CN109992225A - Data output method and relevant apparatus - Google Patents
Data output method and relevant apparatus Download PDFInfo
- Publication number
- CN109992225A CN109992225A CN201910269778.5A CN201910269778A CN109992225A CN 109992225 A CN109992225 A CN 109992225A CN 201910269778 A CN201910269778 A CN 201910269778A CN 109992225 A CN109992225 A CN 109992225A
- Authority
- CN
- China
- Prior art keywords
- data
- artificial intelligence
- process device
- intelligence process
- buffer zone
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/12—Digital output to print unit, e.g. line printer, chain printer
- G06F3/1201—Dedicated interfaces to print systems
- G06F3/1223—Dedicated interfaces to print systems specifically adapted to use a particular technique
- G06F3/1237—Print job management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/14—Digital output to display device ; Cooperation and interconnection of the display device with other functional units
Abstract
The embodiment of the present application discloses a kind of data output method and relevant apparatus, data output method is applied to the board including data output device, the board includes memory device, interface arrangement and control device and artificial intelligence process device, which is separately connected with the memory device, the interface arrangement and the control device；The memory device, for storing data；The interface arrangement, for realizing the data transmission between the artificial intelligent processor and external equipment；The control device is monitored for the state to the artificial intelligent processor.It can be realized using the embodiment of the present application and data to be printed are sent to general processor from the data buffer zone of artificial intelligence process device automatically.
Description
Technical field
This application involves field of computer technology, and in particular to a kind of data output method and relevant apparatus.
Background technique
When being programmed to artificial intelligence process device, generally require on artificial intelligence process device operation obtain to
A few intermediate result data is copied to general processor, by printing at least one intermediate result data to display screen,
Code is debugged in order to programming personnel or calculated result is analyzed.Currently, by least one intermediate result data
Copy the mode of general processor to are as follows: data buffer zone is distributed in the first memory of artificial intelligence process device manually, it will
At least one intermediate result data is stored to data buffer zone, when hardware instruction, which executes, to be completed, will be stored in data manually and be delayed
At least one intermediate result data for rushing area is copied to general processor, and this mode is cumbersome, inefficient.
Summary of the invention
The embodiment of the present application provides a kind of data output method and relevant apparatus, for automatically by data to be printed from artificial
The data buffer zone of intelligent processor is sent to general processor, is exported data to be printed with realizing.
The first aspect of the embodiment of the present application provides a kind of data output method, which comprises
The executable file that can be run on artificial intelligence process device is received, the executable file includes that hardware refers to
It enables；
Data buffer zone is determined in the first memory of the artificial intelligence process device based on the hardware instruction；
Data to be printed are stored to the data buffer zone；
The data to be printed are sent to general processor from the data buffer zone.
In conjunction with the embodiment of the present application in a first aspect, in the first possible implementation of the first aspect, the base
Before the hardware instruction determines data buffer zone in the first memory of the artificial intelligence process device, the method is also
Include:
The executable file is parsed, flag bit is obtained；
Judge whether the flag bit meets preset condition；
If the flag bit meets the preset condition, execute based on the hardware instruction in the artificial intelligence process
The operation of data buffer zone is determined in the first memory of device.
In conjunction with the first possible implementation of the embodiment of the present application first aspect, second in first aspect may
Implementation in, it is described to determine that data are slow in the first memory of the artificial intelligence process device based on the hardware instruction
Rush area, comprising:
The hardware instruction is parsed, the size of the data buffer zone is obtained；
Target storage is chosen from the free storage of the first memory, using the target storage as described in
Data buffer zone.
In conjunction with second of possible implementation of the embodiment of the present application first aspect, the third in first aspect may
Implementation in, the data to be printed include at least one child print data, described to store data to be printed to described
Data buffer zone, comprising:
Obtain the size of data of each child print data；
According to the size of data of each child print data, determine each child print data in the data buffering
The target storage position in area；
Each child print data are deposited from the target that second memory is carried to its corresponding data buffer zone
Storage space is set.
In conjunction with the third possible implementation of the embodiment of the present application first aspect, in the 4th kind of possibility of first aspect
Implementation in, the size of data according to each child print data determines that each child print data are slow in the data
Rush the target storage position in area, comprising:
The hardware instruction is parsed, the print space needed for printing every time is obtained；
Print space needed for size of data and each printing based on current child print data determines described current
The corresponding printing times of child print data；
Obtain the task identification and the corresponding timestamp of the current child print data of the current child print data；
According to print space needed for each printing, the task identification, described current of the current child print data
The corresponding printing times of child print data and the corresponding timestamp of the current child print data calculate the current child print
The corresponding address offset amount of data；
Based on the corresponding address offset amount of the current child print data, determine the current child print data in the number
According to the target storage position of buffer area.
In conjunction with the 4th kind of possible implementation of the embodiment of the present application first aspect, in the 5th kind of possibility of first aspect
Implementation in, it is described that the data to be printed are sent to general processor from the data buffer zone, comprising:
After the completion of the hardware instruction executes, the data to be printed are sent to described lead to from the data buffer zone
Use processor；Alternatively,
Whenever the hardware instruction is executed to print command, then by the corresponding child print data of the print command from described
Data buffer zone is sent to the general processor.
In conjunction with the 5th kind of possible implementation of the embodiment of the present application first aspect, in the 6th kind of possibility of first aspect
Implementation in, it is described that the data to be printed are sent to general processor from the data buffer zone, comprising:
Whenever the hardware instruction is executed to print command, then the corresponding child print data of the print command are converted to
Character string, and the character string is sent to the general processor from the data buffer zone.
The second aspect of the embodiment of the present application provides a kind of data output method, is applied to general processor and artificial intelligence
Energy processor, which comprises
The general processor sends executable file to the artificial intelligence process device, and the executable file includes hard
Part instruction；
The artificial intelligence process device receives the executable file that can be run on the artificial intelligence process device,
The executable file includes the hardware instruction, is stored based on the hardware instruction the first of the artificial intelligence process device
Data buffer zone is determined in device；
The artificial intelligence process device stores data to be printed to the data buffer zone；
The data to be printed are sent to the general procedure from the data buffer zone by the artificial intelligence process device
Device；
The general processor receives the data to be printed of the artificial intelligence process device transmission, will be described to be printed
Data output display is on a display screen.
The third aspect of the embodiment of the present application provides a kind of data output device, and described device includes that the first reception is single
Member, the first determination unit, the first storage unit and the first transmission unit, in which:
First receiving unit, it is described for receiving the executable file that can be run on artificial intelligence process device
Executable file includes hardware instruction；
First determination unit, for based on the hardware instruction the artificial intelligence process device first memory
Middle determining data buffer zone；
First storage unit, for storing data to be printed to the data buffer zone；
First transmission unit, for the data to be printed to be sent to general procedure from the data buffer zone
Device.
The fourth aspect of the embodiment of the present application provides a kind of data output device, is applied to general processor and artificial intelligence
Energy processor, described device include transmission unit, the second receiving unit, the second determination unit, the second storage unit, the second transmission
Unit, third receiving unit and output display unit, in which:
The transmission unit, for sending executable file to the artificial intelligence process device, the executable file packet
Include hardware instruction；
Second receiving unit, for receiving the executable text that can be run on the artificial intelligence process device
Part, the executable file include the hardware instruction；
Second determination unit, for based on the hardware instruction the artificial intelligence process device first memory
Middle determining data buffer zone；
Second storage unit, for storing data to be printed to the data buffer zone；
Second transmission unit, for by the data to be printed from the data buffer zone be sent to it is described it is general from
Manage device；
The third receiving unit, for receiving the data to be printed of the artificial intelligence process device transmission；
The output display unit, for showing on a display screen the data output to be printed.
The 5th aspect of the embodiment of the present application provides a kind of artificial intelligence process device, and the artificial intelligence process device is included in this
Apply for data output device described in the embodiment third aspect.
The 6th aspect of the embodiment of the present application provides a kind of electronic equipment, and the electronic equipment includes the embodiment of the present application the 5th
Artificial intelligence process device described in aspect.
The 7th aspect of the embodiment of the present application provides a kind of board, and the board includes described in the 5th aspect of the embodiment of the present application
Artificial intelligence process device.
The embodiment of the present application eighth aspect provides a kind of artificial intelligence process device, the artificial intelligence process device for realizing
Some or all of method described in the embodiment of the present application first aspect and second aspect step.
The 9th aspect of the embodiment of the present application provides a kind of computer readable storage medium, above-mentioned computer-readable storage medium
Matter is used to store the computer program of electronic data interchange, and above-mentioned computer program makes computer execute such as the embodiment of the present application
Some or all of method described in first aspect and second aspect step.
The tenth aspect of the embodiment of the present application provides a kind of computer program product, and above-mentioned computer program product includes depositing
The non-transient computer readable storage medium of computer program is stored up, above-mentioned computer program is operable to execute computer
Step some or all of described in method as described in the embodiment of the present application first aspect and second aspect.The computer journey
Sequence product can be a software installation packet.
As can be seen that in the embodiment of the present application, what artificial intelligence process device reception general processor was sent can be at it
The executable file of upper operation, executable file include hardware instruction, based on hardware instruction the first of artificial intelligence process device
Data buffer zone is automatically determined in memory, print data is stored to data buffer zone, by data to be printed from data buffering
Area is sent to general processor, so as to be connected data to be printed output display to general processor by general processor
On the display screen connect.Compared to data buffer zone is distributed in the first memory of artificial intelligence process device manually, will deposit manually
The data copy to be printed of data buffer zone is stored in general processor, it is slow based on data that artificial intelligence process device has been achieved
The size for rushing area distributes data buffer zone automatically, automatically transmits data to be printed from the data buffer zone of artificial intelligence process device
To general processor, so that the display screen that data to be printed output display is extremely connect with general processor by general processor
On, or by data-printing to be printed into default file folder.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application or in background technique below will be implemented the application
Attached drawing needed in example or background technique is illustrated.
Fig. 1 is a kind of flow diagram of data output method provided by the embodiments of the present application；
Fig. 2 is the flow diagram of another data output method provided by the embodiments of the present application；
Fig. 3 is the flow diagram of another data output method provided by the embodiments of the present application；
Fig. 4 is the flow diagram of another data output method provided by the embodiments of the present application；
Fig. 5 is a kind of functional unit composition block diagram of data output device provided by the embodiments of the present application；
Fig. 6 is the functional unit composition block diagram of another data output device provided by the embodiments of the present application；
Fig. 7 is a kind of structural schematic diagram of board provided by the embodiments of the present application.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
The description and claims of this application and term " first " in above-mentioned attached drawing, " second " etc. are for distinguishing
Different objects, are not use to describe a particular order.In addition, term " includes " and " having " and their any deformations, it is intended that
It is to cover and non-exclusive includes.Such as the process, method, system, product or equipment for containing a series of steps or units do not have
It is defined in listed step or unit, but optionally further comprising the step of not listing or unit, or optionally also wrap
Include other step or units intrinsic for these process, methods, product or equipment.
" embodiment " mentioned in this application is it is meant that a particular feature, structure, or characteristic described can be in conjunction with the embodiments
Included at least one embodiment of the application.The phrase, which occurs, in each position in the description might not each mean phase
Same embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art are explicitly
Implicitly understand, embodiments described herein can be combined with other embodiments.
The data output method of the application is applied to the field that general processor (such as CPU) is interacted with artificial intelligence process device
Scape, general processor can be connect with artificial intelligence process device by bus.General processor may include main memory, main memory
Reservoir is that artificial intelligent processor is sent to general processor for storing data to be printed, data to be printed.Artificial intelligence
Processor may include register, neural metamemory (NRAM), weight storage device (WRAM) and device memory；Register is used for
The corresponding address offset amount of current child print data is calculated, NRAM can be used for storing single print data and timestamp, equipment
Memory includes data buffer zone, and for storing data to be printed, hardware instruction be can store in NRAM, can also for data buffer zone
To be stored in device memory.In the embodiment of the present application, first memory is device memory, and second memory may include
NRAM and WRAM.
Based on the storage organization of above-mentioned computer heterogeneous system (including general processor and artificial intelligence process device), this Shen
Please the data output process of embodiment may include two parts, a portion refers to artificial intelligence process device by data to be printed
It exports to the process of CPU, another part is CPU by the process in data-printing to be printed to display or default file folder.
It describes in detail below to the embodiment of the present application.
Referring to Fig. 1, Fig. 1 is a kind of flow diagram of data output method provided by the embodiments of the present application, the data
Output method includes step 101-105, specific as follows:
101: the general processor sends executable file to the artificial intelligence process device, the executable file packet
Include hardware instruction.
Wherein, in the embodiment of the present application, general processor can be central processing unit (CPU), and executable file can be with
It is the binary file that can be run on artificial intelligence process device, specifically can be ELF file.
102: the artificial intelligence process device reception can be run described executable on the artificial intelligence process device
File, the executable file include the hardware instruction, based on the hardware instruction the of the artificial intelligence process device
Data buffer zone is determined in one memory.
In a possible example, artificial intelligence process device is based on the hardware instruction in the artificial intelligence process device
First memory in determine data buffer zone before, the method also includes:
Artificial intelligence process device parses the executable file, obtains flag bit；
Artificial intelligence process device judges whether the flag bit meets preset condition；
If the flag bit meets the preset condition, artificial intelligence process device is executed based on the hardware instruction in institute
State the operation that data buffer zone is determined in the first memory of artificial intelligence process device.
Further, the method also includes:
If the flag bit is unsatisfactory for the preset condition, user can by writing the manual modes such as program statement,
Output data space is distributed on the first memory, and the output data space is for storing data to be printed.Artificial intelligence process
Device hardware instruction all execute after the completion of, or hardware instruction execution refer to print command, by the output data from output number
The general processor is sent to according to space.
Wherein, the value of flag bit can be indicated using 0 or 1, determine whether the flag bit is full by the value of flag bit
Sufficient preset condition.For example, when the value of flag bit is 1, it may be considered that flag bit meets preset condition；When the value of flag bit is
When 0, it may be considered that being unsatisfactory for preset condition.Certainly, in other alternative-embodiments, which can also be using difference
Symbol be indicated, be only used for herein for example, be not used to limit flag bit representation.Further, work as mark
Will position meets preset condition, indicates user using data buffer zone needed for automatically determining data to be printed, and by number to be printed
According to storing to data buffer zone, and then data to be printed are sent to general procedure from the data buffer zone of artificial intelligence process device
The function of device.When flag bit is unsatisfactory for preset condition, indicate that user may be by the way of manual allocation data buffer zone, people
Work intelligent processor can be by data transmission to be printed to general processor.
In a possible example, artificial intelligence process device is based on the hardware instruction in the artificial intelligence process device
First memory in determine data buffer zone, comprising:
Artificial intelligence process device parses the hardware instruction, obtains the size of the data buffer zone；
Artificial intelligence process device chooses target storage from the free storage of the first memory, by the target
Memory block is as the data buffer zone.
Wherein, size of the target storage for any one in the free storage of first memory with data buffer zone
Identical memory block.
103: the artificial intelligence process device stores data to be printed to the data buffer zone.
Specifically, which is stored in second memory, artificial intelligence process device can according to hardware instruction,
By data to be printed from the data buffer zone that second memory is carried to first memory.Optionally, it is deposited in second memory
Contain single print data.
In a possible example, artificial intelligence process device stores data to be printed to before data buffer zone, institute
State method further include:
Artificial intelligence process device parses hardware instruction, obtains input data space and operational order；
Artificial intelligence process device reads input data and N number of weight from input data space, and N is the integer greater than 1；
Artificial intelligence process device is based on input data, N number of weight and operational order and carries out corresponding operation, and it is a to obtain (N-1)
Intermediate result data；
Artificial intelligence process device is by (N-1) a intermediate result data as data to be printed.
Optionally, which can be the part memory space in device memory, input data space and number
There is no intersection according to buffer area, input data space and output data space do not have intersection.
In a possible example, data to be printed include at least one child print data, and artificial intelligence process device will
Data to be printed are stored to the data buffer zone, comprising:
Artificial intelligence process device obtains the size of data of each child print data；
Artificial intelligence process device determines each child print data in the number according to the size of data of each child print data
According to the target storage position of buffer area；
Each child print data are carried to its corresponding data buffering from second memory by artificial intelligence process device
The target storage position in area.
Wherein, an intermediate result data is a sub- print data, and a sub- print data corresponds at least one printing
Number.That is, data to be printed may include multiple child print data, each child print data need to beat at least once
Print.
In a possible example, artificial intelligence process device determines every according to the size of data of each child print data
A sub- print data before the target storage position of data buffer zone, the method also includes:
Artificial intelligence process device obtains the size of the current residual memory headroom of data buffer zone；
Artificial intelligence process device judges the size of the current residual memory headroom of data buffer zone, if is greater than or equal to son
The size of memory space needed for print data；
If the size of the current residual memory headroom of data buffer zone, big less than memory space needed for child print data
Small, then artificial intelligence process device discharges the partial memory space of data buffer zone, the residue of the data buffer zone after being released
Memory headroom, the size of memory space needed for the size in partial memory space is greater than or equal to child print data and data buffer zone
Current residual memory headroom size difference, the initial address and the initial address phase of data buffer zone in partial memory space
Together.
Specifically, each child print data are carried to its corresponding data from second memory and delayed by artificial intelligence process device
The embodiment for rushing the target storage position in area can be with are as follows: if the corresponding printing times of child print data are M, M is whole greater than 1
Number, then after i-th (i is less than or equal to the positive integer of M) secondary printing, artificial intelligence process device will be stored in second memory
I-th prints the target storage position that corresponding print data is carried to the corresponding data buffer zone of child print data, i-th
It prints to any primary in M printing.
In a possible example, artificial intelligence process device determines every according to the size of data of each child print data
Target storage position of a sub- print data in the data buffer zone, comprising:
Artificial intelligence process device parses the hardware instruction, obtains the print space needed for printing every time；
Printing needed for size of data and each printing of the artificial intelligence process device based on current child print data is empty
Between determine the corresponding printing times of the current child print data；
Artificial intelligence process device obtain the current child print data task identification and the current child print data pair
The timestamp answered；
The task of artificial intelligence process device print space according to needed for each printing, the current child print data
Mark, the current corresponding printing times of child print data and the corresponding timestamp of the current child print data calculate
The corresponding address offset amount of the current child print data；
Artificial intelligence process device is based on the corresponding address offset amount of the current child print data, determines that the current son is beaten
Printing is according to the target storage position in the data buffer zone.
Specifically, size of data of the artificial intelligence process device based on current child print data and every time printing needed for printing
Space determines that the embodiment of the corresponding printing times of current child print data can be with are as follows: artificial intelligence process device determines current son
The ratio of the size of print space needed for the size of memory space needed for print data and every time printing；If current child print number
The ratio of the size of print space needed for size and each printing according to required memory space is integer, then artificial intelligence process
Device using the size of memory space needed for current child print data and every time printing needed for print space size ratio as
The currently corresponding printing times of child print data.Alternatively, if the size of memory space needed for current child print data and beating every time
The ratio of the size of print space needed for print is decimal, then artificial intelligence process device will store empty needed for current child print data
Between size and every time printing needed for print space size ratio integer part add one be used as current child print data
Corresponding printing times.
Wherein, the task identification of current child print data indicates which sub- print data is current child print data be.
Specifically, the embodiment that artificial intelligence process device obtains the corresponding timestamp of current child print data can be with are as follows:
Artificial intelligence process device parses hardware instruction, obtains timestamp space, and timestamp space is stabbed for storage time；At artificial intelligence
Reason device reads the corresponding timestamp of current child print data from timestamp space.Optionally, which can be
Part memory space in two memories, still optionally further, the timestamp space can be the part memory space in NRAM.
Specifically, artificial intelligence process device is according to print space needed for each printing, the task of current child print data
Mark, the corresponding printing times of current child print data and the corresponding timestamp of current child print data calculate current child print
The embodiment of the corresponding address offset amount of data can be with are as follows: artificial intelligence process device is empty according to printing needed for each printing
Between, the task identification of current child print data, the corresponding printing times of current child print data, current child print data it is corresponding
Timestamp and offset formula calculate the corresponding address offset amount of current child print data.
Wherein, offset formula is pre-stored within artificial intelligence process device, and offset formula is specifically as follows:
Offset=sizeof (printf_record) * (num_records_per_task*taskid+
Timestamp),
Offset is the corresponding offset of current child print data, and sizeof (printf_record) is printing institute every time
The print space needed, num_records_per_task are the corresponding printing times of current child print data, and taskid is current
The task identification of child print data, timestamp are the corresponding timestamp of current child print data.
Specifically, artificial intelligence process device is based on the corresponding address offset amount of current child print data, determines that current son is beaten
Printing can be with according to the embodiment of the target storage position in data buffer zone are as follows: artificial intelligence process device obtains data buffer zone
First address；First address and current child print data corresponding address offset of the artificial intelligence process device based on data buffer zone
Amount, determines initial address and end address of the current child print data in data buffer zone.Artificial intelligence process device will current son
Initial address and end address target as current child print data in data buffer zone of the print data in data buffer zone
Storage location.
Wherein, in the embodiment of the present application, after each printing, timestamp plus one are stored to timestamp space.
104: the data to be printed are sent to described general by the artificial intelligence process device from the data buffer zone
Processor.
In a possible example, artificial intelligence process device transmits the data to be printed from the data buffer zone
To general processor, comprising:
After the completion of the hardware instruction executes, artificial intelligence process device is by the data to be printed from the data buffering
Area is sent to the general processor；Alternatively,
Whenever the hardware instruction is executed to print command, then artificial intelligence process device is by the corresponding son of the print command
Print data is sent to the general processor from the data buffer zone.Real time print can be thus achieved.
Still optionally further, user can realize the selection of different printing types by the way that default printing model is arranged.For example,
Flag bit can further include printing model flag bit in the hardware instruction.When printing model flag bit is 1, artificial intelligence
Processor is printed according to first way, i.e., after the completion of the hardware instruction executes, artificial intelligence process device will be described
Data to be printed are sent to the general processor from the data buffer zone.When printing model flag bit position 0, artificial intelligence
Processor can carry out real time print according to the second way, i.e., whenever the hardware instruction is executed to print command, then manually
The corresponding child print data of the print command are sent to the general processor from the data buffer zone by intelligent processor.
In a possible example, artificial intelligence process device transmits the data to be printed from the data buffer zone
To general processor, comprising:
Whenever the hardware instruction is executed to print command, then artificial intelligence process device is by the corresponding son of the print command
Print data is converted to character string, and the character string is sent to the general processor from the data buffer zone.
105: the general processor receives the data to be printed of artificial intelligence process device transmission, will it is described to
Print data output display is on a display screen；Alternatively, by the data-printing to be printed into default file folder.
As can be seen that in the embodiment of the present application, what artificial intelligence process device reception general processor was sent can be at it
The executable file of upper operation, executable file include hardware instruction, based on hardware instruction the first of artificial intelligence process device
Data buffer zone is automatically determined in memory, print data is stored to data buffer zone, by data to be printed from data buffering
Area is sent to general processor, so as to be connected data to be printed output display to general processor by general processor
On the display screen connect.Compared to data buffer zone is distributed in the first memory of artificial intelligence process device manually, will deposit manually
The data copy to be printed of data buffer zone is stored in general processor, it is slow based on data that artificial intelligence process device has been achieved
The size for rushing area distributes data buffer zone automatically, automatically transmits data to be printed from the data buffer zone of artificial intelligence process device
To general processor, so that the display screen that data to be printed output display is extremely connect with general processor by general processor
On, or by data-printing to be printed into default file folder.
It is described before general processor shows data to be printed output on a display screen in a possible example
Method further include:
If data to be printed are character string, general processor is based on character string selection rule and screens to character string,
Character string after being screened；
General processor shows the character string output after screening on a display screen.
Wherein, character string selection rule is pre-stored within general processor, and character string selects rule to go out for assisting sifting less
Legitimate characters.
It is consistent with above-mentioned embodiment shown in FIG. 1, referring to Fig. 2, Fig. 2 is another number provided by the embodiments of the present application
According to the flow diagram of output method, it is applied to artificial intelligence process device, which includes step 201-204, tool
Body is as follows:
201: artificial intelligence process device receives the executable file that can be run on artificial intelligence process device, described to hold
Part of composing a piece of writing includes hardware instruction.
