CN109460535A - A kind of finite field matrix inversion device based on cloud and inversion technique - Google Patents
A kind of finite field matrix inversion device based on cloud and inversion technique Download PDFInfo
- Publication number
- CN109460535A CN109460535A CN201811354486.3A CN201811354486A CN109460535A CN 109460535 A CN109460535 A CN 109460535A CN 201811354486 A CN201811354486 A CN 201811354486A CN 109460535 A CN109460535 A CN 109460535A
- Authority
- CN
- China
- Prior art keywords
- matrix
- cloud
- array
- finite field
- look
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
- G06F9/30003—Arrangements for executing specific machine instructions
- G06F9/30007—Arrangements for executing specific machine instructions to perform operations on data operands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a kind of finite field matrix inversion device based on cloud, including central processing unit, memory, cloud table look-up multiplication array, cloud of adder array, cloud of tabling look-up are tabled look-up array, original matrix manager, unit matrix manager, normalizing arithmetic unit and the n ary operation device that disappears of inverting.The invention also discloses the inversion techniques based on above-mentioned finite field matrix inversion device based on cloud.The present invention can invert to the matrix in finite field, and major calculations include finite field addition, multiplication and invert, and are completed beyond the clouds, have the characteristics that fireballing.
Description
Technical field
The present invention relates to the arithmetic unit of finite field, in particular to a kind of finite field matrix inversion device based on cloud and ask
Inverse approach.
Background technique
Matrix is one of the important concept in algebra field and tool, and the addition of matrix, is inverted as mathematics, password at multiplication
One of important basic operations in fields such as, communication.The operation of addition of matrices is fairly simple, it is only necessary to which two matrixes are corresponding
Element is added.The operation of matrix multiplication then needs to realize by the multiplication and addition of corresponding element.Matrix inversion
Operation be to find a matrix, make to obtain a unit matrix after matrix multiple.In these three types of operations, matrix inversion operation
It is the most cumbersome.
The matrix inversion of matrix inversion, especially finite field, is widely applied in cryptography.For example, based on polynary multinomial
The password of formula needs to invert using multi-degree matrix.The matrix inversion of finite field is needed using finite field addition, multiplication and fortune of inverting
It calculates.Finite field matrix inversion operation needs long time, computational complexity height, resource consumption big, makes it promotion cryptographic system
The bottleneck of performance.Cloud computing is current popular technology, belongs to one kind of generation information technology.It is in sides such as calculating, storages
Face is more superior compared to traditional computer.
Summary of the invention
In order to overcome the disadvantages mentioned above and deficiency of the prior art, the purpose of the present invention is to provide a kind of based on cloud limited
Domain matrix is inverted device, has the characteristics that arithmetic speed is fast.
Another object of the present invention is to provide a kind of inversion techniques based on above-mentioned device of inverting.
The purpose of the present invention is achieved through the following technical solutions:
A kind of finite field matrix inversion device based on cloud, comprising:
Cloud is tabled look-up adder array, m finite field adder and m addition scheduler including concurrent operation beyond the clouds;
The finite field adder be used for by searching for form return addition results;The addition scheduler is used for received operation
Number is assigned to idle finite field adder;M is positive integer;
Cloud is tabled look-up multiplication array, m Galois field multiplier and m multiplication scheduler including concurrent operation beyond the clouds;
The Galois field multiplier be used for by searching for form return multiplication result;The multiplication scheduler is used for received operation
Number is assigned to idle Galois field multiplier;
Cloud is tabled look-up array of inverting, and m finite field inverter and m including concurrent operation beyond the clouds are inverted scheduler;
The finite field inverter be used for by searching for form return invert result;The scheduler of inverting is used for received operation
Number is assigned to idle finite field inverter;
Original matrix manager, including original matrix computing inverse circuit and original matrix memory;The original matrix computing inverse circuit is used for
The read-write operation of original matrix;The original matrix memory is used for storage management of the original matrix in RAM;
Unit matrix manager, including unit matrix computing inverse circuit and unit matrix memory;The unit matrix is inverted
Circuit is used for the read-write operation of unit matrix;The unit matrix memory is used for storage management of the unit matrix in RAM;
Normalizing arithmetic unit, including normalizing computing circuit and normalizing operation scheduler;The normalizing computing circuit is for completing
The normalizing operation of original matrix and unit matrix;The normalizing operation scheduler is used for for calling cloud to table look-up adder array, cloud
Multiplication array is tabled look-up at end and cloud is tabled look-up array of inverting;
Disappear n ary operation device, including disappear n ary operation circuit and the n ary operation scheduler that disappears;The n ary operation circuit that disappears is for completing
The n ary operation that disappears of original matrix and unit matrix;The n ary operation scheduler that disappears is for calling table look-up adder array, cloud of cloud to look into
Table multiplication array and cloud are tabled look-up array of inverting;
Memory, including RAM and register;The RAM is for storing original matrix and unit matrix;The register is used for
Table look-up multiplication array and cloud is tabled look-up the result of array operation of inverting in table look-up adder array, cloud of storage cloud;
Central processing unit, including arithmetic processor and interface controller;The interface controller for receive original matrix and
Export result of inverting;The arithmetic processor is tabled look-up for dispatching cloud table look-up multiplication array, cloud of adder array, cloud of tabling look-up
Invert array, original matrix manager, unit matrix manager, normalizing arithmetic unit, disappear n ary operation device and memory.
The finite field matrix inversion device based on cloud, the register include 5000 registers, each deposit
The memory space of device is double byte.
The finite field matrix inversion device based on cloud, the finite field adder include a finite field addition fortune
The look-up table of calculation.
The finite field matrix inversion device based on cloud, the Galois field multiplier include a finite field multiplier fortune
The look-up table of calculation.
The finite field matrix inversion device based on cloud, the finite field inverter include a finite field inversions fortune
The look-up table of calculation.
The inversion technique of the finite field matrix inversion device based on cloud, comprising the following steps:
(1) arithmetic processor obtains the scale of matrix from original matrix manager, is identified using m × m, m is a positive integer;
(2) iteration count is arranged in arithmetic processor, starts counting from 1, counts cut-off to m;
(3) matrix in arithmetic processor setting unit matrix manager is the unit matrix that diagonal line is all 1, and scale is
m×m;
(4) arithmetic processor starts counter, starts to be iterated operation:
(4.1) arithmetic processor looks for the original matrix and unit matrix of original matrix manager and unit matrix manager
Pivot operation;If current iteration is the i-th wheel iteration, judge whether the element of the i-th row i-th column of original matrix is 0, if not 0
It is selected as pivot;If 0, then the i-th row and other following rows are exchanged, guarantees that the element of the i-th row i-th column is non-zero;
(4.2) arithmetic processor calls normalizing arithmetic unit, to the original matrix of original matrix manager and unit matrix manager
Normalizing operation is carried out with unit matrix;If current iteration is the i-th wheel iteration, by the inverse element of the pivot of original matrix be multiplied by original matrix and
All elements of the i-th row of unit matrix;
(4.3) arithmetic processor calls the n ary operation device that disappears, to the original matrix of original matrix manager and unit matrix manager
The atom operation that disappears is carried out with unit matrix;If current iteration is the i-th wheel iteration, by original matrix and unit matrix other than the i-th row
All elements carry out the member that disappears;
(4.4) arithmetic processor is related to addition, multiplication and inverting calls table look-up adder array, cloud of cloud to table look-up respectively
Multiplication array and cloud are tabled look-up array of inverting.
Compared with prior art, the present invention has the following advantages and beneficial effects:
The present invention is based on the finite field matrix inversion devices of cloud, can invert to the matrix in finite field, main to transport
It calculates including finite field addition, multiplication and inverts, complete, have the characteristics that fireballing beyond the clouds.
Detailed description of the invention
The finite field matrix inversion apparatus structure schematic diagram based on cloud of Fig. 1 the embodiment of the present invention.
Specific embodiment
Below with reference to embodiment, the present invention is described in further detail, embodiments of the present invention are not limited thereto.
Embodiment
As shown in Figure 1, a kind of finite field matrix inversion device based on cloud of the present embodiment includes central processing unit, storage
It tables look-up array, original matrix manager, the unit matrix pipe of inverting in device, cloud table look-up multiplication array, cloud of adder array, cloud of tabling look-up
Reason device, normalizing arithmetic unit, disappear n ary operation device.
Cloud table look-up adder array be the present apparatus basic operations component, the m finite field including concurrent operation beyond the clouds
Adder and m addition scheduler;The finite field adder be used for by searching for form return addition results;The addition
Scheduler is used to for received operand to be assigned to idle finite field adder;M is positive integer;
Cloud table look-up multiplication array be the present apparatus basic operations component, the m finite field including concurrent operation beyond the clouds
Multiplier and m multiplication scheduler;The Galois field multiplier be used for by searching for form return multiplication result;The multiplication
Scheduler is used to for received operand to be assigned to idle Galois field multiplier;
Cloud table look-up invert array be the present apparatus basic operations component, the m finite field including concurrent operation beyond the clouds
It inverts device and m schedulers of inverting;The finite field inverter be used for by searching for form return invert result;It is described to invert
Scheduler is used to for received operand to be assigned to idle finite field inverter;
Original matrix manager is the logic unit of the present apparatus, including original matrix computing inverse circuit and original matrix memory;
The original matrix computing inverse circuit is used for the read-write operation of original matrix;The original matrix memory is used for original matrix depositing in RAM
Storage management;
Unit matrix manager is the logic unit of the present apparatus, including unit matrix computing inverse circuit and unit matrix are deposited
Reservoir;The unit matrix computing inverse circuit is used for the read-write operation of unit matrix;The unit matrix memory is used for unit square
Storage management of the battle array in RAM;
Normalizing arithmetic unit is the logic unit of the present apparatus, including normalizing computing circuit and normalizing operation scheduler;Institute
Normalizing computing circuit is stated for completing the normalizing operation of original matrix and unit matrix;The normalizing operation scheduler is used for for adjusting
Multiplication array is tabled look-up and cloud is tabled look-up array of inverting with table look-up adder array, cloud of cloud;
The n ary operation device that disappears is the logic unit of the present apparatus, including disappear n ary operation circuit and the n ary operation scheduler that disappears;Institute
The n ary operation circuit that disappears is stated for completing the n ary operation that disappears of original matrix and unit matrix;The n ary operation scheduler that disappears is for calling cloud
Table look-up multiplication array and cloud is tabled look-up array of inverting in table look-up adder array, cloud of end;
Memory is the storage unit of the present apparatus, including RAM and register;The RAM is for storing original matrix and unit
Matrix;The register tables look-up multiplication array and cloud is tabled look-up array fortune of inverting for storing table look-up adder array, cloud of cloud
The result of calculation;
Central processing unit is the core component of the present apparatus, including arithmetic processor and interface controller;The Interface Controller
Device is for receiving original matrix and output is inverted result;The arithmetic processor is looked into for dispatching table look-up adder array, cloud of cloud
Table multiplication array, cloud table look-up invert array, original matrix manager, unit matrix manager, normalizing arithmetic unit, disappear n ary operation device
And memory.
The course of work that a kind of finite field matrix inversion device based on cloud of the present embodiment executes inversion operation is as follows:
(1) matrix is input to the present apparatus from input port PA by user, and the interface controller of central processing unit receives former
Matrix, and store to original matrix manager;
(2) arithmetic processor of central processing unit obtains the scale of matrix from original matrix manager, is identified using m × m, m
It is a positive integer;
(3) iteration count is arranged in arithmetic processor, starts counting from 1, counts cut-off to m;
(4) matrix in arithmetic processor setting unit matrix manager is the unit matrix that diagonal line is all 1, and scale is
m×m;
(5) arithmetic processor starts counter, starts to be iterated operation:
(5.1) arithmetic processor looks for the original matrix and unit matrix of original matrix manager and unit matrix manager
Pivot operation.If current iteration is the i-th wheel iteration, judge whether the element of the i-th row i-th column of original matrix is 0, if not 0
It is selected as pivot;If 0, then the i-th row and other following rows are exchanged, guarantees that the element of the i-th row i-th column is non-zero;
(5.2) arithmetic processor calls normalizing arithmetic unit, to the original matrix of original matrix manager and unit matrix manager
Normalizing operation is carried out with unit matrix.If current iteration is the i-th wheel iteration, by the inverse element of the pivot of original matrix be multiplied by original matrix and
All elements of the i-th row of unit matrix;
(5.3) arithmetic processor calls the n ary operation device that disappears, to the original matrix of original matrix manager and unit matrix manager
The atom operation that disappears is carried out with unit matrix.If current iteration is the i-th wheel iteration, by original matrix and unit matrix other than the i-th row
All elements carry out the member that disappears;
(5.4) arithmetic processor is related to addition, multiplication and inverting calls table look-up adder array, cloud of cloud to table look-up respectively
Multiplication array and cloud are tabled look-up array of inverting;
(6) interface controller is by the Output matrix of unit matrix manager to output port PB.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by the embodiment
Limitation, other any changes, modifications, substitutions, combinations, simplifications made without departing from the spirit and principles of the present invention,
It should be equivalent substitute mode, be included within the scope of the present invention.
Claims (6)
1. a kind of finite field matrix inversion device based on cloud characterized by comprising
Cloud is tabled look-up adder array, m finite field adder and m addition scheduler including concurrent operation beyond the clouds;It is described
Finite field adder be used for by searching for form return addition results;The addition scheduler is used for received operand point
It is fitted on idle finite field adder;M is positive integer;
Cloud is tabled look-up multiplication array, m Galois field multiplier and m multiplication scheduler including concurrent operation beyond the clouds;It is described
Galois field multiplier be used for by searching for form return multiplication result;The multiplication scheduler is used for received operand point
It is fitted on idle Galois field multiplier;
Cloud is tabled look-up array of inverting, and m finite field inverter and m including concurrent operation beyond the clouds are inverted scheduler;It is described
Finite field inverter be used for by searching for form return invert result;The scheduler of inverting is for dividing received operand
It is fitted on idle finite field inverter;
Original matrix manager, including original matrix computing inverse circuit and original matrix memory;The original matrix computing inverse circuit is used for former square
The read-write operation of battle array;The original matrix memory is used for storage management of the original matrix in RAM;
Unit matrix manager, including unit matrix computing inverse circuit and unit matrix memory;The unit matrix computing inverse circuit
Read-write operation for unit matrix;The unit matrix memory is used for storage management of the unit matrix in RAM;
Normalizing arithmetic unit, including normalizing computing circuit and normalizing operation scheduler;The normalizing computing circuit is for completing former square
The normalizing operation of battle array and unit matrix;The normalizing operation scheduler is used for for calling table look-up adder array, cloud of cloud to look into
Table multiplication array and cloud are tabled look-up array of inverting;
Disappear n ary operation device, including disappear n ary operation circuit and the n ary operation scheduler that disappears;The n ary operation circuit that disappears is for completing former square
The n ary operation that disappears of battle array and unit matrix;The n ary operation scheduler that disappears is for calling table look-up adder array, cloud of cloud to table look-up and multiply
Method array and cloud are tabled look-up array of inverting;
Memory, including RAM and register;The RAM is for storing original matrix and unit matrix;The register is for storing
Table look-up multiplication array and cloud is tabled look-up the result of array operation of inverting in table look-up adder array, cloud of cloud;
Central processing unit, including arithmetic processor and interface controller;The interface controller is for receiving original matrix and output
It inverts result;The arithmetic processor tables look-up and inverts for dispatching cloud table look-up multiplication array, cloud of adder array, cloud of tabling look-up
Array, original matrix manager, unit matrix manager, normalizing arithmetic unit, disappear n ary operation device and memory.
2. finite field matrix inversion device based on cloud according to claim 1, which is characterized in that the register includes
5000 registers, the memory space of each register are double bytes.
3. finite field matrix inversion device based on cloud according to claim 1, which is characterized in that the finite field addition
Device includes the look-up table of a finite field add operation.
4. finite field matrix inversion device based on cloud according to claim 1, which is characterized in that the finite field multiplier
Device includes the look-up table of a finite field multiplier operation.
5. finite field matrix inversion device based on cloud according to claim 1, which is characterized in that the finite field inversions
Device includes the look-up table of a finite field inversions operation.
6. based on the inversion technique of the described in any item finite field matrix inversion devices based on cloud of Claims 1 to 5, feature
It is, comprising the following steps:
(1) arithmetic processor obtains the scale of matrix from original matrix manager, is identified using m × m, m is a positive integer;
(2) iteration count is arranged in arithmetic processor, starts counting from 1, counts cut-off to m;
(3) matrix in arithmetic processor setting unit matrix manager be diagonal line be all 1 unit matrix, scale be m ×
m;
(4) arithmetic processor starts counter, starts to be iterated operation:
(4.1) arithmetic processor carries out looking for pivot to the original matrix and unit matrix of original matrix manager and unit matrix manager
Operation;If current iteration is the i-th wheel iteration, judge whether the element of the i-th row i-th column of original matrix is 0, if not 0 selects
For pivot;If 0, then the i-th row and other following rows are exchanged, guarantees that the element of the i-th row i-th column is non-zero;
(4.2) arithmetic processor calls normalizing arithmetic unit, to the original matrix and list of original matrix manager and unit matrix manager
Bit matrix carries out normalizing operation;If current iteration is the i-th wheel iteration, the inverse element of the pivot of original matrix is multiplied by original matrix and unit
All elements of the i-th row of matrix;
(4.3) arithmetic processor calls the n ary operation device that disappears, to the original matrix and list of original matrix manager and unit matrix manager
Bit matrix carries out the atom operation that disappears;If current iteration is the i-th wheel iteration, original matrix and unit matrix are owned other than the i-th row
Element carry out the member that disappears;
(4.4) arithmetic processor is related to addition, multiplication and inverting calls table look-up adder array, cloud of cloud to table look-up multiplication respectively
Array and cloud are tabled look-up array of inverting.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811354486.3A CN109460535B (en) | 2018-11-14 | 2018-11-14 | Finite field matrix inversion device and inversion method based on cloud |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811354486.3A CN109460535B (en) | 2018-11-14 | 2018-11-14 | Finite field matrix inversion device and inversion method based on cloud |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109460535A true CN109460535A (en) | 2019-03-12 |
CN109460535B CN109460535B (en) | 2023-02-03 |
Family
ID=65610425
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811354486.3A Active CN109460535B (en) | 2018-11-14 | 2018-11-14 | Finite field matrix inversion device and inversion method based on cloud |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109460535B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110224829A (en) * | 2019-06-14 | 2019-09-10 | 深圳职业技术学院 | Post-quantum encryption method and device based on matrix |
CN110266481A (en) * | 2019-06-14 | 2019-09-20 | 深圳职业技术学院 | Rear quantum Encrypt and Decrypt method and decryption device based on matrix |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110249755A1 (en) * | 2008-12-16 | 2011-10-13 | Youji Shibahara | Moving image coding method, moving image decoding method, moving image coding apparatus, moving image decoding apparatus, program, and integrated circuit |
CN103533046A (en) * | 2013-10-12 | 2014-01-22 | 苏州大学 | Public-verifiable linear algebra entrusted calculation system |
EP3399758A1 (en) * | 2017-05-04 | 2018-11-07 | Thomson Licensing | Method and apparatus to encode and decode two-dimension point clouds |
-
2018
- 2018-11-14 CN CN201811354486.3A patent/CN109460535B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110249755A1 (en) * | 2008-12-16 | 2011-10-13 | Youji Shibahara | Moving image coding method, moving image decoding method, moving image coding apparatus, moving image decoding apparatus, program, and integrated circuit |
CN103533046A (en) * | 2013-10-12 | 2014-01-22 | 苏州大学 | Public-verifiable linear algebra entrusted calculation system |
EP3399758A1 (en) * | 2017-05-04 | 2018-11-07 | Thomson Licensing | Method and apparatus to encode and decode two-dimension point clouds |
Non-Patent Citations (1)
Title |
---|
易海博,聂哲: "基于云计算技术的高职计算机专业教学模式的研究——以计算机编程语言课程为例", 《教育现代化》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110224829A (en) * | 2019-06-14 | 2019-09-10 | 深圳职业技术学院 | Post-quantum encryption method and device based on matrix |
CN110266481A (en) * | 2019-06-14 | 2019-09-20 | 深圳职业技术学院 | Rear quantum Encrypt and Decrypt method and decryption device based on matrix |
CN110224829B (en) * | 2019-06-14 | 2022-05-13 | 深圳职业技术学院 | Matrix-based post-quantum encryption method and device |
CN110266481B (en) * | 2019-06-14 | 2022-05-20 | 深圳职业技术学院 | Post-quantum encryption and decryption method and device based on matrix |
Also Published As
Publication number | Publication date |
---|---|
CN109460535B (en) | 2023-02-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103970720B (en) | Based on extensive coarseness imbedded reconfigurable system and its processing method | |
CN101547089B (en) | Method for realizing elliptic curve cryptosystem algorithm over prime field in integrated circuit | |
CN106951211B (en) | A kind of restructural fixed and floating general purpose multipliers | |
US10877733B2 (en) | Segment divider, segment division operation method, and electronic device | |
CN115880132B (en) | Graphics processor, matrix multiplication task processing method, device and storage medium | |
Kudithi | An efficient hardware implementation of the elliptic curve cryptographic processor over prime field | |
CN109460535A (en) | A kind of finite field matrix inversion device based on cloud and inversion technique | |
CN107015782A (en) | A kind of Galois field multiplier based on irreducible trinomial | |
CN109739433A (en) | The method and terminal device of data processing | |
CN103793199A (en) | Rapid RSA cryptography coprocessor capable of supporting dual domains | |
CN109190413A (en) | A kind of serial communication system based on FPGA and md5 encryption | |
CN102231101A (en) | Divider and division processing method | |
CN106325812A (en) | Processing method and device for multiplication and accumulation operation | |
Li et al. | Scalable and parallel optimization of the number theoretic transform based on FPGA | |
CN109144472A (en) | A kind of binary expands the scalar multiplication and its realization circuit of domain elliptic curve | |
CN106681691A (en) | Data processing method and modular multiplication operation method and apparatus based on Montgomery modular-multiplication | |
RU2666303C1 (en) | Method and device for calculating hash function | |
CN107580015A (en) | Data processing method and device, server | |
CN103888246A (en) | Low-energy-consumption small-area data processing method and data processing device thereof | |
CN101561797A (en) | Method and device for singular value and feature value composition of matrix on processing system | |
CN115408061A (en) | Hardware acceleration method, device, chip and storage medium for complex matrix operation | |
CN108255463A (en) | A kind of digital logical operation method, circuit and fpga chip | |
WO2013097235A1 (en) | Parallel bit order reversing device and method | |
Vestias et al. | Parallel decimal multipliers and squarers using Karatsuba-Ofman's algorithm | |
CN104951279A (en) | Vectorized Montgomery modular multiplier design method based on NEON engine |
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 |