CN105159766A - Synchronous access method and synchronous access device of data - Google Patents
Synchronous access method and synchronous access device of data Download PDFInfo
- Publication number
- CN105159766A CN105159766A CN201510548924.XA CN201510548924A CN105159766A CN 105159766 A CN105159766 A CN 105159766A CN 201510548924 A CN201510548924 A CN 201510548924A CN 105159766 A CN105159766 A CN 105159766A
- Authority
- CN
- China
- Prior art keywords
- data
- access
- synchronized
- atomic operation
- operation instruction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multi Processors (AREA)
Abstract
The invention discloses a synchronous access method and synchronous access device of data. The synchronous access method of the data comprises the following steps: distributing a continuous memory unit for data to be synchronously accessed, wherein the data digit of the continuous memory unit is a sum of the data digits of all pieces of data to be synchronously accessed; on the basis of the amount of the data to be synchronously accessed and the data digit of each piece of data to be synchronously accessed, dividing an atomic operation instruction into data segments corresponding to the amount of the data to be synchronously accessed, wherein the digit of each data segment is greater than or equal to the digit of the data to be synchronously accessed, and the data to be synchronously accessed corresponds to each data segment; and within an instruction period, accessing the data to be synchronously accessed, wherein the instruction period is duration for executing the atomic operation instruction. According to the scheme of the invention, multiple pieces of data with an association relationship can be synchronously accessed in the same atomic operation instruction period, and data access efficiency is improved so as to quicken computer data processing speed.
Description
Technical field
The disclosure relates generally to computer technology, is specifically related to data access technology, particularly relates to synchronization of access method and the synchronization of access device of data.
Background technology
In the prior art, data are positioned at certain position of storage area, and each data correspondence one is for synchronous synchronization object.
To sharing, variable data respective synchronization of access time, synchronization object corresponding to setting data is no signal condition, by atomic operation instruction access data, if judge that the value of data meets preassigned corresponding relation, then corresponding synchronization object is set for there being signal condition.
To when there is the synchronization of access of incidence relation data, wait for that synchronization object corresponding to every other data is for there being signal condition, then by atomic operation instruction access notebook data.
But existing synchronization of access method, for the synchronization of access of data that there is incidence relation, needs to wait for synchronization object, affects efficiency.In addition, when the IRQ level of processor is on thread scheduling level is other, this method is unavailable.
Summary of the invention
In view of above-mentioned defect of the prior art or deficiency, expect synchronization of access method and synchronization of access device that a kind of data are provided, synchronization of access can be carried out to multiple data that there is incidence relation within the same atomic operation instruction cycle, improve the efficiency of data access, thus accelerate the speed of computer digital animation.
First aspect, the embodiment of the present application provides a kind of synchronization of access method of data, comprising: the data to access to be synchronized distribute contiguous memory unit, and wherein, the data bits of contiguous memory unit is the data bits sum of the data of each access to be synchronized; Based on the data bits of the quantity of the data of access to be synchronized and the data of each access to be synchronized, atomic operation instruction is divided into the data segment corresponding with the quantity of the data of access to be synchronized, wherein, the figure place of each data segment is more than or equal to the figure place of the data of access to be synchronized corresponding with it; And within an instruction cycle, access the data of access to be synchronized, wherein, the instruction cycle is the duration performing atomic operation instruction.
Second aspect, the embodiment of the present application additionally provides a kind of synchronization of access device of data, comprising: distribution module, and the data be configured for access to be synchronized distribute contiguous memory unit, wherein, the data bits of contiguous memory unit is the data bits sum of each data; Divide module, be configured for the data bits based on the quantity of the data of access to be synchronized and the data of each access to be synchronized, atomic operation instruction is divided into the data segment corresponding with the quantity of the data of access to be synchronized, wherein, the figure place of each data segment is more than or equal to the figure place of the data of access to be synchronized corresponding with it; And access modules, be configured within an instruction cycle, access the data of access to be synchronized, wherein, the instruction cycle is the duration performing atomic operation instruction.
The scheme that the embodiment of the present application provides, can access multiple data simultaneously, improve the efficiency of reading and writing data in an atomic operation instruction cycle.
In addition, be less than or equal to the prerequisite of atomic operation instruction figure place at the total bit of data under, carry out the synchronization of access of data, other threads can be avoided the amendment of data, ensure that the correctness of incidence relation between each data.
In some implementations of the embodiment of the present application, the incidence relation can also determining between each data by an atomic operation instruction.
Accompanying drawing explanation
By reading the detailed description done non-limiting example done with reference to the following drawings, the other features, objects and advantages of the application will become more obvious:
Fig. 1 shows the indicative flowchart of the synchronization of access method of the data according to the application's embodiment;
Fig. 2 shows in Fig. 1, based on the data bits of the quantity of the data of access to be synchronized and the data of each access to be synchronized, atomic operation instruction is divided into the indicative flowchart of the data segment corresponding with the quantity of the data of access to be synchronized;
Fig. 3 shows the schematic diagram of an application scenarios of the synchronization of access method of the data according to the embodiment of the present application;
Fig. 4 shows the schematic diagram of the synchronization of access device of the data according to the application's embodiment.
Embodiment
Below in conjunction with drawings and Examples, the application is described in further detail.Be understandable that, specific embodiment described herein is only for explaining related invention, but not the restriction to this invention.It also should be noted that, for convenience of description, illustrate only in accompanying drawing and invent relevant part.
It should be noted that, when not conflicting, the embodiment in the application and the feature in embodiment can combine mutually.Below with reference to the accompanying drawings and describe the application in detail in conjunction with the embodiments.
Shown in Figure 1, be schematic flow Figure 100 of the synchronization of access method of the data according to the application's embodiment.
Specifically, in step 110, the data to access to be synchronized distribute contiguous memory unit.Wherein, the data bits of contiguous memory unit is the data bits sum of the data of each access to be synchronized.
Memory Allocation, refers in the process performed in program the operation distributing or reclaim storage space.And the continuous dispensing mode of internal memory, refer to be that a user program distributes a continuous print memory headroom.The continuous dispensing mode of internal memory comprises single continuous dispensing, fixed partition distribution and dynamic partition distribution etc.
In the present embodiment, by distributing contiguous memory unit to data, to the access fast and efficiently of each data in subsequent step, thus treatment effeciency can be improved.
In some optional implementations, such as, have the data of four access to be synchronized, the data of each access to be synchronized all comprise 16.So, when carrying out the distribution of contiguous memory unit to these data, 64 contiguous memory unit (16 × 4) can be distributed, for depositing the data of these access to be synchronized.
Then, in the step 120, based on the data bits of the quantity of the data of access to be synchronized and the data of each access to be synchronized, atomic operation instruction is divided into the data segment corresponding with the quantity of the data of access to be synchronized, wherein, the figure place of each data segment is more than or equal to the figure place of the data of access to be synchronized corresponding with it.
Atomic operation, refers to not interruptable one or sequence of operations, the operation that namely can not be interrupted by thread scheduling mechanism, and run duration does not have any contextual processing (contextswitch).
So, when adopting the data of atomic operation instruction to each access to be synchronized to conduct interviews, this access can not be interrupted by other thread, in other words, before atomic operation instruction instruction is finished, the value of the data stored in internal storage location can not change by other thread.
Same to have the data of four access to be synchronized, the packet of each access to be synchronized is described containing 16.In order to carry out concurrent access to the data of four access to be synchronized, atomic operation instruction can be divided into four data segments, distinguish the data of corresponding these four access to be synchronized of access.And the data processing figure place of each data segment is not less than 16.
Here, it should be noted that, in order to the magnitude relationship of the data bits of the data of data processing figure place and access to be synchronized that atomic operation instruction is described, these data sentencing each access to be synchronized include 16 and are illustrated.But in a practical situation, the data of each access to be synchronized may have identical data bits, also may have different data bitss.Correspondingly, in order to be adapted to the data bits of the data of each access to be synchronized, the data processing figure place of the data segment of the atomic operation instruction corresponding from the data of each access to be synchronized also may be identical or different.
The data bits of the such as data A of access to be synchronized is 16, the data bits of the data B of access to be synchronized is 8, so when carrying out data segment and dividing, data segment for accessing the data A of access to be synchronized at least has the data processing figure place of 16, and at least has the data processing figure place of 8 for the data segment of the data B accessing access to be synchronized.
Then, in step 130, within an instruction cycle, access the data of access to be synchronized, wherein, the instruction cycle is the duration performing atomic operation instruction.
In other words, in this step, the data of each access to be synchronized of corresponding access are carried out by each data segment of atomic operation instruction.
Here, reading, write or other class of operation can such as be comprised to the access of the data of each access to be synchronized.
Adopt the synchronization of access method of data of the present embodiment, can within an instruction cycle, simultaneously to the access that the data of multiple access to be synchronized walk abreast.In addition, owing to being visited the data of these access to be synchronized by atomic operation instruction, this access can not be interrupted by other thread scheduling mechanism.
Shown in Figure 2, in the synchronization of access method for the data of the present embodiment, based on the data bits of each data, call schematic flow Figure 200 of the step (namely step 120) as shown in Figure 1 of the atomic operation instruction of processor.
Specifically, in step 210, the data bits of the data of each access to be synchronized is obtained.
In some optional implementations, such as, the data bits of the data of each access to be synchronized can be determined by the data bits of the contiguous memory unit distributed to the data of access to be synchronized.
As shown in Figure 1, contiguous memory unit is assigned with based on the data bits of data to data in step 110.So, can based on the data bits of contiguous memory unit and the data bits determining the data of each access to be synchronized to the size of memory headroom shared during each data storage allocation unit.
Return and continue with reference to figure 2.In a step 220, the data bits sum of the data of more each access to be synchronized and the data processing figure place of atomic operation instruction.
Then, be more than or equal to the data bits sum of the data of each access to be synchronized in step 230 based on the data processing figure place of atomic operation instruction, atomic operation instruction is divided into the data segment corresponding with the quantity of data.
Such as, equally to have the data (A ~ D) of four access to be synchronized, each packet is described containing 16.If the data processing figure place of atomic operation instruction is 64, in other words, the data processing figure place of atomic operation instruction equals the data bits sum (16 × 4) of the data of each access to be synchronized, so atomic operation instruction can be divided into four data segments.Each data segment can distinguish the data of corresponding one of them access to be synchronized of access.
Otherwise, if the data processing figure place of atomic operation instruction is 32, in other words, the data processing figure place of atomic operation instruction is less than the data bits sum (16 × 4) of the data of each access to be synchronized, then corresponding data segment division is not carried out in atomic operation instruction.Its reason is, due to the upper limit of the data bits that the data bits sum of these four access to be synchronized can process beyond instruction cycle of an atomic operation instruction, these visit datas to be synchronized cannot complete synchronization of access within the instruction cycle of same atomic operation instruction.
Return and continue with reference to figure 1.In some optional implementations, each atomic operation command synchronization of execution of step 130 accesses the operational example of data corresponding with it as comprised, and reads and/or Update Table within an instruction cycle.Here, the instruction cycle is the duration performing atomic operation instruction.
Such as, in some optional implementations, the execution content of atomic operation instruction is " reading ".So, the numerical value of each data can return as rreturn value after performing by atomic operation instruction.
Or in other implementations, the execution content of atomic operation instruction is " amendment ".So, after atomic operation instruction performs, the numerical value of each data will be changed accordingly.
In some optional implementations, the synchronization of access method of the data of the present embodiment can also comprise step 140, within the instruction cycle, based on the rreturn value of the data of access access to be synchronized, determines the incidence relation of the data of each access to be synchronized.
The incidence relation of the data of each access to be synchronized such as can comprise numerical operation relation or logical operation relation.
Such as, equally to have the data (A ~ D) of four access to be synchronized, each packet is described containing 16.In some optional implementations, according to one of them value in the data of these four access to be synchronized, the value of the data of other access to be synchronized can be determined, such as, when the numerical value of the data of B, C, D tri-access to be synchronized is 0, then the value of the data A of access to be synchronized is set to 1.Or, according to numerical value wherein several in the data of these four access to be synchronized, the numerical value of remainder data can also be calculated, such as, according to the value of the data of the access to be synchronized of A ~ D, the value of A can be upgraded, in other words, calculate A=A+B+C+D.
, the application scenarios shown in composition graphs 3 is set forth further the implementation of the synchronization of access method of the data of the embodiment of the present application below, illustrated more fully to enable its feature.
As shown in Figure 3, suppose have four visit data A, B, C, D to be synchronized.With reference to the flow process shown in Fig. 1, first, for these four visit data A ~ D to be synchronized distribute continuous print internal storage location 310 (as Suo Shi the step 110 in Fig. 1).
Then, in order to carry out synchronization of access to the data A of these four access to be synchronized ~ D within the instruction cycle of an atomic operation instruction, if the data bits sum of data A ~ D is no more than the data processing figure place of atomic operation instruction, then atomic operation instruction is divided into four data segments 320, namely corresponding with the data A ~ D of four access to be synchronized respectively data segment one, data segment two, data segment three and data segment four (as Suo Shi the step 120 in Fig. 1), and within an instruction cycle, data A ~ the D (as Suo Shi the step 130 in Fig. 1) of each to be synchronized access corresponding with each data segment is accessed concurrently by each data segment.
Then, as shown in Reference numeral 330, according to the access result of each data segment to each visit data A ~ D to be synchronized, in the same atomic operation instruction cycle, the incidence relation (as Suo Shi the step 140 in Fig. 1) between each visit data A ~ D to be synchronized can also be determined.After incidence relation is determined, the data based on wherein one or more access to be synchronized may be needed to upgrade other data.
Adopt the synchronization of access method of above-mentioned data, in an atomic operation instruction cycle, the data of multiple access to be synchronized can be accessed simultaneously, improve the efficiency of reading and writing data.
In addition, the synchronization of access of the data of multiple access to be synchronized is carried out be less than or equal to the prerequisite of the data processing figure place of atomic operation instruction at the total bit of data under, other threads can be avoided the amendment of the data of these multiple access to be synchronized, the correctness of incidence relation between the data that ensure that each access to be synchronized.
Shown in Figure 4, be the schematic diagram 400 of the synchronization of access device of the data according to the application's embodiment.
The synchronization of access device of the data of the present embodiment can comprise distribution module 410, divide module 420 and access modules 430.
Wherein, distribution module 410 is configurable distributes contiguous memory unit for the data to access to be synchronized.
Here, the data bits of contiguous memory unit is the data bits sum of the data of each access to be synchronized.
Divide the data bits of the data of the configurable quantity for the data based on access to be synchronized of module 420 and each access to be synchronized, atomic operation instruction is divided into the data segment corresponding with the quantity of the data of access to be synchronized.
Here, the figure place of each data segment is more than or equal to the figure place of the data of access to be synchronized corresponding with it.
Access modules 430 is configurable within an instruction cycle, accesses the data of access to be synchronized.
Here, the instruction cycle is the duration performing atomic operation instruction.
In some optional implementations, divide the data bits that module 420 also can be configured for the data obtaining each access to be synchronized further; The data bits sum of the data of more each access to be synchronized and the data processing figure place of atomic operation instruction; And the data bits sum of the data of each access to be synchronized is more than or equal to based on the data processing figure place of atomic operation instruction, atomic operation instruction is divided into the data segment corresponding with the quantity of data.
In some optional implementations, access modules 430 also can be configured for further and read and/or revise the data of access to be synchronized within an instruction cycle.
In some optional implementations, the synchronization of access device of the data of the present embodiment can also comprise incidence relation determination module 440.
Incidence relation determination module 440 is configurable within the instruction cycle, based on the rreturn value of the data of access access to be synchronized, determines the incidence relation of the data of each access to be synchronized.
Here, incidence relation such as can comprise numerical operation relation or logical operation relation.
Process flow diagram in accompanying drawing and block diagram, illustrate according to the architectural framework in the cards of the system of various embodiments of the invention, method and computer program product, function and operation.In this, each square frame in process flow diagram or block diagram can represent a part for module, program segment or a code, and a part for described module, program segment or code comprises one or more executable instruction for realizing the logic function specified.Also it should be noted that at some as in the realization of replacing, the function marked in square frame also can be different from occurring in sequence of marking in accompanying drawing.Such as, in fact the square frame that two adjoining lands represent can perform substantially concurrently, and they also can perform by contrary order sometimes, and this determines according to involved function.Also it should be noted that, the combination of the square frame in each square frame in block diagram and/or process flow diagram and block diagram and/or process flow diagram, can realize by the special hardware based system of the function put rules into practice or operation, or can realize with the combination of specialized hardware and computer instruction.
Unit involved by being described in the embodiment of the present application or module can be realized by the mode of software, also can be realized by the mode of hardware.Described unit or module also can be arranged within a processor, such as, can be described as: a kind of processor comprises distribution module, divides module and access modules.Wherein, the title of these unit or module does not form the restriction to this unit or module itself under certain conditions, and such as, distribution module can also be described to " for distributing the module of contiguous memory unit to data ".
As another aspect, present invention also provides a kind of computer-readable recording medium, this computer-readable recording medium can be the computer-readable recording medium comprised in device described in above-described embodiment; Also can be individualism, be unkitted the computer-readable recording medium in the equipment of allocating into.Computer-readable recording medium stores more than one or one program, and described program is used for performance description in the formula input method of the application by one or more than one processor.
More than describe and be only the preferred embodiment of the application and the explanation to institute's application technology principle.Those skilled in the art are to be understood that, invention scope involved in the application, be not limited to the technical scheme of the particular combination of above-mentioned technical characteristic, also should be encompassed in when not departing from described inventive concept, other technical scheme of being carried out combination in any by above-mentioned technical characteristic or its equivalent feature and being formed simultaneously.The technical characteristic that such as, disclosed in above-mentioned feature and the application (but being not limited to) has similar functions is replaced mutually and the technical scheme formed.
Claims (10)
1. a synchronization of access method for data, is characterized in that, comprising:
Data to access to be synchronized distribute contiguous memory unit, and wherein, the data bits of described contiguous memory unit is the data bits sum of the data of each described access to be synchronized;
Based on the data bits of the quantity of the data of described access to be synchronized and the data of each described access to be synchronized, atomic operation instruction is divided into the data segment corresponding with the quantity of the data of access to be synchronized, wherein, the figure place of each described data segment is more than or equal to the figure place of the data of access described to be synchronized corresponding with it; And
Within an instruction cycle, access the data of described access to be synchronized, wherein, the described instruction cycle is the duration performing described atomic operation instruction.
2. method according to claim 1, it is characterized in that, the data bits of the quantity of the described data based on described access to be synchronized and the data of each described access to be synchronized, is divided into the data segment corresponding with the quantity of the data of access to be synchronized by atomic operation instruction and comprises:
Obtain the data bits of the data of each described access to be synchronized;
The data bits sum of the data of more each described access to be synchronized and the data processing figure place of described atomic operation instruction; And
Data processing figure place based on described atomic operation instruction is more than or equal to the data bits sum of the data of each described access to be synchronized, and atomic operation instruction is divided into the data segment corresponding with the quantity of data.
3. method according to claim 1, is characterized in that, described within an instruction cycle, the data of accessing described access to be synchronized comprise:
Within an instruction cycle, read and/or revise the data of described access to be synchronized.
4. method according to claim 3, is characterized in that, described method also comprises:
Within the described instruction cycle, based on the rreturn value of the data of the described access to be synchronized of access, determine the incidence relation of the data of each described access to be synchronized.
5. method according to claim 4, is characterized in that:
Described incidence relation comprises numerical operation relation or logical operation relation.
6. a synchronization of access device for data, is characterized in that, comprising:
Distribution module, the data be configured for access to be synchronized distribute contiguous memory unit, and wherein, the data bits of described contiguous memory unit is the data bits sum of each described data;
Divide module, be configured for the data bits based on the quantity of the data of described access to be synchronized and the data of each described access to be synchronized, atomic operation instruction is divided into the data segment corresponding with the quantity of the data of access to be synchronized, wherein, the figure place of each described data segment is more than or equal to the figure place of the data of access described to be synchronized corresponding with it; And
Access modules, was configured within an instruction cycle, accessed the data of described access to be synchronized, and wherein, the described instruction cycle is the duration performing described atomic operation instruction.
7. device according to claim 6, is characterized in that, described division module is configured for further:
Obtain the data bits of the data of each described access to be synchronized;
The data bits sum of the data of more each described access to be synchronized and the data processing figure place of described atomic operation instruction; And
Data processing figure place based on described atomic operation instruction is more than or equal to the data bits sum of the data of each described access to be synchronized, and atomic operation instruction is divided into the data segment corresponding with the quantity of data.
8. device according to claim 6, is characterized in that, described access modules is configured for further:
Within an instruction cycle, read and/or revise the data of described access to be synchronized.
9. the device according to claim 6-8 any one, is characterized in that, described device also comprises:
Incidence relation determination module, is configured within the described instruction cycle, based on the rreturn value of the data of the described access to be synchronized of access, determines the incidence relation of the data of each described access to be synchronized.
10. device according to claim 9, is characterized in that:
Described incidence relation comprises numerical operation relation or logical operation relation.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510548924.XA CN105159766B (en) | 2015-08-31 | 2015-08-31 | Synchronous access method and synchronous access device for data |
| PCT/CN2015/099893 WO2017036041A1 (en) | 2015-08-31 | 2015-12-30 | Data synchronous access method and synchronous access device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510548924.XA CN105159766B (en) | 2015-08-31 | 2015-08-31 | Synchronous access method and synchronous access device for data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105159766A true CN105159766A (en) | 2015-12-16 |
| CN105159766B CN105159766B (en) | 2018-05-25 |
Family
ID=54800629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510548924.XA Active CN105159766B (en) | 2015-08-31 | 2015-08-31 | Synchronous access method and synchronous access device for data |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105159766B (en) |
| WO (1) | WO2017036041A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017036041A1 (en) * | 2015-08-31 | 2017-03-09 | 安一恒通（北京）科技有限公司 | Data synchronous access method and synchronous access device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101052947A (en) * | 2004-11-03 | 2007-10-10 | 皇家飞利浦电子股份有限公司 | Programmable data processing circuit that supports simd instruction |
| CN101133396A (en) * | 2005-01-24 | 2008-02-27 | 国际商业机器公司 | Method for managing access to shared resources in a multi-processor environment |
| US20130151798A1 (en) * | 2011-12-10 | 2013-06-13 | International Business Machines Corporation | Expedited Module Unloading For Kernel Modules That Execute Read-Copy Update Callback Processing Code |
| US20140181421A1 (en) * | 2012-12-21 | 2014-06-26 | Advanced Micro Devices, Inc. | Processing engine for complex atomic operations |
| CN103970506A (en) * | 2008-03-28 | 2014-08-06 | 英特尔公司 | Vector instruction to enable efficient synchronization and parallel reduction operations |
| CN104025031A (en) * | 2011-12-28 | 2014-09-03 | 英特尔公司 | Reducing the number of sequential operations in an application to be performed on a shared memory cell |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105159766B (en) * | 2015-08-31 | 2018-05-25 | 安一恒通（北京）科技有限公司 | Synchronous access method and synchronous access device for data |
-
2015
- 2015-08-31 CN CN201510548924.XA patent/CN105159766B/en active Active
- 2015-12-30 WO PCT/CN2015/099893 patent/WO2017036041A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101052947A (en) * | 2004-11-03 | 2007-10-10 | 皇家飞利浦电子股份有限公司 | Programmable data processing circuit that supports simd instruction |
| CN101133396A (en) * | 2005-01-24 | 2008-02-27 | 国际商业机器公司 | Method for managing access to shared resources in a multi-processor environment |
| CN103970506A (en) * | 2008-03-28 | 2014-08-06 | 英特尔公司 | Vector instruction to enable efficient synchronization and parallel reduction operations |
| US20130151798A1 (en) * | 2011-12-10 | 2013-06-13 | International Business Machines Corporation | Expedited Module Unloading For Kernel Modules That Execute Read-Copy Update Callback Processing Code |
| CN104025031A (en) * | 2011-12-28 | 2014-09-03 | 英特尔公司 | Reducing the number of sequential operations in an application to be performed on a shared memory cell |
| US20140181421A1 (en) * | 2012-12-21 | 2014-06-26 | Advanced Micro Devices, Inc. | Processing engine for complex atomic operations |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017036041A1 (en) * | 2015-08-31 | 2017-03-09 | 安一恒通（北京）科技有限公司 | Data synchronous access method and synchronous access device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105159766B (en) | 2018-05-25 |
| WO2017036041A1 (en) | 2017-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100862124B1 (en) | Simulating multiported memories using lower port count memories | |
| CN101630276B (en) | High-efficiency memory access method | |
| US20150128144A1 (en) | Data processing apparatus and method for processing a plurality of threads | |
| CN103744726B (en) | A kind of two-level scheduler method of Windows system real-time extension | |
| CN104111897A (en) | Data processing method, data processing device and computer system | |
| JP2011522325A (en) | Local and global data sharing | |
| CN103197916A (en) | Methods and apparatus for source operand collector caching | |
| US10296400B2 (en) | Configuring resources used by a graphics processing unit | |
| TW201403321A (en) | Dynamic bank mode addressing for memory access | |
| CN103176848A (en) | Compute work distribution reference counters | |
| JP7164733B2 (en) | data storage | |
| CN113032007B (en) | Data processing method and device | |
| US7243354B1 (en) | System and method for efficiently processing information in a multithread environment | |
| CN105988875B (en) | Method and device for running process | |
| CN104021094B (en) | Data storage device and flash memory control method | |
| US11620503B2 (en) | Neural network processing | |
| CN108459906B (en) | Method and device for scheduling VCPU (virtual host processor unit) thread | |
| JP4801605B2 (en) | SIMD type microprocessor | |
| CN108255526B (en) | System starting and running method and device | |
| CN105159766A (en) | Synchronous access method and synchronous access device of data | |
| CN103593606A (en) | Contextual information managing method and system | |
| CN103389893A (en) | Read-write method and device for configuration register | |
| CN110162483B (en) | Static memory defragmentation method, device, computer equipment and storage medium | |
| CN115034950A (en) | Thread construction method and device | |
| CN100511195C (en) | Method for implementing two-dimensional data delivery using DMA controller |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20190826 Address after: 100085 Beijing, Haidian District, No. ten on the ground floor, No. 10 Baidu building, layer 2 Patentee after: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY Co.,Ltd. Address before: 100091 Beijing, Haidian District, northeast Wang West Road, No. 4, Zhongguancun Software Park, building C, block, 1-03 Patentee before: Pacify a Heng Tong (Beijing) Science and Technology Ltd. |
|
| TR01 | Transfer of patent right |