202: artificial intelligence process device is based on the hardware instruction in the first memory of the artificial intelligence process device
Determine data buffer zone.
203: artificial intelligence process device stores data to be printed to the data buffer zone.
204: the data to be printed are sent to general processor from the data buffer zone by artificial intelligence process device.
It should be noted that the specific implementation process of each step of method shown in Fig. 2 can be found in described in the above method
Specific implementation process, no longer describe herein.
It is consistent with above-mentioned Fig. 1 and embodiment shown in Fig. 2, referring to Fig. 3, Fig. 3 is provided by the embodiments of the present application another
A kind of flow diagram of data output method, which includes step 301-309, specific as follows:
301: general processor sends executable file to artificial intelligence process device, and the executable file includes that hardware refers to
It enables.
302: artificial intelligence process device receives the executable file that can be run on the artificial intelligence process device,
The executable file includes the hardware instruction, parses the hardware instruction, obtains the size of data buffer zone.
303: artificial intelligence process device is chosen from the free storage of the first memory of the artificial intelligence process device
Target storage.
304: artificial intelligence process device is using the target storage as the data buffer zone.
305: artificial intelligence process device obtains the size of data of each child print data.
306: artificial intelligence process device determines each child print data in institute according to the size of data of each child print data
State the target storage position of data buffer zone.
307: each child print data are carried to its corresponding data from second memory by artificial intelligence process device
The target storage position of buffer area.
308: after the completion of the hardware instruction executes, artificial intelligence process device is by data to be printed from the data buffering
Area is sent to the general processor, and the data to be printed include at least one child print data.
309: general processor receives the data to be printed of the artificial intelligence process device transmission, will be described to be printed
Data output display is on a display screen；Alternatively, by the data-printing to be printed into default file folder.
It should be noted that the specific implementation process of each step of method shown in Fig. 3 can be found in described in the above method
Specific implementation process, no longer describe herein.
It is consistent with above-mentioned Fig. 1, Fig. 2 and embodiment shown in Fig. 3, referring to Fig. 4, Fig. 4 is that the embodiment of the present application provides
Another data output method flow diagram, which includes step 401-409, specific as follows:
401: general processor sends executable file to artificial intelligence process device, and the executable file includes that hardware refers to
It enables.
402: artificial intelligence process device receives the executable file that can be run on the artificial intelligence process device,
The executable file includes the hardware instruction, parses the executable file, obtains flag bit.
403: artificial intelligence process device judges whether the flag bit meets preset condition.
404: if the flag bit meets the preset condition, artificial intelligence process device parses the hardware instruction, obtains
To the size of data buffer zone.
405: artificial intelligence process device is chosen from the free storage of the first memory of the artificial intelligence process device
Target storage.
406: artificial intelligence process device is using the target storage as the data buffer zone.
407: artificial intelligence process device stores data to be printed to the data buffer zone.
408: after the completion of the hardware instruction executes, artificial intelligence process device is by the data to be printed from the data
Buffer area is sent to the general processor.
409: general processor receives the data to be printed of the artificial intelligence process device transmission, will be described to be printed
Data output display is on a display screen；Alternatively, by the data-printing to be printed into default file folder.
It should be noted that the specific implementation process of each step of method shown in Fig. 4 can be found in described in the above method
Specific implementation process, no longer describe herein.
It is above-mentioned that mainly the scheme of the embodiment of the present application is described from the angle of method side implementation procedure.It is understood that
, in order to realize the above functions, it comprises execute the corresponding hardware configuration of each function and/or software for data output device
Module.Those skilled in the art should be readily appreciated that, list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, the application can be realized with the combining form of hardware or hardware and computer software.Some function is actually
It is executed in a manner of hardware or computer software driving hardware, the specific application and design constraint item depending on technical solution
Part.Professional technician can specifically realize described function to each using distinct methods, but this reality
Now it is not considered that exceeding scope of the present application.
The embodiment of the present application can carry out the division of functional unit, example according to above method example to data output device
Such as, each functional unit of each function division can be corresponded to, two or more functions can also be integrated at one
It manages in unit.Above-mentioned integrated unit both can take the form of hardware realization, can also be in the form of software functional units
It realizes.It should be noted that being schematical, only a kind of logic function stroke to the division of unit in the embodiment of the present application
Point, there may be another division manner in actual implementation.
Referring to Fig. 5, the functional unit that Fig. 5 is a kind of data output device provided by the embodiments of the present application forms block diagram,
The data output device 500 includes the first receiving unit 501, the first determination unit 502, the first storage unit 503 and the first biography
Send unit 504, in which:
First receiving unit 501, for receiving the executable file that can be run on artificial intelligence process device, it is described can
Executing file includes hardware instruction；
First determination unit 502, for based on the hardware instruction the artificial intelligence process device first memory
Middle determining data buffer zone；
First storage unit 503, for storing data to be printed to the data buffer zone.
First transmission unit 504, for the data to be printed to be sent to general processor from the data buffer zone.
As can be seen that in the embodiment of the present application, data output device reception can be run on artificial intelligence process device
Executable file, executable file includes hardware instruction, based on hardware instruction artificial intelligence process device first memory
Middle determining data buffer zone, print data is stored to data buffer zone, data to be printed is sent to from data buffer zone logical
With processor, show so as to pass through general processor for data to be printed output to the display screen being connect with general processor
On.Compared to data buffer zone is distributed in the first memory of artificial intelligence process device manually, it will be stored in data manually and delay
The data copy to be printed in area is rushed to general processor, size of the artificial intelligence process device based on data buffer zone has been achieved
Data to be printed are sent to general procedure from the data buffer zone of artificial intelligence process device automatically by automatic distribution data buffer zone
Device, so that general processor is by data to be printed output display to the display screen that connect with general processor, or will be to
Print data is printed into default file folder.
In a possible example, above-mentioned data output device 500 further includes resolution unit 505,506 and of judging unit
Execution unit 507, in which:
Resolution unit 505 obtains flag bit for parsing the executable file；
Judging unit 506, for judging whether the flag bit meets preset condition；
Execution unit 507, if judging that the flag bit meets the preset condition for the judging unit 506,
Execute the operation for determining data buffer zone in the first memory of the artificial intelligence process device based on the hardware instruction.
In a possible example, based on the hardware instruction the artificial intelligence process device first memory
In terms of middle determining data buffer zone, above-mentioned first determination unit 502 is specifically used for:
The hardware instruction is parsed, the size of the data buffer zone is obtained；
Target storage is chosen from the free storage of the first memory, using the target storage as described in
Data buffer zone.
In a possible example, in terms of storing data to be printed to the data buffer zone, above-mentioned first is deposited
Storage unit 503 is specifically used for:
Obtain the size of data of each child print data；
According to the size of data of each child print data, determine each child print data in the target of the data buffer zone
Storage location；
Each child print data are stored into position from the target that second memory is carried to its corresponding data buffer zone
It sets.
In a possible example, in the size of data according to each child print data, each child print data are determined
In terms of the target storage position of the data buffer zone, above-mentioned first storage unit 403 is specifically used for:
The hardware instruction is parsed, the print space needed for printing every time is obtained；
Print space needed for size of data and each printing based on current child print data determines described current
The corresponding printing times of child print data；
Obtain the task identification and the corresponding timestamp of the current child print data of the current child print data；
According to print space needed for each printing, the task identification, described current of the current child print data
The corresponding printing times of child print data and the corresponding timestamp of the current child print data calculate the current child print
The corresponding address offset amount of data；
Based on the corresponding address offset amount of the current child print data, determine the current child print data in the number
According to the target storage position of buffer area.
In a possible example, the data to be printed are being sent to general processor from the data buffer zone
Aspect, above-mentioned first transmission unit 504 are specifically used for:
After the completion of the hardware instruction executes, the data to be printed are sent to described lead to from the data buffer zone
Use processor；Alternatively,
Whenever the hardware instruction is executed to print command, then by the corresponding child print data of the print command from described
Data buffer zone is sent to the general processor.
In a possible example, the data to be printed are being sent to general processor from the data buffer zone
Aspect, above-mentioned first transmission unit 504 are specifically used for:
Whenever the hardware instruction is executed to print command, then the corresponding child print data of the print command are converted to
Character string, and the character string is sent to the general processor from the data buffer zone.
Referring to Fig. 6, the functional unit that Fig. 6 is a kind of data output device provided by the embodiments of the present application forms block diagram,
The data output device 600 is applied to general processor and artificial intelligence process device, and data output device 600 includes transmission unit
601, the second receiving unit 602, the second determination unit 603, the second storage unit 604, the second transmission unit 605, third receive
Unit 606 and output display unit 607, in which:
Transmission unit 601, for sending executable file to the artificial intelligence process device, the executable file includes
Hardware instruction；
Second receiving unit 602, for receiving the executable text that can be run on the artificial intelligence process device
Part, the executable file include the hardware instruction；
Second determination unit 603, for based on the hardware instruction the artificial intelligence process device first memory
Middle determining data buffer zone；
Second storage unit 604, for storing data to be printed to the data buffer zone；
Second transmission unit 605, for by the data to be printed from the data buffer zone be sent to it is described it is general from
Manage device；
Third receiving unit 606, for receiving the data to be printed of the artificial intelligence process device transmission；
Display unit 607 is exported, for showing on a display screen the data output to be printed；Alternatively, will it is described to
Print data is printed into default file folder.
The embodiment of the present application provides a kind of artificial intelligence process device, which includes described in above-mentioned Fig. 4
Data output device.
The embodiment of the present application provides a kind of electronic equipment, which includes above-mentioned artificial intelligence process device.
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, projector, 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.
The embodiment of the present application provides a kind of board, and refering to Fig. 7, the board is in addition to including above-mentioned artificial intelligence process device
It can also include other matching components, which includes but is not limited to: memory device 790, interface arrangement other than 789
791 and control device 792；
The memory device 790 is connect with the artificial intelligence process device 789 by bus, for storing data.
The memory device may include multiple groups storage unit 793.Storage unit described in each group and the artificial intelligence
Processor 789 is connected by bus.It is appreciated that storage unit described in each group can be DDR SDRAM (English: Double
Data Rate SDRAM, Double Data Rate synchronous DRAM).
DDR, which does not need raising clock frequency, can double to improve the speed of SDRAM.DDR allows the rising in clock pulses
Edge and failing edge read data.The speed of DDR is twice of standard SDRAM.In one embodiment, the storage device can be with
Including storage unit described in 4 groups.Storage unit described in each group may include multiple DDR4 particles (chip).In one embodiment
In, it may include 4 72 DDR4 controllers inside the artificial intelligence process device 789, in above-mentioned 72 DDR4 controllers
64bit is used for transmission data, and 8bit is used for ECC check.It is appreciated that using DDR4- in storage unit described in working as each group
When 3200 particle, the theoretical bandwidth of data transmission can reach 25600MB/s.
In a possible example, storage unit described in each group include multiple Double Data Rates being arranged in parallel synchronize it is dynamic
State random access memory.DDR can transmit data twice within a clock cycle.Control is set in the artificial intelligence process device
The controller of DDR processed, the control for data transmission and data storage to each storage unit.
The interface arrangement is electrically connected with the artificial intelligence process device.The interface arrangement is for realizing the artificial intelligence
Data between energy processor and external equipment (such as server or computer) are transmitted.Such as in one embodiment, described
Interface arrangement can be standard PCIE interface.For example, data to be processed are transferred to institute by standard PCIE interface by server
Artificial intelligence process device is stated, realizes data transfer.Preferably, when using the transmission of 16 interface of PCIE 3.0X, theoretical bandwidth can
Reach 16000MB/s.In another possible example, the interface arrangement can also be other interfaces, and the application is implemented
Example is not intended to limit the specific manifestation form of above-mentioned other interfaces, and the interface unit can be realized signaling transfer point.In addition,
The calculated result of the artificial intelligence process device still sends back external equipment (such as server) by the interface arrangement.
The control device is electrically connected with the artificial intelligence process device.The control device is used for the artificial intelligence
The state of processor is monitored.Specifically, the artificial intelligence process device and the control device can pass through SPI interface electricity
Connection.The control device may include single-chip microcontroller (Micro Controller Unit, MCU).Such as the artificial intelligence process
Device may include multiple processing chips, multiple processing cores or multiple processing circuits, can drive multiple loads.Therefore, the people
Work intelligent processor may be at the different working condition such as multi-load and light load.It may be implemented pair by the control device
The regulation of the working condition of multiple processing chips, multiple processing and/or multiple processing circuits in the artificial intelligence process device.
The embodiment of the present application also provides a kind of computer storage medium, and the computer storage medium is for storing computer journey
Sequence, above-mentioned computer program are executed by central processing unit, to realize the portion such as either record method in above method embodiment
Divide or Overall Steps, above-mentioned computer include electronic equipment.
The embodiment of the present application also provides a kind of computer program product, and above-mentioned computer program product includes storing calculating
The non-transient computer readable storage medium of machine program, above-mentioned computer program are operable to that computer is made to execute such as above-mentioned side
Some or all of either record method step in method embodiment.The computer program product can be a software installation
Packet, above-mentioned computer includes electronic equipment.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the application is not limited by the described action sequence because
According to the application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, related actions and modules not necessarily the application
It is necessary.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed device, it can be by another way
It realizes.For example, the apparatus embodiments described above are merely exemplary, such as the division of said units, it is only a kind of
Logical function partition, there may be another division manner in actual implementation, such as multiple units or components can combine or can
To be integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Coupling, direct-coupling or communication connection can be through some interfaces, the indirect coupling or communication connection of device or unit,
It can be electrical or other forms.
Above-mentioned unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If above-mentioned integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer-readable access to memory.Based on this understanding, the technical solution of the application substantially or
Person says that all or part of the part that contributes to existing technology or the technical solution can body in the form of software products
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.) executes all or part of each embodiment above method of the application
Step.And memory above-mentioned includes: USB flash disk, read-only memory (ROM, Read-Only Memory), random access memory
The various media that can store program code such as (RAM, Random Access Memory), mobile hard disk, magnetic or disk.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of above-described embodiment is can
It is completed with instructing relevant hardware by program, which can store in a computer-readable memory, memory
May include: flash disk, read-only memory (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 expounded, the description of the example is only used to help understand the method for the present application and its core ideas；
At the same time, for those skilled in the art can in specific implementation and application range according to the thought of the application
There is change place, to sum up above-mentioned, the contents of this specification should not be construed as limiting the present application.
Claims (10)
1. a kind of data output method, which is characterized in that the described method includes:
The executable file that can be run on artificial intelligence process device is received, the executable file includes hardware instruction；
Data buffer zone is determined in the first memory of the artificial intelligence process device based on the hardware instruction；
Data to be printed are stored to the data buffer zone；
The data to be printed are sent to general processor from the data buffer zone.
2. the method according to claim 1, wherein described be based on the hardware instruction at the artificial intelligence
It manages before determining data buffer zone in the first memory of device, the method also includes:
The executable file is parsed, flag bit is obtained；
Judge whether the flag bit meets preset condition；
If the flag bit meets the preset condition, execute based on the hardware instruction in the artificial intelligence process device
The operation of data buffer zone is determined in first memory.
3. method according to claim 1 or 2, which is characterized in that described to be based on the hardware instruction in the artificial intelligence
Data buffer zone can be determined in the first memory of processor, comprising:
The hardware instruction is parsed, the size of the data buffer zone is obtained；
Target storage is chosen from the free storage of the first memory, using the target storage as the data
Buffer area.
4. the method according to claim 1, wherein the data to be printed include at least one child print number
According to described to store data to be printed to the data buffer zone, comprising:
Obtain the size of data of each child print data；
According to the size of data of each child print data, determine each child print data in the data buffer zone
Target storage position；
Each child print data are stored into position from the target that second memory is carried to its corresponding data buffer zone
It sets.
5. according to the method described in claim 4, it is characterized in that, the size of data according to each child print data, really
Target storage position of the fixed each child print data in the data buffer zone, comprising:
The hardware instruction is parsed, the print space needed for printing every time is obtained；
Print space needed for size of data and each printing based on current child print data determines that the current son is beaten
Printing is according to corresponding printing times；
Obtain the task identification and the corresponding timestamp of the current child print data of the current child print data；
It is beaten according to print space needed for each printing, the task identification of the current child print data, the current son
Printing calculates the current child print data according to corresponding printing times and the corresponding timestamp of the current child print data
Corresponding address offset amount；
Based on the corresponding address offset amount of the current child print data, determine that the current child print data are slow in the data
Rush the target storage position in area.
6. method according to claim 1-5, which is characterized in that it is described by the data to be printed from the number
General processor is sent to according to buffer area, comprising:
The hardware instruction execute after the completion of, by the data to be printed from the data buffer zone be sent to it is described it is general from
Manage device；Alternatively,
Whenever the hardware instruction is executed to print command, then by the corresponding child print data of the print command from the data
Buffer area is sent to the general processor.
7. method according to claim 1-5, which is characterized in that it is described by the data to be printed from the number
General processor is sent to according to buffer area, comprising:
Whenever the hardware instruction is executed to print command, then the corresponding child print data of the print command are converted into character
String, and the character string is sent to the general processor from the data buffer zone.
8. a kind of data output method, which is characterized in that be applied to general processor and artificial intelligence process device, the method packet
It includes:
The general processor sends executable file to the artificial intelligence process device, and the executable file includes that hardware refers to
It enables；
The artificial intelligence process device receives the executable file that can be run on the artificial intelligence process device, described
Executable file includes the hardware instruction, based on the hardware instruction in the first memory of the artificial intelligence process device
Determine data buffer zone；
The artificial intelligence process device stores data to be printed to the data buffer zone；
The data to be printed are sent to the general processor from the data buffer zone by the artificial intelligence process device；
The general processor receives the data to be printed of the artificial intelligence process device transmission, by the data to be printed
Output display is on a display screen；Alternatively, by the data-printing to be printed into default file folder.
9. a kind of artificial intelligence process device, which is characterized in that the artificial intelligence process device is appointed for realizing such as claim 1-8
Some or all of method described in one step.
