CN105550140A - Electronic device and data processing method - Google Patents
Electronic device and data processing method Download PDFInfo
- Publication number
- CN105550140A CN105550140A CN201410610789.2A CN201410610789A CN105550140A CN 105550140 A CN105550140 A CN 105550140A CN 201410610789 A CN201410610789 A CN 201410610789A CN 105550140 A CN105550140 A CN 105550140A
- Authority
- CN
- China
- Prior art keywords
- running status
- storage medium
- data
- status instruction
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention discloses an electronic device and a data processing method. The electronic device comprises a processing unit for performing central control processing, and at least two processing sub-units connected with the processing unit, wherein the at least two processing sub-units are in data connection with the processing unit by an interface unit; the interface unit is an interface which are shared by the at least two processing sub-units, and used for encapsulating an interaction protocol among the at least two processing sub-units and the processing unit to build a first channel, thus data interaction is performed among the processing unit and the at least two processing sub-units via the first channel; an arbitration unit is positioned among the interface unit and the at least two processing sub-units, for arbitrating and scheduling the occupancy of the storage medium to which the data processing operation points in data interaction; and at least one of the at least two processing sub-units is provided with the storage medium which is the storage resource shared by the at least two processing sub-units.
Description
Technical field
The present invention relates to the communication technology, particularly relate to a kind of electronic equipment and data processing method.
Background technology
Present inventor, in the process realizing the embodiment of the present application technical scheme, at least finds to there is following technical matters in prior art:
Integrated circuit (IC) design develops into the integrated of logic gate gradually from the integrated of transistor, develops into again the integrated of IP at present, i.e. SoC chip, and SoC is the abbreviation of System-on-a-Chip.In simple terms, SoC chip is on a single die owing to widely using pre-customized module---IP and be able to the integrated circuit of fast Development.
Ripe modular design can be used, i.e. IP in a large number in current SoC chip design.In the prior art, these IP generally have independently bus interface, as ahb bus, and AXI bus etc.; Multiple IP is conduct independently component form existence usually in SoC chip; In multiple IP, there is independently storage resources each IP inside, and as SPRAM, DPRAM etc., these storage resources are independent separately, as shown in Figure 1.
The problem that the chip design of above-mentioned prior art causes is: multiple IP standalone module form in the chips, multi-bus interface, the storage resources of each IP inside is independent separately, cannot share, make to cause chip area increasing to adapt to these designs, manufacturing cost is more and more higher, and the module in chip more at most power consumption also can be increasing, takes electricity.
But, in correlation technique, for this problem, there is no effective solution.
Summary of the invention
In view of this, the embodiment of the present invention, desirable to provide a kind of electronic equipment and data processing method, solve at least prior art Problems existing.
The technical scheme of the embodiment of the present invention is achieved in that
A kind of electronic equipment of the embodiment of the present invention, described electronic equipment comprises: for the processing unit of center-control process, at least two sub-processing units being connected with described processing unit;
Described at least two sub-processing units are by an interface unit and described processing unit data cube computation;
Described interface unit for described in the interface that shares of at least two sub-processing units, interaction protocol described in encapsulation between at least two sub-processing units and described processing unit, to build first passage, carries out data interaction by described first passage at described processing unit and described at least two sub-processing units;
Arbitration unit, between described interface unit and described at least two sub-processing units, takies the storage medium carrying out data processing operation sensing in described data interaction and carries out arbitration scheduling;
At least one in described at least two sub-processing units has described storage medium, described storage medium for described in the storage resources that shares of at least two sub-processing units.
In such scheme, described at least two sub-processing units have different process kernels;
Any one process kernel in described at least two sub-processing units, for pointing to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium.
In such scheme, described storage medium is: the storage medium that in described at least two sub-processing units, memory capacity is maximum.
In such scheme, described storage medium is: in described at least two sub-processing units, memory capacity is greater than the storage medium subscribing threshold value.
In such scheme, described process kernel, is further used for:
Receive the first steering order that described processing unit sends, and detect the running status of self, obtain a testing result;
If described testing result is for being in the first state, then generates the first corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described first running status instruction;
Obtain according to the first dispatch command that described arbitration unit returns the authority taking described storage medium, read described storage medium to obtain the first data based on second channel;
The the first data executable operations performing corresponding described first steering order according to described first data obtains the first result;
Based on described first result of second channel write in described storage medium, switch to the second running status instruction by described first running status instruction.
In such scheme, described arbitration unit, is further used for:
Receive described first running status instruction, resolve described first running status instruction, obtain described first state if resolve, then generate described first dispatch command, and described first running status instruction is multiplexed with switching command to open described second channel;
Receive described second running status instruction, and described second running status instruction is multiplexed with switching command to be switched to the described second channel of closedown.
In such scheme, described process kernel, is further used for:
Receive the second steering order that described processing unit sends, and detect the running status of self, obtain a testing result;
If described testing result is for being in the second state, then generates the second corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described second running status instruction;
The authority forbidding described storage medium is obtained according to the second dispatch command that described arbitration unit returns; The first running status instruction is switched to by described second running status instruction;
According to the first dispatch command that described arbitration unit returns, obtain the authority taking described storage medium, read described storage medium to obtain the second data based on second channel;
The the second data executable operations performing corresponding described second steering order according to described second data obtains the second result, based on described second result of second channel write in described storage medium.
In such scheme, described arbitration unit, is further used for:
Receive described second running status instruction, resolve described second running status instruction, obtain described second state if resolve, then generate described second dispatch command, and described second running status instruction is multiplexed with switching command to close described second channel;
Receive described first running status instruction, and described first running status instruction is multiplexed with switching command to be switched to the described second channel of unlatching, and generate described first dispatch command.
A kind of data processing method of the embodiment of the present invention, the method is applied in electronic equipment, and described electronic equipment comprises: for the processing unit of center-control process, at least two sub-processing units being connected with described processing unit;
Described at least two sub-processing units are by an interface unit and described processing unit data cube computation; Described interface unit for described in the interface that shares of at least two sub-processing units, arbitration unit is between described interface unit and described at least two sub-processing units, at least one in described at least two sub-processing units has storage medium, described storage medium for described in the storage resources that shares of at least two sub-processing units;
Described method comprises:
By the interaction protocol described in described interface unit encapsulation between at least two DEU data execution unit and described processing unit to build first passage, carry out data interaction by described first passage at described processing unit and described at least two sub-processing units;
Take by arbitration unit and carry out arbitration to carrying out storage medium that data processing operation in described data interaction points to and dispatch.
In such scheme, described at least two sub-processing units have different process kernels, and described method also comprises:
Any one process kernel in described at least two sub-processing units points to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium.
In such scheme, described process kernel points to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium, comprising:
Receive the first steering order, and detect the running status of self, obtain a testing result;
If described testing result is for being in the first state, then generates the first corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described first running status instruction;
Obtain according to the first dispatch command that described arbitration unit returns the authority taking described storage medium, read described storage medium to obtain the first data based on second channel;
The the first data executable operations performing corresponding described first steering order according to described first data obtains the first result;
Based on described first result of second channel write in described storage medium, and switch to the second running status instruction by described first running status instruction.
In such scheme, describedly take by arbitration unit and carry out arbitration to carrying out storage medium that data processing operation in described data interaction points to and dispatch, comprising:
Receive described first running status instruction, resolve described first running status instruction, obtain described first state if resolve, then generate described first dispatch command, and described first running status instruction is multiplexed with switching command to open described second channel;
Receive described second running status instruction, and described second running status instruction is multiplexed with switching command to be switched to the described second channel of closedown.
In such scheme, described process kernel points to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium, comprising:
Receive the second steering order, and detect the running status of self, obtain a testing result;
If described testing result is for being in the second state, then generates the second corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described second running status instruction;
The authority forbidding described storage medium is obtained according to the second dispatch command that described arbitration unit returns; The first running status instruction is switched to by described second running status instruction;
According to the first dispatch command that described arbitration unit returns, obtain the authority taking described storage medium, read described storage medium to obtain the second data based on second channel;
The the second data executable operations performing corresponding described second steering order according to described second data obtains the second result, based on described second result of second channel write in described storage medium.
In such scheme, describedly take by arbitration unit and carry out arbitration to carrying out storage medium that data processing operation in described data interaction points to and dispatch, comprising:
Receive described second running status instruction, resolve described second running status instruction, obtain described second state if resolve, then generate described second dispatch command, and described second running status instruction is multiplexed with switching command to close described second channel;
Receive described first running status instruction, and described first running status instruction is multiplexed with switching command to be switched to the described second channel of unlatching, and generate described first dispatch command.
The described electronic equipment of the embodiment of the present invention comprises: for the processing unit of center-control process, at least two sub-processing units being connected with described processing unit; Described at least two sub-processing units are by an interface unit and described processing unit data cube computation; Described interface unit for described in the interface that shares of at least two sub-processing units, interaction protocol described in encapsulation between at least two sub-processing units and described processing unit, to build first passage, carries out data interaction by described first passage at described processing unit and described at least two sub-processing units; Arbitration unit, between described interface unit and described at least two sub-processing units, takies the storage medium carrying out data processing operation sensing in described data interaction and carries out arbitration scheduling; At least one in described at least two sub-processing units has described storage medium, described storage medium for described in the storage resources that shares of at least two sub-processing units.Adopt the embodiment of the present invention, because multiple sub-processing unit carries out data cube computation by an interface unit and processing unit, at least one in multiple sub-processing unit has described storage medium, and interface unit and storage medium are that multiple sub-processing unit shares, thus, all storage unit is set without the need to too much interface and each sub-processing unit and greatly reduces the area of total chip, reduce manufacturing cost, module in chip more at least power consumption also can reduce greatly, economizing on energy and electricity.
Accompanying drawing explanation
Fig. 1 is a composition structural representation of electronic equipment embodiment one of the present invention;
Fig. 2 is a composition structural representation of electronic equipment embodiment two of the present invention;
Fig. 3 is the chip composition structural drawing of a prior art embody rule scene;
Fig. 4 is the data interaction schematic diagram of Fig. 3;
Fig. 5 is the chip composition structural drawing of an application embodiment of the present invention embody rule scene;
Fig. 6 is a realization flow schematic diagram of the inventive method embodiment one;
Fig. 7 is a realization flow schematic diagram of the inventive method embodiment two.
Embodiment
Be described in further detail below in conjunction with the enforcement of accompanying drawing to technical scheme.
Electronic equipment embodiment one:
A kind of electronic equipment of the embodiment of the present invention, as shown in Figure 1, described electronic equipment comprises:
For the processing unit of center-control process, at least two sub-processing units being connected with described processing unit; Described at least two sub-processing units are by an interface unit and described processing unit data cube computation.
Described interface unit for described in the interface that shares of at least two sub-processing units, interaction protocol described in encapsulation between at least two sub-processing units and described processing unit, to build first passage, carries out data interaction by described first passage at described processing unit and described at least two sub-processing units.
Arbitration unit, between described interface unit and described at least two sub-processing units, takies the storage medium carrying out data processing operation sensing in described data interaction and carries out arbitration scheduling.
At least one in described at least two sub-processing units has described storage medium, described storage medium for described in the storage resources that shares of at least two sub-processing units.
Wherein, described processing unit can be CPU in a particular application, and described sub-processing unit can carry out the IP module of data interaction in a particular application for the multiple and CPU in chip.Described first passage can be the passage that CPU and IP module carries out data interaction in a particular application.
As shown in Figure 1, sub-processing unit is N number of, N be greater than 2 positive integer, be not have storage medium in every sub-processing unit, at present, the storage medium 1 that in Fig. 1, solid line represents is the storage resources that current multiple sub-processing unit is shared, and the storage medium 2 that in Fig. 1, dotted line represents be current multiple sub-processing unit with storage medium 1 be the storage resources shared cause reading or writing speed slow in, add storage medium 2 together as shared storage resources.
Adopt the embodiment of the present invention, because multiple sub-processing unit carries out data cube computation by an interface unit and processing unit, at least one in multiple sub-processing unit has described storage medium, and interface unit and storage medium are that multiple sub-processing unit shares, thus, all storage unit is set without the need to too much interface and each sub-processing unit and greatly reduces the area of total chip, reduce manufacturing cost, module in chip more at least power consumption also can reduce greatly, economizing on energy and electricity.
Electronic equipment embodiment two:
The electronic equipment of the embodiment of the present invention, as shown in Figure 2, described at least two sub-processing units have different process kernels;
Any one process kernel in described at least two sub-processing units, for pointing to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium.
As shown in Figure 2, sub-processing unit is N number of, N be greater than 2 positive integer, be not have storage medium in every sub-processing unit, at present, the storage medium 1 that in Fig. 2, solid line represents is the storage resources that current multiple sub-processing unit is shared, and the storage medium 2 that in Fig. 2, dotted line represents be current multiple sub-processing unit with storage medium 1 be the storage resources shared cause reading or writing speed slow in, add storage medium 2 together as shared storage resources.In N number of sub-processing unit, each sub-processing unit all independently can process kernel containing one, but it is all the same for being not the function of the process kernel of every sub-processing unit, and that is, at least two sub-processing units have different process kernels.
In the embodiment of the present invention one embodiment, described storage medium is: the storage medium that in described at least two sub-processing units, memory capacity is maximum.
In the embodiment of the present invention one embodiment, described storage medium is: in described at least two sub-processing units, memory capacity is greater than the storage medium subscribing threshold value.
In the embodiment of the present invention one embodiment, described process kernel, is further used for:
Receive the first steering order that described processing unit sends, and detect the running status of self, obtain a testing result; If described testing result is for being in the first state, then generates the first corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described first running status instruction; Obtain according to the first dispatch command that described arbitration unit returns the authority taking described storage medium, read described storage medium to obtain the first data based on second channel; The the first data executable operations performing corresponding described first steering order according to described first data obtains the first result; Based on described first result of second channel write in described storage medium, switch to the second running status instruction by described first running status instruction.
Wherein, described first state in a particular application can for busy state, and in corresponding another embodiment follow-up, the second state is not busy state; First running status instruction is accordingly for the current sub-processing unit being in the first state is at present busy operating instruction, and in corresponding another embodiment follow-up, the second running status instruction is the current sub-processing unit being in the second state is at present not busy operating instruction.Wherein, time instruction is busy, the first dispatch command of arbitration unit is for can occupy share storage resource; Time instruction is not busy, the second dispatch command of corresponding is arbitration unit, for occupying share storage resource.Described second channel in a particular application can for carrying out the reading and writing data passage that digital independent and write operation are opened up.
In the embodiment of the present invention one embodiment, described arbitration unit, is further used for:
Receive described first running status instruction, resolve described first running status instruction, obtain described first state if resolve, then generate described first dispatch command, and described first running status instruction is multiplexed with switching command to open described second channel; Receive described second running status instruction, and described second running status instruction is multiplexed with switching command to be switched to the described second channel of closedown.
In the embodiment of the present invention one embodiment, described process kernel, is further used for:
Receive the second steering order that described processing unit sends, and detect the running status of self, obtain a testing result; If described testing result is for being in the second state, then generates the second corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described second running status instruction; The authority forbidding described storage medium is obtained according to the second dispatch command that described arbitration unit returns; The first running status instruction is switched to by described second running status instruction; According to the first dispatch command that described arbitration unit returns, obtain the authority taking described storage medium, read described storage medium to obtain the second data based on second channel; The the second data executable operations performing corresponding described second steering order according to described second data obtains the second result, based on described second result of second channel write in described storage medium.
Wherein, described second state can be not busy state in a particular application, and before correspondence, in another embodiment, the first state is busy state; Second running status instruction is the operating instruction that the current sub-processing unit being in the second state is at present not busy accordingly, and before correspondence, in another embodiment, the first running status instruction is the current sub-processing unit being in the first state is at present busy operating instruction.Wherein, time instruction is busy, the first dispatch command of arbitration unit is for can occupy share storage resource; Time instruction is not busy, the second dispatch command of corresponding is arbitration unit, for occupying share storage resource.Described second channel in a particular application can for carrying out the reading and writing data passage that digital independent and write operation are opened up.
In the embodiment of the present invention one embodiment, described arbitration unit, is further used for:
Receive described second running status instruction, resolve described second running status instruction, obtain described second state if resolve, then generate described second dispatch command, and described second running status instruction is multiplexed with switching command to close described second channel; Receive described first running status instruction, and described first running status instruction is multiplexed with switching command to be switched to the described second channel of unlatching, and generate described first dispatch command.
Embody rule scene is below adopted to be exemplified below the embodiment of the present invention:
In this application scene, relate to CPU and by multiple IP module composition integrated circuit (IC) chip between the process of data interaction.
For this application scene, in existing a solution, comprise: in the existing design of current SoC chip, ripe modular design can be used in a large number, i.e. IP module, these IP modules generally all have independently bus interface, as ahb bus, AXI bus etc., and also these IP modules are all exist as standalone module form.In existing design, there is independently storage resources much IP inside, as SPRAM, DPRAM etc., and these storage resources are independent separately, as shown in Figure 3, can find out in Fig. 3 and have 2 IP modules to be example, there are 2 root interface lines to be interconnected via BUS bus and CPU, a nested structure is respectively had in 2 IP modules, comprise an interface unit, a control module, a core processing unit, a storage unit, that is, each IP module adopts the same configuration structure, and, respectively by different interface units, respective storage unit is adopted to carry out computing in conjunction with core processing unit, to complete data manipulation instruction that CPU issues to obtain operation result and to restore storage unit, reported result is to CPU afterwards, realize data interaction, concrete data interaction as shown in Figure 4.
Existing design Problems existing is: the storage resources of each IP inside is independent separately, cannot share.Memory module resource is more, and chip area is larger, and cost is higher.
For this problem, for this application scenarios, a solution of the application embodiment of the present invention is: multiple IP shares the chip design method of storage resources, multiple IP can be integrated, and shares a bus interface; Between the control module and interface unit of IP, increase a memory access arbitration unit; Two or more IP, shares a storage unit; Use combinational logic, do not affect accessing time sequence, while minimizing storage resources, do not affect the performance of IP, be illustrated in figure 5 the floor layout of the embodiment of the present invention.
Based on the different chip designs of Fig. 3-4 from Fig. 5, the benefit contrasting the embodiment of the present invention chip design discussing employing Fig. 5 with the example of a security module encryption is as follows:
In existing design, comprise multiple cryptographic algorithm module, wherein in SHA algorithm IP, need the single port RAM using 2K byte; Public key algorithm IP inside employs the single port RAM of 2.5K byte.These two IP are independently IP, all hang on the system bus, need the SRAM of 4.5K byte altogether.
Problems existing is: IP internal storage resources can not directly be shared.Reason is: because when conducting interviews through the storer of bus to IP inside, generally can there is the Delay of 1-3 system clock; If directly directly access another IP internal resource from an IP, there is the Delay of 2-6 clock.If directly connected by signal in design, capability error can be caused.For adapting to Delay, then indoor design must be revised.This changes comparatively large, and risk is very large; Run counter to the principle using IP; Amendment IP internal core processing unit, easily introduces timing error, affects function and the stability of IP; Even if having modified the accessing time sequence of IP inside, also IP hydraulic performance decline can be caused.Thus affect whole chip performance.
