CN115934365B - Task scheduling coupling system applied to CPU - Google Patents

Task scheduling coupling system applied to CPU Download PDF

Info

Publication number
CN115934365B
CN115934365B CN202310224321.9A CN202310224321A CN115934365B CN 115934365 B CN115934365 B CN 115934365B CN 202310224321 A CN202310224321 A CN 202310224321A CN 115934365 B CN115934365 B CN 115934365B
Authority
CN
China
Prior art keywords
task
module
unit
thread
cpu
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202310224321.9A
Other languages
Chinese (zh)
Other versions
CN115934365A (en
Inventor
龙小昂
胡丽华
朱丹
吴辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
SHENZHEN HUALONG XUNDA INFORMATION TECHNOLOGY CO LTD
Original Assignee
SHENZHEN HUALONG XUNDA INFORMATION TECHNOLOGY CO LTD
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 SHENZHEN HUALONG XUNDA INFORMATION TECHNOLOGY CO LTD filed Critical SHENZHEN HUALONG XUNDA INFORMATION TECHNOLOGY CO LTD
Priority to CN202310224321.9A priority Critical patent/CN115934365B/en
Publication of CN115934365A publication Critical patent/CN115934365A/en
Application granted granted Critical
Publication of CN115934365B publication Critical patent/CN115934365B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Debugging And Monitoring (AREA)

Abstract

The invention provides a task scheduling coupling system applied to a CPU (Central processing Unit), which comprises a server, a CPU module, an occupation detection module, a priority management module and a response management module, wherein the occupation detection module is used for detecting threads of the CPU module to acquire execution states of all threads of the CPU module, the priority management module is used for detecting all tasks processed through the CPU module to acquire priorities corresponding to all processed tasks, and the response management module is used for collecting task data of the occupation detection module and the priority management module and evaluating current tasks according to the collected task data. According to the invention, the task management unit and the evaluation unit are mutually matched, so that threads in the task execution process are evaluated, the high efficiency and the accuracy of the whole system on task scheduling are improved, and the whole system is ensured to autonomously and dynamically schedule the tasks.

Description

Task scheduling coupling system applied to CPU
Technical Field
The invention relates to the technical field of resource allocation of a CPU (Central processing Unit), in particular to a task scheduling coupling system applied to the CPU.
Background
The CPU module is a digital operation controller with a microprocessor for automatic control, and controls various production equipment through digital or analog input and output, and is an indispensable part of the industrial automatic control field. At present, the production equipment is basically provided with traditional CPU module equipment or CPU modules based on other foreign main control chips such as Intel, ARM and the like. The traditional CPU module and the control circuit are connected in a wired mode, wiring is complex, time and labor are wasted, and transmission distance is limited by the length of the wires; the CPU module based on the foreign main control chip is easily limited by foreign monopoly.
For example, CN112130977B discloses a task scheduling method, device, equipment and medium, and the current parallel programming language divides the initialization task into a plurality of subtasks that can be executed in parallel, and the operating system distributes the subtasks to each CPU according to the hardware condition. However, in the allocation mode, the operating system scheduling module only mechanically schedules the subtasks, which results in frequent access operation between the subtasks running in different CPUs when the subtasks with higher coupling degree are allocated to different CPUs, so that the subtask blocking problem is caused, and therefore, the task execution efficiency is low, and further, the data processing efficiency of the whole computer system is reduced, and the performance of the computer system is reduced.
Another typical task scheduling method disclosed in the prior art, such as CN111026514B, is that when the task amount of the task to be processed is large, such as when large-scale machine learning data needs to be processed, the efficiency of the above manner of performing task allocation and scheduling by using the main processor is low, which affects the processing efficiency of the computer system.
Looking at a distributed task scheduling method and task scheduling system disclosed in the prior art of CN102387208B, after receiving the task end response of the preceding task machine, the data management center reads the stored task table, and then sends a task start instruction to the following task machine corresponding to the preceding task machine according to the dependency relationship between the tasks in the task table, so that the following task machine executes the corresponding task. The plurality of task machines do not communicate directly with each other. The above-described conventional task management method has the following problems: (1) timing scheduling can only be performed for stand-alone tasks. 2) During the execution of the task machine, if the task fails, an alarm cannot be defined. (3) The task is maintained and managed without a unified interface, a user has to log on the operated task machine to check manually through a command line, and under the condition that the number of the task machines and the number of the tasks are large, the time and the labor are very consumed, and the level of automatic management cannot be reached.
The invention is designed for solving the problems that the interactivity of the execution task is poor, the intelligent degree is low, the execution of the task cannot be dynamically adjusted, the coordination of the task scheduling is poor, the execution efficiency of the task is low and the like in the prior art.
Disclosure of Invention
The invention aims to provide a task scheduling coupling system applied to a CPU (Central processing Unit) aiming at the defects existing at present.
In order to overcome the defects in the prior art, the invention adopts the following technical scheme:
the task scheduling coupling system comprises a server, an occupancy detection module, a priority management module and a response management module, wherein the server is respectively connected with the occupancy detection module, the priority management module and the response management module, the occupancy detection module is used for detecting threads of a CPU module to obtain execution states of all threads of the CPU module, the priority management module is used for detecting all tasks processed by the CPU module to obtain priorities corresponding to all processed tasks, and the response management module is used for collecting execution state data of the occupancy detection module and task data of the priority management module and evaluating the tasks currently processed by the CPU module according to the collected state data and task data;
the response management module comprises a task management unit and an evaluation unit, wherein the task management unit is used for collecting task data of the occupation detection module and the priority management module, and the evaluation unit evaluates task threads of the current CPU module according to the execution state data and the task data to determine a scheduling strategy of the task threads;
the occupation detection module comprises a thread occupation detection unit and a data storage unit, wherein the thread occupation detection unit is used for detecting the thread occupation of the CPU module, and the data storage unit is used for storing the data detected by the thread occupation detection unit;
the thread occupation detection unit comprises an executable program and a memory, wherein the executable program is executed on the CPU module to acquire the occupation condition of threads of each channel of the CPU module, and the memory is used for storing data corresponding to the occupation condition of the executable program.
Optionally, the priority management module includes a task detection unit and a priority management unit, where the task detection unit is configured to detect a task processed by the CPU module to obtain a key working node of the task, and the priority management unit determines, according to a resource occupancy rate of the key working node, whether a priority corresponding to the task is balanced and analyzes the priority;
the task detection unit acquires a key working node used for executing a task to obtain the resource occupancy rate of the key working node;
and if the resource utilization rate of the operating key working node reaches the limit, the non-key working node is redistributed to other working nodes.
Optionally, the task management unit acquires the occupation condition of the thread occupation detection unit and the resource occupation rate of the key working node, transmits the acquired occupation condition of the thread occupation detection unit and the acquired resource occupation rate of the key working node to the evaluation unit, and triggers the evaluation unit to execute the task of the CPU module.
Optionally, the evaluation unit obtains the occupancy condition of the thread occupancy detection unit and the resource occupancy rate of the key working node, and satisfies the following formula during scheduling:
Figure SMS_1
wherein R is ni_input Increased resource occupancy for work nodes after task scheduling, O ni For the resource occupancy rate of the original working node, R ni The maximum limit value of the proportion of occupied resources for the working node is set by the system;
if the above formula is not satisfied, the task is reassigned.
Optionally, the evaluation unit needs to satisfy the following formula when reassigning the task:
Figure SMS_2
in the formula, IPOC is the reassigned task number, ILP j For the average number of instructions per cycle when the jth thread executes in the total time, the load is set by the system j The specific weight of the actual execution time of the task thread in the execution of the j-th thread completed in the total time is the specific weight of the actual execution time of the task thread in the total time; j is the current thread count, and m is the total number of threads.
Optionally, the task scheduling coupling system further includes an interaction module, where the interaction module is configured to perform interaction display to an operator, so as to display a current task scheduling state to the operator;
the interaction module comprises a prompt unit and an early warning unit, the early warning unit triggers early warning according to the evaluation result of the evaluation unit, and the prompt unit prompts the early warning signal of the early warning unit to the operator.
The beneficial effects obtained by the invention are as follows:
1. the task management unit and the evaluation unit are matched with each other, so that threads in the task execution process are evaluated, the efficiency and the accuracy of the whole system on task scheduling are improved, and the whole system is ensured to perform dynamic scheduling on the tasks autonomously;
2. the thread occupation detection unit and the data storage unit are matched with each other, so that the occupation condition of the CPU module can be accurately detected, and the accuracy and the high efficiency of the whole system on task scheduling are improved;
3. the task is scheduled through the evaluation result of the evaluation unit, so that the synergy of task scheduling and the high efficiency of task scheduling are improved, and the whole system has the advantages of high automation degree, high task scheduling interactivity and high scheduling efficiency;
4. through the cooperation of suggestion unit and early warning unit for the operator can grasp current early warning dynamically, and grasp the execution state of task in real time, promotes the interactive travelling comfort of entire system.
Drawings
The invention will be further understood from the following description taken in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments. Like reference numerals designate corresponding parts throughout the different views.
Fig. 1 is a schematic block diagram of the overall structure of the present invention.
Fig. 2 is a schematic diagram of an evaluation flow of the resource occupancy rate by the evaluation unit according to the present invention.
FIG. 3 is a schematic diagram of an evaluation flow of task scheduling reassignment by the evaluation unit of the present invention.
Fig. 4 is a schematic diagram of an evaluation unit, an early warning unit and a prompt unit according to the present invention.
FIG. 5 is a partial block schematic diagram of a CPU module according to the present invention.
Detailed Description
The following embodiments of the present invention are described in terms of specific examples, and those skilled in the art will appreciate the advantages and effects of the present invention from the disclosure herein. The invention is capable of other and different embodiments and its several details are capable of modification and variation in various respects, all without departing from the spirit of the present invention. The drawings of the present invention are merely schematic illustrations, and are not intended to be drawn to actual dimensions. The following embodiments will further illustrate the related art content of the present invention in detail, but the disclosure is not intended to limit the scope of the present invention.
Embodiment one:
according to fig. 1, fig. 2, fig. 3, fig. 4, and fig. 5, the present embodiment provides a task scheduling coupling system applied to a CPU, where the task scheduling coupling system includes a server, and further includes an occupancy detection module, a priority management module, and a response management module, where the server is connected to the occupancy detection module, the priority management module, and the response management module, respectively, and the occupancy detection module is configured to detect threads of the CPU module to obtain execution states of each thread of the CPU module, and the priority management module is configured to detect each task processed by the CPU module to obtain priorities corresponding to each processed task, and the response management module is configured to collect execution state data of the occupancy detection module and task data of the priority management module, and evaluate, according to the collected state data and task data, a task currently processed by the CPU module;
the CPU module is also in control connection with the server, the occupancy detection module, the priority management module and the response management module, and is used for carrying out centralized control on the occupancy detection module, the priority management module and the response management module based on the CPU module so as to realize accurate scheduling of each task and promote efficient execution of the CPU module;
in this embodiment, the occupancy detection module, the priority management module, and the response management module may be preset on the control bus of the CPU module, so as to implement task management or task allocation for each task executed by the CPU module;
optionally, the occupation detection module includes a thread occupation detection unit and a data storage unit, where the thread occupation detection unit is used to detect the thread occupation of the CPU module, and the data storage unit is used to store the data detected by the thread occupation detection unit;
the thread occupation detection unit comprises an executable program and a memory, wherein the executable program is executed on the CPU module to acquire the occupation condition of threads of each channel of the CPU module, and the memory is used for storing data corresponding to the occupation condition of the executable program;
meanwhile, in the process of detecting the thread occupation of the CPU module, the executable program or the executable tool is required to run on the CPU module so as to obtain the occupation condition of the threads of each channel of the CPU module, thereby obtaining the data corresponding to the occupation condition of the CPU module;
the executable program or the executable tool is a technical means well known to those skilled in the art, and those skilled in the art can query related technical manuals to obtain the technology, so that the description is omitted in this embodiment;
the data storage unit comprises at least one memory, and the memory is used for storing the data obtained by the detection of the thread occupation detection unit, so that a group of detection data can be obtained by each detection and stored in the at least one memory, and the occupation data of each thread can be inquired, so that the accuracy and the high efficiency of the whole system in task scheduling are improved;
in addition, the thread occupation detection unit and the data storage unit are matched with each other, so that the occupation condition of the CPU module can be accurately detected, and the accuracy and the high efficiency of the whole system on task scheduling are improved;
optionally, the priority management module includes a task detection unit and a priority management unit, where the task detection unit is configured to detect a task processed by the CPU module to obtain a key working node of the task, and the priority management unit determines, according to a resource occupancy rate of the key working node, whether a priority corresponding to the task is balanced and analyzes the priority;
the task detection unit acquires a key working node used for executing a task to obtain the resource occupancy rate of the key working node;
the method comprises the steps that when the resource utilization rate of a key operating node reaches a limit, non-key operating nodes are redistributed to other operating nodes;
the priority management unit evaluates the evaluation priority index level (t) of the current task according to the resource occupancy rate of the key working node:
Figure SMS_3
wherein t is the execution time of the current task, n is the total number of threads currently executed in the CPU module, NS i The normalized performance speed ratio of the currently executed thread i in the CPU module is as follows:
Figure SMS_4
wherein p is i For the priority of thread i, where the priority of the thread task is between 1 and 10, and the higher the value, the higher the priority, i.e. the higher the execution is, in this embodiment, the default base priority is 5, CYC is the number of sampling clock cycles, INST is the total number of instructions that a thread has committed after CYC clock cycles, IPC i alone The theoretical performance of each thread when independently running is set by a system and preset in a database of a priority management unit;
if the evaluation priority index level (t) is lower than a set monitoring threshold value group, the priority of the currently executed task is unbalanced, and the reassignment of the task is triggered;
meanwhile, the set monitoring threshold group is set by an operator or a system, different values are set in different application scenes, and the set monitoring threshold group is compared with the evaluation priority index level (t), which is a technical means well known to those skilled in the art, and those skilled in the art can inquire about related technical manuals to obtain the technology, so that the detailed description is omitted in the embodiment;
the response management module comprises a task management unit and an evaluation unit, wherein the task management unit is used for collecting task data of the occupation detection module and the priority management module, and the evaluation unit evaluates task threads of the current CPU module according to execution state data and task data to determine a scheduling strategy of the task;
optionally, the task management unit acquires the occupation condition of the thread occupation detection unit and the resource occupation rate of the key working node, transmits the acquired occupation condition of the thread occupation detection unit and the acquired resource occupation rate of the key working node to the evaluation unit, and triggers the evaluation unit to execute the task of the CPU module;
the task management unit and the evaluation unit are matched with each other, so that threads in the task execution process are evaluated, the efficiency and the accuracy of the whole system on task scheduling are improved, and the whole system is ensured to autonomously and dynamically schedule the tasks;
optionally, the evaluation unit obtains the occupancy condition of the thread occupancy detection unit and the resource occupancy rate of the key working node, and satisfies the following formula during scheduling:
Figure SMS_5
wherein R is ni_input Increased resource occupancy for work nodes after task scheduling, O ni For the resource occupancy rate of the original working node, R ni The maximum limit value of the occupied resource ratio for the working node is set by the system;
if the above formula is not satisfied, reassigning the task;
optionally, the evaluation unit needs to satisfy the following formula when reassigning the task:
Figure SMS_6
in the formula, IPOC is the reassigned task number, ILP j For the average number of instructions per cycle when the jth thread executes in the total time, the load is set by the system j The specific weight of the actual execution time of the task thread in the execution of the j-th thread completed in the total time is the specific weight of the actual execution time of the task thread in the total time; j is the current thread number, m is the total number of threads;
scheduling the tasks through the evaluation result of the evaluation unit so as to improve the synergy of task scheduling and the high efficiency of task scheduling, so that the whole system has the advantages of high automation degree, high task scheduling interactivity and high scheduling efficiency;
optionally, the task scheduling coupling system further includes an interaction module, where the interaction module is configured to perform interaction display to an operator, so as to display a current task scheduling state to the operator;
the interaction module comprises a prompt unit and an early warning unit, wherein the early warning unit triggers early warning according to the evaluation result of the evaluation unit, and the prompt unit prompts the early warning signal of the early warning unit to the operator;
the early warning unit compares the evaluation unit of the evaluation unit with a set early warning threshold value, if the condition for triggering early warning is met, the early warning is triggered, and the early warning is transmitted to the prompting unit so as to prompt or display an early warning signal to an operator in cooperation with the prompting unit;
the comparison and the triggering of the early warning by the early warning unit according to the evaluation result of the evaluation unit are well known technical means by those skilled in the art, and those skilled in the art can query the related technical manual to obtain the technology, so in this embodiment, the details are not repeated;
the prompt unit comprises a prompt execution program and prompt information, wherein the prompt execution program is executed on the CPU module and converts the early warning information of the early warning unit into the prompt information so as to display the prompt information to the operator;
after the prompt information is displayed to the operator, the operator can grasp task execution, an evaluation result of the evaluation unit and an early warning state of the early warning unit in real time;
through the cooperation of the prompting unit and the early warning unit, an operator can dynamically grasp the current early warning, grasp the execution state of a task in real time, and improve the interaction comfort of the whole system.
Embodiment two:
this embodiment should be understood to include at least all the features of any one of the foregoing embodiments, and further improve on the foregoing embodiments, and according to the embodiments shown in fig. 1, 2, 3, 4, and 5, the CPU module further includes a loongson processor, a loongson bridge chip, a memory, a power interface card, a network interface card, a CFast interface card, a touch display panel, a debian10 system, and an openplc platform;
the Loongson processor, the Loongson bridge chip and the memory are arranged on the PCB bottom plate in a surface mount mode; the Loongson bridge chip and the PCB bottom plate are connected with the Loongson processor through a circuit; the Loongson bridge chip forms 3 slots on the PCB bottom plate through a circuit; the power interface card is arranged in a power slot of the PCB base plate and is connected with the Loongson bridge piece; the network interface card is arranged in a network slot of the PCB bottom plate and is connected with the Loongson bridge piece; the CFast interface card is arranged in a CFast interface slot of the PCB base plate and connected with the Loongson bridge piece; the touch display panel is connected with the CFast interface card through a flat cable;
wherein, the Loongson processor: the CPU is used for calculating and signal processing functions of the CPU module; loongson bridge piece: the Loongson processor is connected with the Loongson processor and used for signal processing bridging; memory: the device is connected with the Loongson processor and is used for caching bottom data; a power interface card: the CPU module is connected with the Loongson bridge chip and is used for external power supply connection of the CPU module; CFast interface card: the Loongson bridge chip is connected with the Loongson bridge chip and used for operating system carriers and data storage; the network interface card is connected with the Loongson bridge chip and used for Ethernet data communication; touch display panel: the CFast interface card is connected with the CFast interface card, receives and displays video signals and user touch information;
the invention realizes the 100% localization goal of core devices such as CPU and the like through the completely autonomous controllable domestic CPU module, eliminates the information potential safety hazard from the root, and provides a basic hardware platform for various control systems with information safety requirements.
The foregoing disclosure is only a preferred embodiment of the present invention and is not intended to limit the scope of the invention, so that all equivalent technical changes made by applying the description of the present invention and the accompanying drawings are included in the scope of the present invention, and in addition, elements in the present invention can be updated as the technology develops.

Claims (5)

1. The task scheduling coupling system is applied to a CPU and comprises a server and a CPU module, and is characterized by further comprising an occupation detection module, a priority management module and a response management module, wherein the server is respectively connected with the CPU module, the occupation detection module, the priority management module and the response management module, the occupation detection module is used for detecting threads of the CPU module to acquire execution states of all threads of the CPU module, the priority management module is used for detecting all tasks processed by the CPU module to acquire priorities corresponding to all processed tasks, and the response management module is used for acquiring execution state data of the occupation detection module and task data of the priority management module and evaluating the tasks currently processed by the CPU module according to acquired state data and task data;
the response management module comprises a task management unit and an evaluation unit, wherein the task management unit is used for collecting execution state data of the occupation detection module and task data of the priority management module, and the evaluation unit evaluates task threads of the current CPU module according to the execution state data and the task data to determine a scheduling strategy of the task threads;
the occupation detection module comprises a thread occupation detection unit and a data storage unit, wherein the thread occupation detection unit is used for detecting the thread occupation of the CPU module, and the data storage unit is used for storing the data detected by the thread occupation detection unit;
the thread occupation detection unit comprises an executable program and a memory, wherein the executable program is executed on the CPU module to acquire the occupation condition of threads of each channel of the CPU module, and the memory is used for storing data corresponding to the occupation condition of the executable program;
the priority management module comprises a task detection unit and a priority management unit, wherein the task detection unit is used for detecting a task processed by the CPU module so as to obtain a key working node of the task processed by the CPU module, and the priority management unit determines whether the priority corresponding to the task is balanced or not for analysis according to the resource occupancy rate of the key working node;
the task detection unit acquires a key working node used for executing a task to obtain the resource occupancy rate of the key working node;
the method comprises the steps that when the resource utilization rate of a key operating node reaches a limit, non-key operating nodes are redistributed to other operating nodes;
the priority management unit evaluates the evaluation priority index level (t) of the current task according to the resource occupancy rate of the key working node:
Figure QLYQS_1
wherein t is the execution time of the current task, n is the total number of threads currently executed in the CPU module, NS i The normalized performance speed ratio of the currently executed thread i in the CPU module is as follows:
Figure QLYQS_2
;/>
wherein p is i The priority of the thread i is that the priority of the thread task is between 1 and 10, and the higher the value is, the higher the priority is, namely the higher the execution is, the faster the default basic priority is 5, CYC is the sampling clock cycle number, INST is the total number of instructions submitted by a certain thread after CYC clock cycles, IPC i alone The theoretical performance of each thread when independently running is set by a system and preset in a database of a priority management unit;
if the evaluation priority index level (t) is lower than the set monitoring threshold group, the priority of the currently executed task is unbalanced, and the reassignment of the task is triggered.
2. The task scheduling coupling system for a CPU according to claim 1, wherein the task management unit obtains an occupancy of the thread occupancy detection unit and a resource occupancy of the critical working node, transmits the acquired occupancy of the thread occupancy detection unit and the acquired resource occupancy of the critical working node to the evaluation unit, and triggers the execution of the task by the evaluation unit on the CPU module.
3. The task scheduling coupling system for a CPU according to claim 2, wherein the evaluation unit obtains an occupancy condition of the thread occupancy detection unit and a resource occupancy rate of the critical work node, and satisfies the following formula when scheduling:
Figure QLYQS_3
wherein R is ni_input Increased resource occupancy for work nodes after task scheduling, O ni For the resource occupancy rate of the original working node, R ni The maximum limit value of the occupied resource ratio for the working node is set by the system;
if the above formula is not satisfied, the task is reassigned.
4. A task scheduling coupling system applied to a CPU according to claim 3, wherein the evaluation unit, when reassigning the task, needs to satisfy the following formula:
Figure QLYQS_4
in the formula, IPOC is the reassigned task number, ILP j For the average number of instructions per cycle when the jth thread executes in the total time, the load is set by the system j The specific weight of the actual execution time of the task thread in the execution of the j-th thread completed in the total time is the specific weight of the actual execution time of the task thread in the total time; j is the current thread count, and m is the total number of threads.
5. The task scheduling coupling system for a CPU of claim 4, further comprising an interactive module for interactive display to an operator to display a current task scheduling status to the operator;
the interaction module comprises a prompt unit and an early warning unit, the early warning unit triggers early warning according to the evaluation result of the evaluation unit, and the prompt unit prompts the early warning signal of the early warning unit to the operator.
CN202310224321.9A 2023-03-10 2023-03-10 Task scheduling coupling system applied to CPU Active CN115934365B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310224321.9A CN115934365B (en) 2023-03-10 2023-03-10 Task scheduling coupling system applied to CPU

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310224321.9A CN115934365B (en) 2023-03-10 2023-03-10 Task scheduling coupling system applied to CPU

Publications (2)

Publication Number Publication Date
CN115934365A CN115934365A (en) 2023-04-07
CN115934365B true CN115934365B (en) 2023-05-23

Family

ID=85825466

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310224321.9A Active CN115934365B (en) 2023-03-10 2023-03-10 Task scheduling coupling system applied to CPU

Country Status (1)

Country Link
CN (1) CN115934365B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116932230B (en) * 2023-09-15 2023-12-08 湖南马栏山视频先进技术研究院有限公司 Video rendering method based on dynamic task scheduling

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014139851A (en) * 2014-05-08 2014-07-31 Fujitsu Ltd Multi-core processor system, control method of multi-core processor system and control program of multi-core processor system

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102360310B (en) * 2011-09-28 2014-03-26 中国电子科技集团公司第二十八研究所 Multitask process monitoring method in distributed system environment
CN106844027A (en) * 2017-01-13 2017-06-13 广西电网有限责任公司电力科学研究院 A kind of method for scheduling task based on node load
CN115756866A (en) * 2022-11-30 2023-03-07 Oppo广东移动通信有限公司 Load balancing method, device and storage medium

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014139851A (en) * 2014-05-08 2014-07-31 Fujitsu Ltd Multi-core processor system, control method of multi-core processor system and control program of multi-core processor system

Also Published As

Publication number Publication date
CN115934365A (en) 2023-04-07

Similar Documents

Publication Publication Date Title
CN110727512B (en) Cluster resource scheduling method, device, equipment and storage medium
CN109471727A (en) A kind of task processing method, apparatus and system
CN103729248B (en) A kind of method and apparatus of determination based on cache perception task to be migrated
CN115934365B (en) Task scheduling coupling system applied to CPU
CN106843170B (en) Method for scheduling task based on token
US10929181B1 (en) Developer independent resource based multithreading module
CN101341468A (en) Information processing apparatus, computer, resource distribution method and resource distribution program
CN112579267A (en) Decentralized big data job flow scheduling method and device
CN111045911A (en) Performance test method, performance test device, storage medium and electronic equipment
CN115827256B (en) Task transmission scheduling management system for multi-core memory and calculation integrated accelerator network
CN102708006A (en) Processing optimization load adjustment
CN113157379A (en) Cluster node resource scheduling method and device
CN205472063U (en) Lift control cabinet test system
Chang A study of factors affecting due-date predictability in a simulated dynamic job shop
CN109739634A (en) A kind of atomic task execution method and device
CN109840141A (en) Thread control method, device, electronic equipment and storage medium based on cloud monitoring
US20070150899A1 (en) Semaphore management method and computer product
KR20210147594A (en) Edge computing devices and methods that provide optimization for energy data collection and management
CN113658351B (en) Method and device for producing product, electronic equipment and storage medium
CN105378650B (en) Method and apparatus for controlling the operation mode of processing module
CN117311990B (en) Resource adjustment method and device, electronic equipment, storage medium and training platform
CN117130888A (en) Automatic server tuning method and system based on historical data and machine learning
CN117435412A (en) Server testing method and device, storage medium and electronic equipment
CN109100440A (en) On-line chromatograph control analysis system and its application method based on network server
CN113888028A (en) Patrol task allocation method and device, electronic equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant