CN107330106A - A kind of data filtering method and device based on FPGA - Google Patents
A kind of data filtering method and device based on FPGA Download PDFInfo
- Publication number
- CN107330106A CN107330106A CN201710551317.8A CN201710551317A CN107330106A CN 107330106 A CN107330106 A CN 107330106A CN 201710551317 A CN201710551317 A CN 201710551317A CN 107330106 A CN107330106 A CN 107330106A
- Authority
- CN
- China
- Prior art keywords
- data
- filter
- filter data
- relative position
- position relation
- 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
- 238000001914 filtration Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000013135 deep learning Methods 0.000 description 4
- 238000013500 data storage Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000002775 capsule Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
- G06F16/337—Profile generation, learning or modification
-
- 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
- G06F9/52—Program synchronisation; Mutual exclusion, e.g. by means of semaphores
Abstract
The invention discloses a kind of data filtering method and device based on FPGA, this method includes:The initial data of specified quantity is received, is numbered according to the relative position relation between each initial data, and filtration treatment is carried out to initial data by filter algorithm, filter data was obtained;The relative position relation between filter data was determined according to the corresponding numbering of filter data excessively;Output array is created, and filter data write-in is exported into array according to the relative position relation crossed between filter data.As can be seen here, this method avoids can not determine that each crossed filter data and the corresponding relation of memory cell after filter data was obtained, it ensure that the entirety of filter data sequentially met the relative position in initial data, be not in covering or the loss between data when also ensure that filter data excessively writing output array simultaneously, improve the security and availability of data.In addition, the present invention also provides a kind of data filtering device based on FPGA, beneficial effect is as described above.
Description
Technical field
The present invention relates to FPGA development fields, more particularly to a kind of data filtering method and device based on FPGA.
Background technology
With the development of big data, the deep learning related to big data turns into hot topic instantly, and deep learning is often
Need to use filter algorithm to screen big data to obtain qualified data.In order to accelerate the hair of deep learning
Exhibition, can carry out the realization of deep learning by FPGA (field programmable gate array), due to FPGA holding using hardware circuit
Line mode is handled data, so performing speed is higher than the speed that tradition CPU is handled data, therefore uses FPGA
Data-handling efficiency can be improved.
When performing filter algorithm, it is necessary to by undesirable rejection of data, and by satisfactory data according to mistake
Relative position is sequentially written in the memory cell of array before filter.
However, because FPGA uses asynchronous computing mechanism, so when FPGA performs filter algorithm, often because
The multiple data of parallel processing, and whether lead to not the data for learning remaining parallel filtering by filtering, therefore can not be according to symbol
The relative position for closing data before filtering determines that the data after each filtering should write the specific memory cell of array, and then may
The data of output are caused while writing in the same memory cell of array and data occur and lost because capped or occur mistake
By mistake situations such as, reduce the security and availability of data.
When carrying out data filtering under FPGA there is provided a kind of data filtering method based on FPGA to improve as can be seen here,
The security and availability of data, are those skilled in the art's urgent problems to be solved.
The content of the invention
It is an object of the invention to provide a kind of data filtering method and device based on FPGA, the security of data is improved
And availability.
In order to solve the above technical problems, the present invention provides a kind of data filtering method based on FPGA, including:
The initial data of specified quantity is received, is numbered according to the relative position relation between each initial data, and lead to
Cross filter algorithm and filtration treatment is carried out to initial data, obtain filter data;
The relative position relation between filter data was determined according to the corresponding numbering of filter data excessively;
Output array is created, and filter data write-in is exported into array according to the relative position relation crossed between filter data.
It is preferred that, after the relative position relation between filter data was determined according to the corresponding numbering of filter data excessively, the party
Method further comprises:
The quantity of record filtering data;
Then corresponding, the quantity of the memory cell in output array is identical with the quantity for crossing filter data.
It is preferred that, should before the relative position relation between filter data was determined according to the corresponding numbering of filter data excessively
Method further comprises:
Create two-dimensional array;
It is then corresponding, by the relative position relation between the first dimension record filtering data of two-dimensional array, pass through two
The quantity of second dimension record filtering data of dimension group.
It is preferred that, the initial data for receiving specified quantity is specially:
Receive the initial data that incoming specified quantity is cached by DDR.
It is preferred that, initial data is specially the initial data of float.
It is preferred that, specified quantity is specially 8.
In addition, the present invention also provides a kind of data filtering device based on FPGA, including:
Filtering module, the initial data for receiving specified quantity, according to the relative position relation between each initial data
It is numbered, and filtration treatment is carried out to initial data by filter algorithm, obtained filter data;
Relative position logging modle, for filter data is corresponding to number the relative position determined between filter data according to crossing
Relation;
Output module, for creating output array, and according to the relative position relation crossed between filter data by filter data
Write-in output array.
It is preferred that, the device further comprises:
Quantity logging modle, the quantity for record filtering data;
Then corresponding, the quantity of the memory cell in output array is identical with the quantity for crossing filter data.
It is preferred that, the device further comprises:
Two-dimensional array creation module, for creating two-dimensional array;
It is then corresponding, by the relative position relation between the first dimension record filtering data of two-dimensional array, pass through two
The quantity of second dimension record filtering data of dimension group.
It is preferred that, initial data is specially the initial data of float.
Data filtering method provided by the present invention based on FPGA, by the way that initial data is numbered, it is determined that every
Relative position of one target initial data where in all initial data.And pass through the filtering performed parallel in initial data
Algorithm was obtained after filter data, and the numbering according to where crossing the corresponding initial data of filter data determined relative between filter data
Position.In the method, the numbering according to where crossing the corresponding initial data of filter data determined the relative position between filter data
Put, equivalent to determination, each crosses filter data as relative position during initial data in data queue, to all filterings
The position that data carry out on the whole is determined, so as to ensure to cross the position relationship of filter data during each filtering data output with other
Do not changed compared to initial data.It can be seen that, this method avoids each filtering can not be determined after filter data was obtained
The corresponding relation of data and memory cell, and by it is multiple filtering data storage to same memory cell the problem of, it is ensured that mistake
The entirety of filter data sequentially meets the relative position in initial data.In addition, also ensure that will cross filter data write-in output number
Be not in covering or the loss between data during group, improve the security and availability of data.In addition, the present invention is also provided
A kind of data filtering device based on FPGA, corresponding with above-mentioned method, beneficial effect is as described above.
Brief description of the drawings
In order to illustrate the embodiments of the present invention more clearly, the required accompanying drawing used in embodiment will be done simply below
Introduce, it should be apparent that, drawings in the following description are only some embodiments of the present invention, for ordinary skill people
For member, on the premise of not paying creative work, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of flow chart of the data filtering method based on FPGA provided in an embodiment of the present invention;
Fig. 2 is the flow chart of another data filtering method based on FPGA provided in an embodiment of the present invention;
Fig. 3 is the schematic diagram in filtering data Ji Lu two-dimensional arrays;
Fig. 4 is a kind of data filtering device structure chart based on FPGA provided in an embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.Based on this
Embodiment in invention, those of ordinary skill in the art are not under the premise of creative work is made, and what is obtained is every other
Embodiment, belongs to the scope of the present invention.
The core of the present invention is to provide a kind of data filtering method and device based on FPGA, and raising enters line number under FPGA
During according to filtering, the security and availability of data.
In order that those skilled in the art more fully understand the present invention program, with reference to the accompanying drawings and detailed description
The present invention is described in further detail.
Embodiment one
Fig. 1 is a kind of flow chart of the data filtering method based on FPGA provided in an embodiment of the present invention.It refer to Fig. 1,
The specific steps of data filtering method based on FPGA include:
Step S10:The initial data of specified quantity is received, is compiled according to the relative position relation between each initial data
Number, and filtration treatment is carried out to initial data by filter algorithm, obtained filter data.
It is understood that the purpose for carrying out filtration treatment to initial data is by undesirable number in initial data
According to removal, other passed through should keep and filter between the data of filtering before identical relative position relation, and to original
The numbering that data carry out on position is the follow-up foundation for being used for judging relative position.It should be noted that the mode of numbering is preferred
Can use order digital or letter because numeral and letter all put in order, therefore, it is possible to more direct
Reflect the order between numbered initial data.
Step S11:The relative position relation between filter data was determined according to the corresponding numbering of filter data excessively.
This step can determine the position between filter data by crossing filter data numbering of position in initial data
Put relation.Each crosses the numbering that filter data corresponds to initial data, although filtering caused filter data can only corresponding part volume
Number, but position relationship still can be embodied between numbering, therefore the position between filter data still can be determined according to numbering
Put relation
Step S12:Output array is created, and it is according to the relative position relation crossed between filter data that filter data write-in is defeated
Go out array.
It is understood that by satisfactory data according to the suitable of the preceding relative position of filtering after being filtered to data
In the memory cell of sequence write-in array.Therefore, create output array as output data capsule, and by filter data according to
The output order determined before is exported, and follow-up for user is used.
Data filtering method provided by the present invention based on FPGA, by the way that initial data is numbered, it is determined that every
Relative position of one target initial data where in all initial data.And pass through the filtering performed parallel in initial data
Algorithm was obtained after filter data, and the numbering according to where crossing the corresponding initial data of filter data determined relative between filter data
Position.In the method, the numbering according to where crossing the corresponding initial data of filter data determined the relative position between filter data
Put, equivalent to determination, each crosses filter data as relative position during initial data in data queue, to all filterings
The position that data carry out on the whole is determined, so as to ensure to cross the position relationship of filter data during each filtering data output with other
Do not changed compared to initial data.It can be seen that, this method avoids each filtering can not be determined after filter data was obtained
The corresponding relation of data and memory cell, and by it is multiple filtering data storage to same memory cell the problem of, it is ensured that mistake
The entirety of filter data sequentially meets the relative position in initial data.In addition, also ensure that will cross filter data write-in output number
Be not in covering or the loss between data during group, improve the security and availability of data.
Embodiment two
Fig. 2 is the flow chart of another data filtering method based on FPGA provided in an embodiment of the present invention.Step in Fig. 2
S10-S12 is identical with Fig. 1, will not be repeated here.
As shown in Fig. 2 as a preferred embodiment, crossing the corresponding numbering of filter data in foundation determined filter data
Between relative position relation after, this method further comprises:
Step S20:The quantity of record filtering data.
Then corresponding, the quantity of the memory cell in output array is identical with the quantity for crossing filter data.
It is understood that the quantity of record filtering data is partly in order to the filtering situation of statistics, follow-up
Reference role is served during to the use or processing of data.The purpose of another aspect is to determine output according to the quantity for crossing filter data
The quantity of the memory cell of array, that is, export the size of array, so has in all filter datas of crossing of guarantee in output array
While memory cell, it also can accordingly reduce and extra resource overhead is brought to system because creating unnecessary storage list.
As shown in Fig. 2 as a preferred embodiment, crossing the corresponding numbering of filter data in foundation determined filter data
Between relative position relation before, this method further comprises:
Step S21:Create two-dimensional array.
It is then corresponding, by the relative position relation between the first dimension record filtering data of two-dimensional array, pass through two
The quantity of second dimension record filtering data of dimension group.
In this step, equivalent to one container cached of two-dimensional array will be distributed and perform what filter algorithm was obtained
Data Integration is filtered in two-dimensional array.After filter data was obtained, filter data is remembered according to each numbering for crossing filter data
Record in the first dimension with the corresponding position of numbering.Further, since the order for obtaining filter data is uncertain, therefore two
The number that filter data is crossed when obtaining filter data is recorded in second dimension of dimension group, for being carried out to the quantity for crossing filter data
The subsequent operations such as statistics.It can be seen that, it is follow-up overall for convenience and accurately by data using two-dimensional array record filtering data
Write-in output array.It should be noted that this step and step S10 execution sequence are not fixed simultaneously, naturally it is also possible to perform,
Do not limit herein.
For convenience to the understanding of above-mentioned steps, Fig. 3 refer to.As shown in Figure 3, it is filtering data Ji Lu two-dimemsional numbers
Schematic diagram in group.The first dimension (transverse axis) in figure in two-dimensional array, it is corresponding be by the numbering of filtration treatment be 1-8's
8 initial data, it is to be understood that the data that numbering is 2,6,8 are removed after filtration treatment, remaining filtering number
Position relationship during according to still according to initial data is arranged in two-dimensional array.The second dimension in figure in two-dimensional array
(longitudinal axis), corresponding was the quantity of filter data, it is to be understood that filtration treatment there remains five data after terminating, therefore
Each point in two-dimensional array just accordingly correspond to the 1-5 data, and each puts that represent was filter data.Can
See, can accurately determine that filter data was written into the position of output array according to the record of two-dimensional array.
In addition, as a preferred embodiment, the initial data for receiving specified quantity is specially:
Receive the initial data that incoming specified quantity is cached by DDR.
Because DDR can carry out read/write operation twice within a clock cycle, therefore FPGA obtains data from DDR
When, DDR execution speed faster, with higher efficiency, saves expense in time.
In addition, as a preferred embodiment, initial data is specially the initial data of float.
It is understood that filtering is to exceed the data of prescribed limit to remove, and defined model in a practical situation
Enclose often very small, therefore the initial data filtered is universal all in prescribed limit or close to the vicinity point of prescribed limit
Differed between cloth, therefore initial data small.Because floating type can more accurately embody the value of initial data, therefore it can fit
For more accurately filtration treatment in actual conditions.
In addition, as a preferred embodiment, specified quantity is specially 8.
The quantity of initial data per treatment depending on the specific performance according to current FPGA, can be defined as the purpose of 8
It is in order to adaptable with universal FPGA performances.It is understood that the specified quantity it is not strictly necessary that, other implementation
In example, other quantity are can also be.
Embodiment three
Hereinbefore the embodiment for the data filtering method based on FPGA is described in detail, and the present invention is also carried
For a kind of data filtering device based on FPGA, because the embodiment of device part and the embodiment of method part are mutually corresponding,
Therefore the embodiment of device part refers to the description of the embodiment of method part, wouldn't repeat here.
Fig. 4 is a kind of data filtering device structure chart based on FPGA provided in an embodiment of the present invention.The embodiment of the present invention
A kind of data filtering device based on FPGA provided, including:
Filtering module 10, the initial data for receiving specified quantity is closed according to the relative position between each initial data
System is numbered, and carries out filtration treatment to initial data by filter algorithm, obtains filter data.
Relative position logging modle 11, for filter data is corresponding to number the relative position determined between filter data according to crossing
Put relation.
Output module 12, number will be filtered for creating output array, and according to the relative position relation crossed between filter data
Array is exported according to write-in.
Data filtering device provided by the present invention based on FPGA, by the way that initial data is numbered, it is determined that every
Relative position of one target initial data where in all initial data.And pass through the filtering performed parallel in initial data
Algorithm was obtained after filter data, and the numbering according to where crossing the corresponding initial data of filter data determined relative between filter data
Position.In the present apparatus, the numbering according to where crossing the corresponding initial data of filter data determined the relative position between filter data
Put, equivalent to determination, each crosses filter data as relative position during initial data in data queue, to all filterings
The position that data carry out on the whole is determined, so as to ensure to cross the position relationship of filter data during each filtering data output with other
Do not changed compared to initial data.It can be seen that, present arrangement avoids each filtering can not be determined after filter data was obtained
The corresponding relation of data and memory cell, and by it is multiple filtering data storage to same memory cell the problem of, it is ensured that mistake
The entirety of filter data sequentially meets the relative position in initial data.In addition, also ensure that will cross filter data write-in output number
Be not in covering or the loss between data during group, improve the security and availability of data.
On the basis of embodiment three, the device further comprises:
Quantity logging modle, the quantity for record filtering data;
Then corresponding, the quantity of the memory cell in output array is identical with the quantity for crossing filter data.
On the basis of embodiment three, the device further comprises:
Two-dimensional array creation module, for creating two-dimensional array;
It is then corresponding, by the relative position relation between the first dimension record filtering data of two-dimensional array, pass through two
The quantity of second dimension record filtering data of dimension group.
On the basis of embodiment three, as a preferred embodiment, initial data is specially float
Initial data.
A kind of data filtering method and device based on FPGA provided by the present invention are described in detail above.Say
Each embodiment is described by the way of progressive in bright book, and what each embodiment was stressed is the difference with other embodiment
Between part, each embodiment identical similar portion mutually referring to.For device disclosed in embodiment, due to its with
Method is corresponding disclosed in embodiment, so description is fairly simple, related part is referring to method part illustration.It should refer to
Go out, for those skilled in the art, under the premise without departing from the principles of the invention, can also be to the present invention
Some improvement and modification are carried out, these are improved and modification is also fallen into the protection domain of the claims in the present invention.
It should also be noted that, in this manual, such as first and second or the like relational terms be used merely to by
One entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between there is any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant meaning
Covering including for nonexcludability, so that process, method, article or equipment including a series of key elements not only include that
A little key elements, but also other key elements including being not expressly set out, or also include be this process, method, article or
The intrinsic key element of equipment.In the absence of more restrictions, the key element limited by sentence "including a ...", is not arranged
Except also there is other identical element in the process including the key element, method, article or equipment.
Claims (10)
1. a kind of data filtering method based on FPGA, it is characterised in that including:
The initial data of specified quantity is received, is numbered according to the relative position relation between each initial data, and lead to
Cross filter algorithm and filtration treatment is carried out to the initial data, obtain filter data;
The relative position relation crossed between filter data is determined according to the corresponding numbering of filter data of crossing;
Create output array, and according to it is described cross filter data between relative position relation by it is described cross filter data write-in it is described defeated
Go out array.
2. according to the method described in claim 1, it is characterised in that described according to the corresponding numbering of the filter data excessively
Determine after the relative position relation between the filter data excessively, this method further comprises:
Record the quantity for crossing filter data;
Then corresponding, the quantity of the memory cell in the output array is identical with the quantity for crossing filter data.
3. method according to claim 2, it is characterised in that described according to the corresponding numbering of the filter data excessively
Determine before the relative position relation between the filter data excessively, this method further comprises:
Create two-dimensional array;
It is then corresponding, the relative position relation crossed between filter data is recorded by the first dimension of the two-dimensional array, led to
The second dimension for crossing the two-dimensional array records the quantity for crossing filter data.
4. the method according to claims 1 to 3 any one, it is characterised in that the original number of the reception specified quantity
According to specially:
Receive the initial data that incoming specified quantity is cached by DDR.
5. the method according to claims 1 to 3 any one, it is characterised in that the initial data is specially floating number
The initial data of type.
6. the method according to claims 1 to 3 any one, it is characterised in that the specified quantity is specially 8.
7. a kind of data filtering device based on FPGA, it is characterised in that including:
Filtering module, the initial data for receiving specified quantity, according to the relative position relation between each initial data
It is numbered, and filtration treatment is carried out to the initial data by filter algorithm, obtained filter data;
Relative position logging modle, for determining described cross between filter data according to the corresponding numbering of filter data of crossing
Relative position relation;
Output module, for creating output array, and according to the relative position relation crossed between filter data by the filtering
Data write the output array.
8. device according to claim 7, it is characterised in that the device further comprises:
Quantity logging modle, for recording the quantity for crossing filter data;
Then corresponding, the quantity of the memory cell in the output array is identical with the quantity for crossing filter data.
9. device according to claim 7, it is characterised in that the device further comprises:
Two-dimensional array creation module, for creating two-dimensional array;
It is then corresponding, the relative position relation crossed between filter data is recorded by the first dimension of the two-dimensional array, led to
The second dimension for crossing the two-dimensional array records the quantity for crossing filter data.
10. device according to claim 7, it is characterised in that the initial data is specially the original of float
Data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710551317.8A CN107330106B (en) | 2017-07-07 | 2017-07-07 | Data filtering method and device based on FPGA |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710551317.8A CN107330106B (en) | 2017-07-07 | 2017-07-07 | Data filtering method and device based on FPGA |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107330106A true CN107330106A (en) | 2017-11-07 |
CN107330106B CN107330106B (en) | 2020-11-20 |
Family
ID=60196974
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710551317.8A Active CN107330106B (en) | 2017-07-07 | 2017-07-07 | Data filtering method and device based on FPGA |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107330106B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5086408A (en) * | 1987-05-13 | 1992-02-04 | Hitachi, Ltd. | Method and apparatus for merging |
CN102314336A (en) * | 2010-07-05 | 2012-01-11 | 深圳市腾讯计算机系统有限公司 | Data processing method and system |
CN105117402A (en) * | 2015-07-16 | 2015-12-02 | 中国人民大学 | Log data fragmentation method based on segment order-preserving Hash and log data fragmentation device based on segment order-preserving Hash |
CN106383695A (en) * | 2016-09-14 | 2017-02-08 | 中国科学技术大学苏州研究院 | FPGA-based clustering algorithm acceleration system and design method thereof |
CN106776456A (en) * | 2017-01-18 | 2017-05-31 | 中国人民解放军国防科学技术大学 | High speed matching regular expressions hybrid system and method based on FPGA+NPU |
CN106815343A (en) * | 2017-01-16 | 2017-06-09 | 上海小海龟科技有限公司 | A kind of data processing method and data processing equipment |
-
2017
- 2017-07-07 CN CN201710551317.8A patent/CN107330106B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5086408A (en) * | 1987-05-13 | 1992-02-04 | Hitachi, Ltd. | Method and apparatus for merging |
CN102314336A (en) * | 2010-07-05 | 2012-01-11 | 深圳市腾讯计算机系统有限公司 | Data processing method and system |
CN105117402A (en) * | 2015-07-16 | 2015-12-02 | 中国人民大学 | Log data fragmentation method based on segment order-preserving Hash and log data fragmentation device based on segment order-preserving Hash |
CN106383695A (en) * | 2016-09-14 | 2017-02-08 | 中国科学技术大学苏州研究院 | FPGA-based clustering algorithm acceleration system and design method thereof |
CN106815343A (en) * | 2017-01-16 | 2017-06-09 | 上海小海龟科技有限公司 | A kind of data processing method and data processing equipment |
CN106776456A (en) * | 2017-01-18 | 2017-05-31 | 中国人民解放军国防科学技术大学 | High speed matching regular expressions hybrid system and method based on FPGA+NPU |
Also Published As
Publication number | Publication date |
---|---|
CN107330106B (en) | 2020-11-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104111870B (en) | Interrupt processing device and method | |
CN105825191A (en) | Face multi-attribute information-based gender recognition method and system and shooting terminal | |
CN107547433A (en) | The method, apparatus and equipment of current limliting are carried out based on Token Bucket | |
CN103324466B (en) | Data dependency serialization IO parallel processing method | |
CN108108217A (en) | Method and device for cutting long screen | |
WO2010135939A1 (en) | Handwriting input method and device for mobile terminal and mobile terminal | |
CN107070897A (en) | Network log storage method based on many attribute Hash duplicate removals in intruding detection system | |
CN101866277B (en) | Data reordering method and device | |
CN102629235A (en) | Method for increasing read-write speed of double data rate (DDR) memory | |
CN103473191A (en) | Interrupt processing method, device and system | |
CN107769755A (en) | A kind of design method of parallel FIR decimation filters and parallel FIR decimation filters | |
CN107330106A (en) | A kind of data filtering method and device based on FPGA | |
CN104811407B (en) | Communication means and system, signal of communication method of reseptance and device | |
CN110414450A (en) | Keyword detection method, apparatus, storage medium and electronic equipment | |
CN106802787A (en) | MapReduce optimization methods based on GPU sequences | |
CN107832852A (en) | Data processing learning method, system and electronic equipment | |
CN107463340A (en) | The data-storage system of computer | |
CN106991083A (en) | A kind of method and device of electronic document processing | |
CN104750621A (en) | Caching method and control system | |
CN104730307B (en) | Tonal gradation digital oscilloscope and its waveform processing module and method | |
CN110059312A (en) | Short phrase picking method, apparatus and electronic equipment | |
CN103425558A (en) | Method for achieving board card IO port test based on test configuration table | |
CN112731558B (en) | Joint inversion method and device for seismic surface wave and receiving function | |
CN104144310B (en) | Ultra high-definition image in different resolution treating method and apparatus | |
CN107357739A (en) | A kind of method and apparatus of data internal sort |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20201102 Address after: 215100 No. 1 Guanpu Road, Guoxiang Street, Wuzhong Economic Development Zone, Suzhou City, Jiangsu Province Applicant after: SUZHOU LANGCHAO INTELLIGENT TECHNOLOGY Co.,Ltd. Address before: 450018 Henan province Zheng Dong New District of Zhengzhou City Xinyi Road No. 278 16 floor room 1601 Applicant before: ZHENGZHOU YUNHAI INFORMATION TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |