fourth defense control signal; the buffer module 24 is configured to control the load 3 to perform rapid enable buffering when receiving the buffer control signal.
[0092] In the embodiment of the present disclosure, the frequency control module 21 can perform frequency control through a clock source (Clock Source, Clock Src). Specifically, the frequency control module 21 can generate the clock signal required during the operation of the load 3, and at the same time can receive the control of the defense control management module 14 to complete the frequency adjustment of the load.
[0093] Exemplarily, when a power supply drop is detected, the defense control management module 14 generates a first defense control signal and sends the signal to the frequency control module 21. After receiving the first defense control signal, the frequency control module 21 controls the load 3 to perform rapid enable clock downscaling through the clock source, where the downscaling amplitude can be in gears such as 10%, 20%, 30%, etc.
[0094] It should be noted that rapid enable clock downscaling (Rapid Clock Frequency Reduction) is a technology used to dynamically adjust the system operating frequency, especially in cases where the load is reduced or energy savings are required. This technology can quickly reduce the clock frequency of the processor or other hardware components to reduce power consumption and manage heat generation.
[0095] In some instances, when a power supply overshoot is detected, the defense control management module 14 generates a second defense control signal and sends the signal to the power supply module 23. After receiving the second defense control signal, the power supply module 23 sends a buffer control signal to the buffer module 24, and the buffer module 24 completes the buffer chain voltage division switching.
[0096] In the embodiments of the present application, the completion of the buffer chain voltage division switching can be achieved by controlling the switching load buffer chain and completing the buffer chain voltage division conversion.
[0097] Exemplarily, the power supply module 23 represents a power technology module, and its voltage regulation method has two control methods: 1. Controlling the on-chip power supply, such as on-chip low-dropout linear regulators (OCLDO), on-chip voltage drop converters, on-chip digital (DLDO), etc.; 2. Controlling external power supply devices, such as power management integrated circuits (Power Management IC, PMIC) and core buck converters. Correspondingly, the buffer module 24 is a general term for a class of load buffer control designs, which can limit the power supply fluctuation range and can send out control interaction signals externally to jointly complete the power supply fluctuation limitation with the IP; (for example: a long or short chain built by a register, a buffer (Buffer, BUF), an inverter (Inverter, INV), a combination chain of logic gates or a certain combination chain (cell), and configured to have capacitance or resistance characteristics), and its function is to receive the hardware control signal sent by the power supply module 23 and complete the buffering of the power supply mutation (overshoot or undershoot) within one load clock cycle.
[0098] For this embodiment, when it is predicted that there is an instantaneous power consumption mutation based on the load behavior information and the load power consumption information, the defense control management module 14 generates a third defense control signal and sends the signal to the energy consumption scheduling control module 22. After receiving the third defense control signal, the energy consumption scheduling control module 22 triggers hardware behaviors such as CPU execution pipeline suppression operations, and triggers the kernel software to perform task reallocation, thread rescheduling, etc. Among them, triggering software-level task reallocation and thread rescheduling by hardware behaviors such as CPU execution pipeline suppression operations is an efficient and low-latency method, which can significantly improve the system's response speed and resource utilization rate.
[0099] For the embodiment, when it is predicted that there is an instantaneous power consumption surge based on the correlation analysis result, the defense control management module 14 can generate a first defense control signal or a fourth defense control signal. If the first defense signal is generated, the signal is sent to the frequency control module 21. After receiving the first defense control signal, the frequency control module 21 quickly enables clock downscaling of the load 3 through clock source control. Among them, the downscaling amplitude can be in gears such as 10%, 20%, 30%, etc.; correspondingly, if the fourth defense control signal is generated, the signal is sent to the power supply module 23. After receiving the fourth defense control signal, the power supply module 23 performs power supply voltage regulation control on the load 3.
