CN107453843A - A kind of data transfer of computer system - Google Patents
A kind of data transfer of computer system Download PDFInfo
- Publication number
- CN107453843A CN107453843A CN201710643764.6A CN201710643764A CN107453843A CN 107453843 A CN107453843 A CN 107453843A CN 201710643764 A CN201710643764 A CN 201710643764A CN 107453843 A CN107453843 A CN 107453843A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- basic matrix
- matrix
- structural
- 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
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0002—Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/313—Selection or weighting of terms for indexing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/80—Information retrieval; Database structures therefor; File system structures therefor of semi-structured data, e.g. markup language structured data such as SGML, XML or HTML
- G06F16/84—Mapping; Conversion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
- G06F40/151—Transformation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/0001—Systems modifying transmission characteristics according to link quality, e.g. power backoff
- H04L1/0006—Systems modifying transmission characteristics according to link quality, e.g. power backoff by adapting the transmission format
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
- H04L1/0056—Systems characterized by the type of code used
- H04L1/0057—Block codes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L1/00—Arrangements for detecting or preventing errors in the information received
- H04L1/004—Arrangements for detecting or preventing errors in the information received by using forward error control
- H04L1/0056—Systems characterized by the type of code used
- H04L1/0061—Error detection codes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
Abstract
The invention discloses a kind of data transfer of computer system, the Transmission system merges structural data with unstructured data to be transmitted in one file, enable structural data and non-structural data are transmitted, exchange synchronous with when sharing in a network, data nonsynchronous problem when avoiding separated transmission be present;This method is by introducing free factor r to structural data codingfAs one degree of freedom, mitigate in spreading factor zfUnder the second basic matrix of the generation the problem of error floor is higher be present, improve the reliability of data transfer;The network equipment of the Transmission system can determine the clock frequency ratio relation of data reception module and data outputting module in different clock-domains, asynchronous FIFO is logically not used, but the output speed of counter controls data is used, so as to not only avoid the risk that the data caused by asynchronous FIFO queue are overflowed.
Description
Technical field
The present invention relates to data communication technology field, and in particular to a kind of data transfer of computer system.
Background technology
Data transfer is the communication process that data are sent to another place from a place.Data transmission system generally by
Transmission channel and the data circuit terminating equipment at channel both ends (DCE) composition, in some cases, in addition to channel both ends are answered
Use equipment.Transmission channel can be a special communication channel, can also be by data switched network, switched telephone network or other classes
The exchanging network of type provides.The input-output equipment of data transmission system is terminal or computer, is referred to as data terminal equipment
(DTE) data message that, it is sent be typically all letter, the combination of numbers and symbols, in order to transmit these information, just need by
Each letter, numeral or symbol are represented with binary code.
Low-density checksum (low density parity check, abbreviation LDPC) code is that one kind has sparse verification
The Linear block coding of matrix.Because LDPC not only has the superperformance for approaching shannon limit, and translated with flexible structure
The characteristics of code complexity is relatively low, therefore can be widely used in various communication systems.
When being carried out data transmission using LDPC, it is necessary first to construct a basic matrix for Wireless Telecom Equipment.Due to
May be that Wireless Telecom Equipment distributes different size of wireless resource block according to the difference of transmission demand in wireless communication system
(resource block, abbreviation RB), and under different size of RB, the LDPC that Wireless Telecom Equipment is supported grows also each not phase
Together.To enable the LDPC of the compatible different code length of Wireless Telecom Equipment, one can be previously generated by m row n column matrix elements institute
The basic matrix of composition, wherein, the product of m=n-k, k and spreading factor is the length of structural data in LDPC, and m, n, k's takes
Value is positive integer, and is pre-set at spreading factor corresponding to each LDPC appearance.But work as and use multiple different extensions
When the same basic matrix of factor pair is deployed, it is generally difficult to which each check matrix for ensureing to be formed has good ring
Long characteristic.
Two class data are generally related in the data transmission:Structural data and unstructured data.Generally, data transfer
When structural data and unstructured data are separately handled.But structural data and unstructured data in many cases
It is closely related, there is strong correlation, if separately transmission can brings many problems with processing.
At present, requirement of the various communications protocol to message transmission rate, it is difficult flexibly suitable even more to allow IC hardware interface designs
With various application scenarios.Under some complex scenes, it is also necessary to increase asynchronous FIFO (FIFO, First Input First
Output) queue.However, asynchronous FIFO queue is not omnipotent, because asynchronous FIFO queue needs to have in two clock zones
Corresponding interface, and just can guarantee that asynchronous FIFO queue plays a role using handshake mechanism, if any one clock zone does not have
There is method to realize handshake mechanism, then the asynchronous FIFO queue just has the risk that data are overflowed.
For the risk for how avoiding data from overflowing, the way of presently relevant technology is to increase the depth of asynchronous FIFO queue
Degree, i.e., according to the depth of transmitting terminal and the ratio of the clock frequency of receiving terminal, suitably increase fifo queue.For data bit width
For the smaller asynchronous FIFO queue such as 1bit, expense caused by this design is in the range of receiving;But for number
For comparing the asynchronous FIFO queue as large as 256bit according to bit wide, the expense such as this increased Buffer size of design is huge.
The content of the invention
The present invention provides a kind of data transfer of computer system, and the Transmission system is by structural data and unstructured data
Fusion is transmitted in one file so that structural data and non-structural data are transmitted, exchange and are total in a network
Can be synchronous when enjoying, data nonsynchronous problem when avoiding separated transmission be present;The Transmission system encodes to structural data
It is by introducing free factor rfAs one degree of freedom, lead to the free factor r of conversionf, can be in generation and spreading factor zfRelatively
During the second basic matrix answered, entirely different matrix structure distribution is obtained, so as to directly use spreading factor zfTo
One basic matrix deployed obtained by basic matrix error floor it is higher when, by change matrix structure be distributed, obtain error floor
The second relatively low basic matrix, mitigates in spreading factor zfUnder the second basic matrix of the generation have that error floor is higher to ask
Topic, improve the reliability of data transfer;The network equipment of the Transmission system can determine the data receiver in different clock-domains
The clock frequency ratio relation of module and data outputting module, according to the clock frequency ratio relation, determines data transfer
Count value, when detecting that the data reception BOB(beginning of block) receives data, start the counter, and in the data output mould
Block output data, until when the counter reaches the count value, stop the data output of the output end, in this way, patrolling
Upper unused asynchronous FIFO is collected, but uses the output speed of counter controls data, so as to not only avoid because of asynchronous FIFO team
The risk that data caused by row are overflowed.
To achieve these goals, the present invention provides a kind of data transfer of computer system, and the system is set including computer
The standby, network equipment and server, wherein,
The computer equipment includes:
Check matrix generation module, for generating low-density parity check code check matrix;
Structural data coding module, structural data is encoded for above-mentioned density parity check code check matrix, will
Structural data is converted to the structural data with preset data coded format;
Unstructured data processing module, default every attribute information of each file in unstructured data is obtained, according to non-
The quantity N of file in structural data, obtain with preset data coded format structural data in unstructured data
In N number of file one-to-one N number of field respectively, by default every attribute information of each file in unstructured data, point
The reference of respective file in unstructured data as the extended field of corresponding field in structural data, Tian Jia not be formed, its
In, there is the field of extended field in structured data, compound fields are formed with corresponding extended field;
Data concatenation module, for by file header, have preset data coded format structural data and unstructured data
Sequentially splice, form semi-structured data;
Computer data sending module, for sending the semi-structured data;
The network equipment includes:
Data reception module, for receiving the semi-structured data;
Message transmission rate adjustment module, for the transmission rate of regulating networks equipment, including counter;
Data outputting module, for exporting the semi-structured data to server;
Data transmission control module, for according to the transmission rate, controlling the data transmission procedure of the network equipment, including data
The course of work of receiving module and data outputting module;
The server includes:
Server data transport module, for receiving the semi-structured data from the network equipment;
Data decoder module, for decoding the semi-structured data;
Memory module, for storing decoded data;
Control module, for controlling the operation of the server.
