Unlock instant, AI-driven research and patent intelligence for your innovation.

Inter-core communication method

An inter-core communication and orientation technology, applied in the field of inter-core communication, can solve the problems of not being able to maximize sharing, reducing the utilization of shared memory space, and not being able to apply for shared memory.

Pending Publication Date: 2021-09-10
上海擎昆信息科技有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that after splitting, each core cannot apply for shared memory of other cores, resulting in failure to maximize sharing and reducing the utilization of shared memory space

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Inter-core communication method
  • Inter-core communication method
  • Inter-core communication method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] figure 1 It is a flow chart of the inter-core communication method provided by the embodiment of the present invention. Such as figure 1 As shown, the inter-core communication method in this embodiment includes:

[0046] Step 1: Receive the memory block application request from the sender. The memory block application request includes: sending orientation flag, receiving orientation flag and user data length.

[0047] Step 2: traverse the target memory block according to the memory block application request, and determine the first memory block. The target memory block is a plurality of divided memory blocks obtained by randomly dividing the shared memory space by the main core; the first memory block is a divided memory block greater than or equal to the memory required by the sender.

[0048] Step 3: Determine the offset address of the user data according to the first memory block and the memory block application request.

[0049] Step 4: The sender communicates ...

Embodiment 2

[0083] In this embodiment, an inter-core communication method is introduced in detail by taking a sender and a receiver as examples.

[0084] In Embodiment 2, the main core (manager) is the C1 core, the sender is the C2 core, and the receiver is the C3 core, and the C2 core needs to send the message "CMD=0x10, DATA=hello world" to the C3 core, shared memory The total space is 20KB=20*1024B, and the shared memory space is divided into 160 64B small memory blocks and 10 1024B large memory blocks. The basic format definition of each memory block data storage is shown in Table 2:

[0085] Table 2 Basic format of data storage

[0086] send bearing sign receiving bearing sign user data length User data

[0087] Among them, the first three fields constitute the control field, and the total number of bytes occupied is 4B, among which the number of bytes occupied by the sending position mark is 1B, the number of bytes occupied by the receiving position mark is 1B,...

Embodiment 3

[0102] In this embodiment, an inter-core communication method is introduced in detail by taking one sender and two receivers as an example.

[0103] In Embodiment 3, the main core (manager) is the C1 core, the sender is the C2 core, the receiver is the C3 core and the C4 core, and the C2 core needs to send the message "CMD=0x10, DATA=hello world" to the C3 core and C4 core. The quad-core bit flags and shared memory base address definition (take 32-bit address as an example) are shown in Table 5:

[0104] Table 5 Quad-core bit flags and shared memory base address definitions

[0105] nuclear sequence number bit flag Shared memory base address C1 0x01 0x60000000 C2 0x02 0x80000000 C3 0x04 0xA0000000 C4 0x08 0xC0000000

[0106] Except for the above, others are the same as in Embodiment 2, and will not be repeated here.

[0107] Such as image 3 As shown, the process of communication between the three cores is:

[0108] (1) C1 initi...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an inter-core communication method. The method comprises the following steps: receiving a memory block application request of a sender; traversing target memory blocks according to the memory block application request, and determining a first memory block, wherein the target memory blocks are a plurality of segmented memory blocks obtained by randomly segmenting the shared memory space by a main core, and the first memory block is a segmented memory block greater than or equal to the memory required by the sender; determining an offset address of the user data according to the first memory block and the memory block application request; and communicating, by the sender, with a receiver according to the offset address. A shared memory space is divided into a plurality of memory blocks; all the memory blocks are managed by the main core; the main core searches for the appropriate memory block according to the request of the sender; the sender and the receiver can communicate only by knowing the offset address of the memory block; the shared space division method improves the utilization rate of the shared memory space.

Description

technical field [0001] The present invention relates to the technical field of inter-core communication, in particular to an inter-core communication method. Background technique [0002] When performing inter-core communication, the following methods are usually used to divide the shared memory space: (1) Divide the shared memory space into several small memory blocks with fixed lengths, and the applicant traverses and retrieves the first memory block, which is locked and used . This method divides small memory blocks into fixed lengths, which cannot cope with the scenario of large data storage space application, and has the problem of low space utilization for a small amount of data. (2) Divide the shared memory space to each core for management. The disadvantage of this method is that after splitting, each core cannot apply for the shared memory of other cores, resulting in the inability to maximize sharing and reducing the utilization rate of the shared memory space. ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F15/173
CPCG06F15/17331
Inventor 董华进是元吉何波
Owner 上海擎昆信息科技有限公司