[0100] As an alternative, when it is predicted based on the correlation analysis result that there is a sudden drop in instantaneous power consumption, the defense control management module 14 may generate a second defense control signal or a third defense control signal. If the second defense control signal is generated, the signal is sent to the power supply module 23. After receiving the second defense control signal, the power supply module 23 sends a buffer control signal to the buffer module 24, and the buffer module 24 completes the buffer chain voltage division switching; correspondingly, if the third defense control signal is generated, the signal is sent to the energy consumption scheduling control module 22, and after receiving the third defense control signal, the energy consumption scheduling control module 22 triggers hardware behaviors such as CPU execution pipeline suppression operations, and triggers the kernel software to perform task reallocation, thread rescheduling, etc.
[0101] Optionally, the load 3 includes: a voltage sensing module 31; the voltage sensing module 31 is connected to the on-chip power supply noise sensing module 13; the voltage sensing module is used to monitor the voltage of the load 3 to obtain the power supply fluctuation information to be corrected.
[0102] In the embodiment of the present disclosure, the voltage sensing module 31 adopts a distributed architecture, is distributed at multiple positions within the load power supply domain, and performs real-time voltage monitoring to improve the detection accuracy of power supply noise, and sends the collected power supply fluctuation information to the on-chip power supply noise sensing module 13.
[0103] It should be noted that by adopting distributed load power supply network noise monitoring, fine-grained power supply fluctuation information of the load circuit is obtained, so as to avoid defense lag or over-defense caused by inaccurate information.
[0104] Compared with the current existing technologies, in this embodiment, a power integrity defense risk assessment is performed on the load based on the load characteristic information and power supply fluctuation information corresponding to the load to generate a defense control signal, and then the load is controlled based on the defense control signal. The real-time change of the load performance can be fitted through the load characteristic information and power supply fluctuation information to realize the prediction of the load behavior and energy consumption demand, and it can also avoid defense lag caused by inaccurate information; further, performing a power integrity defense risk assessment on the load can predict the change of the load before the load mutation, and generate a defense control signal according to the predicted change, and then perform defense control on the load, so that this embodiment can take active defense against the load, avoid the problem of further power mutation in the case of load mutation, and further avoid causing functional problems, and can also improve the safety performance of the load.
[0105] Furthermore, the embodiment of the present disclosure further provides a chip, including the system as Figure 1 shown. By using the chip provided by the embodiment of the present disclosure, functional problems caused by the load can be avoided, and the safety performance of the load can also be improved.
[0106] Furthermore, this embodiment provides a defense control method. As Figure 2 shown, the method includes:
[0107] Step 101: Perform a power integrity defense risk assessment on the load according to the load characteristic information and power fluctuation information corresponding to the load, and generate a defense control signal according to the assessment result.
[0108] Optionally, before step 101, the method of this embodiment further includes: obtaining load characteristic information, power noise information, and power fluctuation information to be corrected, determining the characteristics of the power noise based on the power noise information, and performing correction processing on the power fluctuation information to be corrected based on the characteristics of the power noise to obtain the power fluctuation information.
[0109] Among them, the load characteristic information includes load behavior information and load power consumption information, and the power fluctuation information to be corrected is obtained by monitoring the load.
[0110] In the embodiments of the present disclosure, the load may specifically be a load in a System on a Chip (SoC). Specifically, the load refers to the amount of resources consumed by each component or module inside the SoC when performing a specific task, especially electrical energy and computing power.
[0111] In some examples, as an optional manner, the load characteristic information (Load Characteristic Information) may be a data set describing how a device or system consumes electrical energy, processes data, responds to requests, etc. under different working conditions. It not only covers energy consumption and power consumption, but also includes multiple dimensions such as performance, stability, and response time.
[0112] Correspondingly, the power fluctuation information of the load (Power Fluctuation Information of Load) may be the situation of the electrical energy and power consumed by the load changing over time within a certain period. These fluctuations may be caused by the dynamic characteristics of the load itself, external environmental factors, or the transient response of the power supply system.
[0113] For this embodiment, the power integrity (PI) defense risk assessment is a key step to ensure the stable and reliable operation of an electronic system in the face of various power-related threats. This assessment not only involves the analysis of the existing design, but also includes the prediction of future potential problems and the formulation of preventive measures. Through a comprehensive risk assessment, factors that may lead to power failures can be identified, and corresponding countermeasures can be taken to reduce these risks.
