[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN113721989A - Multiprocessor parallel operation system and computer architecture - Google Patents

Multiprocessor parallel operation system and computer architecture Download PDF

Info

Publication number
CN113721989A
CN113721989A CN202110811048.0A CN202110811048A CN113721989A CN 113721989 A CN113721989 A CN 113721989A CN 202110811048 A CN202110811048 A CN 202110811048A CN 113721989 A CN113721989 A CN 113721989A
Authority
CN
China
Prior art keywords
processor
operating system
processors
tasks
shared memory
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.)
Pending
Application number
CN202110811048.0A
Other languages
Chinese (zh)
Inventor
陆放
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to CN202110811048.0A priority Critical patent/CN113721989A/en
Publication of CN113721989A publication Critical patent/CN113721989A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/4401Bootstrapping
    • G06F9/4405Initialisation of multiprocessor systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/54Interprogram communication
    • G06F9/544Buffers; Shared memory; Pipes

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • Multi Processors (AREA)

Abstract

The invention relates to the technical field of computer architecture and software operating system, in particular to a multiprocessor parallel operating system and a computer architecture. The multiprocessor parallel operating system and the computer architecture provided by the invention have the advantages that different function groups can respectively and simultaneously cooperate to run various functions of the operating system, and simultaneously, because the software of each function group runs independently and simultaneously without interference, the speed can be greatly improved, and the traditional complex and low-efficiency operating system is divided into a plurality of simple function group software which are respectively independent and can simultaneously run efficiently, so that the simple and high-efficiency multiprocessor parallel operating system is formed.

Description

Multiprocessor parallel operation system and computer architecture
Technical Field
The invention relates to the technical field of computer architectures and software operating systems, in particular to a multiprocessor parallel operating system and a computer architecture.
Background
The current computer architecture and operating system are based on a single processor running a number of different programs in an interrupted manner, but suffer from the following disadvantages: 1. because the processor needs to save the environment state of the existing program before the processor switches to operate another program midway for returning the processor to continue operating and recovering the environment state for use, frequent switching wastes a large amount of processor time and memory, so that the operating efficiency of the system is greatly reduced; 2. operating systems have become very complex due to the problems of running numerous programs with different functions separately in time segments using a single processor, different programs having different priority and latency response times, and the like.
The operating system using a single processor to execute programs with different functions in a time-sharing manner in an interrupt mode is due to the fact that early chip technology lags behind and the processor is very expensive, but the advantages of the prior art cannot be brought into play by using the traditional computer architecture and the complex software operating system architecture due to the high development of the current chip technology.
In view of this, there is a need for improvements and enhancements in the prior art.
Disclosure of Invention
The invention aims to solve the defects of the prior art and provides a software operating system with simple and efficient structure and a corresponding computer architecture. The invention distributes the operating system function classification to a plurality of processors to run simultaneously respectively so as to avoid or reduce the frequent switching of the processors among different programs and greatly simplify the complexity of the software operating system.
In order to achieve the above object, the technical solution of the multiprocessor parallel operating system provided by the present invention is as follows:
a multi-processor parallel operating system that breaks down an operating system into functional groups according to its functionality, the functional groups comprising one or more operating system functions, each of the functional groups being run with one or more processors.
The invention also has the following preferable technical scheme:
further, the multiprocessor parallel operating system comprises a processor shared memory buffer used for issuing or receiving tasks and transmitting data.
Furthermore, the multiple processors can issue or receive tasks through the processor shared memory buffer, and can use multiple or one processor to complete one or multiple tasks through data transmission.
Further, the processors may each run various operating systems, which may be the same or different.
In another aspect of the present invention, a computer architecture is also provided, which includes the multiprocessor parallel operating system.
Advantageous effects of the invention
The multiprocessor parallel operating system and the computer architecture can comprise software and hardware of a user interface functional group, software and hardware of an application functional group, software and hardware of a large-capacity storage input and output functional group, software and hardware of a network connection functional group, software and hardware of a network browser functional group, software and hardware of an external device functional group and the like. Each functional group mutually communicates and coordinates to issue task transmission data and the like through a processor shared memory buffer area which can be read and written by each processor so as to complete tasks required by users. Thus, different function groups can respectively and simultaneously cooperate to run various functions of the operating system. The complexity is greatly reduced since the software of the respective functional groups only needs to perform a single or a few functions. Meanwhile, because the software of each function group runs independently and simultaneously without interference, the speed can be greatly improved, and the traditional complex and low-efficiency operating system is divided into a plurality of simple function group software which are independent and can run simultaneously and efficiently, thereby forming a simple and efficient multiprocessor parallel operating system. The system has several processors running different or same operating systems, including available traditional operating system, and thus has greatly raised system speed.
Drawings
FIG. 1 illustrates a structural schematic diagram of a computer architecture of the present invention.
Detailed Description
According to the above basic principles of multiprocessor parallel operating systems and computer architectures, there are many different designs, one of which is:
the design includes user interface function processor, application function processor(s), large capacity memory I/O function processor, network connection function processor, network tour processor and external equipment function processor. And task issuing and data exchange are carried out among the functional processors through the processor shared memory buffer area. The function processors run the functions as follows:
1. user interface function processor runs user interface operating system program to execute the following tasks
All user interface functions are run, including but not limited to the following:
A. the user input is read and displayed by presenting the user interface to the display function processor issuing the task.
B. And issuing related tasks to the related processors according to the input of the user and coordinating the operation of the function processing to complete the functions required by the user. Which interfaces with the various processors by issuing and receiving tasks and inputting and outputting data, etc. through the processor shared memory buffer.
2. The application function processor runs one or more applications requested to be run by a user, and receives tasks, input/output data and the like through the processor shared memory buffer to interface with each processor. It may be necessary to run other functional processors to issue tasks through the processor's shared memory buffer.
3. The display function processor includes a display memory to implement the display functions (which may include one or more displays) required by the system. Which interfaces with the various processors by accepting tasks and input/output data, etc. through the processor shared memory buffer. It can run other function processor to issue task through processor shared memory buffer area if necessary
4. The multi-interface high-speed memory (comprising a processor shared memory buffer area which can be read and written by each processor and is used for issuing or receiving tasks and transmitting data, a task issuing area and a data exchange area of each processor are respectively provided in the processor shared memory buffer area, the task issuing area comprises a task issuing instruction number, a task state number and the like, the task issuing instruction number comprises a required task type number, a processor number for executing the task, a data exchange address and the like, the task state number comprises a request type of the task, the task is completed during task execution, and the like), and the task and data handover among the processors and the required storage during the operation of the processors are provided.
5. The mass storage I/O function processor reads data from the mass storage (such as a hard disk and the like) to each processor or vice versa according to the task instruction. Which interfaces with the various processors by accepting tasks and input/output data, etc. through the processor shared memory buffer. It may be necessary to run other functional processors to issue tasks through the processor's shared memory buffer.
6. The network connection function processor processes all network connections (including WIFI and the like) and data transceiving functions. Which interfaces with the various processors by accepting tasks and input/output data, etc. through the processor shared memory buffer. It may be necessary to run other functional processors to issue tasks through the processor's shared memory buffer.
7. And the network browser function processor executes the network browser function. Which interfaces with the various processors by accepting tasks and input/output data, etc. through the processor shared memory buffer. It may be necessary to run other functional processors to issue tasks through the processor's shared memory buffer.
8. And the external equipment function processor is used for processing all external equipment functions. Which interfaces with the various processors by accepting tasks and input/output data, etc. through the processor shared memory buffer. It may be necessary to run other functional processors to issue tasks through the processor's shared memory buffer.
After the system is powered on, each processor (user interface removal processor) respectively starts to run a respective operating system to scan the shared memory buffer of the processor until a task request is found, and then a relevant task program is run.
The user interface processor starts to run an operating system of the user interface processor, then scans the user input and the shared memory buffer area of the processor, if the user input is found, the user input is carried out according to the input of the user, the related sub-processors are assigned with tasks by setting a task state number of an instruction number and the like in the shared memory buffer area of the processor, the data are mutually transmitted with the related processors according to the requirement to complete the task required by the user, and the task state number is set to be in a completion state after the task is completed. If other processors have task requests for the user interface processor, the user interface processor performs corresponding processing according to the request type to complete the request.
The application processor can be one or more than one application which can run one or more than one different application at the same time, and the application processor downloads and runs the application after receiving the task and the application program address through the shared memory buffer of the processor. When the functions needing to be processed by other processors are met in operation, tasks are issued through the shared memory buffer of the processors, and data are transmitted to and from the related sub-processors according to needs. Each processor may also issue tasks and communicate data to and from the associated processor as needed through the processor's shared memory buffer as needed for its other processor functions. Thus, multiple processors can issue or receive tasks and perform data transmission between each other through the processor shared memory buffer, so that multiple or one processor can be used to complete one or more tasks.
Compared with the prior art, the method and the device distribute the functions of the operating system to the function processors for execution, thereby greatly simplifying the complexity of the operating system. The operating systems are distributed in each functional processor to independently run in parallel, and switching is very simple without switching back and forth among different programs, so that tasks can be completed at high speed without a high-performance processor. The software system run by each processor is not complex because of single function or few functions, and each functional processor does not need high-performance devices except for the application functional processor which needs higher-performance devices. The overall computer speed will be greatly increased. I.e., processors that can be produced using a few levels of lower chip technology, can reach and even exceed the computer speed of existing processors produced using the highest level of chip technology. Thereby greatly reducing the production cost and the requirement for high-grade chip technology.
It is to be understood that the invention is not limited to the examples described above, but that modifications and variations may be effected thereto by those of ordinary skill in the art in light of the foregoing description, and that all such modifications and variations are intended to be within the scope of the invention as defined by the appended claims.

Claims (5)

1. A multi-processor parallel operating system which decomposes an operating system into functional groups according to its functions, the functional groups including one or more operating system functions, each of the functional groups being run with one or more processors.
2. A multiprocessor parallel operating system according to claim 1, comprising a processor shared memory buffer for issuing or accepting tasks and transferring data.
3. A multiprocessor parallel operating system according to claim 1, wherein the processors can issue or receive tasks to or from each other via a processor shared memory buffer, and data transfer is performed to enable one or more processors to complete one or more tasks.
4. A multiprocessor parallel operating system according to claim 1, wherein the processors are each operable to run the same or different operating systems.
5. A computer architecture comprising a multiprocessor parallel operating system as claimed in any one of claims 1 to 4.
CN202110811048.0A 2021-07-19 2021-07-19 Multiprocessor parallel operation system and computer architecture Pending CN113721989A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110811048.0A CN113721989A (en) 2021-07-19 2021-07-19 Multiprocessor parallel operation system and computer architecture

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110811048.0A CN113721989A (en) 2021-07-19 2021-07-19 Multiprocessor parallel operation system and computer architecture

Publications (1)

Publication Number Publication Date
CN113721989A true CN113721989A (en) 2021-11-30

Family

ID=78673457

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110811048.0A Pending CN113721989A (en) 2021-07-19 2021-07-19 Multiprocessor parallel operation system and computer architecture

Country Status (1)

Country Link
CN (1) CN113721989A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11972265B2 (en) 2022-04-22 2024-04-30 Red Hat, Inc. Parallel booting operating system

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101149728A (en) * 2007-10-29 2008-03-26 中国科学院计算技术研究所 Multiple core processing system and its management method
CN102354306A (en) * 2011-07-19 2012-02-15 西安翔迅科技有限责任公司 Embedded single-board multi-processor parallel system
CN102521209A (en) * 2011-12-12 2012-06-27 浪潮电子信息产业股份有限公司 Parallel multiprocessor computer design method
CN102541805A (en) * 2010-12-09 2012-07-04 沈阳高精数控技术有限公司 Multi-processor communication method based on shared memory and realizing device thereof
CN103020002A (en) * 2012-11-27 2013-04-03 中国人民解放军信息工程大学 Reconfigurable multiprocessor system
CN111459647A (en) * 2020-06-17 2020-07-28 北京机电工程研究所 DSP multi-core processor parallel operation method and device based on embedded operating system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101149728A (en) * 2007-10-29 2008-03-26 中国科学院计算技术研究所 Multiple core processing system and its management method
CN102541805A (en) * 2010-12-09 2012-07-04 沈阳高精数控技术有限公司 Multi-processor communication method based on shared memory and realizing device thereof
CN102354306A (en) * 2011-07-19 2012-02-15 西安翔迅科技有限责任公司 Embedded single-board multi-processor parallel system
CN102521209A (en) * 2011-12-12 2012-06-27 浪潮电子信息产业股份有限公司 Parallel multiprocessor computer design method
CN103020002A (en) * 2012-11-27 2013-04-03 中国人民解放军信息工程大学 Reconfigurable multiprocessor system
CN111459647A (en) * 2020-06-17 2020-07-28 北京机电工程研究所 DSP multi-core processor parallel operation method and device based on embedded operating system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11972265B2 (en) 2022-04-22 2024-04-30 Red Hat, Inc. Parallel booting operating system

Similar Documents

Publication Publication Date Title
CN102446158B (en) Multi-core processor and multi-core processor set
JP2564805B2 (en) Information processing device
CN101751285B (en) Centralized device virtualization layer for heterogeneous processing units
EP0901659B1 (en) Parallel processor with redundancy of processor pairs and method
CN108416433B (en) Neural network heterogeneous acceleration method and system based on asynchronous event
US9052957B2 (en) Method and system for conducting intensive multitask and multiflow calculation in real-time
CN103221937A (en) Load/store circuitry for a processing cluster
CN112199173B (en) Data processing method for dual-core CPU real-time operating system
CN103019838B (en) Multi-DSP (Digital Signal Processor) platform based distributed type real-time multiple task operating system
CN104714846A (en) Resource processing method, operating system and equipment
JP2001142842A (en) Dma handshake protocol
CN101013415A (en) Thread aware distributed software system for a multi-processor array
CN102135950A (en) On-chip heterogeneous multi-core system based on star type interconnection structure, and communication method thereof
CN109857702B (en) Laser radar data read-write control system and chip based on robot
CN115203142A (en) Multi-core real-time communication system and method
CN112131176B (en) FPGA (field programmable Gate array) quick local reconstruction method based on PCIE (peripheral component interface express)
CN111857669A (en) Software and hardware decoupling software radar system, real-time design method and server
JP5578713B2 (en) Information processing device
CN108415859B (en) Hardware acceleration circuit for laser gyroscope data
CN113721989A (en) Multiprocessor parallel operation system and computer architecture
EP1987428A2 (en) Real-time distributed processor environment
CN205103599U (en) Cross -border trade BPO uses cloud terminating set
CN109992539B (en) Double-host cooperative working device
CN112506676A (en) Inter-process data transmission method, computer device and storage medium
US20230153153A1 (en) Task processing method and apparatus

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