CN205451035U - Image processing buffer memory system - Google Patents
Image processing buffer memory system Download PDFInfo
- Publication number
- CN205451035U CN205451035U CN201620173899.1U CN201620173899U CN205451035U CN 205451035 U CN205451035 U CN 205451035U CN 201620173899 U CN201620173899 U CN 201620173899U CN 205451035 U CN205451035 U CN 205451035U
- Authority
- CN
- China
- Prior art keywords
- module
- view data
- image
- image processing
- image procossing
- 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.)
- Withdrawn - After Issue
Links
- 238000000034 method Methods 0.000 claims description 15
- 230000007087 memory ability Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
Landscapes
- Image Input (AREA)
- Image Processing (AREA)
Abstract
The utility model discloses an image processing buffer memory system, including reading control module, with read the image processing module that control module links to each other, the output cache module who links to each other with image processing module and the screen drive module that links to each other of output cache module, read control module and judge whether the screen output has the image data order of looking ahead, if have, then be based on look ahead order and passing through of image data image processing module is write in into after handling image data output cache module, output cache module basis image data looks ahead the image data of order after will handling and exports to screen drive module. The utility model discloses make required buffer memory memory cell reduce, and can reduce the unstable situation of chronogenesis when data fetching, under the circumstances that does not increase required data bandwidth, strengthened the buffer memory ability.
Description
Technical field
This utility model relates to image processing field, particularly relates to a kind of image procossing caching system.
Background technology
In image processing process, generally require and multiple figure layers are done overlap-add operation, during outputing image to screen, need the view data ensureing output continuous and complete, and original digital image data by memory space read the sequential of graphics processing unit be probably indefinite, especially when the situation having multiple master control can operate memory space, it is thus desirable in advance a part of view data is read graphics processing unit before output starts to do pretreatment, carry out the situation that the floating sequential fetched data is unstable.
In the prior art, the method of the pre-processing image data typically taked is that the data of the layer by there is a need to overlap-add operation read in corresponding caching the most in advance, the length of pre-read is probably two row (during zoom operations), a line or hemistich, need to carry out image procossing again during output, and needs image resolution ratio is more and more higher when, required data buffer storage will be multiplied, thus chip cost is caused to be significantly increased.
Utility model content
The purpose of this utility model is to overcome the deficiencies in the prior art, there is provided a kind of image procossing caching system so that required buffer memory unit reduces, and can reduce sequential unsteady phenomena when fetching data, in the case of not increasing desired data bandwidth, enhance caching capabilities.
The purpose of this utility model is achieved through the following technical solutions: a kind of image procossing caching system, including reading control module, the image processing module being connected with reading control module, the output buffer module being connected with image processing module and the screen being connected with output buffer module drive module, described reading control module judges whether screen outfan has view data prefetched command, if had, then write described output buffer module according to described view data prefetched command and after view data being processed by described image processing module, view data output after described output buffer module will process according to described view data prefetched command drives module to described screen.
Described reading control module includes for determining whether described view data prefetched command and reading the access submodule of row data according to described view data prefetched command.
Whether described image processing module includes arranging submodule for the parameter arranging figure layer parameter, being judging submodule and controlling submodule for carrying out the operation of image manipulation process according to described view data prefetched command of last column for judging whether to have in described view data prefetched command the row data of overlap-add operation and reading.
Described figure layer parameter includes the image procossing maximum superposition number of plies, view data address and image procossing mode.
Described image procossing mode includes overlap-add operation, zoom operations and brightness adjustment operation, and described image manipulation processes and includes that image overlay operation process and image scale operation process.
The beneficial effects of the utility model are: required buffer memory unit is reduced, and can reduce sequential unsteady phenomena when fetching data, in the case of not increasing desired data bandwidth, enhance caching capabilities.
Accompanying drawing explanation
Fig. 1 is the system architecture diagram of this utility model image procossing caching system；
Fig. 2 is the workflow diagram of this utility model image procossing caching system.
Detailed description of the invention
The technical solution of the utility model is described in further detail below in conjunction with the accompanying drawings, but protection domain of the present utility model is not limited to the following stated.
As shown in Figure 1, Fig. 1 is the system architecture diagram of this utility model image procossing caching system, this utility model image procossing caching system includes reading control module, the image processing module being connected with reading control module, the output buffer module being connected with image processing module and the screen being connected with output buffer module drive module, read control module and judge whether screen outfan has view data prefetched command, if had, output buffer module is write according to view data prefetched command after then view data being processed by image processing module, view data output after output buffer module will process according to view data prefetched command drives module to screen.
Wherein, read control module to include accessing submodule, for determining whether view data prefetched command and reading row data according to view data prefetched command, image processing module includes that parameter arranges submodule, judge that submodule and operation control submodule, parameter arranges submodule for arranging figure layer parameter, including the view data maximum superposition number of plies, view data address and image procossing mode (include overlap-add operation, zoom operations, brightness adjustment operation etc.), judge whether submodule is last column for judging whether to have in view data prefetched command the row data of overlap-add operation and reading, operation controls submodule for carrying out image overlay according to view data prefetched command, image scalings etc. operate.
As in figure 2 it is shown, the workflow diagram that Fig. 2 is this utility model image procossing caching system, comprise the following steps:
Step one, action starts.
Step 2, arranges submodule by the parameter of image processing module and arranges figure layer parameter, including the image procossing maximum superposition number of plies, view data address and image procossing mode (including overlap-add operation, zoom operations, brightness adjustment operation etc.).
By reading control module, step 3, judges whether screen outfan has view data prefetched command, i.e. judges whether screen outfan there is a need to the requirement of display, if it is, enter next step；If it is not, then continue executing with this step.
Step 4, judges submodule to judge in view data prefetched command whether to have overlap-add operation by image processing module, if it is, read the row data of there is a need to superimposed layer by reading the access submodule of control module, enters next step；If it is not, then read the row data of the display layer needing display by reading the access submodule of control module, enter next step.
Step 5, controls submodule according to view data prefetched command by the operation of image processing module and carries out image manipulation process, and including image overlay operation, image scale operation etc., operation processes.
Step 6, writes output buffer module after being processed view data by image processing module.
Step 7, the view data output after being processed according to view data prefetched command by output buffer module drives module to screen；That passes through image processing module judges that submodule judges whether the row data read are last column, if it is, enter next step simultaneously；If it is not, then return step 4.
By reading control module, step 8, judges whether screen outfan has tenth skill order, if it is, release；If it is not, then return step 2.
This utility model image procossing caching system compared with prior art, has the advantage that 1. are no longer necessary to each layer and all cache complete a line so that required buffer memory unit is reduced to nearly 1/n (n is the maximum superposition number of plies)；The data cached the most in advance are regular length (1 row or 2 row), it is to avoid be likely to be due to zoom operations in prior art and the situation of the data cached minimizing of actual output that causes, can reduce sequential unsteady phenomena when fetching data；3., in the case of not increasing desired data bandwidth, enhance caching capabilities.
In sum, this utility model image procossing caching system so that required buffer memory unit reduces, and can reduce sequential unsteady phenomena when fetching data, and in the case of not increasing desired data bandwidth, enhances caching capabilities.
Claims (5)
1. an image procossing caching system, it is characterized in that: described image procossing caching system includes reading control module, the image processing module being connected with reading control module, the output buffer module being connected with image processing module and the screen being connected with output buffer module drive module, described reading control module judges whether screen outfan has view data prefetched command, if had, then write described output buffer module according to described view data prefetched command and after view data being processed by described image processing module, view data output after described output buffer module will process according to described view data prefetched command drives module to described screen.
Image procossing caching system the most according to claim 1, it is characterised in that: described reading control module includes for determining whether described view data prefetched command and reading the access submodule of row data according to described view data prefetched command.
Image procossing caching system the most according to claim 2, it is characterised in that: whether described image processing module includes arranging submodule for the parameter arranging figure layer parameter, being judging submodule and controlling submodule for carrying out the operation of image manipulation process according to described view data prefetched command of last column for judging whether to have in described view data prefetched command the row data of overlap-add operation and reading.
Image procossing caching system the most according to claim 3, it is characterised in that: described figure layer parameter includes the image procossing maximum superposition number of plies, view data address and image procossing mode.
Image procossing caching system the most according to claim 4, it is characterised in that: described image procossing mode includes overlap-add operation, zoom operations and brightness adjustment operation, and described image manipulation processes and includes that image overlay operation process and image scale operation process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620173899.1U CN205451035U (en) | 2016-03-08 | 2016-03-08 | Image processing buffer memory system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201620173899.1U CN205451035U (en) | 2016-03-08 | 2016-03-08 | Image processing buffer memory system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN205451035U true CN205451035U (en) | 2016-08-10 |
Family
ID=56605229
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201620173899.1U Withdrawn - After Issue CN205451035U (en) | 2016-03-08 | 2016-03-08 | Image processing buffer memory system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN205451035U (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107168660A (en) * | 2016-03-08 | 2017-09-15 | 成都锐成芯微科技股份有限公司 | Image procossing caching system and method |
| CN112422832A (en) * | 2020-11-20 | 2021-02-26 | 展讯通信(天津)有限公司 | Image data transmission method, mobile terminal and storage medium |
-
2016
- 2016-03-08 CN CN201620173899.1U patent/CN205451035U/en not_active Withdrawn - After Issue
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107168660A (en) * | 2016-03-08 | 2017-09-15 | 成都锐成芯微科技股份有限公司 | Image procossing caching system and method |
| CN107168660B (en) * | 2016-03-08 | 2024-05-10 | 成都锐成芯微科技股份有限公司 | Image processing cache system and method |
| CN112422832A (en) * | 2020-11-20 | 2021-02-26 | 展讯通信(天津)有限公司 | Image data transmission method, mobile terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9472018B2 (en) | Graphics processing systems | |
| US9105112B2 (en) | Power management for image scaling circuitry | |
| US20150186278A1 (en) | Runtime persistence | |
| KR101350541B1 (en) | Prefetch instruction | |
| US10261796B2 (en) | Processor and method for executing in-memory copy instructions indicating on-chip or off-chip memory | |
| US20150084983A1 (en) | Method and apparatus for generating an output surface from one or more input surfaces in data processing systems | |
| US20210065657A1 (en) | Apparatus and Method for Command Stream Optimization and Enhancement | |
| US20170024138A1 (en) | Memory management | |
| CN205451035U (en) | Image processing buffer memory system | |
| US9058301B2 (en) | Efficient transfer of matrices for matrix based operations | |
| US20160373757A1 (en) | Analytics Assisted Encoding | |
| CN106681659A (en) | Data compression method and device | |
| WO2020199489A1 (en) | Dual-interface architecture suitable for nvme namespace configuration | |
| US10613987B2 (en) | Operand cache coherence for SIMD processor supporting predication | |
| US20180067852A1 (en) | Polarity based data transfer function for volatile memory | |
| CN112148366A (en) | FLASH acceleration method for reducing power consumption and improving performance of chip | |
| CN107168660B (en) | Image processing cache system and method | |
| CN1821944A (en) | Method for writing data into memory and the control device | |
| US10936047B2 (en) | Power state management | |
| CN112115075A (en) | Memory access | |
| US9990142B2 (en) | Mass storage system and method of storing mass data | |
| US20060294316A1 (en) | Selectively prefetch method and bridge module | |
| US11972504B2 (en) | Method and system for overlapping sliding window segmentation of image based on FPGA | |
| US20160180909A1 (en) | Write operations in spin transfer torque memory | |
| WO2024118071A1 (en) | Reduced power consumption in machine learning models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| AV01 | Patent right actively abandoned |
Granted publication date: 20160810 Effective date of abandoning: 20240510 |
|
| AV01 | Patent right actively abandoned |
Granted publication date: 20160810 Effective date of abandoning: 20240510 |
|
| AV01 | Patent right actively abandoned | ||
| AV01 | Patent right actively abandoned |