10. a kind of board, which is characterized in that the board includes: memory device, interface arrangement and control device and such as right
It is required that artificial intelligence process device described in 9, in which:
The artificial intelligence process device is separately connected with the memory device, the interface arrangement and the control device；
The memory device, for storing data；
The interface arrangement, for realizing the data transmission between the artificial intelligence process device and external equipment；
The control device is monitored for the state to the artificial intelligence process device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910269778.5A CN109992225B (en) | 2019-04-04 | 2019-04-04 | Data output method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910269778.5A CN109992225B (en) | 2019-04-04 | 2019-04-04 | Data output method and related device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109992225A true CN109992225A (en) | 2019-07-09 |
| CN109992225B CN109992225B (en) | 2022-02-22 |
Family
ID=67131398
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910269778.5A Active CN109992225B (en) | 2019-04-04 | 2019-04-04 | Data output method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109992225B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111290720A (en) * | 2020-03-13 | 2020-06-16 | 惠州市蓝微电子有限公司 | Data printing method and equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108153190A (en) * | 2017-12-20 | 2018-06-12 | 福建新大陆电脑股份有限公司 | A kind of artificial intelligence microprocessor |
| WO2018194988A1 (en) * | 2017-04-17 | 2018-10-25 | Microsoft Technology Licensing, Llc | Reducing power consumption in a neural network processor by skipping processing operations |
| CN109117945A (en) * | 2017-06-22 | 2019-01-01 | 上海寒武纪信息科技有限公司 | Processor and its processing method, chip, chip-packaging structure and electronic device |
| US20190057302A1 (en) * | 2017-08-16 | 2019-02-21 | SK Hynix Inc. | Memory device including neural network processor and memory system including the memory device |
| CN109416756A (en) * | 2018-01-15 | 2019-03-01 | 深圳鲲云信息科技有限公司 | Acoustic convolver and its applied artificial intelligence process device |
| CN109564638A (en) * | 2018-01-15 | 2019-04-02 | 深圳鲲云信息科技有限公司 | Artificial intelligence process device and its applied processing method |
-
2019
- 2019-04-04 CN CN201910269778.5A patent/CN109992225B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018194988A1 (en) * | 2017-04-17 | 2018-10-25 | Microsoft Technology Licensing, Llc | Reducing power consumption in a neural network processor by skipping processing operations |
| CN109117945A (en) * | 2017-06-22 | 2019-01-01 | 上海寒武纪信息科技有限公司 | Processor and its processing method, chip, chip-packaging structure and electronic device |
| US20190057302A1 (en) * | 2017-08-16 | 2019-02-21 | SK Hynix Inc. | Memory device including neural network processor and memory system including the memory device |
| CN108153190A (en) * | 2017-12-20 | 2018-06-12 | 福建新大陆电脑股份有限公司 | A kind of artificial intelligence microprocessor |
| CN109416756A (en) * | 2018-01-15 | 2019-03-01 | 深圳鲲云信息科技有限公司 | Acoustic convolver and its applied artificial intelligence process device |
| CN109564638A (en) * | 2018-01-15 | 2019-04-02 | 深圳鲲云信息科技有限公司 | Artificial intelligence process device and its applied processing method |
Non-Patent Citations (2)
| Title |
|---|
| RICHARD M.STALLMAN 等: "Debugging with GDB", 《THE GNU SOURCE-LEVEL DEBUGGER》 * |
| 林广栋 等: "一种针对处理器集群的源代码级调试系统实现方案", 《中国集成电路》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111290720A (en) * | 2020-03-13 | 2020-06-16 | 惠州市蓝微电子有限公司 | Data printing method and equipment |
| CN111290720B (en) * | 2020-03-13 | 2023-09-05 | 惠州市蓝微电子有限公司 | Data printing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109992225B (en) | 2022-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7594226B2 (en) | Implementation of packet-based communications in a reconfigurable hardware element | |
| US7577776B2 (en) | Multiple virtual USB devices with virtual HUB implemented using one USB device controller | |
| CN103714029B (en) | Novel two-line synchronous communication protocol and application | |
| CN109740751A (en) | The framework fusion method and relevant apparatus of neural network model | |
| CN109634720B (en) | Method, system and device for sharing FPGA (field programmable Gate array) board card by multiple virtual machines | |
| CN108111382A (en) | Communicator and its communication means based on I3C buses | |
| WO2019072218A1 (en) | Method and device for signal conversion, home bus system (hbs) circuit, and user equipment | |
| CN109783340A (en) | Test code programming method, IP test method and the device of SoC | |
| CN105808476B (en) | The transmission method and device of clock-domain crossing data | |
| CN106851183A (en) | Multi-channel video processing system and method based on FPGA | |
| CN109992225A (en) | Data output method and relevant apparatus | |
| CN109286558A (en) | Message distributing method, device, electronic equipment and storage medium | |
| CN204595794U (en) | USB computer switcher signal extender and extender system | |
| CN108924325A (en) | Data processing method and relevant apparatus | |
| KR910001404B1 (en) | Apparatus for synchronizing a stream of data bits received over a single coaxial conductor | |
| CN110083532B (en) | Method and device for positioning operation errors in fusion mode based on deep learning framework | |
| CN107239418A (en) | Data memory module read-write equipment and I2The C means of communication | |
| CN106455324A (en) | Method and system for generating topological structures | |
| CN110442059A (en) | Controlled device expanding method, device and control equipment | |
| CN109739514A (en) | Parameter processing method and Related product | |
| CN109634884A (en) | PORT COM connection method and device | |
| CN114064545A (en) | Serial port function identification method and device, main control chip, household appliance and medium | |
| CN110096002A (en) | A kind of automatization test system and test method based on CANFD bus | |
| CN102929828A (en) | Data transmission method and device supporting standard and non-standard I2C (Inter-Integrated Circuit) interface simultaneously | |
| CN107087115A (en) | One kind, which is taken pictures, controls circuit and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 100000 room 644, No. 6, No. 6, South Road, Beijing Academy of Sciences Applicant after: Zhongke Cambrian Technology Co., Ltd Address before: 100000 room 644, No. 6, No. 6, South Road, Beijing Academy of Sciences Applicant before: Beijing Zhongke Cambrian Technology Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |