WO2017016358A1 - 运算单元的控制方法、系统和计算机存储介质 - Google Patents

运算单元的控制方法、系统和计算机存储介质 Download PDF

Info

Publication number
WO2017016358A1
WO2017016358A1 PCT/CN2016/087152 CN2016087152W WO2017016358A1 WO 2017016358 A1 WO2017016358 A1 WO 2017016358A1 CN 2016087152 W CN2016087152 W CN 2016087152W WO 2017016358 A1 WO2017016358 A1 WO 2017016358A1
Authority
WO
WIPO (PCT)
Prior art keywords
current value
target frequency
sum
arithmetic unit
arithmetic
Prior art date
Application number
PCT/CN2016/087152
Other languages
English (en)
French (fr)
Inventor
张文彦
Original Assignee
深圳市万普拉斯科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市万普拉斯科技有限公司 filed Critical 深圳市万普拉斯科技有限公司
Priority to US15/747,547 priority Critical patent/US10656694B2/en
Priority to EP16829724.0A priority patent/EP3330853B1/en
Publication of WO2017016358A1 publication Critical patent/WO2017016358A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234—Power saving characterised by the action undertaken
    • G06F1/324—Power saving characterised by the action undertaken by lowering clock frequency
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26—Power supply means, e.g. regulation thereof
    • G06F1/32—Means for saving power
    • G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3024—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a central processing unit [CPU]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/3058—Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00—Error detection; Error correction; Monitoring
    • G06F11/30—Monitoring
    • G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
    • G06F11/3442—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment for planning or managing the needed capacity
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present invention relates to a current control technique for an arithmetic unit group, and more particularly to a control method, system and computer storage medium for an efficient computing unit.
  • the computing power of processors for smart mobile terminals is becoming more and more powerful. More and more computing units are included in the processor in a very small physical package, which makes the processor's heating problem more and more concerned.
  • the current control of the arithmetic unit dynamically adjusts the allowable execution of the maximum frequency and the execution voltage of the arithmetic unit with reference to the temperature rise and the maximum current that can be supplied by the whole machine, thereby controlling the maximum current when the arithmetic unit is executed.
  • multi-operational unit groups multi-core
  • the idle arithmetic units in the multi-operation unit group independently enter the deep sleep mode to achieve power saving. Reduce the number of Power Rails and Clock Sources.
  • the trigger points of the current technology for current control are mostly temperature threshold triggers, and the consideration points are all high temperature to reduce the current to avoid more heat accumulation.
  • embodiments of the present invention are expected to provide a control method, system, and computer storage medium for an arithmetic unit with high efficiency and improved user experience.
  • An embodiment of the present invention provides a method for controlling an operation unit, including the following steps:
  • the target frequency corresponding to the unit is a series of frequencies that the operation unit can run;
  • the sum of the calculated current values is compared with the determined relative current value. If the current value is less than the relative current value, it is determined that the target frequency corresponding to the sum of the current values is the operating frequency to be selected.
  • the step of determining the relative current value comprises:
  • a relative current value is determined based on the performance.
  • the steps of determining the performance of the system requirements and/or application requirements are:
  • the temperature of the aforementioned arithmetic unit is determined.
  • the step of calculating a sum of current values of all currently operating arithmetic units based on the target frequency and temperature comprises:
  • the current value of each arithmetic unit is calculated based on the target frequency and temperature of each arithmetic unit; the calculated current values are added to obtain the sum of the current values of all the operating units.
  • the method further includes the steps of: ordering the target frequency from high to low, and initially calculating a sum of current values of all currently operated arithmetic units corresponding to the highest target frequency, if the calculated current value and The current value is greater than the relative current value, and the next target frequency is determined according to the order of the target frequency, and the sum of the current values of all currently operated arithmetic units corresponding to the next target frequency is calculated.
  • An embodiment of the present invention further provides a control system of an operation unit, including
  • control module configured to determine a relative current value and configured to determine a target frequency corresponding to all currently operated arithmetic units
  • a temperature sensor configured to determine the temperature of all currently operating arithmetic units
  • a current calculator configured to calculate a sum of current values of all currently operating units based on the target frequency and temperature, wherein a target frequency corresponding to each of the operating units is a series of frequencies that the unit can operate;
  • the control module is further configured to compare the sum of the calculated current values with the determined relative current value, and if the current value is less than the relative current value, determine a target frequency corresponding to the sum of the current values to be Selected operating frequency;
  • the operation unit group is configured to receive the operating frequency to be selected, and set the to-be-selected operating frequency to the operating frequency of all currently operated arithmetic units.
  • control module is further configured to determine a performance corresponding to a system requirement and/or an application requirement; and determine a relative current value based on the performance.
  • control module is further configured to obtain the number of required arithmetic units according to system requirements and/or application requirements;
  • the control module is further configured to acquire an operating frequency required by the foregoing computing unit according to system requirements and/or application requirements;
  • the temperature sensor is further configured to determine the temperature of the aforementioned arithmetic unit.
  • the current calculator is further configured to calculate a current value of each of the arithmetic units based on a target frequency and temperature of each of the arithmetic units; add the calculated current values to obtain currents of all the operating units The sum of the values.
  • control module is further configured to classify the target frequency from high to low, and initially calculate a sum of current values of all currently operating units corresponding to the highest target frequency, if the calculated a current value and a row greater than the relative current value according to a target frequency The sequence determines the next target frequency and calculates the sum of the current values of all currently operating units corresponding to the next target frequency.
  • the embodiment of the invention further provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions are used to execute the control method of the arithmetic unit according to the embodiment of the invention.
  • the control method, system and computer storage medium of the arithmetic unit determine the relative current value in advance, and then use the relative current value as a reference. And calculating a sum of current values of the actually operated arithmetic unit according to the target frequency and the current temperature, and comparing the sum of the current values with the relative current value as a reference, if the sum of the current values is less than the relative current value, and the current value
  • the corresponding target frequency can be used as the candidate operating frequency of the currently operating arithmetic unit.
  • the maximum operating frequency to be selected is set as the operating frequency of the currently operating arithmetic unit.
  • the user can satisfy the operating condition of the arithmetic unit within the range of the relative current value, achieve current suppression, improve the efficiency of the arithmetic unit, and not inhibit the operational performance of the arithmetic unit, thereby improving the user experience.
  • 1 is a flow chart of a control method of an arithmetic unit
  • FIG. 2 is a block diagram of a control system of an arithmetic unit
  • Figure 3 is a flow chart for finding the optimal operating frequency.
  • the processing unit in this paper may be an arithmetic unit in a single system on chip (SoC) processing chip, which may be the core of a central processing unit (CPU) in the processor, for example , typical conventional processor for a mobile terminal, such as Qualcomm's Qualcomm TM multi-core processors used in mobile phones and the like, comprising a central processing unit may have four, six or eight cores.
  • the arithmetic unit may also be a graphics processing unit (GPU) in the processor. It will be appreciated that those skilled in the art will appreciate that the arithmetic unit is not limited to the foregoing two.
  • the computing unit may have calculations for the core, the main core, the sub-core, and the hardware engine in the processor. The component of the ability.
  • the above arithmetic unit may be a single one as described above, or a combination of the above.
  • FIG. 1 is a flowchart of a method for controlling an operation unit in an embodiment of the present invention, the method comprising the following steps:
  • step S110 a relative current value is determined.
  • the relative current value is determined as needed, which refers to system requirements and/or application requirements.
  • the required performance is determined according to the requirements of the system (such as a mobile phone operating system) and/or an application (such as an application running in the mobile phone), and the performance is defined as "temperature (°C)
  • the steps to determine the performance of the system requirements and/or application requirements include:
  • the operating frequency required for the aforementioned arithmetic unit is obtained as needed.
  • the temperature of the aforementioned arithmetic unit is determined.
  • the operating frequency and the temperature of the arithmetic unit are substantially inversely proportional to each other, which is in accordance with a typical strategy of the operating unit based on its temperature control, for example, when the temperature of the operating unit is high, the operating unit can be operated. The highest frequency is lowered, and as its temperature decreases, the highest frequency at which the arithmetic unit can operate is raised.
  • the temperature corresponding to the aforementioned operating frequency can be determined based on the pre-stored operating frequency and the relationship table before the temperature. It is understood that the method of determining the temperature is not limited to the foregoing.
  • an intelligent mobile terminal currently runs two applications (such as an instant messaging application and music playing music) at the same time, and determines that the required performance is "60
  • the performance provided at runtime, where systems and applications can run smoothly/no stalls. That is, the system and the application program will not suffer from the crash, slow response, etc., which affect the user experience when the operating frequency is 100% of the utilization rate of the computing unit.
  • determining the relative current value according to the requirement may refer to the current value of the actually obtained arithmetic unit, for example, the current value measured in advance and stored in various performances, for example, the performance is “60
  • the performance is “60
  • determining the relative current value according to demand may also refer to calculating a relative current value based on a particular formula.
  • Vt is the corrected voltage of the arithmetic unit at the temperature t
  • Fn is the operating frequency of the aforementioned arithmetic unit nth power
  • Step S120 determining a target frequency corresponding to all currently operated arithmetic units, determining a temperature of all currently operating arithmetic units, and calculating a sum of current values of all currently operating arithmetic units based on the target frequency and temperature.
  • the target frequency corresponding to each running arithmetic unit is a series of frequencies that the operating unit can run.
  • the target frequency corresponding to each operation unit is stored in advance, for example, the target frequency includes 384 MHz, 480 MHz, 768 MHz, 864 MHz, 960 MHz, 1248 MHz, 1344MHz, 1632MHz, 1766MHz. It should be noted that, in one embodiment, if the currently running arithmetic units share the same clock source, the operating frequency of the currently running arithmetic unit can be adjusted synchronously.
  • each of the arithmetic units is provided with a corresponding temperature sensor, and the temperature of each of the arithmetic units at any time can be obtained by the temperature sensor.
  • the step of calculating a sum of current values of all currently operating units based on the target frequency and temperature includes:
  • the current value of each arithmetic unit is calculated based on the target frequency and temperature of each arithmetic unit.
  • the current value of each operation unit currently running can be calculated by using the formula Vt*Fn/(1-Lt), Vt is the corrected voltage when the temperature is t, Fn is a target frequency n-th power, and Lt is the temperature t.
  • the processor if included (e.g., multi-core processors Qualcomm TM) is provided with a plurality of computing resources current calculator (Instant Power Calculator), you can use the current calculator calculates all currently running operation The sum of the current values of the cells.
  • the current calculator is also calculated based on a target frequency and temperature of each operating unit.
  • the current calculator can also calculate the current state of the current operating unit (such as idle or running), and calculate the sum of the current values of all currently operating units.
  • Step S130 comparing the sum of the current values calculated in step S120 with the relative current value in step S110, and if the current value is less than the relative current value, determining a target frequency corresponding to the sum of the current values Is the operating frequency to be selected.
  • FIG. 3 is a flow chart of searching for an optimal operating frequency; in combination with FIG. 3, in the present embodiment, the target frequency is sorted from high to low, and the current target frequency corresponding to the highest target frequency is initially calculated. If the calculated current value is greater than the relative current value, the next target frequency is determined according to the order of the target frequency, and then returns to step S120 to calculate the current corresponding to the next target frequency. The sum of the current values of all running arithmetic units.
  • the selected operating frequency corresponding to the sum of the first current values smaller than the relative current value is the largest of all the selected operating frequencies, and at this time, all of the The largest of the operating frequencies to be selected is set to the operating frequency of all running arithmetic units.
  • the currently running arithmetic units share the same clock source, assuming that the currently operating arithmetic units have the same target frequency: 384 MHz, 480 MHz, 768 MHz, 864 MHz, 960 MHz, 1248 MHz, 1344 MHz, 1632 MHz, 1766 MHz. Calculating the sum of the current values of all currently operating units corresponding to each target frequency in order of high to low, until the sum of the current values of all currently operating units smaller than the relative current value is found. Corresponding maximum candidate frequency.
  • a certain number of candidate frequencies may be determined, and the specific number of candidate frequencies are smaller than the maximum candidate frequency, which is not an optimal selection object, but may be reserved. frequency.
