CN201765584U - Device for sending general calculation data of graphics processing unit with digital visual interface (DVI) - Google Patents
Device for sending general calculation data of graphics processing unit with digital visual interface (DVI) Download PDFInfo
- Publication number
- CN201765584U CN201765584U CN2010201530638U CN201020153063U CN201765584U CN 201765584 U CN201765584 U CN 201765584U CN 2010201530638 U CN2010201530638 U CN 2010201530638U CN 201020153063 U CN201020153063 U CN 201020153063U CN 201765584 U CN201765584 U CN 201765584U
- Authority
- CN
- China
- Prior art keywords
- data
- module
- texture
- dvi
- result data
- 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.)
- Expired - Lifetime
Links
Images
Landscapes
- Image Processing (AREA)
- Controls And Circuits For Display Device (AREA)
Abstract
The utility model relates to a device for sending general calculation data of a graphics processing unit with a digital visual interface (DVI). The device comprises a graphics card and a virtual display module, wherein the graphics card comprises a texture establishing module, a texture binding module, a vertical synchronization signal monitoring module, a DVI and a kernel program computation module. The kernel program computation module calculates initial data; the texture binding module can bind the calculated result data and a texture; the calculated result data can be transmitted to the virtual display module by the DVI; a vertical synchronization (VSYNC) signal contained in the result data can be monitored by the vertical synchronization signal monitoring module; once one VSYNC signal is monitored, the kernel program computation module can be started for the calculation of the next frame; and the result data can be converted to a parallel peripheral device interface format by the virtual display module. The device can send the general calculated result data of a graphics processing unit (GPU) by utilizing the DVI and does not need a main memory of a system as transfer, thereby saving the storage space of a computer and reducing the delay of general calculation process of the GPU at the same time.
Description
Technical field
The utility model relates to field of data transmission, particularly about utilizing the DVI interface to send the device of graphic process unit general-purpose computations data.
Background technology
Raising along with Modern Graphic processor (GPU Graphic Processing Unit) programmability and performance, GPU can be integrated with hundreds of simple computation engines---tinter, these tinters make GPU not only can be used as drawing engine, and can be used as the computing engines of PC, promptly utilize GPU to carry out general parallel computation.The existing application programming interfaces that are used to support GPU to carry out general parallel computation have CUDA, OpenCL and DirectCompute.Under the support of these application programming interfaces, GPU can realize general parallel computation, and the computation model of following computing machine will develop to the Heterogeneous Computing model, promptly use CPU and GPU application programs to handle simultaneously: the order part of application program is moved on CPU, and the computation-intensive part is moved on GPU.Using GPU to calculate can be than using CPU to calculate fast 2 to 10 times, and the user will obviously experience the quickening of program operation speed, and reduce the energy consumption of system.
When GPU is used for general parallel computation, the data after the GPU processing need be sent to commercial unit or instrument to be used for control or to be further processed.The method of the result data after the transmission process at present is: as shown in Figure 1, at first GPU reads raw data and raw data is calculated from video memory, GPU deposits calculation result data in the video memory in then, CPU records a demerit the calculating in the video memory copying data again to the main memory of system, and system hosts sends to peripherals by the PCI-E bus with result data.
The defective of this data transfer mode is: because system sends result data to peripherals with main memory as transfer, therefore when the data volume of result of calculation is very big, will causes transmission delay, and waste the memory source and the cpu resource of computing machine; In addition, because PCI-E bus width commonly used is limited, therefore can't satisfy the demand (for example video flow processing application, digital modulation, software radio, radar system, computed tomography and ultrasonic imaging etc.) that some have the application apparatus of big bandwidth, simultaneously, because the delay of PCI-E bus is unfixing, make the input and output of data in the video memory can not be synchronous, directly influence the processing speed of GPU general parallel computation.
Therefore be necessary the transmission mode of existing GPU calculation result data is improved, the delay between input raw data and the output result data reduced, and save the storage space of computing machine, the efficient of data transmission is improved.
Summary of the invention
Introduced the notion of a series of reduced forms in the summary of the invention part, this will further describe in the embodiment part.Summary of the invention part of the present utility model does not also mean that key feature and the essential features that will attempt to limit technical scheme required for protection, does not more mean that the protection domain of attempting to determine technical scheme required for protection.
The invention provides the device that a kind of DVI of utilization interface sends graphic process unit general-purpose computations data, it is characterized in that comprising:
Graphics card, described graphics card comprises: texture is set up module, sets up a texture, and the preservation texture pointer corresponding with described texture; The kernel program computing module calculates result data to raw data; The texture binding module receives the result data that sends from described kernel program computing module, and sets up the described texture pointer that module sends from described texture, with described result data and the binding of described texture pointer; The DVI interface receives the described result data after the binding that sends from described texture binding module; The vertical synchronizing signal monitoring modular receives the result data after the described binding that sends from described DVI interface, and sends enabling signal to described kernel program computing module;
Described device also comprises, the virtual monitor module, and the result data that described DVI interface is sent after the described binding carries out Data Format Transform.
According to an aspect of the present invention, it is characterized in that described virtual monitor module comprises: the Data Format Transform module sends to peripherals after the result data after the described binding being converted to the data of parallel suitable peripheral interface form.
According to an aspect of the present invention, it is characterized in that described virtual monitor module also comprises extending display identification data ROM (read-only memory), described extending display identification data ROM (read-only memory) sends the resolution of image and the numerical value of refresh rate arrives described graphics card.
According to an aspect of the present invention, it is characterized in that described Data Format Transform module adopts programmable gate array to realize.
According to an aspect of the present invention, it is characterized in that described virtual monitor module adopts programmable gate array to realize the resolution of described programmable gate array memory image and refresh rate.
According to an aspect of the present invention, it is characterized in that the described chip that data can be converted to parallel form is the SiI163B chip.
According to an aspect of the present invention, it is characterized in that, the result data of described vertical synchronizing signal monitoring modular after to described binding carries out the vertical synchronizing signal monitoring, if monitor described vertical synchronizing signal, then sends enabling signal to described kernel program computing module.
According to an aspect of the present invention, it is characterized in that, can increase the number of opening described DVI interface, and described Data Format Transform modular design is the whole DVI interfaces of connection according to the increase of resolution.
According to an aspect of the present invention, it is characterized in that described extending display identification data ROM (read-only memory) and described Data Format Transform module are provided with independently of one another.
The utility model utilizes the DVI interface on the graphics card to send the GPU calculation result data, then result data is converted to the data that are fit to the peripheral interface form, therefore need not be by system hosts as transfer, improve GPU general-purpose computations travelling speed, saved the memory source of computing machine simultaneously.In addition, utilize the broader bandwidth of DVI interface transmission data, can satisfy the demand of big bandwidth peripherals.
Description of drawings
Following accompanying drawing of the present utility model is used to understand the utility model at this as a part of the present utility model.Embodiment of the present utility model and description thereof have been shown in the accompanying drawing, have been used for explaining principle of the present utility model.In the accompanying drawings,
Fig. 1 is a graphic process unit calculation result data output principle synoptic diagram of the prior art;
Fig. 2 is a structural representation of the present utility model.
Embodiment
In the following description, a large amount of concrete details have been provided so that more thorough understanding of the invention is provided.Yet, it will be apparent to one skilled in the art that the utility model can need not one or more these details and implemented.In other example,, be not described for technical characterictics more well known in the art for fear of obscuring with the utility model.
Obviously, execution of the present utility model is not limited to the specific details that those skilled in the art has the knack of.Preferred embodiment of the present utility model is described in detail as follows, yet except these were described in detail, the utility model can also have other embodiments.
The utility model is that platform is realized with the graphics card that has DVI (Digital Visual Interface digital visual interface) interface.Described graphics card means the computer fittings of the interface that comprises GPU, display buffer (abbreviation video memory), BIOS (Basic Input Output System Basic Input or Output System (BIOS)), digital analog converter (RAMDAC Random Access Memory Digital-to-Analog Converter), graphics card basically and electric capacity, resistance etc.