[0114] Exemplarily, as Figure 3As shown, if the load is the load in mobile device A, it is necessary to obtain the load characteristic information, power noise information, and power fluctuation information to be corrected of the load in mobile device A, and determine the power fluctuation information of the load in mobile device A based on the power noise information and the power fluctuation information to be corrected.
[0115] Optionally, step 101 may specifically include: making a threshold judgment and behavior prediction on the power fluctuation condition of the load based on the power fluctuation information, and monitoring the power fluctuation of the load according to the threshold judgment result and behavior prediction result; generating a first defense control signal in the case of detecting a power sag, and generating a second defense control signal in the case of detecting a power overshoot.
[0116] In the embodiments of the present disclosure, power sag and power surge are two common abnormal phenomena in the power system, which can affect electronic devices to varying degrees. Among them, power sag can be a process in which the supply voltage suddenly drops within a short period of time and then returns to normal. This phenomenon usually lasts from a few milliseconds to several seconds, but its amplitude may be sufficient to affect the normal operation of sensitive electronic devices. Correspondingly, power overshoot refers to the phenomenon that the supply voltage rises sharply beyond the normal range within a short period of time. It can also be short-lived, but it may also be a high-voltage state that exists for a long time.
[0117] Exemplarily, the power fluctuation condition can be monitored based on the threshold judgment result and behavior prediction result of the power fluctuation condition to determine whether there is a power sag or power overshoot. If a power sag is detected, a first defense control signal needs to be generated to control the load through the first defense control signal; correspondingly, if a power overshoot is detected, a second defense control signal needs to be generated to control the load through the second defense control signal.
[0118] For example, after determining the power fluctuation information of the load in mobile device A, it is necessary to make a threshold judgment and behavior prediction on the power fluctuation condition of the load in mobile device A based on the power fluctuation information, and monitor the power fluctuation of the load according to the threshold judgment result and behavior prediction result of the load in mobile device A; generate a first defense control signal in the case of detecting a power sag of the load in mobile device A, and generate a second defense control signal in the case of detecting a power overshoot of the load in mobile device A.
[0119] Optionally, step 101 may specifically further include: predicting the instantaneous power consumption change condition of the load based on the load behavior information and load power consumption information, and generating a third defense control signal in the case of predicting an instantaneous power consumption mutation.
[0120] In the embodiments of the present disclosure, the Instantaneous Power Variation may be a rapid fluctuation of the power consumption of an electronic device within an extremely short period of time; correspondingly, the instantaneous power variation of the load can be predicted based on the load behavior information and the load power consumption information, and a third defense control signal is generated when it is predicted that there is an instantaneous power mutation (which may be an instantaneous power surge or an instantaneous power sudden decrease), and the load is controlled through the third defense control signal.
[0121] Exemplarily, it is also necessary to predict the instantaneous power variation of the load in the mobile device A based on the load behavior information and the load power consumption information, and generate a third defense control signal when it is predicted that there is an instantaneous power mutation in the load of the mobile device A.
[0122] Optionally, step 101 may specifically further include: performing a correlation analysis on the behavior prediction result and the load power consumption information, predicting the instantaneous power variation of the load based on the correlation analysis result; judging the power mutation trend when it is predicted that there is an instantaneous power mutation, generating a first defense control signal or a fourth defense control signal when it is determined that the power mutation trend is a power surge, and generating a second defense control signal or a third defense control signal when it is determined that the power mutation trend is a power sudden decrease.
[0123] For this embodiment, the instantaneous power variation can also be predicted through the correlation analysis result between the behavior prediction result of the power supply fluctuation and the load power consumption information. When it is predicted that there is an instantaneous power surge, a first defense control signal or a fourth defense control signal needs to be generated to control the load through the first defense control signal or the fourth defense control signal; correspondingly, when it is predicted that there is an instantaneous power sudden decrease, a second defense control signal or a third defense control signal needs to be generated to control the load through the second defense control signal or the third defense control signal.
[0124] Exemplarily, it is also necessary to predict the instantaneous power variation of the load of the mobile device A based on the correlation analysis result between the behavior prediction result of the power supply fluctuation and the load power consumption information, generate a first defense control signal or a fourth defense control signal when it is determined that the power mutation trend of the load of the mobile device A is a power surge, and generate a second defense control signal or a third defense control signal when it is determined that the power mutation trend of the load of the mobile device A is a power sudden decrease.