Preferably, the check matrix generation module, generates low-density parity check code check matrix with the following method:
The first basic matrix of LDPC code is obtained, wherein, m is the line number of first basic matrix, and n is the row of first basic matrix
Number;
Obtain the spreading factor z of first basic matrixf, wherein, zfValue be positive integer;
The second basic matrix of the LDPC code is generated, wherein, m is the line number of second basic matrix, and n is second basic matrix
Columns, matrix element in first basic matrix equal to -1 be equal in second basic matrix -1 matrix element position
Identical, at least there is the matrix element p of the i-th row jth row in second basic matrixf,i,jIt is according in first basic matrix
The matrix element p of i-th row jth rowi,j, the zfWith free factor rfGeneration, wherein, pf,i,j< zf, rf, m, n, i's, j takes
Value is integer, 0≤i < m, 0≤j < n.
Preferably,Wherein zmaxWill by first basic matrix
The spreading factor z of supportfMaximum.
Preferably, the first basic matrix of low-density checksum LDPC code is obtained, wherein, m is first basic matrix
Line number, n are the columns of first basic matrix, and m, n values are positive integer;
According to first basic matrix, spreading factor zfWith free factor rfStructural data is encoded to obtain with default
The structural data of coded format, wherein, zfValue be positive integer, rfValue be integer more than or equal to 0.
Preferably, the structural data coding module is according to first basic matrix, spreading factor zfWith free factor rf
Structural data is encoded to obtain the structural data with pre-arranged code form, including:For first basic matrix
In every one i-th row jth row matrix element pi,j, the spreading factor zfWith free factor rfCalculate pf,i,j, wherein, pf,i,j<
zf, i, j value is integer, 0≤i < m, 0≤j < n;According to pf,i,jStructural data is encoded to obtain with default
The structural data of coded format.
Preferably, the message transmission rate scheduler module also includes rate register, can be by different clock-domains
The clock frequency ratio relation of the data reception module and the data outputting module, is preserved into the rate register
Preferably, the data transmission control module, during available for detecting that the data reception BOB(beginning of block) receives data, open
The counter is moved, and in the data outputting module output data, when count value and the speed of the counter are deposited
When the numerical value that device preserves is identical, stop the data output of the data outputting module.
Preferably, the data transmission control module, when stopping the data output of the data outputting module, institute is controlled
State counter O reset.
Preferably, the data transmission control module, the effective of the data of the data reception module reception is being detected
When high level occurs in signal, the data reception BOB(beginning of block) receives data.
Preferably, the data transmission control module, after detecting that the data reception BOB(beginning of block) receives data,
When detecting the data of the data outputting module output has edging trigger, the data of data outputting module output are carried out
Sampling;The edging trigger includes at least one of:Rising edge triggering, trailing edge triggering.
The present invention has advantages below and beneficial effect:(1)Structural data is merged at one with unstructured data
It is transmitted in file so that structural data and non-structural data can be same when being transmitted, exchange and sharing in a network
, data nonsynchronous problem when avoiding separated transmission be present in step;(2)It is by introducing the free factor to structural data coding
rfAs one degree of freedom, lead to the free factor r of conversionf, can be in generation and spreading factor zfDuring corresponding second basic matrix,
Obtain entirely different matrix structure distribution.So as to directly use spreading factor zfExpansion institute is carried out to the first basic matrix
When the basic matrix error floor obtained is higher, it is distributed by changing matrix structure, obtains the second relatively low basic matrix of error floor, subtract
Gently in spreading factor zfUnder the second basic matrix of the generation the problem of error floor is higher be present, improve the reliable of data transfer
Property;(3)The network equipment of the Transmission system can determine data reception module and data outputting module in different clock-domains
Clock frequency ratio relation, according to the clock frequency ratio relation, determine the count value of data transfer, detect the number
When starting to receive data according to receiving module, start the counter, and in the data outputting module output data, until described in
When counter reaches the count value, stop the data output of the output end, in this way, asynchronous FIFO is logically not used,
But the output speed of counter controls data is used, so as to not only avoid the wind that the data caused by asynchronous FIFO queue are overflowed
Danger.
Brief description of the drawings
Fig. 1 shows a kind of block diagram of data transfer of computer system of the present invention.
Figure shows a kind of data transfer flow figure of data transfer of computer system based on the present invention of the present invention.
Embodiment
Fig. 1 show the present invention a kind of data transfer of computer system block diagram, the system include computer equipment 1,
The network equipment 2 and server 3.
Wherein, the computer equipment 1 includes:
Check matrix generation module 12, for generating low-density parity check code check matrix;
Structural data coding module 14, structural data is encoded for above-mentioned density parity check code check matrix,
Structural data is converted into the structural data with preset data coded format;
Unstructured data processing module 15, default every attribute information of each file in unstructured data is obtained, according to
The quantity N of file in unstructured data, obtain with preset data coded format structural data in unstructured number
N number of file one-to-one N number of field respectively in, by default every attribute information of each file in unstructured data,
Extended field of the addition as corresponding field in structural data respectively, the reference of respective file in unstructured data is formed,
Wherein, there is the field of extended field in structured data, compound fields are formed with corresponding extended field;
Data concatenation module 11, for by file header, have preset data coded format structural data and unstructured number
According to sequentially splicing, semi-structured data is formed;
Computer data sending module 13, for sending the semi-structured data.
The network equipment 2 includes:
Data reception module 21, for receiving the semi-structured data;Message transmission rate adjustment module 23, for adjusting net
The transmission rate of network equipment, including counter;Data outputting module 24, for exporting the semi-structured data to server;
Data transmission control module 22, for according to the transmission rate, controlling the data transmission procedure of the network equipment, including data to connect
Receive the course of work of module and data outputting module.
The server 3 includes:
Server data transport module 31, for receiving the semi-structured data from the network equipment;Data decoder module 32, use
In the decoding semi-structured data;Memory module 33, for storing decoded data;Control module 34, for controlling
State the operation of server.
The check matrix generation module 12, generates low-density parity check code check matrix with the following method:
The first basic matrix of LDPC code is obtained, wherein, m is the line number of first basic matrix, and n is the row of first basic matrix
Number;
Obtain the spreading factor z of first basic matrixf, wherein, zfValue be positive integer;
The second basic matrix of the LDPC code is generated, wherein, m is the line number of second basic matrix, and n is second basic matrix
Columns, matrix element in first basic matrix equal to -1 be equal in second basic matrix -1 matrix element position
Identical, at least there is the matrix element p of the i-th row jth row in second basic matrixf,i,jIt is according in first basic matrix
The matrix element p of i-th row jth rowi,j, the zfWith free factor rfGeneration, wherein, pf,i,j< zf, rf, m, n, i's, j takes
Value is integer, 0≤i < m, 0≤j < n.
Wherein,
Wherein zmaxFor first basic matrix spreading factor z to be supportedfMaximum.
The first basic matrix of low-density checksum LDPC code is obtained, wherein, m is the line number of first basic matrix, and n is
The columns of first basic matrix, m, n values are positive integer;
According to first basic matrix, spreading factor zfWith free factor rfStructural data is encoded to obtain with default
The structural data of coded format, wherein, zfValue be positive integer, rfValue be integer more than or equal to 0.
The structural data coding module 14 is according to first basic matrix, spreading factor zfWith free factor rfTo knot
Structure data are encoded to obtain the structural data with pre-arranged code form, including:For every in first basic matrix
The matrix element p of one i-th row jth rowi,j, the spreading factor zfWith free factor rfCalculate pf,i,j, wherein, pf,i,j< zf, i,
J value is integer, 0≤i < m, 0≤j < n;According to pf,i,jStructural data is encoded to obtain with pre-arranged code
The structural data of form.
The message transmission rate scheduler module 23 also includes rate register, can be by the number in different clock-domains
According to receiving module 21 and the clock frequency ratio relation of the data outputting module 24, preserve into the rate register
The data transmission control module 22, available for detect the data reception module 21 start receive data when, start
The counter, and in the output data of data outputting module 24, when count value and the speed of the counter are deposited
When the numerical value that device preserves is identical, stop the data output of the data outputting module 24.
The data transmission control module 22, when stopping the data output of the data outputting module 24, described in control
Counter O reset.
The data transmission control module 22, in the useful signal for the data for detecting the data reception module reception 21
When there is high level, the data reception module 21 starts to receive data.
The data transmission control module 24, after detecting that the data reception module 21 starts to receive data, inspection
When measuring the data that the data outputting module 24 exports has edging trigger, the data of the data outputting module 24 output are entered
Row sampling;The edging trigger includes at least one of:Rising edge triggering, trailing edge triggering.
Fig. 2 shows a kind of data transfer flow figure of the data transfer of computer system based on the present invention.This method has
Body comprises the following steps:
S1. low-density parity check code check matrix is generated.
In the step S1, low-density parity check code check matrix is generated with the following method:
S11. the first basic matrix of LDPC code is obtained, wherein, m is the line number of first basic matrix, and n is first basic matrix
Columns.Computer Wireless Communication equipment directly can obtain first basic matrix from other equipment;Or can also be first
The line number m and the columns n are obtained, then uses density evolution theory or progressive edge growth (progressive edge again
Growth, abbreviation PEG) the first basic matrix of method construct.Wherein, wherein m and n value can be according to the number of Wireless Telecom Equipment
Determined according to transmission demand.The acquisition methods or building method of basic matrix just repeat no more herein.
S12. the spreading factor z of first basic matrix is obtainedf, wherein, zfValue be positive integer;Except need obtain institute
State outside the first basic matrix, Computer Wireless Communication equipment also needs to obtain spreading factor zf.Wherein, the spreading factor zf's
Value can be determined by the code length of the structural data with pre-arranged code form.As a rule, zfValue and basic matrix
The product of columns is the code length of the structural data with pre-arranged code form, and the structural data with pre-arranged code form can
Be structural data waiting for transmission it is encoded after obtained sequence.
Spreading factor zfIt can be any one spreading factor supported needed for first basic matrix, or can also be institute
State in the spreading factor supported needed for the first basic matrix, it is higher that expansion meeting generation error flat bed is directly carried out to the first basic matrix
Some spreading factor of second basic matrix.Wherein, error floor is higher can refer to that error floor is higher than predetermined limits value, institute
Stating predetermined limits value can determine according to the actual demand of data transfer.
S13. the second basic matrix of the LDPC code is generated, wherein, m is the line number of second basic matrix, and n is described the
Diyl matrix column number, matrix element in first basic matrix equal to -1 be equal in second basic matrix -1 matrix
Element position is identical, and second basic matrix at least has the matrix element p of the i-th row jth rowf,i,jIt is according to described first
The matrix element p that the i-th row jth arranges in basic matrixi,j, the zfWith free factor rfGeneration, wherein, pf,i,j< zf, rf, m, n,
I, j value are integer, 0≤i < m, 0≤j < n.
To ensure that the second basic matrix ultimately generated has relatively low error floor relative to the first basic matrix, then it can make institute
The long characteristic of ring for stating the second basic matrix is then better than or equal to first basic matrix.To make the Huan Changte of second basic matrix
Property be then better than first basic matrix, the replacement element pf,i,jAlso need to meet:By matrix element pi,jCorresponding to replacing with
Replace element pf,i,jAfter can eliminate before replacement at least one ring in matrix.If that is, before replacement in matrix, (a1-a2+a3-
a4+...-al) %zf=0, wherein, a1,a2,a3,a4,...,alIt is each on l ring for any one length in matrix before replacement
Individual matrix element, l are the even number more than or equal to 4;So after replacement in matrix, (a1'-a2'+a3'-a4'+...-
al') %zf≠ 0, wherein, a1',a2',a3',a4',...,al' for the matrix element after replacing in matrix, and aq' after replacement
Position and a in matrixqPosition before replacement in matrix is identical, q=1,2,3,4 ..., l.Wherein, matrix before the replacement
For by element pi,jReplace with pf,i,jMatrix before, matrix is by element p after replacementi,jReplace with pf,i,jGenerated afterwards
Matrix.
Preferably,
Wherein zmaxFor first basic matrix spreading factor z to be supportedfMaximum.
S2. structural data is encoded using above-mentioned density parity check code check matrix, structural data is turned
It is changed to the structural data with preset data coded format.
Preferably, in the step S2, the first basic matrix of low-density checksum LDPC code is obtained, wherein, m is institute
The line number of the first basic matrix is stated, n is the columns of first basic matrix, and m, n values are positive integer;
According to first basic matrix, spreading factor zfWith free factor rfStructural data is encoded to obtain with default
The structural data of coded format, wherein, zfValue be positive integer, rfValue be integer more than or equal to 0.
Preferably, it is described according to first basic matrix, spreading factor zfWith free factor rfStructural data is compiled
Code obtains the structural data with pre-arranged code form, including:For every one i-th row jth row in first basic matrix
Matrix element pi,j, the spreading factor zfWith free factor rfCalculate pf,i,j, wherein, pf,i,j< zf, i, j value are whole
Number, 0≤i < m, 0≤j < n;According to pf,i,jStructural data is encoded to obtain the structuring number with pre-arranged code form
According to.
S3. default every attribute information of each file in unstructured data is obtained.
S4. according to the quantity N of file in unstructured data, the structural data with preset data coded format is obtained
In with the one-to-one N number of field respectively of N number of file in unstructured data.
S5. default every attribute information of each file in unstructured data, respectively addition are regard as structural data
The extended field of middle corresponding field, the reference of respective file in unstructured data is formed, wherein, have in structured data and expand
The field of field is opened up, compound fields are formed with corresponding extended field.
S6. the length information and unstructured data of the structural data with preset data coded format are obtained respectively
Length information, then by structural data length information, unstructured data length information, and the present count of structural data
Configuration file head is combined according to coded format three.
S7. file header, the structural data with preset data coded format and unstructured data are sequentially spliced, structure
Into semi-structured data, and carry out data transmission.
Described above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as protection scope of the present invention.The purpose of selecting and describing the exemplary embodiment is that explain the specific original of the present invention
Reason and its practical application, so that those skilled in the art can realize and utilize a variety of exemplary of the present invention
Embodiment and various chooses and changes.The scope of the present invention is intended to be limited by claims and its equivalents
It is fixed.
Claims (10)
1. a kind of data transfer of computer system, the system includes computer equipment, the network equipment and server, wherein,
The computer equipment includes:
Check matrix generation module, for generating low-density parity check code check matrix;
Structural data coding module, structural data is encoded for above-mentioned density parity check code check matrix, will
Structural data is converted to the structural data with preset data coded format;
Unstructured data processing module, default every attribute information of each file in unstructured data is obtained, according to non-
The quantity N of file in structural data, obtain with preset data coded format structural data in unstructured data
In N number of file one-to-one N number of field respectively, by default every attribute information of each file in unstructured data, point
The reference of respective file in unstructured data as the extended field of corresponding field in structural data, Tian Jia not be formed, its
In, there is the field of extended field in structured data, compound fields are formed with corresponding extended field;
Data concatenation module, for by file header, have preset data coded format structural data and unstructured data
Sequentially splice, form semi-structured data;
Computer data sending module, for sending the semi-structured data;
The network equipment includes:
Data reception module, for receiving the semi-structured data;
Message transmission rate adjustment module, for the transmission rate of regulating networks equipment, including counter;
Data outputting module, for exporting the semi-structured data to server;
Data transmission control module, for according to the transmission rate, controlling the data transmission procedure of the network equipment, including data
The course of work of receiving module and data outputting module;
The server includes:
Server data transport module, for receiving the semi-structured data from the network equipment;
Data decoder module, for decoding the semi-structured data;
Memory module, for storing decoded data;
Control module, for controlling the operation of the server.
2. the method as described in claim 1, it is characterised in that the check matrix generation module, generate with the following method
Low-density parity check code check matrix:
The first basic matrix of LDPC code is obtained, wherein, m is the line number of first basic matrix, and n is the row of first basic matrix
Number;
Obtain the spreading factor z of first basic matrixf, wherein, zfValue be positive integer;
The second basic matrix of the LDPC code is generated, wherein, m is the line number of second basic matrix, and n is second basic matrix
Columns, matrix element in first basic matrix equal to -1 be equal in second basic matrix -1 matrix element position
Identical, at least there is the matrix element p of the i-th row jth row in second basic matrixf,i,jIt is according in first basic matrix
The matrix element p of i-th row jth rowi,j, the zfWith free factor rfGeneration, wherein, pf,i,j< zf, rf, m, n, i's, j takes
Value is integer, 0≤i < m, 0≤j < n.
3. method as claimed in claim 2, it is characterised in thatWherein
zmaxFor first basic matrix spreading factor z to be supportedfMaximum.
4. method as claimed in claim 3, it is characterised in that the first basic matrix of low-density checksum LDPC code is obtained,
Wherein, m is the line number of first basic matrix, and n is the columns of first basic matrix, and m, n values are positive integer;
According to first basic matrix, spreading factor zfWith free factor rfStructural data is encoded to obtain with default
The structural data of coded format, wherein, zfValue be positive integer, rfValue be integer more than or equal to 0.
5. method as claimed in claim 4, it is characterised in that the structural data coding module is according to first group moment
Battle array, spreading factor zfWith free factor rfStructural data is encoded to obtain the structural data with pre-arranged code form,
Including:For the matrix element p of every one i-th row jth row in first basic matrixi,j, the spreading factor zfWith the free factor
rfCalculate pf,i,j, wherein, pf,i,j< zf, i, j value is integer, 0≤i < m, 0≤j < n;According to pf,i,jTo structuring number
According to being encoded to obtain the structural data with pre-arranged code form.
6. the method as described in claim 1-5 is any, it is characterised in that the message transmission rate scheduler module also includes speed
Rate register, can be by the data reception module and the clock frequency ratio of the data outputting module in different clock-domains
Relation, preserve into the rate register.
7. method as claimed in claim 6, it is characterised in that the data transmission control module, it is described available for detecting
When data reception BOB(beginning of block) receives data, start the counter, and in the data outputting module output data, when described
When the count value of counter is identical with the numerical value that the rate register preserves, the data for stopping the data outputting module are defeated
Go out.
8. method as claimed in claim 7, it is characterised in that the data transmission control module, the data are defeated stopping
When going out the data output of module, the counter O reset is controlled.
9. method as claimed in claim 8, it is characterised in that the data transmission control module, detecting the data
When high level occurs in the useful signal for the data that receiving module receives, the data reception BOB(beginning of block) receives data.
10. method as claimed in claim 9, it is characterised in that the data transmission control module, detecting the data
Receiving module starts after receiving data, when detecting the data of the data outputting module output has edging trigger, to described
The data of data outputting module output are sampled;The edging trigger includes at least one of:Rising edge triggering, trailing edge
Triggering.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710643764.6A CN107453843A (en) | 2017-08-19 | 2017-08-19 | A kind of data transfer of computer system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710643764.6A CN107453843A (en) | 2017-08-19 | 2017-08-19 | A kind of data transfer of computer system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107453843A true CN107453843A (en) | 2017-12-08 |
Family
ID=60489290
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710643764.6A Pending CN107453843A (en) | 2017-08-19 | 2017-08-19 | A kind of data transfer of computer system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107453843A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109995379A (en) * | 2017-12-29 | 2019-07-09 | 华为技术有限公司 | The method and apparatus for handling information |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050246616A1 (en) * | 2004-04-22 | 2005-11-03 | Samsung Electronics Co., Ltd. | System, apparatus and method for transmitting and receiving data coded by low density parity check code having variable coding rate |
CN104821831A (en) * | 2015-03-24 | 2015-08-05 | 东南大学 | Dual cycle construction method suitable for high code rate quasi cyclic-low density parity check (QC-LDPC) code |
CN106776974A (en) * | 2016-12-06 | 2017-05-31 | 广东金赋科技股份有限公司 | A kind of big data monitoring method based on configuration, device and platform |
CN106849958A (en) * | 2016-12-29 | 2017-06-13 | 上海华为技术有限公司 | The building method of low-density parity check code check matrix, coding method and system |
-
2017
- 2017-08-19 CN CN201710643764.6A patent/CN107453843A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20050246616A1 (en) * | 2004-04-22 | 2005-11-03 | Samsung Electronics Co., Ltd. | System, apparatus and method for transmitting and receiving data coded by low density parity check code having variable coding rate |
CN104821831A (en) * | 2015-03-24 | 2015-08-05 | 东南大学 | Dual cycle construction method suitable for high code rate quasi cyclic-low density parity check (QC-LDPC) code |
CN106776974A (en) * | 2016-12-06 | 2017-05-31 | 广东金赋科技股份有限公司 | A kind of big data monitoring method based on configuration, device and platform |
CN106849958A (en) * | 2016-12-29 | 2017-06-13 | 上海华为技术有限公司 | The building method of low-density parity check code check matrix, coding method and system |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109995379A (en) * | 2017-12-29 | 2019-07-09 | 华为技术有限公司 | The method and apparatus for handling information |
CN109995379B (en) * | 2017-12-29 | 2021-07-16 | 华为技术有限公司 | Method and device for processing information |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
RU2210185C2 (en) | Coding/decoding facility and procedure to process frame data in correspondence with quality of servicing | |
US20220416895A1 (en) | Data transmission method and apparatus, terminal device and storage medium | |
CN101706763B (en) | Method and device for serialization and deserialization | |
CN107342773A (en) | Coding, interpretation method and equipment | |
US11936475B2 (en) | Method, apparatus, and system for improving reliability of data transmission involving an ethernet device | |
US20210360093A1 (en) | Multimode interconnection interface controller for converged network | |
CN109842458A (en) | A kind of coding method, device, electronic equipment and storage medium | |
CN109672560A (en) | Flexible ethernet management channel extended method and equipment | |
CN106998308A (en) | A kind of frame hopping transmission method in Sparse Code multiple access access based on time-varying code book | |
WO2016109999A1 (en) | Data processing method and data processing apparatus | |
CN101977092B (en) | Forward error correction mapping and de-mapping techniques | |
CN109150378A (en) | A kind of data processing method and data processing equipment | |
CN107453843A (en) | A kind of data transfer of computer system | |
CN105162554B (en) | Real-time interpretation method and device in a kind of coding slotted ALOHA system | |
CN108563604B (en) | PCS protocol multiplexing chip and method | |
CN106358240B (en) | A kind of data frame transmission method and device of virtual elasticity CPRI interface | |
CN108631941A (en) | Communication means and device | |
CN101141351B (en) | Method of settling frame loss of frequency offset | |
US20220149988A1 (en) | Method for Adjusting Transmission Rate, Processor, Network Device, and Network System | |
CN107615810A (en) | Header compression system and method for online network code | |
CN104683070A (en) | Transmission control method based on random linear network coding | |
EP2621121A2 (en) | Supercharged codes | |
US20230246730A1 (en) | Data transmission method and apparatus, circuit board, storage medium and electronic apparatus | |
CN110572237B (en) | Signal sending and relaying method and related equipment | |
JPS59228440A (en) | Data transmission system |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171208 |
|
WD01 | Invention patent application deemed withdrawn after publication |