As shown in Figure 2, the device according to transmission graphic process unit general-purpose computations data of the present utility model comprises graphics card 201 and virtual monitor module 202.Wherein graphics card 201 comprises: a texture is set up module 201a, a texture binding module 201b, a vertical synchronizing signal monitoring modular 201c, a DVI interface 201d and a kernel program computing module 201e.Wherein, the output terminal that texture is set up module 201a connects input end and the video memory 201f of texture binding module 201b respectively, and texture is set up module 201a and set up a texture in video memory 201f, and sends the texture signal-arm to texture binding module 201b.The input end of kernel program computing module 201e connects the output terminal of video memory 201f, and kernel program computing module 201e reads the raw data among the described video memory 201f.The output terminal of kernel program computing module 201e connects the input end of texture binding module 201b, and the result data that kernel program computing module 201e is calculated sends texture binding module 201b to.The output terminal of texture binding module 201b connects the input end of DVI interface 201d, and the result data after texture binding module 201b will bind sends DVI interface 201d to.The output terminal of DVI interface 201d connects the input end of vertical synchronizing signal monitoring modular 201c, sends the result data after the binding to vertical synchronizing signal monitoring modular 201c from DVI interface 201d.The output terminal of vertical synchronizing signal monitoring modular 201c connects the input end of kernel program computing module 201e, and enabling signal is sent to kernel program computing module 201e.The effect of graphics card 201 is with result data and texture binding." texture " is a kind of bitmap of storage surface material color, and final scene of drawing may be displayed on the output device.Result data after will binding is again sent out graphics card 201 with the form of texture by DVI interface 201d.
The effect of virtual monitor module 202 is as virtual " display ", because DVI interface 201d is the interface of transmitting display signal therefor, therefore have only when receiving trap is display device, DVI interface 201d can send data to receiving trap, and promptly the virtual monitor module 202.And then with the Data Format Transform of the result data that receives for being fit to external unit 203 interface formats.The utility model must deposit the resolution and the refresh rate of virtual " display " among the EDID ROM202b in before use, and GPU reads the data among the EDID ROM202b one time then, and graphics card 201 thinks that promptly virtual monitor module 202 is one " displays ".Principle of work of the present utility model is:
(1) texture is set up module 201a and is utilized OpenGL (Open Graphics Library) or Direct3D (Direct 3D is based on the 3D graphical application DLL (dynamic link library) of the general object pattern (COM Common ObjectMode) of Microsoft) to set up a texture in video memory 201f, the size of texture is less than or equal to output resolution ratio (size that is texture is for holding frame data), then the texture pointer is sent to texture binding module 201b;
(2) kernel program computing module 201e calculates the raw data that reads from video memory 201f, and sends the result data that calculates to texture binding module 201b;
(3) texture binding module 201b is placed on result data in the texture pointer texture pointed, and will send DVI interface 201d to the result data after the texture binding;
(4) DVI interface 201d sends to Data Format Transform module 202a with result data, vertical synchronizing signal judge module 201c judges whether the result data that sends from DVI interface 201d comprises vertical synchronizing signal (VSYNC Vertical Synchronization), if comprise, then send enabling signal to kernel program computing module 201e, repeat (2) then, if do not comprise, then continue the result data among the DVI interface 201d is monitored;
(5) Data Format Transform module 202a is converted to parallel form with result data, again the result data of parallel form is converted to the data layout that is fit to peripherals 203 interfaces, sends the local bus of result data by peripherals 203 to peripherals 203 at last.
Above-mentioned virtual monitor module 202 can adopt FPGA (Field Programmable Gate Array programmable gate array) to realize, i.e. integrated EDID ROM 202b and Data Format Transform module 202a on a FPGA, Data Format Transform module 202a is converted to parallel peripheral interface form with result data.Virtual monitor module 202 can also adopt the chip (for example SiI163B chip) and the combination of FPGA that data can be converted to parallel form to realize.Wherein, the chip that data can be converted to parallel form is used for result data is converted to parallel form, and FPGA is used for the result data of parallel form is converted to the data layout that is fit to peripherals 203 interfaces.At this moment, EDID ROM 202b is independent of the FPGA setting; The perhaps resolution of FPGA stored " display " and the numerical value of refresh rate, thus EDID ROM 202b need not be set.
In the foregoing description, DVI interface 201d is the DVI interface (Single-link DVI) of strand knot.In fact, can open a plurality of above-mentioned DVI interface 201d along with the increase of resolution, as open two strands and tie DVI (Dual-link DVI) interface or two double-stranded knot DVI (Two Dual-link DVI) interfaces, correspondingly, Data Format Transform module 202a can be designed to connect a plurality of DVI interface 201d.
The utility model utilizes vertical synchronizing signal monitoring modular 201c that the VSYNC signal that result data comprised among the DVI interface 201d is monitored in real time, whenever monitor a VSYNC signal, illustrate that then DVI interface 201d sends a frame result data, the purpose of doing like this is: because the computing velocity of kernel program computing module 201e sends the speed of data far away faster than DVI interface 201d, this will cause the previous frame result data not send, and the calculation result data of next frame will cover the previous frame result data in the video memory (being texture).For fear of losing of result data, after monitoring a VSYNC signal, restart kernel program computing module 201e and carry out the calculating of next frame, so just can avoid losing of result data.
The utility model has realized utilizing the DVI interface 201d on the graphics card to send GPU general-purpose computations result data, and the main memory that need not pass through system has been saved the storage space of computing machine as transfer, has reduced the delay of the general-purpose computations process of GPU simultaneously.In addition, utilize the broader bandwidth of DVI interface 201d transmission data, can satisfy the demand of big bandwidth peripherals.
The utility model is illustrated by the foregoing description, but should be understood that, the foregoing description just is used for for example and illustrative purposes, but not is intended to the utility model is limited in the described scope of embodiments.It will be understood by those skilled in the art that in addition; the utility model is not limited to the foregoing description; can also make more kinds of variants and modifications according to instruction of the present utility model, these variants and modifications all drop in the utility model scope required for protection.Protection domain of the present utility model is defined by the appended claims and equivalent scope thereof.
Claims (10)
1. device that utilizes the DVI interface to send graphic process unit general-purpose computations data is characterized in that comprising:
-graphics card, described graphics card comprises:
-texture is set up module, sets up a texture, and the preservation texture pointer corresponding with described texture;
-kernel program computing module calculates result data to raw data;
-texture binding module receives the result data that sends from described kernel program computing module, and sets up the described texture pointer that module sends from described texture, with described result data and the binding of described texture pointer;
-DVI interface receives the described result data after the binding that sends from described texture binding module;
-vertical synchronizing signal monitoring modular receives the result data after the described binding that sends from described DVI interface, and sends enabling signal to described kernel program computing module; Described device also comprises,
-virtual monitor module, the result data that described DVI interface is sent after the described binding carries out Data Format Transform.
2. a kind of device that utilizes the DVI interface to send graphic process unit general-purpose computations data as claimed in claim 1 is characterized in that described virtual monitor module comprises:
-Data Format Transform module sends to peripherals after the result data after the described binding being converted to the data of parallel suitable peripheral interface form.
3. a kind of device that utilizes the DVI interface to send graphic process unit general-purpose computations data as claimed in claim 1, it is characterized in that: described virtual monitor module also comprises extending display identification data ROM (read-only memory), and described extending display identification data ROM (read-only memory) sends the resolution of image and the numerical value of refresh rate arrives described graphics card.
4. a kind of device that utilizes the DVI interface to send graphic process unit general-purpose computations data as claimed in claim 2 is characterized in that: described Data Format Transform module adopts programmable gate array to realize.
5. a kind of device that utilizes the DVI interface to send graphic process unit general-purpose computations data as claimed in claim 2 is characterized in that: described Data Format Transform module adopts the chip and the programmable gate array that data can be converted to parallel form to realize.
6. a kind of device that utilizes the DVI interface to send graphic process unit general-purpose computations data as claimed in claim 1, it is characterized in that: described virtual monitor module adopts programmable gate array to realize the resolution of described programmable gate array memory image and refresh rate.
7. a kind of device that utilizes the DVI interface to send graphic process unit general-purpose computations data as claimed in claim 5, it is characterized in that: the described chip that data can be converted to parallel form is the SiI163B chip.
8. a kind of device that utilizes the DVI interface to send graphic process unit general-purpose computations data as claimed in claim 1, it is characterized in that: described vertical synchronizing signal monitoring modular is used for the result data after the described binding is carried out the vertical synchronizing signal monitoring, if monitor described vertical synchronizing signal, then send enabling signal to described kernel program computing module.
9. a kind of device that utilizes the DVI interface to send graphic process unit general-purpose computations data as claimed in claim 2, it is characterized in that: can increase the number of opening described DVI interface according to the increase of resolution, and described Data Format Transform modular design is the whole DVI interfaces of connection.
10. as claim 2 or 3 described a kind of devices that utilize the DVI interface to send graphic process unit general-purpose computations data, it is characterized in that: described extending display identification data ROM (read-only memory) and described Data Format Transform module are provided with independently of one another.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010201530638U CN201765584U (en) | 2010-04-08 | 2010-04-08 | Device for sending general calculation data of graphics processing unit with digital visual interface (DVI) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010201530638U CN201765584U (en) | 2010-04-08 | 2010-04-08 | Device for sending general calculation data of graphics processing unit with digital visual interface (DVI) |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN201765584U true CN201765584U (en) | 2011-03-16 |
Family
ID=43718192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010201530638U Expired - Lifetime CN201765584U (en) | 2010-04-08 | 2010-04-08 | Device for sending general calculation data of graphics processing unit with digital visual interface (DVI) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN201765584U (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102237071A (en) * | 2010-05-07 | 2011-11-09 | 英属维京群岛商硕颖科技有限公司 | Simulation device for display |
| CN102779020A (en) * | 2011-05-12 | 2012-11-14 | 北京牡丹电子集团有限责任公司 | Ultra high definition liquid crystal display device |
| CN103106638A (en) * | 2011-11-14 | 2013-05-15 | 辉达公司 | Graphic processing device for real-time image processing |
| CN103164180A (en) * | 2011-12-14 | 2013-06-19 | 技嘉科技股份有限公司 | Display card and information storage method thereof |
| CN103986549A (en) * | 2013-02-07 | 2014-08-13 | 辉达公司 | Device, system and method used for network data transmission |
-
2010
- 2010-04-08 CN CN2010201530638U patent/CN201765584U/en not_active Expired - Lifetime
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102237071A (en) * | 2010-05-07 | 2011-11-09 | 英属维京群岛商硕颖科技有限公司 | Simulation device for display |
| CN102779020A (en) * | 2011-05-12 | 2012-11-14 | 北京牡丹电子集团有限责任公司 | Ultra high definition liquid crystal display device |
| CN103106638A (en) * | 2011-11-14 | 2013-05-15 | 辉达公司 | Graphic processing device for real-time image processing |
| US9508109B2 (en) | 2011-11-14 | 2016-11-29 | Nvidia Corporation | Graphics processing |
| CN103164180A (en) * | 2011-12-14 | 2013-06-19 | 技嘉科技股份有限公司 | Display card and information storage method thereof |
| CN103164180B (en) * | 2011-12-14 | 2017-12-15 | 技嘉科技股份有限公司 | Display card and its information storing method |
| CN103986549A (en) * | 2013-02-07 | 2014-08-13 | 辉达公司 | Device, system and method used for network data transmission |
| CN103986549B (en) * | 2013-02-07 | 2018-03-13 | 辉达公司 | Equipment, system and method for network data transmission |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN201765584U (en) | Device for sending general calculation data of graphics processing unit with digital visual interface (DVI) | |
| CN1952979B (en) | Multiple graphics processor systems and methods | |
| US6816163B2 (en) | Updating image frames on a screen comprising memory | |
| CN109032494B (en) | Intelligent interaction system, writing track display method and device, tablet and medium | |
| US9182938B2 (en) | Method for controlling multiple displays and system thereof | |
| CN102981892A (en) | Centralized device virtualization layer for heterogeneous processing units | |
| US8259119B1 (en) | System and method for switching between graphical processing units | |
| CN104010136B (en) | Graphical display system based on airborne graphic engine | |
| US20080192063A1 (en) | Managing Multiple Contexts in a Decentralized Graphics Processing Unit | |
| CN103327281B (en) | A kind of format conversion method and format conversion circuit | |
| JPH0727571B2 (en) | Raster scan display device and graphic data transfer method | |
| CN111090603B (en) | LVDS-to-USB 3.0 adapter | |
| CN104360319A (en) | CUDA platform-based radar B-display processing method | |
| CN107255961B (en) | A kind of intelligent wireless oscillograph of efficient data interaction | |
| TW200821984A (en) | Work based clock management for display sub-system | |
| CN109343954B (en) | Electronic equipment working method and system | |
| CN106648507B (en) | Circuit and method for expanding DVI display output of embedded processor | |
| CN203645774U (en) | Reversal image system combined with radar and camera functions | |
| CN103986549A (en) | Device, system and method used for network data transmission | |
| CN103108165A (en) | Embedded flotation froth image monitoring device based on digital signal processor (DSP) | |
| CN201611480U (en) | Device for transmitting and receiving general-purpose computation data of graphics processing unit by MIO interface | |
| WO2023202367A1 (en) | Graphics processing unit, system, apparatus, device, and method | |
| CN110515658A (en) | Method and apparatus for managing variable length instruction | |
| CN206193755U (en) | Realize structure of quick demonstration when homemade treater starts | |
| CN109308862A (en) | Signal control method, control device, processing unit and signal control equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CX01 | Expiry of patent term | ||
| CX01 | Expiry of patent term |
Granted publication date: 20110316 |