[0125] Step 102: Perform defense control on the load based on the defense control signal.
[0126] Optionally, step 102 may specifically include: when a power dip is detected, controlling the load to perform fast-enabled clock downscaling based on the first defense control signal; when a power overshoot is detected, controlling the load to perform fast-enabled buffering based on the second defense control signal.
[0127] In some examples, based on the example in step 101, when a power dip is detected in the load of mobile device A, the load of mobile device A can be controlled to perform fast-enabled clock downscaling through the clock source based on the first defense control signal, where the downscaling amplitude can be in gears such as 10%, 20%, 30%, etc.
[0128] As an optional method, when a power overshoot is detected in the load of mobile device A, the load of mobile device A can be controlled to perform fast-enabled buffering through the buffer chain based on the second defense control signal.
[0129] Optionally, step 102 may specifically further include: triggering pipeline suppression based on the third defense control signal and controlling the tasks and threads included in the load.
[0130] Exemplarily, when an instantaneous power consumption mutation is predicted in the load of mobile device A, hardware behavior can be triggered to perform, for example, a CPU execution pipeline suppression operation, and the kernel software can be triggered to perform task reallocation, thread rescheduling, etc.
[0131] Optionally, step 102 may specifically further include: when it is determined that the power consumption mutation trend is a power surge, controlling the load to perform fast-enabled clock downscaling based on the first defense control signal, or performing power voltage regulation control on the load based on the fourth defense control signal; when it is determined that the power consumption mutation trend is a power sudden decrease, controlling the load to perform fast-enabled buffering based on the second defense control signal, or triggering pipeline suppression based on the third defense control signal and controlling the tasks and threads included in the load.
[0132] Exemplarily, when it is predicted that the power consumption mutation trend of the load of mobile device A is a power surge, the load of mobile device A can be controlled to perform fast-enabled clock downscaling through the clock source based on the first defense control signal, where the downscaling amplitude can be in gears such as 10%, 20%, 30%, etc.; the voltage of the load of mobile device A can also be regulated based on the fourth defense control signal; correspondingly, when it is predicted that the power consumption mutation trend of the load of mobile device A is a power sudden decrease, the load of mobile device A can be controlled to perform fast-enabled buffering through the buffer chain based on the second defense control signal, and hardware behavior can also be triggered to perform, for example, a CPU execution pipeline suppression operation, and the kernel software can be triggered to perform task reallocation, thread rescheduling, etc.
[0133] Compared with the current existing technologies, in this embodiment, a power integrity defense risk assessment is performed on a load based on the load characteristic information and power fluctuation information corresponding to the load to generate a defense control signal, and then the load is controlled based on the defense control signal. The real-time change of the load performance can be fitted through the load characteristic information and power fluctuation information to realize the prediction of the load behavior and energy consumption demand, and the defense lag caused by inaccurate information can also be avoided. Moreover, performing a power integrity defense risk assessment on the load can predict the change of the load before the load mutation occurs, and generate a defense control signal according to the predicted change situation, and then perform defense control on the load, so that this embodiment can take active defense against the load, avoid the problem of further power mutation in the case of load mutation, and further avoid causing functional problems, and can also improve the safety performance of the load.
[0134] Based on the method as described above Figure 2 shown, correspondingly, this embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method as described above Figure 2 shown is implemented.
[0135] Based on such an understanding, the technical solution of the present disclosure can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various implementation scenarios of the present disclosure.
[0136] Based on the method as described above Figure 2 shown, to achieve the above object, an electronic device provided by an embodiment of the present disclosure further includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to implement the method as described above Figure 2 shown.
[0137] Optionally, the above-mentioned physical device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, sensors, an audio circuit, a WI-FI module, and so on. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), etc. Optionally, the user interface may further include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.
[0138] Those skilled in the art can understand that the above-mentioned physical device structure provided by this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine some components, or have different component arrangements.
[0139] The storage medium may further include an operating system and a network communication module. The operating system is a program for managing the hardware and software resources of the above-mentioned entity device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to implement the communication between the components inside the storage medium, as well as the communication between other hardware and software in the information processing entity device.
[0140] Through the description of the above embodiments, those skilled in the art can clearly understand that the present disclosure can be implemented by means of software plus a necessary general hardware platform, or can also be implemented by hardware. By applying the solution of this embodiment, compared with the current existing technologies, in this embodiment, a power integrity defense risk assessment is performed on the load according to the load characteristic information and power fluctuation information corresponding to the load to generate a defense control signal, and then the load is controlled based on the defense control signal. The real-time change of the load performance can be fitted through the load characteristic information and power fluctuation information to realize the prediction of the load behavior and energy consumption demand, and the defense lag caused by inaccurate information can also be avoided; performing a power integrity defense risk assessment on the load can predict the change of the load before the load mutation, and generate a defense control signal according to the predicted change, and then perform defense control on the load, so that this embodiment can take active defense against the load, avoid the problem of further power mutation in the case of load mutation, and thus avoid causing functional problems, and can also improve the safety performance of the load.
[0141] It should be noted that in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.
[0142] The above description is only the specific implementation manners of the present disclosure, enabling those skilled in the art to understand or implement the present disclosure. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but will be accorded the widest scope consistent with the principles and novel features claimed herein.
Claims
1. A defense control system, characterized in that, Comprising: A defense judgment unit, a defense control unit, and a load, where the defense control unit is respectively connected to the defense judgment unit and the load; The defense judgment unit is configured to perform a power integrity defense risk assessment on the load according to the load characteristic information and power fluctuation information corresponding to the load, and generate a defense control signal according to the assessment result; The defense control unit is configured to perform defense control on the load based on the defense control signal.
2. The system according to claim 1, characterized in that The defense judgment unit includes: an energy efficiency perception scheduling module, a performance monitoring module, an on-chip power noise perception module, and a defense control management module; The energy efficiency perception scheduling module, the performance monitoring module, and the on-chip power noise perception module are respectively connected to the defense control management module; The energy efficiency perception scheduling module is configured to obtain the load behavior information in the load characteristic information; The performance monitoring module is configured to obtain the load power consumption information in the load characteristic information; The on-chip power noise perception module is configured to obtain power noise information and power fluctuation information to be corrected, determine the power noise characteristics based on the power noise information, perform correction processing on the power fluctuation information to be corrected based on the power noise characteristics to obtain the power fluctuation information, and perform threshold judgment and behavior prediction on the power fluctuation situation of the load based on the power fluctuation information.
3. The system according to claim 2, wherein The defense control management module is configured to monitor the power fluctuation of the load based on the threshold judgment result and the behavior prediction result, generate a first defense control signal when a power drop is detected, and generate a second defense control signal when a power overshoot is detected; The defense control management module is further configured to predict the instantaneous power consumption change situation of the load based on the load behavior information and the load power consumption information, and generate a third defense control signal when an instantaneous power consumption mutation is predicted; The defense control management module is further configured to perform a correlation analysis on the behavior prediction result and the load power consumption information, predict the instantaneous power consumption change situation of the load based on the correlation analysis result, judge the power consumption mutation trend when an instantaneous power consumption mutation is predicted, generate the first defense control signal or a fourth defense control signal when it is determined that the power consumption mutation trend is a power consumption surge, and generate the second defense control signal or the third defense control signal when it is determined that the power consumption mutation trend is a power consumption sudden decrease.
4. The system according to claim 3, wherein The defense control unit includes: a frequency control module, an energy consumption scheduling control module, a power supply module, and a buffer module; The frequency control module, the energy consumption scheduling control module, the power supply module, and the buffer module are respectively connected to the defense control management module and the load, where the power supply module is further connected to the buffer module; The frequency control module is configured to receive the first defense control signal and control the load to perform fast enable clock downscaling; The energy consumption scheduling control module is configured to receive the third defense control signal, trigger pipeline suppression, and control the tasks and threads included in the load.
5. The system according to claim 4, wherein the power supply module is configured to receive the second defense control signal and / or the fourth defense control signal, and send a buffer control signal to the buffer module when receiving the second defense control signal, and perform power voltage regulation control on the load when receiving the fourth defense control signal; the buffer module is configured to complete buffer chain voltage division switching when receiving the buffer control signal.
6. The system according to claim 2, wherein The load includes: a voltage sensing module; the voltage sensing module is connected to the on-chip power supply noise sensing module; the voltage sensing module is configured to monitor the voltage of the load to obtain the power supply fluctuation information to be corrected.
7. A chip, characterized in that, Including: the system according to any one of claims 1 to 6.
8. A defense control method, characterized in that, Including: performing a power integrity defense risk assessment on the load according to the load characteristic information and the power supply fluctuation information corresponding to the load, and generating a defense control signal according to the assessment result; performing defense control on the load based on the defense control signal.
9. The method according to claim 8, wherein Before performing the power integrity defense risk assessment on the load according to the load characteristic information and the power supply fluctuation information corresponding to the load, the method further includes: acquiring the load characteristic information, the power supply noise information, and the power supply fluctuation information to be corrected, wherein the load characteristic information includes load behavior information and load power consumption information, and the power supply fluctuation information to be corrected is obtained by monitoring the load; determining the power supply noise characteristics based on the power supply noise information, and performing correction processing on the power supply fluctuation information to be corrected based on the power supply noise characteristics to obtain the power supply fluctuation information.
10. The method according to claim 9, wherein The performing a power integrity defense risk assessment on the load according to the load characteristic information and the power supply fluctuation information corresponding to the load, and generating a defense control signal according to the assessment result includes: performing threshold judgment and behavior prediction on the power supply fluctuation condition of the load based on the power supply fluctuation information, and monitoring the power supply fluctuation of the load according to the threshold judgment result and the behavior prediction result; generating a first defense control signal when a power supply drop is detected, and generating a second defense control signal when a power supply overshoot is detected.
11. The method according to claim 10, wherein The performing defense control on the load based on the defense control signal includes: when a power supply drop is detected, controlling the load to perform fast enable clock downscaling based on the first defense control signal; when a power supply overshoot is detected, completing buffer chain voltage division switching based on the second defense control signal.
12. The method according to claim 9, wherein The performing a power integrity defense risk assessment on the load according to the load characteristic information and the power supply fluctuation information corresponding to the load, and generating a defense control signal according to the assessment result further includes: predicting the instantaneous power consumption change condition of the load based on the load behavior information and the load power consumption information, and generating a third defense control signal when an instantaneous power consumption mutation is predicted; The performing defense control on the load based on the defense control signal further includes: triggering pipeline suppression based on the third defense control signal and controlling the tasks and threads included in the load.
13. The method according to claim 10 or 12, characterized in that, Performing a power integrity defense risk assessment on the load according to the load characteristic information and power supply fluctuation information corresponding to the load, and generating a defense control signal according to the assessment result, further comprising: Performing a correlation analysis on the behavior prediction result and the load power consumption information, and predicting the instantaneous power consumption change condition of the load based on the correlation analysis result; Judging the power consumption mutation trend when it is predicted that there is an instantaneous power consumption mutation, generating the first defense control signal or the fourth defense control signal when it is determined that the power consumption mutation trend is a power consumption surge, and generating the second defense control signal or the third defense control signal when it is determined that the power consumption mutation trend is a power consumption sudden drop.
14. The method according to claim 13, wherein The defense control of the load based on the defense control signal further comprises: When it is determined that the power consumption mutation trend is a power consumption surge, controlling the load to perform fast enable clock downscaling based on the first defense control signal, or performing power supply voltage regulation control on the load based on the fourth defense control signal; When it is determined that the power consumption mutation trend is a power consumption sudden drop, completing the buffer chain voltage division switching based on the second defense control signal, or triggering pipeline suppression and controlling the tasks and threads included in the load based on the third defense control signal.
15. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program, when executed by a processor, implements the method according to any one of claims 8 to 14.
16. An electronic device, characterized in that, Comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor, when executing the computer program, implements the method according to any one of claims 8 to 14.
Citation Information
Cited By
Chip, power supply state control method and equipment
CN120803236A