Adopting the chip of the embodiment of the present invention shown in Fig. 5, is integrated by multiple IP, shares a bus interface; Between the control module and Bus Interface Unit of IP, increase a memory access arbitration unit; Two IP or multiple IP, share storage unit;
Due to employing is combinational logic, therefore, does not affect accessing time sequence, while minimizing storage resources, does not affect IP performance.
Adopt in existing architecture design as follows to the access of IP storage unit:
1) CPU carries out read-write operation by bus to the memory cell of IP; Write primary data, reads final operation result etc.; 2) core processing unit of IP inside reads and writes operation by control module to storer.Bold arrow in Fig. 4 is the access path representing data, as shown in Figure 4, represents the data access path of IP1 respectively and represents the data access path of IP2.
Adopt the chip of the embodiment of the present invention shown in Fig. 5, interface unit shares; An access arbitration unit is increased between interface unit and control module; Several can in the IP of share storage resource, the storer selecting resource (capacity) maximum is as shareable resource; The data access of IP1 and operating process are not changed completely.The IP of shared resource is used to needing, for the IP2 in figure below, original register address and operate constant; Input data and output data address change shared Memory address (sharing the address of memory address-storage unit 1) into, storage unit 1 address of the IP1 namely in figure below; The access of IP2 core processing unit 2 couples of Memory, by arbitration unit, directly the storage unit 1. of access IP1 designs without the need to amendment, is also transparent to user.
Here it is to be noted: the description of following methods item, is similar with above-mentioned electronic device description, and the beneficial effect with electronic equipment describes, and does not repeat.For the ins and outs do not disclosed in the inventive method embodiment, please refer to the description of electronic equipment embodiment of the present invention.
Embodiment of the method one:
A kind of data processing method of the embodiment of the present invention, as shown in Figure 6, the method is applied in electronic equipment, and described electronic equipment comprises: for the processing unit of center-control process, at least two sub-processing units being connected with described processing unit;
Described at least two sub-processing units are by an interface unit and described processing unit data cube computation; Described interface unit for described in the interface that shares of at least two sub-processing units, arbitration unit is between described interface unit and described at least two sub-processing units, at least one in described at least two sub-processing units has storage medium, described storage medium for described in the storage resources that shares of at least two sub-processing units;
Described method comprises:
Step 101, by the interaction protocol described in the encapsulation of described interface unit between at least two DEU data execution unit and described processing unit to build first passage, carry out data interaction by described first passage at described processing unit and described at least two sub-processing units;
Step 102, take by arbitration unit and carry out arbitration to carrying out storage medium that data processing operation in described data interaction points to and dispatch.
Here it is pointed out that the execution sequence of the step 101-102 in the embodiment of the present invention is not restricted to description current in the embodiment of the present invention.
Embodiment of the method two:
In the embodiment of the present invention one embodiment, as shown in Figure 7, described at least two sub-processing units have different process kernels, and described method comprises:
Step 201, by the interaction protocol described in the encapsulation of described interface unit between at least two DEU data execution unit and described processing unit to build first passage, carry out data interaction by described first passage at described processing unit and described at least two sub-processing units;
Any one process kernel in step 202, described at least two sub-processing units points to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium.
Step 203, take by arbitration unit and carry out arbitration to carrying out storage medium that data processing operation in described data interaction points to and dispatch.
Here it is pointed out that the execution sequence of the step 201-203 in the embodiment of the present invention is not restricted to description current in the embodiment of the present invention.
In the embodiment of the present invention one embodiment, described process kernel points to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium, comprising:
Receive the first steering order, and detect the running status of self, obtain a testing result;
If described testing result is for being in the first state, then generates the first corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described first running status instruction;
Obtain according to the first dispatch command that described arbitration unit returns the authority taking described storage medium, read described storage medium to obtain the first data based on second channel;
The the first data executable operations performing corresponding described first steering order according to described first data obtains the first result;
Based on described first result of second channel write in described storage medium, and switch to the second running status instruction by described first running status instruction.
In the embodiment of the present invention one embodiment, describedly take by arbitration unit and carry out arbitration to carrying out storage medium that data processing operation in described data interaction points to and dispatch, comprising:
Receive described first running status instruction, resolve described first running status instruction, obtain described first state if resolve, then generate described first dispatch command, and described first running status instruction is multiplexed with switching command to open described second channel;
Receive described second running status instruction, and described second running status instruction is multiplexed with switching command to be switched to the described second channel of closedown.
In the embodiment of the present invention one embodiment, described process kernel points to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium, comprising:
Receive the second steering order, and detect the running status of self, obtain a testing result;
If described testing result is for being in the second state, then generates the second corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described second running status instruction;
The authority forbidding described storage medium is obtained according to the second dispatch command that described arbitration unit returns; The first running status instruction is switched to by described second running status instruction;
According to the first dispatch command that described arbitration unit returns, obtain the authority taking described storage medium, read described storage medium to obtain the second data based on second channel;
The the second data executable operations performing corresponding described second steering order according to described second data obtains the second result, based on described second result of second channel write in described storage medium.
In the embodiment of the present invention one embodiment, describedly take by arbitration unit and carry out arbitration to carrying out storage medium that data processing operation in described data interaction points to and dispatch, comprising:
Receive described second running status instruction, resolve described second running status instruction, obtain described second state if resolve, then generate described second dispatch command, and described second running status instruction is multiplexed with switching command to close described second channel;
Receive described first running status instruction, and described first running status instruction is multiplexed with switching command to be switched to the described second channel of unlatching, and generate described first dispatch command.
In several embodiments that the application provides, should be understood that disclosed equipment and method can realize by another way.Apparatus embodiments described above is only schematic, such as, the division of described unit, be only a kind of logic function to divide, actual can have other dividing mode when realizing, and as: multiple unit or assembly can be in conjunction with, maybe can be integrated into another system, or some features can be ignored, or do not perform.In addition, the coupling each other of shown or discussed each ingredient or direct-coupling or communication connection can be by some interfaces, and the indirect coupling of equipment or unit or communication connection can be electrical, machinery or other form.
The above-mentioned unit illustrated as separating component or can may not be and physically separates, and the parts as unit display can be or may not be physical location, namely can be positioned at a place, also can be distributed in multiple network element; Part or all of unit wherein can be selected according to the actual needs to realize the object of the present embodiment scheme.
In addition, each functional unit in various embodiments of the present invention can all be integrated in a processing unit, also can be each unit individually as a unit, also can two or more unit in a unit integrated; Above-mentioned integrated unit both can adopt the form of hardware to realize, and the form that hardware also can be adopted to add SFU software functional unit realizes.
One of ordinary skill in the art will appreciate that: all or part of step realizing said method embodiment can have been come by the hardware that programmed instruction is relevant, aforesaid program can be stored in a computer read/write memory medium, this program, when performing, performs the step comprising said method embodiment; And aforesaid storage medium comprises: movable storage device, ROM (read-only memory) (ROM, Read-OnlyMemory), random access memory (RAM, RandomAccessMemory), magnetic disc or CD etc. various can be program code stored medium.
Or, if the above-mentioned integrated unit of the present invention using the form of software function module realize and as independently production marketing or use time, also can be stored in a computer read/write memory medium.Based on such understanding, the technical scheme of the embodiment of the present invention can embody with the form of software product the part that prior art contributes in essence in other words, this computer software product is stored in a storage medium, comprises some instructions and performs all or part of of method described in each embodiment of the present invention in order to make a computer equipment (can be personal computer, server or the network equipment etc.).And aforesaid storage medium comprises: movable storage device, ROM (read-only memory) (ROM, Read-OnlyMemory), random access memory (RAM, RandomAccessMemory), magnetic disc or CD etc. various can be program code stored medium.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (14)
1. an electronic equipment, described electronic equipment comprises: for the processing unit of center-control process, at least two sub-processing units being connected with described processing unit;
Described at least two sub-processing units are by an interface unit and described processing unit data cube computation;
Described interface unit for described in the interface that shares of at least two sub-processing units, interaction protocol described in encapsulation between at least two sub-processing units and described processing unit, to build first passage, carries out data interaction by described first passage at described processing unit and described at least two sub-processing units;
Arbitration unit, between described interface unit and described at least two sub-processing units, takies the storage medium carrying out data processing operation sensing in described data interaction and carries out arbitration scheduling;
At least one in described at least two sub-processing units has described storage medium, described storage medium for described in the storage resources that shares of at least two sub-processing units.
2. electronic equipment according to claim 1, described at least two sub-processing units have different process kernels;
Any one process kernel in described at least two sub-processing units, for pointing to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium.
3. electronic equipment according to claim 1, described storage medium is: the storage medium that in described at least two sub-processing units, memory capacity is maximum.
4. electronic equipment according to claim 1, described storage medium is: in described at least two sub-processing units, memory capacity is greater than the storage medium subscribing threshold value.
5. electronic equipment according to claim 2, described process kernel, is further used for:
Receive the first steering order that described processing unit sends, and detect the running status of self, obtain a testing result;
If described testing result is for being in the first state, then generates the first corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described first running status instruction;
Obtain according to the first dispatch command that described arbitration unit returns the authority taking described storage medium, read described storage medium to obtain the first data based on second channel;
The the first data executable operations performing corresponding described first steering order according to described first data obtains the first result;
Based on described first result of second channel write in described storage medium, switch to the second running status instruction by described first running status instruction.
6. electronic equipment according to claim 5, described arbitration unit, is further used for:
Receive described first running status instruction, resolve described first running status instruction, obtain described first state if resolve, then generate described first dispatch command, and described first running status instruction is multiplexed with switching command to open described second channel;
Receive described second running status instruction, and described second running status instruction is multiplexed with switching command to be switched to the described second channel of closedown.
7. electronic equipment according to claim 2, described process kernel, is further used for:
Receive the second steering order that described processing unit sends, and detect the running status of self, obtain a testing result;
If described testing result is for being in the second state, then generates the second corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described second running status instruction;
The authority forbidding described storage medium is obtained according to the second dispatch command that described arbitration unit returns; The first running status instruction is switched to by described second running status instruction;
According to the first dispatch command that described arbitration unit returns, obtain the authority taking described storage medium, read described storage medium to obtain the second data based on second channel;
The the second data executable operations performing corresponding described second steering order according to described second data obtains the second result, based on described second result of second channel write in described storage medium.
8. electronic equipment according to claim 7, described arbitration unit, is further used for:
Receive described second running status instruction, resolve described second running status instruction, obtain described second state if resolve, then generate described second dispatch command, and described second running status instruction is multiplexed with switching command to close described second channel;
Receive described first running status instruction, and described first running status instruction is multiplexed with switching command to be switched to the described second channel of unlatching, and generate described first dispatch command.
9. a data processing method, the method is applied in electronic equipment, and described electronic equipment comprises: for the processing unit of center-control process, at least two sub-processing units being connected with described processing unit;
Described at least two sub-processing units are by an interface unit and described processing unit data cube computation; Described interface unit for described in the interface that shares of at least two sub-processing units, arbitration unit is between described interface unit and described at least two sub-processing units, at least one in described at least two sub-processing units has storage medium, described storage medium for described in the storage resources that shares of at least two sub-processing units;
Described method comprises:
By the interaction protocol described in described interface unit encapsulation between at least two DEU data execution unit and described processing unit to build first passage, carry out data interaction by described first passage at described processing unit and described at least two sub-processing units;
Take by arbitration unit and carry out arbitration to carrying out storage medium that data processing operation in described data interaction points to and dispatch.
10. method according to claim 9, described at least two sub-processing units have different process kernels, and described method also comprises:
Any one process kernel in described at least two sub-processing units points to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium.
11. methods according to claim 10, described process kernel points to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium, comprising:
Receive the first steering order, and detect the running status of self, obtain a testing result;
If described testing result is for being in the first state, then generates the first corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described first running status instruction;
Obtain according to the first dispatch command that described arbitration unit returns the authority taking described storage medium, read described storage medium to obtain the first data based on second channel;
The the first data executable operations performing corresponding described first steering order according to described first data obtains the first result;
Based on described first result of second channel write in described storage medium, and switch to the second running status instruction by described first running status instruction.
12. methods according to claim 11, are describedly taken by arbitration unit and carry out arbitration to carrying out storage medium that data processing operation in described data interaction points to and dispatch, and comprising:
Receive described first running status instruction, resolve described first running status instruction, obtain described first state if resolve, then generate described first dispatch command, and described first running status instruction is multiplexed with switching command to open described second channel;
Receive described second running status instruction, and described second running status instruction is multiplexed with switching command to be switched to the described second channel of closedown.
13. methods according to claim 10, described process kernel points to described storage medium according to the data processing operation obtained in described data interaction, to obtain data to perform described data processing operation from described storage medium, comprising:
Receive the second steering order, and detect the running status of self, obtain a testing result;
If described testing result is for being in the second state, then generates the second corresponding running status instruction, send to described arbitration unit to dispatch for described arbitration described second running status instruction;
The authority forbidding described storage medium is obtained according to the second dispatch command that described arbitration unit returns; The first running status instruction is switched to by described second running status instruction;
According to the first dispatch command that described arbitration unit returns, obtain the authority taking described storage medium, read described storage medium to obtain the second data based on second channel;
The the second data executable operations performing corresponding described second steering order according to described second data obtains the second result, based on described second result of second channel write in described storage medium.
14. methods according to claim 13, are describedly taken by arbitration unit and carry out arbitration to carrying out storage medium that data processing operation in described data interaction points to and dispatch, and comprising:
Receive described second running status instruction, resolve described second running status instruction, obtain described second state if resolve, then generate described second dispatch command, and described second running status instruction is multiplexed with switching command to close described second channel;
Receive described first running status instruction, and described first running status instruction is multiplexed with switching command to be switched to the described second channel of unlatching, and generate described first dispatch command.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410610789.2A CN105550140B (en) | 2014-11-03 | 2014-11-03 | A kind of electronic equipment and data processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410610789.2A CN105550140B (en) | 2014-11-03 | 2014-11-03 | A kind of electronic equipment and data processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105550140A true CN105550140A (en) | 2016-05-04 |
| CN105550140B CN105550140B (en) | 2018-11-09 |
Family
ID=55829330
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410610789.2A Active CN105550140B (en) | 2014-11-03 | 2014-11-03 | A kind of electronic equipment and data processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105550140B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109564562A (en) * | 2018-10-30 | 2019-04-02 | 北京比特大陆科技有限公司 | Big data operation acceleration system and chip |
| WO2020087278A1 (en) * | 2018-10-30 | 2020-05-07 | 北京比特大陆科技有限公司 | Big data computing acceleration system and method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020169938A1 (en) * | 2000-12-14 | 2002-11-14 | Scott Steven L. | Remote address translation in a multiprocessor system |
| CN1783033A (en) * | 2004-11-19 | 2006-06-07 | 英特尔公司 | Heterogeneous processors sharing a common cache |
| CN101000596A (en) * | 2007-01-22 | 2007-07-18 | 北京中星微电子有限公司 | Chip and communication method of implementing communicating between multi-kernel in chip and communication method |
| CN101385008A (en) * | 2006-03-14 | 2009-03-11 | 英特尔公司 | A common analog interface for multiple processor cores |
| CN101382583A (en) * | 2008-10-30 | 2009-03-11 | 中国人民解放军国防科学技术大学 | Multi-core microprocessor JTAG debug method |
| CN102035658A (en) * | 2010-11-26 | 2011-04-27 | 北京航空航天大学 | High-speed 1553B fiber bus IP core |
| CN102135950A (en) * | 2011-03-10 | 2011-07-27 | 中国科学技术大学苏州研究院 | On-chip heterogeneous multi-core system based on star type interconnection structure, and communication method thereof |
| CN102804103A (en) * | 2010-03-01 | 2012-11-28 | Arm有限公司 | Data processing apparatus and method for transferring workload between source and destination processing circuitry |
-
2014
- 2014-11-03 CN CN201410610789.2A patent/CN105550140B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020169938A1 (en) * | 2000-12-14 | 2002-11-14 | Scott Steven L. | Remote address translation in a multiprocessor system |
| CN1783033A (en) * | 2004-11-19 | 2006-06-07 | 英特尔公司 | Heterogeneous processors sharing a common cache |
| CN101385008A (en) * | 2006-03-14 | 2009-03-11 | 英特尔公司 | A common analog interface for multiple processor cores |
| CN101000596A (en) * | 2007-01-22 | 2007-07-18 | 北京中星微电子有限公司 | Chip and communication method of implementing communicating between multi-kernel in chip and communication method |
| CN101382583A (en) * | 2008-10-30 | 2009-03-11 | 中国人民解放军国防科学技术大学 | Multi-core microprocessor JTAG debug method |
| CN102804103A (en) * | 2010-03-01 | 2012-11-28 | Arm有限公司 | Data processing apparatus and method for transferring workload between source and destination processing circuitry |
| CN102035658A (en) * | 2010-11-26 | 2011-04-27 | 北京航空航天大学 | High-speed 1553B fiber bus IP core |
| CN102135950A (en) * | 2011-03-10 | 2011-07-27 | 中国科学技术大学苏州研究院 | On-chip heterogeneous multi-core system based on star type interconnection structure, and communication method thereof |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109564562A (en) * | 2018-10-30 | 2019-04-02 | 北京比特大陆科技有限公司 | Big data operation acceleration system and chip |
| WO2020087278A1 (en) * | 2018-10-30 | 2020-05-07 | 北京比特大陆科技有限公司 | Big data computing acceleration system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105550140B (en) | 2018-11-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2417412C2 (en) | Standard analogue interface for multi-core processors | |
| CN111856258A (en) | Method, device, storage medium and corresponding chip for testing a chip | |
| US20220269645A1 (en) | Memory mat as a register file | |
| KR20130058719A (en) | Dual-trigger low-energy flip-flop circuit | |
| CN104598405A (en) | Expansion chip and expandable chip system and control method | |
| US20230176999A1 (en) | Devices for time division multiplexing of state machine engine signals | |
| US20110260764A1 (en) | Semiconductor integrated circuit, method for designing semiconductor integrated circuit, and computer readable recording medium | |
| Cambou et al. | Ag conductive bridge rams for physical unclonable functions | |
| US9531351B1 (en) | Configurable latch circuit | |
| CN105550140A (en) | Electronic device and data processing method | |
| US6324122B1 (en) | RAM synchronized with a signal | |
| CN103198854B (en) | There is in FPGA the Block RAM of multiple write mode | |
| Kamaraj et al. | Design of Space-Efficient Nano Router in Reversible Logic with Multilayer Architecture | |
| US11386009B2 (en) | Programmable device configuration memory system | |
| CN104678815A (en) | Interface structure and configuration method of FPGA (field programmable gate array) chip | |
| US9934170B2 (en) | Circuit for controlling access to memory using arbiter | |
| Poppen | Low power design guide | |
| Jia et al. | Research on communication technology of complex system based on FPGA dual-port RAMs | |
| US9350355B2 (en) | Semiconductor apparatus | |
| US7043417B1 (en) | High speed software driven emulator comprised of a plurality of emulation processors with improved multiplexed data memory | |
| CN204496487U (en) | Extended chip and extendible chip system | |
| Rodolfo et al. | Quasi Delay Insensitive FIFOs: Design Choices Exploration and Comparison | |
| US20220301608A1 (en) | Memory module based data buffer communication bus training | |
| US11429769B1 (en) | Implementing a hardware description language memory using heterogeneous memory primitives | |
| US10963029B1 (en) | Power virus generation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |