CN108021393A

CN108021393A - A kind of computational methods and Related product

Info

Publication number: CN108021393A
Application number: CN201711362567.3A
Authority: CN
Inventors: 胡帅; 刘恩赫; 张尧; 孟小甫
Original assignee: Beijing Zhongke Cambrian Technology Co Ltd
Current assignee: Anhui Cambricon Information Technology Co Ltd
Priority date: 2017-12-15
Filing date: 2017-12-15
Publication date: 2018-05-11
Anticipated expiration: 2037-12-15
Also published as: CN108021393B

Abstract

Present disclose provides a kind of information processing method, the method is applied in computing device, and the computing device includes：Storage medium, register cell and matrix calculation unit；Described method includes following steps：The computing device controls the matrix calculation unit to obtain the first operational order, and the vector that first operational order includes performing needed for described instruction reads instruction；The computing device controls the arithmetic element to read instruction according to the vector and sends reading order to the storage medium；The computing device controls the arithmetic element to indicate corresponding vector according to using batch reading manner reading vectorial read, and first operational order is performed to the vector.The technical solution that the application provides has the advantages of calculating speed is fast, efficient.

Description

A kind of computational methods and Related product

Technical field

This application involves technical field of data processing, and in particular to a kind of computational methods and Related product.

Background technology

Data processing is the step of most of algorithm needs to pass through or stage, after computer introduces data processing field, More and more data processings realize have computing device carrying out the calculating of matrix data in existing algorithm by computer Shi Sudu is slow, and efficiency is low.

Apply for content

The embodiment of the present application provides a kind of computational methods and Related product, can lift the processing speed of computing device, carry High efficiency.

First aspect, there is provided a kind of computational methods, applied in computing device, the computing device include storage medium, Register cell and matrix operation unit, the described method includes：

The computing device controls the matrix operation unit to obtain the first operational order, and first operational order is used for Realize the computing between vector and matrix, the vector that first operational order includes performing needed for described instruction reads instruction, The required vector is at least one vector, and at least one vector is the vector that length is identical or length is different；

The computing device controls the matrix operation unit to read instruction according to the vector and is sent out to the storage medium Send reading order；

The computing device controls the matrix operation unit to be read using batch reading manner from the storage medium The vector reads the corresponding vector of instruction, and performs first operational order to the vector.

It is described that the vector execution first operational order is included in some possible embodiments：

The computing device controls the matrix operation unit to be held using the calculation of multistage pipelining-stage to the vector Row first operational order.

In some possible embodiments, each pipelining-stage in the multistage pipelining-stage includes at least one computing Device,

The computing device controls the matrix operation unit to be held using the calculation of multistage pipelining-stage to the vector Row first operational order includes：

The computing device controls the matrix operation unit to utilize first order pipelining-stage according to the selection of multiple selector In first choice arithmetic unit to the vector be calculated first as a result, first result is input to second level stream The second Selecting operation device in water level perform be calculated second as a result, and so on, until inputting the i-th -1 result to the The i-th Selecting operation device in i grades of pipelining-stages, which performs, is calculated i-th of result；

I-th of result is inputted to the storage medium and is stored；

Wherein, the quantity i of the multistage pipelining-stage is determined according to the calculating topological structure of first operational order, And i is positive integer.

In some possible embodiments, each pipelining-stage in the multistage pipelining-stage is each configured with corresponding multichannel Selector, the multiple selector, which is set, free option, and the sky option is used to indicate the kth being connected with the multiple selector Level pipelining-stage and follow-up kth+1 are not performed to i-stage pipelining-stage calculates operation, wherein, k is less than or equal to i just Integer.

In some possible embodiments, it is described multistage pipelining-stage in each pipelining-stage included by arithmetic unit and institute The quantity for stating arithmetic unit is by user side or the self-defined setting in computing device side.

In some possible embodiments, each pipelining-stage in the multistage pipelining-stage includes pre-set fixation Arithmetic unit, the fixation arithmetic unit in each pipelining-stage differ,

The computing device controls the matrix operation unit to utilize the fixation arithmetic unit in first order pipelining-stage to described Vector be calculated first as a result, the fixation arithmetic unit first result being input in the pipelining-stage of the second level performs Be calculated second as a result, and so on, until the i-th -1 result inputted to the fixation arithmetic unit in i-stage pipelining-stage holding I-th of result is calculated in row；

I-th of result is inputted to the storage medium and is stored；

In some possible embodiments, the arithmetic unit in the multistage pipelining-stage in each pipelining-stage include it is following in Any one or multinomial combination：Addition of matrices arithmetic unit, matrix-vector multiplication arithmetic unit, nonlinear operator and matrix compare Arithmetic unit.

In some possible embodiments, first operational order includes any one of following：Bivector rotates Instruction SVRO, three-dimensional vector rotation instruction TVRO, vector translation instruction VTRAN, vector scaling instruction VZOOM, vector shearing refer to Make VSHEAR.

In some possible embodiments, first operational order is bivector rotation instruction SVRO or three-dimensional vector Rotation instruction TVRO,

The computing device controls the matrix operation unit to utilize first order pipelining-stage according to the selection of multiple selector In nonlinear operator 1 computing mended into row vector to the vector obtain first as a result, inputting first result to the Move and calculate according to the pivot of acquisition and rotation angle execution matrix element in the nonlinear operator of two level pipelining-stage To second Matrix Multiplication is performed into the matrix-vector multiplication arithmetic unit in third level pipelining-stage as a result, inputting second result The 3rd result is calculated in vector；3rd result is inputted to the storage medium and is stored.

In some possible embodiments, first operational order is any one of to give an order：Vector translation refers to VTRAN, vector scaling instruction VZOOM, vectorial shearing instruction VSHEAR are made,

The computing device controls the matrix operation unit to utilize first order pipelining-stage according to the selection of multiple selector In nonlinear operator 1 computing mended into row vector to the vector obtain first as a result, inputting first result to the It is corresponding in the nonlinear operator of two level pipelining-stage to perform any one of following operation to obtain the second result：According to acquisition Shift factor performs the computing of translation matrix structure, the computing of scaled matrix structure is performed according to the zoom factor of acquisition, according to acquisition Shear factor perform shearing matrix structure computing, second result is inputted to the matrix-vector multiplication in third level pipelining-stage Matrix Multiplication vector is performed in method arithmetic unit the 3rd result is calculated；3rd result is inputted to the storage medium and is carried out Storage.

In some possible embodiments, the instruction format of first operational order includes command code and at least one behaviour Make domain, command code is used for the function of indicating the operational order, and arithmetic element is by identifying that the command code can carry out different matrixes Computing, operation domain are used to indicate the data message of the operational order, wherein, data message can be immediate or register number, For example, when obtaining a vector, vector start address and vector can be obtained in corresponding register according to register number Length, the vector of appropriate address storage is obtained further according to vector start address and vector length in storage medium.Alternatively, may be used Any one of following middle information or multinomial combination are obtained in corresponding registers：Vectorial line number, row needed for described instruction Number, data type, mark, storage address (first address) and dimension length, the dimension length refer to vector line length and/ Or the length of vector row.

In some possible embodiments, the vector, which reads instruction, to be included：Vectorial storage needed for described instruction Vectorial mark needed for location or described instruction.

In some possible embodiments, when the vector, which is read, is designated as mark vectorial needed for described instruction,

The computing device controls the matrix operation unit to read instruction according to the vector and is sent out to the storage medium Reading order is sent to include：

It is single that the computing device controls the matrix operation unit to be used according to the mark from the register cell Position reading manner reads the corresponding storage address of the mark；

The computing device controls the matrix operation unit to be sent to the storage medium and reads the storage address Reading order simultaneously obtains the vector using batch reading manner.

In some possible embodiments, the computing device further includes：Buffer unit, the method further include：

Pending operational order is cached in the buffer unit by the computing device.

In some possible embodiments, control the matrix operation unit to obtain the first computing in the computing device and refer to Before order, the method further includes：

The computing device determines first operational order and the second operational order before first operational order With the presence or absence of incidence relation, if first operational order and second operational order there are incidence relation, will described in First operational order is cached in the buffer unit, after second operational order is finished, from the buffer unit Extract first operational order and be transmitted to the arithmetic element；

Described definite first operational order whether there is with the second operational order before the first operational order to be associated System includes：

Required the first vectorial storage address section in first operational order is extracted according to first operational order, Required the second vectorial storage address section in second operational order is extracted according to second operational order, if described First storage address section has overlapping region with the second storage address section, it is determined that first operational order with Second operational order has incidence relation, if the first storage address section and the second storage address section are not With overlapping region, it is determined that first operational order does not have incidence relation with second operational order.

Second aspect, there is provided a kind of computing device, the computing device include being used for the method for performing above-mentioned first aspect Functional unit.

The third aspect, there is provided a kind of computer-readable recording medium, it stores the computer journey for electronic data interchange Sequence, wherein, the computer program causes computer to perform the method that first aspect provides.

Fourth aspect, there is provided a kind of computer program product, the computer program product include storing computer journey The non-transient computer-readable recording medium of sequence, the computer program are operable to make computer perform first aspect offer Method.

5th aspect, there is provided a kind of chip, the chip include the computing device that as above second aspect provides.

6th aspect, there is provided a kind of chip-packaging structure, the chip-packaging structure include as above the 5th aspect and provide Chip.

7th aspect, there is provided a kind of board, the board include the chip-packaging structure that as above the 6th aspect provides.

Eighth aspect, there is provided a kind of electronic equipment, the electronic equipment include the board that as above the 7th aspect provides.

In certain embodiments, the electronic equipment includes data processing equipment, robot, computer, printer, scanning Instrument, tablet computer, intelligent terminal, mobile phone, automobile data recorder, navigator, sensor, camera, server, cloud server, Camera, video camera, projecting apparatus, wrist-watch, earphone, mobile storage, wearable device, the vehicles, household electrical appliance, and/or medical treatment Equipment.

In certain embodiments, the vehicles include aircraft, steamer and/or vehicle；The household electrical appliance include electricity Depending on, air-conditioning, micro-wave oven, refrigerator, electric cooker, humidifier, washing machine, electric light, gas-cooker, kitchen ventilator；The Medical Devices include Nuclear Magnetic Resonance, B ultrasound instrument and/or electrocardiograph.

Implement the embodiment of the present application, have the advantages that：

As can be seen that by the embodiment of the present application, computing device is provided with register cell and storage medium, is respectively used to Store scalar data and vector data, and unit reading manner and batch are read the application for two kinds of memory distributions Mode, the characteristics of by vector data distribution match the data reading mode of its feature, can be good at utilizing bandwidth, avoid Because influence of the bottleneck of bandwidth to vectorial calculating speed, in addition, for register cell, since its storage is scalar Data, there is provided the reading manner of scalar data, improve the utilization rate of bandwidth, so the technical solution that the application provides can Utilize bandwidth well, avoid influence of the bandwidth to calculating speed, so it is fast with calculating speed, it is efficient the advantages of.

Brief description of the drawings

In order to illustrate more clearly of the technical solution in the embodiment of the present application, make required in being described below to embodiment Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the present application, for ability For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached Figure.

Fig. 1 is a kind of structure diagram of computing device provided by the embodiments of the present application.

Fig. 2 is a kind of structure diagram of arithmetic element provided by the embodiments of the present application.

Fig. 3 is a kind of flow diagram of computational methods provided in an embodiment of the present invention.

Fig. 4 A and Fig. 4 B are the configuration diagrams of two kinds of pipelining-stages provided by the embodiments of the present application.

Fig. 5 is the structure diagram of pipelining-stage provided by the embodiments of the present application.

Fig. 6 A and Fig. 6 B are the form schematic diagrams of two kinds of instruction set provided by the embodiments of the present application.

Fig. 7 is the structure diagram of another computing device provided by the embodiments of the present application.

Fig. 8 is the flow chart that computing device provided by the embodiments of the present application performs two-dimensional/three-dimensional vector rotation instruction.

Embodiment

Below in conjunction with the attached drawing in the embodiment of the present application, the technical solution in the embodiment of the present application is carried out clear, complete Site preparation describes, it is clear that described embodiment is some embodiments of the present application, instead of all the embodiments.Based on this Shen Please in embodiment, the every other implementation that those of ordinary skill in the art are obtained without creative efforts Example, shall fall in the protection scope of this application.

Term " first ", " second ", " the 3rd " in the description and claims of this application and the attached drawing and " Four " etc. be to be used to distinguish different objects, rather than for describing particular order.In addition, term " comprising " and " having " and it Any deformation, it is intended that cover non-exclusive include.Such as contain the process of series of steps or unit, method, be The step of system, product or equipment are not limited to list or unit, but alternatively further include the step of not listing or list Member, or alternatively further include for the intrinsic other steps of these processes, method, product or equipment or unit.

Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments It is contained at least one embodiment of the application.Each position in the description occur the phrase might not each mean it is identical Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and Implicitly understand, embodiment described herein can be combined with other embodiments.

It should be noted that this application involves matrix be specifically as follows m*n matrixes, wherein, m and N are more than or equal to 1 Integer, when m or n is 1, is represented by 1*n matrixes or m*1 matrixes, is referred to as vector；When m and n at the same time for 1 when, can be with It is considered as the Special matrix of 1*1.Following matrixes all can be in above-mentioned three types matrix any one, do not repeating below.

The embodiment of the present application provides a kind of computational methods, which can be applied in computing device.It is this such as Fig. 1 A kind of structure diagram of possible computing device shown in inventive embodiments.Computing device as shown in Figure 1 includes：

Storage medium 201, for storage matrix (or vector).The preferable storage medium can be that scratchpad is deposited Reservoir, it would be preferable to support the matrix data (or vector data) of different length；Necessary calculating data are temporarily stored in by the application In scratchpad (Scratchpad Memory), make this arithmetic unit can be more during matrix operation is carried out Flexibly effectively support the data of different length.Above-mentioned storage medium can also be the outer database of piece, database or other energy Medium enough stored etc..

Register cell 202, for storing scalar data, wherein, which includes but not limited to：Matrix data or Vector data (the application is also referred to as matrix/vector) storage medium 201 storage address and vector with matrix operation when Scalar.In one embodiment, register cell can be scalar register heap, there is provided scalar is posted needed for calculating process Storage, scalar register not only store matrix address, and also storage has scalar data.(i.e. matrix is deposited it is to be understood that matrix address Store up address, such as first address) also it is scalar.When being related to the computing of matrix and vector, arithmetic element not only will be from register list Matrix address is obtained in member, corresponding scalar, such as the line number of matrix, columns, matrix function are also obtained from register cell According to type (alternatively referred to as data type), matrix dimension length (the concretely length of row matrix, length of rectangular array etc.).

Arithmetic element 203 (the application is also referred to as matrix operation unit 203), for obtaining and performing the first operational order. As shown in Fig. 2, the arithmetic element includes multiple arithmetic units, which includes but not limited to：Addition of matrices arithmetic unit 2031, square Battle array multiplicative operator 2032, size comparison operation device 2033 (or matrix comparison operation device), 2034 and of nonlinear operator Matrix-vector multiplication arithmetic unit 2035.

This method is as shown in figure 3, include the following steps：

Step S301, arithmetic element 203 obtains the first operational order, and first operational order is used for realization vector and square The computing of battle array, first operational order include：Perform the vector needed for the instruction and read instruction.

In step S301, needed for the above-mentioned execution instruction vector read instruction be specifically as follows it is a variety of, for example, this Apply in an optional technical solution, it can be required vectorial storage that the vector needed for the above-mentioned execution instruction, which reads instruction, Address.And for example, in the application in another optional technical solution, the vector needed for the above-mentioned execution instruction reads instruction can be with For required vectorial mark, the form of expression of the mark can be a variety of, for example, the title of vector, and for example, vectorial identification Number, register number or storage address of the vector in register cell for another example.

Illustrate that above-mentioned first operational order includes below by the example of a reality perform needed for the instruction to Amount reads instruction, it is assumed here that and the vector operation formula is f (x)=A+B, wherein, A, B are vector.So in the first computing In instruction in addition to carrying the vector operation formula, storage address vectorial needed for the vector operation formula can also be carried, is had Body, such as the storage address of A is 0000-0FFF, the storage address of B is 1000-1FFF.And for example, it can carry A's and B Mark, for example, A be identified as 0101, B be identified as 1010.

Step S302, arithmetic element 203 reads instruction according to the vector and sends reading order to the storage medium 201.

The implementation method of above-mentioned steps S302 is specifically as follows：

It can be required vectorial storage address that such as the vector, which reads instruction, and arithmetic element 203 is sent out to the storage medium 201 Give the reading order of the reading storage address and corresponding vector is obtained using batch reading manner.

And for example the vector reads instruction when can be required vectorial mark, and arithmetic element 203 is according to the mark from deposit The corresponding storage address of the mark is read using unit reading manner at device unit, then arithmetic element 203 is to the storage medium 201 send the reading order of the reading storage address and obtain corresponding vector using batch reading manner.

Above-mentioned single reading manner is specifically as follows, and reads every time as the data of unit, i.e. 1bit data.Set at this time The reason for unit reading manner i.e. 1 reading manner, is, for scalar data, the capacity that it takes is very small, if adopted With batch data reading manner, then the data volume of reading is easily more than the capacity of required data, can so cause bandwidth Waste, so using unit reading manner here for the data of scalar and reading to reduce the waste of bandwidth.

Step S303, arithmetic element 203 reads the corresponding vector of the instruction using batch reading manner, which is performed First operational order.

Batch reading manner is specifically as follows in above-mentioned steps S303, and reading every time is the data of multidigit, such as every time The data bits of reading is 16bit, 32bit or 64bit, i.e., no matter the data volume needed for it is how many, it reads equal every time For the data of fixed long number, the data mode that this batch is read is very suitable for the reading of big data, for vector, due to Capacity shared by it is big, if using single reading manner, its speed read can be very slow, so being read here using batch Mode is taken to obtain the data of multidigit so as to quickly read vector data, is avoided because read vector data influences to gauge slowly excessively The problem of calculating speed.

The computing device for the technical solution that the application provides is provided with register cell and storage medium, it stores mark respectively Measure data and vector data, and the application for two kinds of memory distributions unit reading manner and batch reading manner, The characteristics of by vector data distribution match its feature data reading mode, can be good at utilize bandwidth, avoid because of Influence of the bottleneck of bandwidth to vectorial calculating speed, in addition, for register cell, since its storage is scalar number According to there is provided the reading manner of scalar data, the utilization rate of bandwidth being improved, so the technical solution that the application provides can be very Good utilization bandwidth, avoids influence of the bandwidth to calculating speed, so it is fast with calculating speed, it is efficient the advantages of.

Optionally, it is above-mentioned that vector execution first operational order is specifically as follows：

Arithmetic element 203 can use the calculation of multistage pipelining-stage, and the embodiment of the present application can use the meter of i grades of pipelining-stages Calculation mode performs first operational order to the vector.Specifically include following several embodiments.

In the first embodiment, the computing device can also design at least one multiple selector MMUX to realize multistage The calculating of pipelining-stage.It is specific as what Fig. 4 A and 4B were shown respectively pipelining-stage more than two kinds realizes framework.Such as Fig. 4 A, the computing device Can be that each pipelining-stage designs a multiple selector MMUX；Fig. 4 B are shown as multiple pipelining-stages and set a multiple selector MMUX.Multiple selector it is corresponding needed for control/selection pipelining-stage connection, for select the arithmetic unit in the pipelining-stage with Realize relevant calculating.It is to be understood that arithmetic unit of the multiple selector selected in pipelining-stage is according to the first operational order What corresponding calculating network topology determined, specifically it will be described in detail later.

In the specific implementation, arithmetic element 203 can be according to the selection of multiple selector, using selected by first (level) pipelining-stage First choice arithmetic unit to the vector be calculated first and utilized as a result, the first result then is inputted the second pipelining-stage The selected second Selecting operation device of second pipelining-stage perform be calculated second as a result, and so on, the i-th -1 result is defeated Enter into the i-th pipelining-stage to perform using its selected i-th Selecting operation device and i-th of result is calculated.Here i-th of result As export result (being specially output vector).Further, arithmetic element 203 can store the output result to storage medium 201。

What the quantity i of the multistage pipelining-stage was specifically determined according to the calculating topological structure of first operational order, i For positive integer.In general, i=3.May be provided with arithmetic unit correspondingly in each pipelining-stage, the arithmetic unit include but not limited to Any one of lower or multinomial combination：Addition of matrices arithmetic unit, matrix-vector multiplication arithmetic unit, nonlinear operator, matrix Comparison operation device and other matrix operation devices.It is the quantity of arithmetic unit and arithmetic unit included in each pipelining-stage Can there are user side or the self-defined setting in computing device side, not limit.

With i=3, exemplified by three-level flowing water, arithmetic element can select the first pipelining-stage respectively extremely by three multiple selector The respective required arithmetic unit (alternatively referred to as arithmetic unit) used in 3rd pipelining-stage；Meanwhile the first flowing water is performed to the vector Level is calculated first as a result, the first result is input to calculating for the second pipelining-stage the second pipelining-stage of execution by (optional) To second as a result, (optional) by the second result be input to the 3rd pipelining-stage perform the 3rd pipelining-stage be calculated the 3rd as a result, (optional) stores the 3rd result to storage medium 201.As Fig. 5 shows a kind of operating process schematic diagram of pipelining-stage.

Above-mentioned first pipelining-stage includes but not limited to：Matrix multiplication operation device etc..

Above-mentioned second pipelining-stage includes but not limited to：Addition of matrices arithmetic unit, size comparison operation device etc..

Above-mentioned 3rd pipelining-stage includes but not limited to：Nonlinear operator, matrix-vector multiplication arithmetic unit, matrix scalar multiplication Method arithmetic unit etc..

By three pipelining-stage computings of vector point primarily to improving the speed of computing, for the calculating for vector, example Such as using general processor when calculating, the step of its computing, is specifically as follows, and processor carries out vector to be calculated first As a result, then by the storage of the first result in memory, processor from memory reads the first result and performs is calculated for the second time Two as a result, then by the storage of the second result in memory, processor is calculated for the third time from interior performed from the second result of reading 3rd as a result, then by the storage of the 3rd result in memory.It can be seen that from the step of above-mentioned calculating and carried out in general processor When vector calculates, it does not shunt water level and is calculated, then be required to after calculating every time the data that will have been calculated into Row preservation, needs to again read off when next time calculates, so this scheme needs repetition storage to read multiple data, for the application's For technical solution, the first result that the first pipelining-stage calculates is directly entered the grading row calculating of the second flowing water, the second pipelining-stage meter The second result calculated enters directly into the 3rd pipelining-stage and is calculated, the first result that the first pipelining-stage and the second pipelining-stage calculate With the second result without storage, which reduce the occupied space of memory first, secondly, which obviate result multiple storage and Read, improve the utilization rate of bandwidth, further increase computational efficiency.

In another embodiment of the application, each flowing water component can be freely combined or take level-one pipelining-stage.Such as will Second pipelining-stage and the 3rd pipelining-stage merge, and either all merge first and second and the 3rd assembly line or each Pipelining-stage is responsible for different computings can be with permutation and combination.For example, first order flowing water is responsible for comparison operation, and partial product computing, Two level flowing water is responsible for the combination such as nonlinear operation and matrix-vector multiplication.It is that the i pipelining-stage designed in the application is supported to appoint Multiple pipelining-stages of anticipating are in parallel, connect and merge, and to form different permutation and combination, the application does not limit.

It should be noted that being also provided with sky option in each multiple selector, i.e., it is connected with the multiple selector Pipelining-stage and follow-up pipelining-stage are not involved in computing.It that is to say, sky option described herein is used to indicate to select with the multichannel Select the kth level pipelining-stage of device connection and follow-up kth+1 not performs to i-stage pipelining-stage and calculates operation, wherein, k is Positive integer less than or equal to i.

With i=3, exemplified by three-level flowing water, if the multiple selector selected as sky option of the 3rd pipelining-stage of connection, the 3rd Pipelining-stage is not involved in computing, and the current pipelining-stage for performing arithmetic operation is less than three；For example, certain operational order is instructed comprising two-stage, Then the corresponding multiple selector of the 3rd pipelining-stage chooses sky option.

Using above-mentioned computing device (be designed with multiple selector select to need in every grade of pipelining-stage the arithmetic unit that uses/ Arithmetic unit), have the advantages that：In addition to bandwidth is improved, while have that logic is clear and definite, the output result of no arithmetic unit From rear pipelining-stage redirecting to preceding pipelining-stage, the characteristics of input interface and output interface are single, good operability.

In second of embodiment, the computing device can be that the fixation pipelining-stage of every kind of operational order design correspondingly is real Existing framework.The corresponding three-level pipelining-stage of a kind of operational order as shown in figure 5 above realizes framework.It is to refer to for certain computing For order, arithmetic unit included in each pipelining-stage is that the fixed setting in advance of user side or the computing device side is good, this The alternatively referred to as fixed arithmetic unit of application.In addition, fixation arithmetic unit in each pipelining-stage can it is identical also can be different, typically not Identical.For example, the first pipelining-stage is addition of matrices arithmetic unit, second level flowing water is matrix multiplication operation device, third level flowing water For nonlinear operator；And for example, the first pipelining-stage is addition of matrices arithmetic unit, and second level flowing water is addition of matrices arithmetic unit, the Three-level flowing water is matrix multiplication operation device etc..I.e. different operational orders, is related to different flowing water stage arrangements (realizing framework). It is to be understood that realizing demand according to what nonidentity operation instructed, the quantity i of its pipelining-stage being related to can be different, can correspond to increase or Less, the application does not limit.

In the specific implementation, arithmetic element 203 utilizes the fixation arithmetic unit in first (level) pipelining-stage to the vector successively First be calculated as a result, the first result is inputted the second pipelining-stage to be calculated using the fixation arithmetic unit execution in it To second as a result, and so on, until the i-th -1 result is inputted to the i-th pipelining-stage to be held using the fixation arithmetic unit in it I-th of result is calculated in row.Here i-th of result is to export result (being specially output vector).Further, computing list Member 203 can store the output result to storage medium 201.Quantity i and each pipelining-stage on the multistage pipelining-stage The fixation arithmetic unit of middle design can be found in the related elaboration in previous embodiment, and which is not described herein again.

With i=3, exemplified by three-level flowing water.Referring to earlier figures 5, a kind of the fixed real of the corresponding pipelining-stage of operational order is shown Existing framework.Specifically, the multiplication that arithmetic element performs the vector the first pipelining-stage is calculated first as a result, by the first result The additional calculation for being input to the second pipelining-stage the second pipelining-stage of execution obtains second as a result, the second result is input to the 3rd flowing water The NONLINEAR CALCULATION that level performs the 3rd pipelining-stage obtains the 3rd as a result, storing the 3rd result (exporting result) to storage medium 201。

It should be noted that the arithmetic unit in above-mentioned computing device in each pipelining-stage be in advance it is self-defined set, Once it is determined that do not allow to change；That is i grades of pipelining-stage may be designed as the permutation and combination of any arithmetic unit, i grades of pipelining-stages once driving not Change again, different operational orders can design different i level flowing water stage arrangements.Wherein, which can be according to specific instruction Demand, the quantity of adaptability increase/less pipelining-stage.Finally, the flowing water stage arrangement designed for different instruction can be combined Together, the computing device is formed.

Using above-mentioned computing device (i.e. arithmetic unit/arithmetic unit design in every grade of pipelining-stage is fixed), have with following Beneficial effect：In addition to bandwidth is improved, have specificity high, without unnecessary logic judgment, further improve operational performance, arithmetic speed The characteristics of fast.

Optionally, above-mentioned computing device can also include：Buffer unit 204, for caching the first operational order.Instruction exists In implementation procedure, while also it is buffered in instruction cache unit, after an instruction has performed, if the instruction is at the same time It is not to be submitted an instruction earliest in instruction in instruction cache unit, which will carry on the back and submits, once submit, this instruction Change of the operation of progress to unit state will be unable to cancel.In one embodiment, instruction cache unit can be reset Sequence caches.

Optionally, the above method can also include before step S301：

Determine that first operational order whether there is incidence relation with the second operational order before the first operational order, such as First operational order there are incidence relation, is then performed with the second operational order before the first operational order in the second operational order After finishing, first operational order is extracted from buffer unit and is transferred to arithmetic element 203.If the first operational order is with being somebody's turn to do Instruction onrelevant relation before first operational order, then be directly transferred to arithmetic element by the first operational order.

Above-mentioned definite first operational order whether there is with the second operational order before the first operational order to be associated The concrete methods of realizing of system can be：

Required the first vectorial storage address section, foundation in first operational order are extracted according to first operational order Second operational order extracts required the second vectorial storage address section in second operational order, such as the first stored address area Between with the second storage address section there is overlapping region, it is determined that the first operational order has with the second operational order to be associated System.Such as the first storage address section and the non-overlapping region in the second storage address section, it is determined that the first operational order and second Operational order does not have incidence relation.

There is overlapping region the first operational order of explanation occur in trivial of this storage and have accessed phase with the second operational order Same vector, for vector, is as judgement since the space of its storage is bigger, such as using identical storage region The no condition for incidence relation, in fact it could happen that situation be, the second operational order access storage region contain the first computing The storage region accessed is instructed, is deposited for example, the second operational order accesses A vectors storage region, B vectors storage region and C vectors Storage area domain, if A, B storage region are adjacent or A, C storage region are adjacent, the second operational order access storage region be, A, B storage regions and C storage regions, or A, C storage region and B storage regions.In this case, if the first operational order The storage region for A vectors and D vectors accessed, then the vectorial storage region that the first operational order accesses can not be with second The vectorial storage region of operational order model essay is identical, if using identical Rule of judgment, it is determined that the first operational order with Second operational order does not associate, but it was verified that the first operational order and the second operational order belong to incidence relation at this time, institute With the application by whether have overlapping region to determine whether for incidence relation condition, the erroneous judgement of the above situation can be avoided.

Illustrate which kind of situation belongs to incidence relation below with the example of a reality, which kind of situation belongs to dereferenced pass System.It is assumed here that the vector needed for the first operational order is A vector sums D vectors, the storage region of wherein A vectors is【0001, 0FFF】, the storage region of D vectors is【A000, AFFF】, it is A vectors, B vector sums C for the vector needed for the second operational order Vector, its corresponding storage region are【0001,0FFF】、【1000,1FFF】、【B000, BFFF】, refer to for the first computing For order, its corresponding storage region is：【0001,0FFF】、【A000, AFFF】, for the second operational order, it is corresponded to Storage region be：【0001,1FFF】、【B000, BFFF】, so the storage region of the second operational order and the first operational order Storage region there is overlapping region【0001,0FFF】, so the first operational order has incidence relation with the second operational order.

It is assumed here that the vector needed for the first operational order is E vector sums D vectors, the storage region of wherein A vectors is 【C000, CFFF】, the storage region of D vectors is【A000, AFFF】, it is A vectors, B for the vector needed for the second operational order Vector sum C vectors, its corresponding storage region are【0001,0FFF】、【1000,1FFF】、【B000, BFFF】, for For one operational order, its corresponding storage region is：【C000, CFFF】、【A000, AFFF】, come for the second operational order Say, its corresponding storage region is：【0001,1FFF】、【B000, BFFF】, so the storage region of the second operational order and the The storage region of one operational order does not have overlapping region, so the first operational order and the second operational order onrelevant relation.

In the application, if Fig. 6 A are a kind of instruction (concretely the first operational order, or operation that the application provides Instruction) instruction set form schematic diagram, as shown in Figure 6A, operational order includes a command code and an at least operation domain, wherein, Command code is used to indicate the function of the operational order, arithmetic element by identifying that the command code can carry out different vector operations, Operation domain is used to indicate the data message of the operational order, wherein, data message can be immediate or register number, for example, When obtaining a vector, vector start address and vector length can be obtained in corresponding register according to register number, The vector of appropriate address storage is obtained in storage medium further according to vector start address and vector length.

I.e. the first operational order can include：Operation domain and at least one command code, by taking vector operation instruction as an example, such as Shown in table 1, wherein, register 0, register 1, register file 2, register 3, register 4 can be operation domain.Wherein, each Register 0, register 1, register 2, register 3, register 4 be used for marker register numbering, its can be one or Multiple registers.It is to be understood that the quantity of register does not limit in command code, each register is used to storage computing and refers to The related data information of order.

If Fig. 6 B are the fingers for another instruction (can be the first operational order, be alternatively referred to as operational order) that the application provides Make collection form schematic diagram, as shown in Figure 6B, instruction include at least two command codes and at least an operation domain, wherein, it is described extremely Few two command codes include the first command code and the second command code (diagram is respectively command code 1 and command code 2).The command code 1 is used for the type (i.e. certain major class instruction) of indicator, such as can concretely I/O instruction, logical order or operational order etc. Deng, the command code 2 is used for the function (explanation of the specific instruction i.e. under major class instruction) of indicator, such as in operational order Matrix operation command (such as Matrix Multiplication vector instruction MMUL, matrix inversion command M INV), vector operation instruction is (as vector is asked Lead instruction VDIER etc.) etc., the application does not limit.

It is to be understood that the form of instruction can be user side or the self-defined setting in computing device side.The behaviour of instruction Regular length, such as 8bit, 16bit etc. are may be designed as code.Instruction format as shown in Fig. 6 A has the advantage that feature： Command code occupancy digit is few, decoding system design is simple.Instruction format as shown in Fig. 6 B has the advantage that feature：It is variable Long, decoding average efficiency higher, in the case that certain major class instructs lower specific instruction less and calls frequency height, design its second The length of command code (i.e. command code 2) is short and small, can improve decoding efficiency.Moreover it is possible to strengthen the readable and expansible of instruction Property, optimizes the coding structure of instruction.

In the embodiment of the present application, instruction set includes the operational order of difference in functionality, concretely：

Bivector rotation instruction (SVRO), according to the instruction, device from memory (preferable scratchpad or Person's scalar register heap) specified address take out formulate size vector data and make augmentation form into, from scalar register heap The pivot coordinate data specified and pivoting angle data are taken out, spin matrix is generated, Matrix Multiplication is carried out in arithmetic element The multiplying of vector, and result of calculation is written back to memory (preferable scratchpad or scalar register heap) Specified address.What deserves to be explained is vector can be stored in as the matrix (the only matrix of a row element) of special shape In scratchpad.Here memory can include but are not limited to scratchpad, similarly hereinafter.

Three-dimensional vector rotation instruction (TVRO), according to the instruction, device from memory (preferable scratchpad or Person's scalar register heap) specified address take out formulate size vector data and make augmentation form into, from scalar register heap Take out the rotation axis data specified and pivoting angle data, generate spin matrix, carried out in matrix operation unit Matrix Multiplication to The multiplying of amount, and result of calculation is written back to the specified address of memory；What deserves to be explained is vector can be used as it is special The matrix (the only matrix of a row element) of form is stored in scratchpad.

Vector translation instruction (VTRAN) according to the instruction, device taken out from the specified address of memory formulate size to Amount data simultaneously make augmentation form into, and the data that each translation direction specified is taken out from scalar register heap generate translation matrix, The multiplying of Matrix Multiplication vector is carried out in matrix operation unit, and result of calculation is recovered into original dimension from augmentation form and is write back To the specified address of memory；What deserves to be explained is vector can be as matrix (the only square of a row element of special shape Battle array) it is stored in scratchpad.

Vector scaling instruction (VZOOM) according to the instruction, device taken out from the specified address of memory formulate size to Amount data simultaneously make augmentation form into, and the scaling amplitude data specified, generation shearing matrix, in matrix are taken out from scalar register heap The multiplying of Matrix Multiplication vector is carried out in arithmetic element, and result of calculation is written back to the specified address of memory；It is worth saying Bright, vector can be stored in scratchpad as the matrix (the only matrix of a row element) of special shape.

Vectorial shearing instruction (VSHEAR) according to the instruction, device taken out from the specified address of memory formulate size to Amount data simultaneously make augmentation form into, and all directions amplitude data specified, generation shearing matrix, in square are taken out from scalar register heap The multiplying of Matrix Multiplication vector is carried out in battle array arithmetic element, and result of calculation is written back to the specified address of memory；It is worth Illustrate, vector can be stored in scratchpad as the matrix (the only matrix of a row element) of special shape In.

It is to be understood that operation/operational order that the application proposes is mainly used for input vector form and output vector form Arithmetic operation, not limit calculating process caused by intermediate data form.Designed in the application in every grade of pipelining-stage Arithmetic unit is including but not limited to any one of following or multinomial combination：Addition of matrices arithmetic unit, matrix multiplication operation device, square Battle array vector multiplication arithmetic unit, nonlinear operator, matrix comparison operation device.

Be exemplified below this application involves operational order (i.e. the first operational order) calculating.

By taking first operational order is bivector rotation instruction SVRO as an example, calculate the two dimension of given pivot to Amount.During specific implementation, bivector X (x, y), pivot (a, b) and rotation angle c are given, is calculated according to equation below The rotating vector of given vector X.

Correspondingly, the instruction format of bivector rotation instruction SVRO is specially：

With reference to previous embodiment, arithmetic element can obtain bivector rotation instruction SVRO, and after being decoded to it, from deposit Vector X, pivot and rotation angle are read in device unit, non-linear fortune is chosen using the multiple selector of the first pipelining-stage Calculation device carries out vectorial X the operation of benefit 1 and obtains the first result (what is concretely formed after the operation of benefit 1 treats rotating vector)；Profit at the same time Nonlinear operator is chosen with the multiple selector of the second pipelining-stage, and rotation is performed according to the pivot and rotation angle of reading Matrix structure computing (optional, further relate to matrix element moves operation) obtains the second result with correspondence and (concretely rotates Matrix)；The multiple selector that first result and second result are inputted to the 3rd pipelining-stage chooses matrix-vector multiplication Method arithmetic unit performs Matrix Multiplication vector operation (specially treat rotating vector and spin matrix performs Matrix Multiplication vector operation) and obtains To the 3rd result (exporting result).Alternatively, the 3rd result is stored into storage medium.Optionally, can also be by described in First result is inputted into the second pipelining-stage, is disregarded, to wait the second pipelining-stage to be obtained together after building spin matrix Second result.I.e. second result includes spin matrix and treats rotating vector at this time, so as to subsequently only by second result Input is handled to obtain output result into the 3rd pipelining-stage.

By taking first operational order is three-dimensional vector rotation instruction TVRO as an example, the rotation in three dimensions is carried out.Tool When body is realized, a three-dimensional vector X (x, y, z), pivot (u, v, w) and rotation angle c are given, is calculated according to equation below Postrotational three-dimensional vector.

Correspondingly, the instruction format of three-dimensional vector rotation instruction TVRO is specially：

With reference to previous embodiment, arithmetic element can obtain three-dimensional vector rotation instruction TVRO, and after being decoded to it, from deposit Vector X, pivot and rotation angle are read in device unit, non-linear fortune is chosen using the multiple selector of the first pipelining-stage Calculation device carries out vectorial X the operation of benefit 1 and obtains the first result (what is concretely formed after the operation of benefit 1 treats rotating vector)；Profit at the same time Nonlinear operator is chosen with the multiple selector of the second pipelining-stage, and rotation is performed according to the pivot and rotation angle of reading Matrix structure computing (optional, further relate to matrix element moves operation) obtains the second result with correspondence and (concretely rotates Matrix)；The multiple selector that first result and second result are inputted to the 3rd pipelining-stage chooses matrix-vector multiplication Method arithmetic unit performs Matrix Multiplication vector operation (specially treat rotating vector and spin matrix performs Matrix Multiplication vector operation) and obtains To the 3rd result (exporting result).Alternatively, the 3rd result is stored into storage medium.Optionally, can also be by described in First result is inputted into the second pipelining-stage, is disregarded, to wait the second pipelining-stage to be obtained together after building spin matrix Second result.I.e. second result includes spin matrix and treats rotating vector at this time, so as to subsequently only by second result Input is handled to obtain output result into the 3rd pipelining-stage.

By taking first operational order instructs VTRAN for vector translation as an example, the translation vector for giving vector is calculated.Specifically When realizing, vector X (x are given₁,x₂,x₃,..x_n) and translation vector Y (d_x1,d_x2,…d_xn) (alternatively referred to as shift factor), press The vector after the translation of given vector X is calculated according to equation below.

Correspondingly, the instruction format of vector translation instruction VTRAN is specially：

With reference to previous embodiment, arithmetic element can obtain vector translation instruction VTRAN, and after being decoded to it, from register Vector X and translation vector Y is read in unit, nonlinear operator is chosen to vectorial X using the multiple selector of the first pipelining-stage Carry out the operation of benefit 1 and obtain the first result (what is concretely formed after the operation of benefit 1 treats translation vector)；Utilize the second pipelining-stage at the same time Multiple selector choose nonlinear operator according to the translation vector Y of reading perform the computing of translation matrix structure (it is optional, also Be related to matrix element moves operation) the second result (concretely translation matrix) is obtained with correspondence；By first result and Second result inputs to the multiple selector of the 3rd pipelining-stage and chooses matrix-vector multiplication arithmetic unit execution Matrix Multiplication vector Computing (specially treat translation vector and translation matrix performs Matrix Multiplication vector operation) obtains the 3rd result (exporting result). Alternatively, the 3rd result is stored into storage medium.Optionally, first result can be also inputted to the second pipelining-stage In, disregard, to wait the second pipelining-stage to obtain the second result together after building translation matrix.That is second knot at this time Fruit includes translation matrix and treats translation vector, is handled subsequently only to input second result into the 3rd pipelining-stage Obtain output result.

By taking first operational order instructs VZOOM for vector scaling as an example, the scale vectors for giving vector are calculated.Specifically When realizing, vector X (x are given₁,x₂,x₃,..x_n) and zoom factor a, according to equation below calculate the scaling of given vector X to Amount.

Correspondingly, the instruction format of vector scaling instruction VZOOM is specially：

With reference to previous embodiment, arithmetic element can obtain vector scaling instruction VZOOM, and after being decoded to it, from register Vector X and zoom factor a is read in unit, nonlinear operator is chosen to vectorial X using the multiple selector of the first pipelining-stage Carry out the operation of benefit 1 and obtain the first result (what is concretely formed after the operation of benefit 1 treats scale vectors)；Utilize the second pipelining-stage at the same time Multiple selector choose nonlinear operator according to the zoom factor a of reading perform the computing of scaled matrix structure (it is optional, also Be related to matrix element moves operation) the second result (concretely scaled matrix) is obtained with correspondence；By first result and Second result inputs to the multiple selector of the 3rd pipelining-stage and chooses matrix-vector multiplication arithmetic unit execution Matrix Multiplication vector Computing (specially treat scale vectors and scaled matrix performs Matrix Multiplication vector operation) obtains the 3rd result (exporting result). Alternatively, the 3rd result is stored into storage medium.Optionally, first result can be also inputted to the second pipelining-stage In, disregard, to wait the second pipelining-stage to obtain the second result together after building scaled matrix.That is second knot at this time Fruit includes scaled matrix and treats scale vectors, is handled subsequently only to input second result into the 3rd pipelining-stage Obtain output result.

By taking first operational order is vectorial shearing instruction VSHEAR as an example, the shearing matrix to set matrix is calculated.Tool When body is realized, vector X (x are given₁,x₂,x₃,..x_n) and shear vector Y (d₁,d₂,…d_n) (alternatively referred to as shear factor), press The vector after the shearing of given vector X is calculated according to equation below.

Correspondingly, the instruction format of vectorial shearing instruction VSHEAR is specially：

With reference to previous embodiment, arithmetic element can obtain vectorial shearing instruction VSHEAR, and after being decoded to it, from register Vector X and shear vector Y is read in unit, nonlinear operator is chosen to vectorial X using the multiple selector of the first pipelining-stage Carry out the operation of benefit 1 and obtain the first result (what is concretely formed after the operation of benefit 1 treats shear vector)；Utilize the second pipelining-stage at the same time Multiple selector choose nonlinear operator according to the shear vector Y of reading perform the computing of shearing matrix structure (it is optional, also Be related to matrix element moves operation) the second result (concretely shearing matrix) is obtained with correspondence；By first result and Second result inputs to the multiple selector of the 3rd pipelining-stage and chooses matrix-vector multiplication arithmetic unit execution Matrix Multiplication vector Computing (specially treat shear vector and shearing matrix performs Matrix Multiplication vector operation) obtains the 3rd result (exporting result). Alternatively, the 3rd result is stored into storage medium.Optionally, first result can be also inputted to the second pipelining-stage In, disregard, to wait the second pipelining-stage to obtain the second result together after building shearing matrix.That is second knot at this time Fruit includes shearing matrix and treats shear vector, is handled subsequently only to input second result into the 3rd pipelining-stage Obtain output result.

It should be noted that the acquisition and decoding of above-mentioned various operational orders will be described in detail later.Ying Li Solution, each operational order (such as bivector rotation instruction SVRO, three-dimensional vector rotation are realized using the structure of above-mentioned computing device Turn instruction TVRO etc.) calculating, following beneficial effect can be obtained：Support the vector format that stores at regular intervals, avoid pair The executive overhead and the space hold of storage intermediate result that vector format is converted；Support to store information converting with scalar value, Avoid the storage overhead of spin matrix.

Setting length in aforesaid operations instruction (i.e. vector operation instruction/first operational order) can voluntarily be set by user Fixed, in an optional embodiment, which can be arranged to a value by user, certainly in practical applications, The setting length can also be arranged to multiple values by user.The application embodiment does not limit the specific of the setting length Value and number.For the purpose, technical scheme and advantage of the application are more clearly understood, below in conjunction with specific embodiment, and Referring to the drawings, the application is further described.

Refering to Fig. 7, Fig. 7 is another computing device 50 that the application embodiment provides.Shown in Fig. 7, dress is calculated Putting 50 includes：Storage medium 501, register cell 502 (preferably scalar data storage unit, scalar register unit), Arithmetic element 503 (can also claim matrix operation unit 503) and control unit 504；

Storage medium 501, for storage matrix (or vector)；

Scalar data storage unit 502, for storing scalar data, the scalar data includes at least：The matrix ( Can be vector) storage address in the storage medium；

Control unit 504, for controlling the arithmetic element to obtain the first operational order, first operational order is used for Realize the computing between vector and matrix, the vector that first operational order includes performing needed for described instruction reads instruction；

Arithmetic element 503, reading order is sent for reading instruction according to the vector to the storage medium；Foundation is adopted The vector is read with batch reading manner and reads the corresponding vector of instruction, and first operational order is performed to the vector.

Optionally, above-mentioned vector reads instruction and includes：Vectorial storage address or described instruction institute needed for described instruction Need the mark of vector.

Optionally during mark vectorial as needed for the vector reading is designated as described instruction,

Control unit 504, for controlling the arithmetic element to go out according to the mark from the register cell using single Position reading manner reads the corresponding storage address of the mark, controls the arithmetic element to be sent to the storage medium and reads institute State the reading order of storage address and the vector is obtained using batch reading manner.

Optionally, arithmetic element 503, specifically for the calculation using multistage pipelining-stage, institute is performed to the vector State the first operational order.

Optionally, each pipelining-stage in the multistage pipelining-stage includes at least one arithmetic unit,

Arithmetic element 503, specifically for the selection according to multiple selector, utilizes the first choice in first order pipelining-stage Arithmetic unit to the vector be calculated first as a result, first result to be input to second in the pipelining-stage of the second level Selecting operation device perform be calculated second as a result, and so on, until inputting the i-th -1 result into i-stage pipelining-stage The i-th Selecting operation device perform i-th of result is calculated；I-th of result is inputted to the storage medium and is deposited Storage；Wherein, the quantity i of the multistage pipelining-stage is determined according to the calculating topological structure of first operational order, and i is Positive integer.

Optionally, each pipelining-stage in the multistage pipelining-stage is each configured with corresponding multiple selector, described more Road selector, which is set, free option, the sky option be used to indicating the kth level pipelining-stage being connected with the multiple selector and Follow-up kth+1 not performs to i-stage pipelining-stage and calculates operation, wherein, k is the positive integer less than or equal to i.

Optionally, the quantity of the arithmetic unit included by each pipelining-stage in the multistage pipelining-stage and the arithmetic unit It is by user side or the self-defined setting in computing device side.

Optionally, each pipelining-stage in the multistage pipelining-stage includes pre-set fixed arithmetic unit, described every Fixation arithmetic unit in a pipelining-stage differs,

Arithmetic element 503, for the vector to be calculated using the fixation arithmetic unit in first order pipelining-stage First as a result, the fixation arithmetic unit first result being input in the pipelining-stage of the second level performs and the second knot is calculated Fruit, and so on, it is calculated i-th until the i-th -1 result is inputted to the fixation arithmetic unit in i-stage pipelining-stage to perform As a result；I-th of result is inputted to the storage medium and is stored；Wherein, the quantity i of the multistage pipelining-stage is root Determined according to the calculating topological structure of first operational order, and i is positive integer.

Optionally, the arithmetic unit in the multistage pipelining-stage in each pipelining-stage includes any one of following or multinomial Combination：Addition of matrices arithmetic unit, matrix multiplication operation device, matrix-vector multiplication arithmetic unit, nonlinear operator and matrix ratio Compared with arithmetic unit.

Optionally, first operational order is bivector rotation instruction SVRO or three-dimensional vector rotation instruction TVRO,

Arithmetic element 503, for the selection according to multiple selector, utilizes the nonlinear operator in first order pipelining-stage 1 computing is mended into row vector to the vector and obtains first as a result, utilizing the nonlinear operator root in the pipelining-stage of the second level at the same time Matrix element is performed according to the pivot and rotation angle of acquisition move be calculated second as a result, by first result and institute State the second result and input into the matrix-vector multiplication arithmetic unit in third level pipelining-stage and perform Matrix Multiplication vector and be calculated the Three results；3rd result is inputted to the storage medium and is stored.

Optionally, first operational order is any one of to give an order：Vector translation instruction VTRAN, vector contracting Instruction VZOOM, vectorial shearing instruction VSHEAR are put,

Arithmetic element 503, for the selection according to multiple selector, utilizes the nonlinear operator in first order pipelining-stage 1 computing is mended into row vector to the vector and obtains first as a result, utilizing the nonlinear operator pair in the pipelining-stage of the second level at the same time Any one of following operation should be performed to obtain the second result：Translation matrix structure fortune is performed according to the shift factor of acquisition Calculate, the computing of scaled matrix structure is performed according to the zoom factor of acquisition, shearing matrix structure is performed according to the shear factor of acquisition Computing, first result and second result are inputted into the matrix-vector multiplication arithmetic unit in third level pipelining-stage and held Row matrix multiplies vector and the 3rd result is calculated；3rd result is inputted to the storage medium and is stored.

Optionally, the computing device further includes：

Buffer unit 505, for caching pending operational order；

Described control unit 504, for pending operational order to be cached in the buffer unit 504.

Optionally, control unit 504, for determining the before first operational order and first operational order Two operational orders whether there is incidence relation, such as first operational order and second operational order there are incidence relation, Then by first operational order caching with the buffer unit, after second operational order is finished, from described Buffer unit extracts first operational order and is transmitted to the arithmetic element；

Required the first vectorial storage address section in first operational order is extracted according to first operational order, Required the second vectorial storage address section in second operational order is extracted according to second operational order, such as described the One storage address section has overlapping region with the second storage address section, it is determined that first operational order and institute Stating the second operational order has incidence relation, and such as the first storage address section does not have with the second storage address section Overlapping region, it is determined that first operational order does not have incidence relation with second operational order.

Optionally, above-mentioned control unit 503, can be used for obtaining operational order from instruction cache unit, and to the computing After instruction is handled, there is provided to the arithmetic element.Wherein, control unit 503 can be divided into three modules, be respectively： Fetching module 5031, decoding module 5032 and instruction queue module 5033,

Fetching module 5031, for obtaining operational order from instruction cache unit；

Decoding module 5032, for the operational order to acquisition into row decoding；

Instruction queue 5033, for after decoding operational order carry out sequential storage, it is contemplated that different instruction comprising Register on there may exist dependence, for cache decode after instruction, launch after dependence is satisfied and refer to Order.

Refering to Fig. 8, Fig. 8 is the flow chart that computing device provided by the embodiments of the present application performs operational order, such as Fig. 8 institutes Show, the hardware configuration of the computing device is refering to the structure shown in Fig. 7, and storage medium as shown in Figure 7 is with scratchpad Exemplified by, performing the process of two-dimensional/three-dimensional vector rotation instruction includes：

Step S601, computing device control fetching module take out two-dimensional/three-dimensional vector rotation instruction, and by two dimension/tri- Decoding module is sent in dimensional vector rotation instruction.

Step S602, decoding module decode the two-dimensional/three-dimensional vector rotation instruction, and two-dimensional/three-dimensional vector is revolved Turn instruction and be sent to instruction queue.

Step S603, in instruction queue, which needs to obtain from scalar register heap The data in scalar register in instruction corresponding to six operation domains, which includes input vector address, input vector is grown Degree, input pivot vector address, input pivot scalar, output vector address, output vector length.

Step S604, control unit determine the two-dimensional/three-dimensional vector rotation instruction and two-dimensional/three-dimensional vector rotation instruction Operational order before whether there is incidence relation, such as there are incidence relation, two-dimensional/three-dimensional vector rotation instruction is deposited into slow Memory cell, is such as not present associate management, which is transmitted to arithmetic element.

Step S605, the data in scalar register of the arithmetic element according to corresponding to six operation domains from storage (preferably Scratchpad or scalar register heap) in take out the vector data (optional, also including scalar data) needed, Then vector rotation operation is completed in arithmetic element.

Step S606, after the completion of arithmetic element computing, write the result into memory (preferable scratchpad or Scalar register heap) specified address, reorder caching in the two-dimensional/three-dimensional vector rotation instruction be submitted.

Optionally, in above-mentioned steps S605 when arithmetic element performs vector rotation operation, the computing device can use Nonlinear operator, which performs, mends 1 operation and spin matrix structure operation, then performs square using matrix-vector multiplication arithmetic unit Battle array multiplies vector and corresponding rotating vector is calculated.

In the specific implementation, after decoding module decodes the two-dimensional/three-dimensional vector rotation instruction, according to caused by decoding Control signal, by the vector input acquired in S603 to via the selected nonlinear operation of first order pipelining-stage multiple selector Device performs the operation of benefit 1 and obtains the first result (treating rotating vector)；At the same time by the pivot and rotation angle acquired in S603 Input builds to obtain the to performing spin matrix via the selected nonlinear operator of multiple selector in the pipelining-stage of the second level Two results (i.e. spin matrix), then input first result and second result into third level pipelining-stage via more Matrix Multiplication vector operation is performed in the selected matrix-vector multiplication arithmetic unit of road selector and obtains the 3rd result.Further, The multiple selector of level Four pipelining-stage would know that the level is empty option according to control signal.Correspondingly, the 3rd result is made To export as a result, being directly transferred to output terminal.

Operational order in above-mentioned Fig. 8 is by taking two-dimensional/three-dimensional vector rotation instruction as an example, in practical applications, as shown in Figure 8 Two-dimensional/three-dimensional vector rotation instruction in embodiment can use vector translation instruction, the instruction of vector scaling, vectorial shearing instruction etc. Vector operation/operational order is replaced, and is not repeated one by one here.

The embodiment of the present application also provides a kind of computer-readable storage medium, wherein, computer-readable storage medium storage is used for electricity The computer program that subdata exchanges, it is any as described in above-mentioned embodiment of the method which make it that computer is performed Implementation section or Overall Steps.

The embodiment of the present application also provides a kind of computer program product, and the computer program product includes storing calculating The non-transient computer-readable recording medium of machine program, the computer program are operable to make computer perform such as above-mentioned side Any implementation section or Overall Steps described in method embodiment.

The embodiment of the present application additionally provides a kind of accelerator, including：Memory：It is stored with executable instruction；Processor： For performing the executable instruction in storage unit, in execute instruction according to the embodiment described in above method embodiment into Row operation.

Wherein, processor can be single processing unit, but can also include two or more processing units.In addition, Processor can also include general processor (CPU) or graphics processor (GPU)；It is additionally may included in field programmable logic Gate array (FPGA) or application-specific integrated circuit (ASIC), to be configured to neutral net and computing.Processor can also wrap Include the on-chip memory for caching purposes (i.e. including the memory in processing unit).

In some embodiments, a kind of chip is also disclosed, is used to perform above method embodiment institute that includes above-mentioned Corresponding neural network processor.

In some embodiments, a kind of chip-packaging structure is disclosed, that includes said chip.

In some embodiments, a kind of board is disclosed, that includes said chip encapsulating structure.

In some embodiments, a kind of electronic equipment is disclosed, that includes above-mentioned board.

Electronic equipment include data processing equipment, robot, computer, printer, scanner, tablet computer, intelligent terminal, Mobile phone, automobile data recorder, navigator, sensor, camera, server, cloud server, camera, video camera, projecting apparatus, hand Table, earphone, mobile storage, wearable device, the vehicles, household electrical appliance, and/or Medical Devices.

The vehicles include aircraft, steamer and/or vehicle；The household electrical appliance include TV, air-conditioning, micro-wave oven, Refrigerator, electric cooker, humidifier, washing machine, electric light, gas-cooker, kitchen ventilator；The Medical Devices include Nuclear Magnetic Resonance, B ultrasound instrument And/or electrocardiograph.

It should be noted that for foregoing each method embodiment, in order to be briefly described, therefore it is all expressed as a series of Combination of actions, but those skilled in the art should know, the application and from the limitation of described sequence of movement because According to the application, some steps can use other orders or be carried out at the same time.Secondly, those skilled in the art should also know Know, embodiment described in this description belongs to alternative embodiment, involved action and module not necessarily the application It is necessary.

In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion being described in detail in some embodiment Point, it may refer to the associated description of other embodiment.

In several embodiments provided herein, it should be understood that disclosed device, can be by another way Realize.For example, device embodiment described above is only schematical, such as the division of the unit, it is only one kind Division of logic function, can there is an other dividing mode when actually realizing, such as multiple units or component can combine or can To be integrated into another system, or some features can be ignored, or not perform.Another, shown or discussed is mutual Coupling, direct-coupling or communication connection can be by some interfaces, the INDIRECT COUPLING or communication connection of device or unit, Can be electrical or other forms.

The unit illustrated as separating component may or may not be physically separate, be shown as unit The component shown may or may not be physical location, you can with positioned at a place, or can also be distributed to multiple In network unit.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs 's.

In addition, each functional unit in each embodiment of the application can be integrated in a processing unit, can also That unit is individually physically present, can also two or more units integrate in a unit.Above-mentioned integrated list Member can both be realized in the form of hardware, can also be realized in the form of software program module.

If the integrated unit is realized in the form of software program module and is used as independent production marketing or use When, it can be stored in a computer-readable access to memory.Based on such understanding, the technical solution of the application substantially or Person say the part to contribute to the prior art or the technical solution all or part can in the form of software product body Reveal and, which is stored in a memory, including some instructions are used so that a computer equipment (can be personal computer, server or network equipment etc.) performs all or part of each embodiment the method for the application Step.And foregoing memory includes：USB flash disk, read-only storage (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disc or CD etc. are various can be with the medium of store program codes.

One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can To instruct relevant hardware to complete by program, which can be stored in a computer-readable memory, memory It can include：Flash disk, read-only storage (English：Read-Only Memory, referred to as：ROM), random access device (English： Random Access Memory, referred to as：RAM), disk or CD etc..

The embodiment of the present application is described in detail above, specific case used herein to the principle of the application and Embodiment is set forth, and the explanation of above example is only intended to help to understand the present processes and its core concept； Meanwhile for those of ordinary skill in the art, according to the thought of the application, can in specific embodiments and applications There is change part, in conclusion this specification content should not be construed as the limitation to the application.

Claims

1. a kind of computational methods, it is characterised in that applied in computing device, the computing device includes storage medium, deposit Device unit and matrix operation unit, the described method includes：

The computing device controls the matrix operation unit to obtain the first operational order, and first operational order is used for realization Computing between vector and matrix, the vector that first operational order includes performing needed for described instruction reads instruction, described Required vector is at least one vector, and at least one vector is the vector that length is identical or length is different；

The computing device controls the matrix operation unit to read instruction according to the vector and is read to storage medium transmission Take order；

The computing device is controlled described in the matrix operation unit read from the storage medium using batch reading manner Vector reads the corresponding vector of instruction, and using the calculation of multistage pipelining-stage, first fortune is performed to the vector Calculate instruction.

2. according to the method described in claim 1, it is characterized in that, it is described multistage pipelining-stage in each pipelining-stage include to A few arithmetic unit,

The calculation using multistage pipelining-stage, performing first operational order to the vector includes：

The computing device controls selection of the matrix operation unit according to multiple selector, using in first order pipelining-stage First choice arithmetic unit to the vector be calculated first as a result, first result is input to second level pipelining-stage In the second Selecting operation device perform be calculated second as a result, and so on, until inputting the i-th -1 result to i-stage The i-th Selecting operation device in pipelining-stage, which performs, is calculated i-th of result；

I-th of result is inputted to the storage medium and is stored；

Wherein, i-th of result is output vector, and the quantity i of the multistage pipelining-stage is according to first operational order Calculating topological structure determine that and i is positive integer.

3. according to the method described in claim 1, it is characterized in that, it is described multistage pipelining-stage in each pipelining-stage include it is pre- The fixation arithmetic unit first set, the fixation arithmetic unit in each pipelining-stage differ,

The computing device controls the matrix operation unit to utilize the fixation arithmetic unit in first order pipelining-stage to the vector First be calculated as a result, the fixation arithmetic unit execution that first result is input in the pipelining-stage of the second level is calculated To second as a result, and so on, until the i-th -1 result inputted to the fixation arithmetic unit in i-stage pipelining-stage performing calculating Obtain i-th of result；

I-th of result is inputted to the storage medium and is stored；

Wherein, the quantity i of the multistage pipelining-stage is determined according to the calculating topological structure of first operational order, and i For positive integer.

4. according to the method described in claim 2, it is characterized in that, it is described multistage pipelining-stage in each self-configuring of each pipelining-stage There is corresponding multiple selector, the multiple selector, which is set, free option, and the sky option is used to indicate to select with the multichannel Select the kth level pipelining-stage of device connection and follow-up kth+1 not performs to i-stage pipelining-stage and calculates operation, wherein, k is Positive integer less than or equal to i；

Arithmetic unit included by each pipelining-stage and the quantity of the arithmetic unit in the multistage pipelining-stage are by user side Or the self-defined setting in computing device side；Alternatively, the arithmetic unit in the multistage pipelining-stage in each pipelining-stage include with Any one of lower or multinomial combination：It is addition of matrices arithmetic unit, matrix multiplication operation device, matrix-vector multiplication arithmetic unit, non- Linear operator and matrix comparison operation device.

5. according to the described method of any one of claim 1-4, it is characterised in that first operational order include it is following in Any one：Bivector rotation instruction SVRO, three-dimensional vector rotation instruction TVRO, vector translation instruction VTRAN, vector scaling Instruct VZOOM, vectorial shearing instruction VSHEAR；

The instruction format of first operational order includes at least one command code and at least one operation domain, described at least one Command code is used for the function of indicating first operational order, and at least one operation domain is used to indicate that first computing refers to The data message of order, the data message include immediate or register number, and instruction and institute are read for storing the matrix State the length of matrix；Wherein, at least one command code includes the first command code and the second command code, first command code For indicating the type of first operational order, second command code is used for the function of indicating first operational order.

6. according to the method described in claim 2, it is characterized in that, first operational order is bivector rotation instruction SVRO or three-dimensional vector rotation instruction TVRO,

The computing device controls calculation of the matrix operation unit using multistage pipelining-stage, and institute is performed to the vector Stating the first operational order includes：

The computing device controls selection of the matrix operation unit according to multiple selector, using in first order pipelining-stage Nonlinear operator mends 1 computing into row vector to the vector and obtains first as a result, utilizing at the same time non-in the pipelining-stage of the second level Linear operator performs spin matrix structure computing according to the pivot and rotation angle of acquisition and obtains second as a result, by described in First result and second result input into the matrix-vector multiplication arithmetic unit in third level pipelining-stage perform Matrix Multiplication to The 3rd result is calculated in amount；3rd result is inputted to the storage medium and is stored.

7. according to the method described in claim 2, it is characterized in that, first operational order is with any in giving an order ：Vector translation instruction VTRAN, vector scaling instruction VZOOM, vectorial shearing instruction VSHEAR,

The computing device controls selection of the matrix operation unit according to multiple selector, using in first order pipelining-stage Nonlinear operator mends 1 computing into row vector to the vector and obtains first as a result, utilizing at the same time non-in the pipelining-stage of the second level Linear operator, which corresponds to, performs any one of following operation to obtain the second result：Translation is performed according to the shift factor of acquisition Matrix builds computing, the computing of scaled matrix structure is performed according to the zoom factor of acquisition, is performed and cut according to the shear factor of acquisition Matrix structure computing is cut, first result and second result are inputted to the matrix-vector multiplication in third level pipelining-stage Matrix Multiplication vector is performed in arithmetic unit the 3rd result is calculated；3rd result is inputted to the storage medium and is deposited Storage.

8. a kind of computing device, it is characterised in that the computing device includes storage medium, register cell, matrix operation list Member and controller unit；

The storage medium, for storing vector；

The register cell, for storing scalar data, the scalar data includes at least：The vector is situated between in the storage Storage address in matter；

The controller unit, for controlling the matrix operation unit to obtain the first operational order, first operational order The computing being used for realization between vector and matrix, the vector that first operational order includes performing needed for described instruction, which is read, to be referred to Show, the required vector is at least one vector, and at least one vector is the vector that length is identical or length is different；

The matrix operation unit, reading order is sent for reading instruction according to the vector to the storage medium；Foundation The vector is read using batch reading manner and reads the corresponding vector of instruction, using the calculation of multistage pipelining-stage, to institute State vector and perform first operational order.

9. a kind of chip, it is characterised in that the chip includes the as above computing device described in claim 8.

A kind of 10. computer-readable recording medium, it is characterised in that the computer-readable storage medium is stored with computer program, The computer program includes programmed instruction, and described program instruction makes the processor perform such as right when being executed by a processor It is required that 1-7 any one of them methods.