  • the selected maximum candidate frequency must be greater than 700 MHz. That is, the performance that can be provided is higher than the performance required. In another case, if there are currently 3 arithmetic units in use, but because the temperature is only 40 ° C, the final selected maximum candidate frequency also has a good chance of being higher than 700 MHz to achieve within the specified relative current value. Meet the performance of the user experience.
  • the choice of being able to lower the specified relative current value, thereby saving energy and having the greatest chance to satisfy the performance, is user-centric, so that the user experience can be improved.
  • An embodiment of the present invention further provides a computer storage medium, where the computer storage medium
  • the computer executable instructions are stored for executing the control method of the arithmetic unit according to the embodiment of the present invention.
  • FIG. 2 it is a block diagram of the control system of the arithmetic unit.
  • a control unit for an arithmetic unit including
  • the control module 30 is configured to determine a relative current value and configured to determine a target frequency corresponding to all currently operating units.
  • the memory 40 is configured to store a relative current value and a target frequency
  • a temperature sensor 20 configured to determine a temperature of all currently operating arithmetic units
  • the current calculator 10 is configured to calculate a sum of current values of all currently operating arithmetic units based on the target frequency and temperature, wherein a target frequency corresponding to each of the operating units is a series of frequencies that the operating unit can operate;
  • the control module 30 is further configured to compare the sum of the calculated current values with the determined relative current value, and if the current value is less than the relative current value, determine a sum corresponding to the current value
  • the target frequency is the operating frequency to be selected
  • the arithmetic unit group unit 50 is configured to receive the operating frequency to be selected, and set the operating frequency to be selected as the operating frequency of all currently operating arithmetic units.
  • control module 30 is further configured to determine a performance corresponding to a system requirement and/or an application requirement; and determine a relative current value based on the performance.
  • control module 30 is further configured to obtain the number of required arithmetic units according to system requirements and/or application requirements;
  • the control module 30 is further configured to acquire an operating frequency required by the foregoing computing unit according to system requirements and/or application requirements;
  • the temperature sensor 20 is also configured to determine the temperature of the aforementioned arithmetic unit.
  • the current calculator 10 is further configured to calculate a current value of each of the arithmetic units based on a target frequency and temperature of each of the arithmetic units; and add the calculated current values to obtain The sum of the current values of all running arithmetic units.
  • control module 30 is further configured to sort the target frequency from high to low, and initially calculate the sum of the current values of all currently operated arithmetic units corresponding to the highest target frequency, if the calculated The current value is greater than the relative current value, and the next target frequency is determined according to the order of the target frequency, and the sum of the current values of all currently operated arithmetic units corresponding to the next target frequency is calculated.
  • the control method and system of the above arithmetic unit determine the relative current value in advance, and then use the relative current value as a reference. And calculating a sum of current values of the actually operated arithmetic unit according to the target frequency and the current temperature, and comparing the sum of the current values with the relative current value as a reference, if the sum of the current values is less than the relative current value, and the current value
  • the corresponding target frequency can be used as the candidate operating frequency of the currently operating arithmetic unit.
  • the maximum operating frequency to be selected is set as the operating frequency of the currently operating arithmetic unit.
  • the user can satisfy the operating condition of the arithmetic unit within the range of the relative current value, achieve current suppression, improve the efficiency of the arithmetic unit, and not inhibit the operational performance of the arithmetic unit, thereby improving the user experience.
  • control system of the operation unit can be implemented by a personal computer in practical applications.
  • the control module 30, the current calculator 10 and the arithmetic unit group 50 in the control system of the arithmetic unit can be used by a central processing unit (CPU) in the system and a digital signal processor in practical applications.
  • CPU central processing unit
  • DSP Digital Signal Processor
  • MCU Microcontroller Unit
  • FPGA Field-Programmable Gate Array
  • the memory 40 in the control system of the arithmetic unit can be used in practical applications.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner such as: multiple units or components may be combined, or Can be integrated into another system, or some features can be ignored or not executed.
  • the coupling, or direct coupling, or communication connection of the components shown or discussed may be indirect coupling or communication connection through some interfaces, devices or units, and may be electrical, mechanical or other forms. of.
  • the units described above as separate components may or may not be physically separated, and the components displayed as the unit may or may not be physical units, that is, may be located in one place or distributed to multiple network units; Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated into one unit;
  • the unit can be implemented in the form of hardware or in the form of hardware plus software functional units.
  • the foregoing program may be stored in a computer readable storage medium, and the program is executed when executed.
  • the foregoing storage device includes the following steps: the foregoing storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
  • ROM read-only memory
  • RAM random access memory
  • magnetic disk or an optical disk.
  • optical disk A medium that can store program code.
  • the above-described integrated unit of the present invention may be stored in a computer readable storage medium if it is implemented in the form of a software function module and sold or used as a standalone product.
  • the technical solution of the embodiments of the present invention may be embodied in the form of a software product in essence or in the form of a software product stored in a software product.
  • the storage medium includes instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes various media that can store program codes, such as a mobile storage device, a ROM, a RAM, a magnetic disk, or an optical disk.
  • the technical solution of the embodiment of the present invention determines the relative current value in advance, and then uses the relative current value as a reference. And calculating a sum of current values of the actually operated arithmetic unit according to the target frequency and the current temperature, and comparing the sum of the current values with the relative current value as a reference, if the sum of the current values is less than the relative current value, and the current value
  • the corresponding target frequency can be used as the candidate operating frequency of the currently operating arithmetic unit.
  • the maximum operating frequency to be selected is set as the operating frequency of the currently operating arithmetic unit.
  • the user can satisfy the operating condition of the arithmetic unit within the range of the relative current value, achieve current suppression, improve the efficiency of the arithmetic unit, and not inhibit the operational performance of the arithmetic unit, thereby improving the user experience.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Quality & Reliability (AREA)
  • Computer Hardware Design (AREA)
  • Mathematical Physics (AREA)
  • Power Sources (AREA)

Abstract

一种运算单元的控制方法、运算单元的控制系统和计算机存储介质，所述方法包括：确定相对电流值（S110）；确定与当前所有运行的运算单元对应的目标频率，确定当前所有运行的运算单元的温度，基于所述目标频率和温度计算当前所有运行的运算单元的电流值之和（S120），其中，每个运行的运算单元对应的目标频率为该运算单元可运行的一系列频率；将前述计算得到电流值之和与所述确定的相对电流值进行比较，若该电流值和小于所述相对电流值，则确定与该电流值之和对应的目标频率为待选的运行频率（S130）。

Description

运算单元的控制方法、系统和计算机存储介质 技术领域
本发明涉及运算单元群的电流控制技术，特别是涉及一种效率高的运算单元的控制方法、系统和计算机存储介质。
背景技术
随着技术的发展，用于智能移动终端(例如手机、平板电脑)的处理器的计算能力越来越强大。处理器中在极小的物理封装中包含了越来越多的运算单元，这使得处理器的发热问题越来越受到关注。现有技术对于运算单元的电流控制，皆以参考温升与整机可供应的最大电流来动态调整运算单元的可允许执行最大频率与执行电压，藉此控制运算单元执行时的最大电流。随着多运算单元群(多核心)的发展，越来越多的平台设计以多运算单元共享同一频率为主，多运算单元群中闲置的运算单元独立进入深度睡眠模式，来达到省电同时减少电路(Power Rail)与时钟源(Clock Source)数量。
然而，藉由控制运算单元的可运行的最大频率来达到控制运算单元的电流目的，将导致所有同时钟源的运算单元被同时抑制效能，导致用户体验差。此外，现有技术进行电流控制的触发点，多为温度阀值触发，考量点皆为高温时让电流降低来避免热量越积越多。
发明内容
基于此，本发明实施例期望提供一种效率高、提高用户体验的运算单元的控制方法、系统和计算机存储介质。
本发明实施例提供了一种运算单元的控制方法，包括以下步骤：
确定相对电流值；
确定与当前所有运行的运算单元对应的目标频率，确定当前所有运行的运算单元的温度，基于所述目标频率和温度计算当前所有运行的运算单元的电流值之和，其中，每个运行的运算单元对应的目标频率为该运算单元可运行的一系列频率；
将前述计算得到电流值之和与所述确定的相对电流值进行比较，若该电流值和小于所述相对电流值，则确定与该电流值之和对应的目标频率为待选的运行频率。
在其中一个实施例中，确定相对电流值的步骤包括：
确定系统需求和/或应用程序需求所对应的效能；
根据所述效能确定相对电流值。
在其中一个实施例中，确定系统需求和/或应用程序需求所对应的效能的步骤：
根据系统需求和/或应用程序需求获取所需的运算单元的个数；
根据系统需求和/或应用程序需求获取前述的运算单元所需的运行频率；
确定前述的运算单元的温度。
在其中一个实施例中，基于所述目标频率和温度计算当前所有运行的运算单元的电流值之和的步骤包括：
基于每个运算单元的目标频率和温度计算每个运算单元的电流值；将计算得到的电流值相加获得所有运行的运算单元的电流值之和。
在其中一个实施例中，还包括步骤：将目标频率由高到低的排序，初始时计算最高的目标频率所对应的当前所有运行的运算单元的电流值之和，若计算出的电流值和大于所述相对电流值，按照目标频率的排序，确定下一个目标频率，计算该下一个目标频率所对应的当前所有运行的运算单元的电流值之和。
本发明实施例还提供了一种运算单元的控制系统，包括，
控制模块，配置为确定相对电流值及配置为确定与当前所有运行的运算单元对应的目标频率；
温度传感器，配置为确定当前所有运行的运算单元的温度；
电流计算器，配置为基于所述目标频率和温度计算当前所有运行的运算单元的电流值之和，其中，每个运行的运算单元对应的目标频率为该运算单元可运行的一系列频率；
控制模块还配置为将前述计算得到电流值之和与所述确定的相对电流值进行比较，若该电流值和小于所述相对电流值，则确定与该电流值之和对应的目标频率为待选的运行频率；
运算单元群部，配置为接收待选的运行频率，并将该待选的运行频率设定为当前所有运行的运算单元的运行频率。
在其中一个实施例中，所述控制模块还配置为确定系统需求和/或应用程序需求所对应的效能；并根据所述效能确定相对电流值。
在其中一个实施例中，所述控制模块还配置为根据系统需求和/或应用程序需求获取所需的运算单元的个数；
所述控制模块还配置为根据系统需求和/或应用程序需求获取前述的运算单元所需的运行频率；
所述温度传感器还配置为确定前述的运算单元的温度。
在其中一个实施例中，所述电流计算器还配置为基于每个运算单元的目标频率和温度计算每个运算单元的电流值；将计算得到的电流值相加获得所有运行的运算单元的电流值之和。
在其中一个实施例中，所述控制模块还配置为将目标频率由高到低的排序，初始时计算最高的目标频率所对应的当前所有运行的运算单元的电流值之和，若计算出的电流值和大于所述相对电流值，按照目标频率的排 序，确定下一个目标频率，计算该下一个目标频率所对应的当前所有运行的运算单元的电流值之和。
本发明实施例还提供了一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，所述计算机可执行指令用于执行本发明实施例所述的运算单元的控制方法。
本发明实施例提供的运算单元的控制方法、系统和计算机存储介质，通过预先确定相对电流值，然后以相对电流值作为参考。再根据目标频率及当前温度计算实际运行的运算单元的电流值之和，将该电流值之和与作为参考的相对电流值进行比较，若该电流值之和小于相对电流值，与该电流值之和对应的目标频率可以作为当前运行的运算单元的待选的运行频率。当确定最大的待选的运行频率时，将该最大的待选的运行频率设为当前运行的运算单元的运行频率。即用户在相对电流值的范围内，既能满足运算单元的运行条件，达到电流抑制的同时，提高运算单元的效率，且不会抑制运算单元的运行效能，因而又能够提高用户的体验。
附图说明
图1为运算单元的控制方法的流程图；
图2为运算单元的控制系统的模块图；
图3为最佳运行频率查找流程图。
具体实施方式
为了便于理解本发明，下面将参照相关附图对本发明进行更全面的描述。附图中给出了本发明的较佳的实施例。但是，本发明可以以许多不同的形式来实现，并不限于本文所描述的实施例。相反地，提供这些实施例的目的是使对本发明的公开内容的理解更加透彻全面。
除非另有定义，本文所使用的所有的技术和科学术语与属于本发明的 技术领域的技术人员通常理解的含义相同。本文中在本发明的说明书中所使用的术语只是为了描述具体的实施例的目的，不是旨在于限制本发明。本文所使用的术语“及/或”包括一个或多个相关的所列项目的任意的和所有的组合。
本文中的运算单元(Processing Unit)可以为单一片上系统(System on Chip，SoC)处理芯片中的运算单元，其可以为处理器中的中央处理单元(Central Processing Unit，CPU)的核心，例如，现有典型的用于移动终端的处理器，如美国高通公司的用于手机等的多核心骁龙TM处理器，包含的中央处理单元可以具有4个、6个或8个核心。运算单元还可以为处理器中的图形处理单元(Graphics Processing Unit，GPU)。可以理解地，本领域技术人员会意识到，运算单元并不局限于前述二者，在其他实施方式中，该运算单元可以为处理器中的核心、主核心、子核心及硬件引擎等具有计算能力的组件。上述运算单元可以为上述的单独一种，或是上述的多种之组合。
如图1所示，为本发明的一个实施例中的运算单元的控制方法的流程图，该方法包括以下步骤：
步骤S110，确定相对电流值。
在本实施方式中，根据需求确定相对电流值，所述需求指系统需求和/或应用程序需求。具体的，根据系统(例如手机操作系统)和/或应用程序(例如手机中正在运行的应用程序)的需求确定所需的效能，所述的效能的定义为“温度(℃)|运算单元的个数|运行频率(MHz)”。
具体的，确定系统需求和/或应用程序需求的效能的步骤包括：
根据需求获取所需的运算单元的个数。
根据需求获取前述的运算单元所需的运行频率。
确定前述的运算单元的温度。
在一个实施方式中，运算单元的运行频率和温度之间大致成反比关系，这符合运算单元的基于其温度进行控制的典型策略，例如，当运算单元的温度较高时，运算单元的可运行的最高频率被降低，当其温度降低时，运算单元的可运行的最高频率被升高。依据预先存储的运行频率和温度之前的关系表，可以确定前述的运行频率所对应的温度。可以理解地，确定温度的方法并不局限于前述方式。
例如，智能移动终端当前同时运行两个应用程序(例如即时通讯应用和音乐播放音乐)，根据需求确定所需要的效能为“60|2|700”，即2个运算单元在60℃时以700MHz运行时提供的效能，在此效能下，系统和应用程序能够流畅/无卡顿的运行。即系统和应用程序在该运行频率以运算单元的利用率百分之百时亦不会出现死机、反应慢等影响用户体验的情况。
在本实施方式中，根据需求确定相对电流值可以指经过实际测的得到的运算单元的电流值，例如，预先测量并存储在各种效能时的电流值，如效能为“60|2|700”时，此时有2个运算单元在运行，测量得到的2个运算单元的电流值之和即为效能“60|2|700”时的相对电流值。
此外，在其他实施方式中，根据需求确定相对电流值还可以指基于特定的公式来计算出相对电流值。例如，相对电流值＝Vt*Fn/(1-Lt)，其中，Vt为温度t时运算单元的修正后的电压、Fn为前述的运算单元运行频率n次方、Lt为温度t时电压转换遗失率，其中，0<＝Lt<1。
步骤S120，确定与当前所有运行的运算单元对应的目标频率，确定当前所有运行的运算单元的温度，基于所述目标频率和温度计算当前所有运行的运算单元的电流值之和。其中，每个运行的运算单元对应的目标频率为该运算单元可运行的一系列频率。
在一个实施方式中，预先存储每个运算单元对应的目标频率，例如，目标频率包括384MHz、480MHz、768MHz、864MHz、960MHz、1248MHz、 1344MHz、1632MHz、1766MHz。需要注意的是，在一个实施方式中，如果当前运行的运算单元共享同一时钟源(clock source)，则当前运行的运算单元的运行频率可以同步地被调整。
在一个实施方式中，每个运算单元均设置有对应的温度传感器，通过温度传感器能够获得每个运算单元在任意时刻的温度。
具体的，基于所述目标频率和温度计算当前所有运行的运算单元的电流值之和的步骤包括：
首先，基于每个运算单元的目标频率和温度计算每个运算单元的电流值。
具体的，可以采用公式Vt*Fn/(1-Lt)计算当前运行的每个运算单元的电流值，Vt为温度t时修正后的电压、Fn为一个目标频率n次方、Lt为温度t时电压转换遗失率，其中，0<＝Lt<1。
然后，将计算得到的电流值相加获得所有运行的运算单元的电流值之和。
在一个实施方式中，如果包括多运算资源的处理器(例如多核心的骁龙TM处理器)提供有电流计算器(Instant Power Calculator)，则可以利用该电流计算器来计算当前所有运行的运算单元的电流值之和。电流计算器亦根据每个运行的运算单元的一个目标频率和温度进行计算。电流计算器还可以同时考虑当前运算单元的状态(如闲置或运行中)等，计算出更准确的当前所有运行的运算单元的电流值之和。
步骤S130，将步骤S120中计算得到电流值之和与所述步骤S110中的相对电流值进行比较，若该电流值和小于所述相对电流值，则确定与该电流值之和对应的目标频率为待选的运行频率。
图3为最佳运行频率查找流程图；结合图3，在本实施方式中，将目标频率由高到低的排序，初始时计算最高的目标频率所对应的当前所有运行 的运算单元的电流值之和，若计算出的电流值和大于所述相对电流值，按照目标频率的排序，确定下一个目标频率，然后返回步骤S120，计算该下一个目标频率所对应的当前所有运行的运算单元的电流值之和。
依照上述的循环计算方式，确定的第一个小于所述相对电流值的电流值之和所对应的待选的运行频率，为所有待选的运行频率中的最大者，此时，将该所有待选的运行频率中的最大者设为所有运行的运算单元的运行频率。
在本实施方式中，当前运行的运算单元共享同一时钟源，假定当前运行的运算单元具有相同的目标频率：384MHz、480MHz、768MHz、864MHz、960MHz、1248MHz、1344MHz、1632MHz、1766MHz。将目标频率由高到低的顺序依次计算每个目标频率对应的当前所有运行的运算单元的电流值之和，直到找到小于所述相对电流值的当前所有运行的运算单元的电流值之和所对应的最大待选频率。
在其他实施方式中，除了上述最大待选频率，还可确定特定数量的待选频率，所述特定数量的待选频率均小于上述最大待选频率，不是最优的选择对象，但是可以作为后备频率。
以“60|2|700”为所需的效能为例，如果在目前60℃下只有1个运算单元在运行，而其他运算单元闲置或关闭，则被选中的最大待选频率必然大于700MHz，即能提供的性能比需求的性能更高。另一例，如果目前有3个运算单元正在使用，但因为其温度只有40℃，则最终被挑选的最大待选频率也有很大的机会能高于700MHz，才能达到在指定相对电流值内，提供满足用户体验的效能。
基于上述实施例，提供能低于指定相对电流值，从而节约能源，又有最大机会满足效能的选择，以用户为中心，故能够提高用户体验。
本发明实施例还提供了一种计算机存储介质，所述计算机存储介质中 存储有计算机可执行指令，所述计算机可执行指令用于执行本发明实施例所述的运算单元的控制方法。
如图2所示，为运算单元的控制系统的模块图。
一种运算单元的控制系统，包括，
控制模块30，配置为确定相对电流值及配置为确定与当前所有运行的运算单元对应的目标频率。
存储器40，配置为存储相对电流值及目标频率；
温度传感器20，配置为确定当前所有运行的运算单元的温度；
电流计算器10，配置为基于所述目标频率和温度计算当前所有运行的运算单元的电流值之和，其中，每个运行的运算单元对应的目标频率为该运算单元可运行的一系列频率；
所述控制模块30，还配置为将前述计算得到电流值之和与所述确定的相对电流值进行比较，若该电流值和小于所述相对电流值，则确定与该电流值之和对应的目标频率为待选的运行频率；
运算单元群部50，配置为接收待选的运行频率，并将该待选的运行频率设定为当前所有运行的运算单元的运行频率。
在一个实施方式中，所述控制模块30还配置为确定系统需求和/或应用程序需求所对应的效能；并根据所述效能确定相对电流值。
在一个实施方式中，所述控制模块30还配置为根据系统需求和/或应用程序需求获取所需的运算单元的个数；
所述控制模块30还配置为根据系统需求和/或应用程序需求获取前述的运算单元所需的运行频率；
所述温度传感器20还配置为确定前述的运算单元的温度。
在一个实施方式中，所述电流计算器10还配置为基于每个运算单元的目标频率和温度计算每个运算单元的电流值；将计算得到的电流值相加获 得所有运行的运算单元的电流值之和。
在一个实施方式中，所述控制模块30还配置为将目标频率由高到低的排序，初始时计算最高的目标频率所对应的当前所有运行的运算单元的电流值之和，若计算出的电流值和大于所述相对电流值，按照目标频率的排序，确定下一个目标频率，计算该下一个目标频率所对应的当前所有运行的运算单元的电流值之和。
上述运算单元的控制方法和系统通过预先确定相对电流值，然后以相对电流值作为参考。再根据目标频率及当前温度计算实际运行的运算单元的电流值之和，将该电流值之和与作为参考的相对电流值进行比较，若该电流值之和小于相对电流值，与该电流值之和对应的目标频率可以作为当前运行的运算单元的待选的运行频率。当确定最大的待选的运行频率时，将该最大的待选的运行频率设为当前运行的运算单元的运行频率。即用户在相对电流值的范围内，既能满足运算单元的运行条件，达到电流抑制的同时，提高运算单元的效率，且不会抑制运算单元的运行效能，因而又能够提高用户的体验。
本发明实施例中，所述运算单元的控制系统在实际应用中，可通过个人计算机实现。所述运算单元的控制系统中的控制模块30、电流计算器10和运算单元群部50，在实际应用中均可由所述系统中的中央处理器(CPU，Central Processing Unit)、数字信号处理器(DSP，Digital Signal Processor)、微控制单元(MCU，Microcontroller Unit)或可编程门阵列(FPGA，Field－Programmable Gate Array)实现；所述运算单元的控制系统中的存储器40，在实际应用中可由所述系统中的存储器实现。
以上所述实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
在本申请所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，如：多个单元或组件可以结合，或可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的各组成部分相互之间的耦合、或直接耦合、或通信连接可以是通过一些接口，设备或单元的间接耦合或通信连接，可以是电性的、机械的或其它形式的。
上述作为分离部件说明的单元可以是、或也可以不是物理上分开的，作为单元显示的部件可以是、或也可以不是物理单元，即可以位于一个地方，也可以分布到多个网络单元上；可以根据实际的需要选择其中的部分或全部单元来实现本实施例方案的目的。
另外，在本发明各实施例中的各功能单元可以全部集成在一个处理单元中，也可以是各单元分别单独作为一个单元，也可以两个或两个以上单元集成在一个单元中；上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：移动存储设备、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
或者，本发明上述集成的单元如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明实施例的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一 个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本发明各个实施例所述方法的全部或部分。而前述的存储介质包括：移动存储设备、ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以所述权利要求的保护范围为准。
工业实用性
本发明实施例的技术方案通过预先确定相对电流值，然后以相对电流值作为参考。再根据目标频率及当前温度计算实际运行的运算单元的电流值之和，将该电流值之和与作为参考的相对电流值进行比较，若该电流值之和小于相对电流值，与该电流值之和对应的目标频率可以作为当前运行的运算单元的待选的运行频率。当确定最大的待选的运行频率时，将该最大的待选的运行频率设为当前运行的运算单元的运行频率。即用户在相对电流值的范围内，既能满足运算单元的运行条件，达到电流抑制的同时，提高运算单元的效率，且不会抑制运算单元的运行效能，因而又能够提高用户的体验。

Claims (11)

  1. 一种运算单元的控制方法，包括以下步骤：
    确定相对电流值；
    确定与当前所有运行的运算单元对应的目标频率，确定当前所有运行的运算单元的温度，基于所述目标频率和温度计算当前所有运行的运算单元的电流值之和，其中，每个运行的运算单元对应的目标频率为该运算单元可运行的一系列频率；
    将前述计算得到电流值之和与所述确定的相对电流值进行比较，若该电流值和小于所述相对电流值，则确定与该电流值之和对应的目标频率为待选的运行频率。
  2. 根据权利要求1所述的运算单元的控制方法，其中，确定相对电流值的步骤包括：
    确定系统需求和/或应用程序需求所对应的效能；
    根据所述效能确定相对电流值。
  3. 根据权利要求2所述的运算单元的控制方法，其中，确定系统需求和/或应用程序需求所对应的效能的步骤：
    根据系统需求和/或应用程序需求获取所需的运算单元的个数；
    根据系统需求和/或应用程序需求获取前述的运算单元所需的运行频率；
    确定前述的运算单元的温度。
  4. 根据权利要求1所述的运算单元的控制方法，其中，基于所述目标频率和温度计算当前所有运行的运算单元的电流值之和的步骤包括：
    基于每个运算单元的目标频率和温度计算每个运算单元的电流值；将计算得到的电流值相加获得所有运行的运算单元的电流值之和。
  5. 根据权利要求4所述的运算单元的控制方法，其中，还包括步骤：
    将目标频率由高到低的排序，初始时计算最高的目标频率所对应的当前所有运行的运算单元的电流值之和，若计算出的电流值和大于所述相对电流值，按照目标频率的排序，确定下一个目标频率，计算该下一个目标频率所对应的当前所有运行的运算单元的电流值之和。
  6. 一种运算单元的控制系统，包括：
    控制模块，配置为确定相对电流值及配置为确定与当前所有运行的运算单元对应的目标频率；
    温度传感器，配置为确定当前所有运行的运算单元的温度；
    电流计算器，配置为基于所述目标频率和温度计算当前所有运行的运算单元的电流值之和，其中，每个运行的运算单元对应的目标频率为该运算单元可运行的一系列频率；
    所述控制模块，还配置为将前述计算得到电流值之和与所述确定的相对电流值进行比较，若该电流值和小于所述相对电流值，则确定与该电流值之和对应的目标频率为待选的运行频率；
    运算单元群部，配置为接收待选的运行频率，并将该待选的运行频率设定为当前所有运行的运算单元的运行频率。
  7. 根据权利要求6所述的运算单元的控制系统，其中，所述控制模块还配置为确定系统需求和/或应用程序需求所对应的效能；并根据所述效能确定相对电流值。
  8. 根据权利要求7所述的运算单元的控制系统，其中，所述控制模块还配置为根据系统需求和/或应用程序需求获取所需的运算单元的个数；
    所述控制模块还配置为根据系统需求和/或应用程序需求获取前述的运算单元所需的运行频率；
    所述温度传感器还配置为确定前述的运算单元的温度。
  9. 根据权利要求6所述的运算单元的控制系统，其中，所述电流计算 器还配置为基于每个运算单元的目标频率和温度计算每个运算单元的电流值；将计算得到的电流值相加获得所有运行的运算单元的电流值之和。
  10. 根据权利要求6所述的运算单元的控制系统，其中，所述控制模块还配置为将目标频率由高到低的排序，初始时计算最高的目标频率所对应的当前所有运行的运算单元的电流值之和，若计算出的电流值和大于所述相对电流值，按照目标频率的排序，确定下一个目标频率，计算该下一个目标频率所对应的当前所有运行的运算单元的电流值之和。
  11. 一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，所述计算机可执行指令用于执行权利要求1至5任一项所述的运算单元的控制方法。
PCT/CN2016/087152 2015-07-28 2016-06-24 运算单元的控制方法、系统和计算机存储介质 WO2017016358A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US15/747,547 US10656694B2 (en) 2015-07-28 2016-06-24 Method and system for controlling operation unit, and computer storage medium
EP16829724.0A EP3330853B1 (en) 2015-07-28 2016-06-24 Method and system for controlling operation unit, and computer storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510451908.9A CN105068872B (zh) 2015-07-28 2015-07-28 运算单元的控制方法和系统
CN201510451908.9 2015-07-28

Publications (1)

Publication Number Publication Date
WO2017016358A1 true WO2017016358A1 (zh) 2017-02-02

Family

ID=54498249

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/087152 WO2017016358A1 (zh) 2015-07-28 2016-06-24 运算单元的控制方法、系统和计算机存储介质

Country Status (4)

Country Link
US (1) US10656694B2 (zh)
EP (1) EP3330853B1 (zh)
CN (1) CN105068872B (zh)
WO (1) WO2017016358A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105068872B (zh) 2015-07-28 2018-11-23 深圳市万普拉斯科技有限公司 运算单元的控制方法和系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104011626A (zh) * 2011-12-22 2014-08-27 英特尔公司 通过在运行时期间配置功率管理参数的用于高能效和节能的系统、方法和装置
US20140359328A1 (en) * 2013-05-28 2014-12-04 James S. Burns Method and system for run-time reallocation of leakage current and dynamic power supply current
US20150026495A1 (en) * 2013-07-18 2015-01-22 Qualcomm Incorporated System and method for idle state optimization in a multi-processor system on a chip
CN104679586A (zh) * 2013-10-31 2015-06-03 三星电子株式会社 包括异构多核处理器的电子系统及其操作方法
CN105068872A (zh) * 2015-07-28 2015-11-18 深圳市万普拉斯科技有限公司 运算单元的控制方法和系统

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030074591A1 (en) * 2001-10-17 2003-04-17 Mcclendon Thomas W. Self adjusting clocks in computer systems that adjust in response to changes in their environment
US7500122B2 (en) 2006-01-20 2009-03-03 Micro-Star Int'l Co., Ltd. Efficiency optimization method for hardware devices with adjustable clock frequencies
JP2008026948A (ja) * 2006-07-18 2008-02-07 Renesas Technology Corp 半導体集積回路
EP2130106B1 (en) * 2007-03-28 2018-11-14 Nytell Software LLC Electronic device and method determining a workload of an electronic device
CN102023697B (zh) * 2009-09-21 2013-09-04 联想(北京)有限公司 一种cpu电源管理方法、装置以及终端设备
US8788866B2 (en) * 2011-04-25 2014-07-22 Qualcomm Incorporated Method and system for reducing thermal load by monitoring and controlling current flow in a portable computing device
US8769316B2 (en) * 2011-09-06 2014-07-01 Intel Corporation Dynamically allocating a power budget over multiple domains of a processor
US9052901B2 (en) * 2011-12-14 2015-06-09 Intel Corporation Method, apparatus, and system for energy efficiency and energy conservation including configurable maximum processor current
TWI496087B (zh) * 2012-09-21 2015-08-11 Htc Corp 具多重中央處理單元之電子裝置及其效能管理方法
KR102211126B1 (ko) * 2014-04-17 2021-02-02 삼성전자주식회사 동작 성능을 조절하는 메모리 시스템 및 메모리 시스템의 동작방법
US20160147280A1 (en) * 2014-11-26 2016-05-26 Tessil Thomas Controlling average power limits of a processor
US9552447B2 (en) * 2015-04-24 2017-01-24 Globalfoundries Inc. Systems and methods for controlling integrated circuit chip temperature using timing closure-based adaptive frequency scaling

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104011626A (zh) * 2011-12-22 2014-08-27 英特尔公司 通过在运行时期间配置功率管理参数的用于高能效和节能的系统、方法和装置
US20140359328A1 (en) * 2013-05-28 2014-12-04 James S. Burns Method and system for run-time reallocation of leakage current and dynamic power supply current
US20150026495A1 (en) * 2013-07-18 2015-01-22 Qualcomm Incorporated System and method for idle state optimization in a multi-processor system on a chip
CN104679586A (zh) * 2013-10-31 2015-06-03 三星电子株式会社 包括异构多核处理器的电子系统及其操作方法
CN105068872A (zh) * 2015-07-28 2015-11-18 深圳市万普拉斯科技有限公司 运算单元的控制方法和系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3330853A4 *

Also Published As

Publication number Publication date
CN105068872A (zh) 2015-11-18
US10656694B2 (en) 2020-05-19
CN105068872B (zh) 2018-11-23
EP3330853A1 (en) 2018-06-06
US20180217653A1 (en) 2018-08-02
EP3330853B1 (en) 2022-03-16
EP3330853A4 (en) 2018-08-22

Similar Documents

Publication Publication Date Title
KR102380576B1 (ko) 그래픽 프레임 프로세싱에서 전력 소비를 감소시키기 위한 cpu/gpu dcvs 공동 최적화
TWI606397B (zh) 用以排程一背景任務之方法與器件及相關非暫時性機器可讀媒體
CN104615415B (zh) 一种信息处理方法及电子设备
TWI630610B (zh) 用於動態地調整記憶體狀態轉換計時器之系統及方法
US20140013098A1 (en) Thermal Profile Optimization Techniques
CN106293914B (zh) 一种任务调度的方法及终端
CN103838353B (zh) 一种控制处理器运行的方法及终端
EP2847674A1 (en) Scheduling tasks among processor cores
WO2015051685A1 (zh) 一种任务调度方法、装置及系统
US20140053164A1 (en) Region-Weighted Accounting of Multi-Threaded Processor Core According to Dispatch State
CN103189853A (zh) 用于提供高效情境分类的方法和装置
US10031947B2 (en) Method and apparatus for performing a search operation on heterogeneous computing systems
CN107885306A (zh) 中央处理器的休眠控制方法与设备
US20180032418A1 (en) Application-Specific, Performance-Aware Energy Optimization
KR102060431B1 (ko) 멀티 코어 시스템의 전력 관리 장치 및 방법
US9507641B1 (en) System and method for dynamic granularity control of parallelized work in a portable computing device (PCD)
WO2017113696A1 (zh) 调频参数的调节方法、装置、调频器及移动终端
US20160147577A1 (en) System and method for adaptive thread control in a portable computing device (pcd)
CN103902324B (zh) 系统启动方法和电子设备
WO2017016358A1 (zh) 运算单元的控制方法、系统和计算机存储介质
US9715272B2 (en) Portable electronic device and core swapping method thereof
CN107547742B (zh) 一种用于移动终端的唤醒锁释放方法和装置
US10621008B2 (en) Electronic device with multi-core processor and management method for multi-core processor
CN113056717B (zh) 提供功率管理的方法和装置及计算机可读存储介质
US9971721B2 (en) Method and apparatus for controlling performance of electronic device

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16829724

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15747547

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE