CN105703911A - Image processing computer and formation method - Google Patents
Image processing computer and formation method Download PDFInfo
- Publication number
- CN105703911A CN105703911A CN201410685674.XA CN201410685674A CN105703911A CN 105703911 A CN105703911 A CN 105703911A CN 201410685674 A CN201410685674 A CN 201410685674A CN 105703911 A CN105703911 A CN 105703911A
- Authority
- CN
- China
- Prior art keywords
- pieces
- nfs
- router
- switch
- computer
- 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.)
- Pending
Links
Landscapes
- Stored Programmes (AREA)
Abstract
The invention discloses an image processing computer and a formation method. The image processing computer comprises at least two central processing units (CPU), at least two motherboards, one switch or router which is provided with at least four ports, and one NFS server; the at least two CPUs are arranged on the at least two motherboards respectively; at least two motherboards are connected with the switch or router through network cables; and the NFS server is connected with the switch or router through a network cable. According to one embodiment of the invention, commonly used computer components are utilized to form the high-performance image processing computer, and the image processing computer has the advantages of small size, low noises, electricity-saving performance and low cost, and is applicable to a variety of kinds of image processing or calculation processes requiring a large amount of calculation.
Description
Technical field
The present invention relates to Internet technical field, particularly to a kind of pattern process computer and construction method thereof。
Background technology
Image procossing (imageprocessing), is analyzed image with computer, to reach the technology of results needed。Also known as image processing。Image procossing refers generally to Digital Image Processing。Digital picture refers to the big two-dimensional array obtained with equipment such as industrial camera, video camera, scanneies through shooting, and the element of this array is called pixel, and its value is called gray value。Image processing techniques generally comprise compression of images, strengthen and restore, coupling, describe and identify 3 parts。
Digital Image Processing is exactly utilize computer that image information is processed meeting the visual psychology of people or the behavior of application demand。Substantially one section can be shown by computer reduction and be output as the digital code of piece image。Image as the visual basis in the human perception world, is mankind's important means of obtaining information, expressing information and transmission information。Digital Image Processing [9], namely processes image with computer, and its developing history is not long。Digital image processing techniques come from the twenties in 20th century, transmitted a photos by submarine cable at that time, and have employed digital compression technology from London to USA New York。First digital image processing techniques can help that people are more objective, recognize the world exactly, the visual system of people can help the mankind to obtain the information of more than 3/4 from the external world, and image, figure are the carriers of all visual informations, although the resolving ability of human eye is significantly high, may identify which thousands of kinds of colors, but in a lot of situation, image is fuzzy or even sightless for human eye, pass through image enhancement technology, it is possible to make fuzzy even invisible image be apparent from becoming clear。On the other hand, by the mode identification technology in Digital Image Processing, it is possible to the image of human eye None-identified is carried out classification process。Can retrieve, mate and identify various thing rapidly and accurately by computer pattern recognition。
Graph rendering, English is Render, and being referred to as of also having is painted, but generally Shade is called painted, Render is called and renders。Because Render and Shade the two word is distinct two concepts in three-dimensional software, although their function is much like, but has difference。Shade is a kind of displaying scheme, is generally present in the primary window of three-dimensional software, the effect of playing auxiliary observation model the same as the line frame graph of threedimensional model。It is obvious that color mode is easier to let us than wire frame mode understands the structure of model, but it simply simply shows, is referred to as light and shade colouring in digital picture。As in the such advanced three-dimensional software of Maya, simple lighting effects, hatching effect and superficial makings effect can also be demonstrated with Shade, certainly, high-quality coloring effect needs specialty three dimensional graph display card to support, it can accelerate and optimize the display of 3-D graphic。But optimize in any case, it all cannot become the 3-D graphic shown into high-quality image, this is because what Shade adopted is a kind of real-time display technology, the speed of hardware limits the ray tracing effects such as reflection, the refraction that it cannot feed back in scene in real time。And we often to export into image file, video signal or cinematographic film model or scene in practical work, this is necessary for through Render program。
In prior art, specialty 3D graph rendering needs to carry out substantial amounts of floating-point operation and (includes physical entity, geometric transformation, shearing, light efficiency, and triangle setup) and integer arithmetic (including triangle setup and pixel rendering), it is a CPU intensive type task。Existing pattern process computer needs professional workstation, bulky, and price is high, and power consumption ability is superpower, is not suitable for general image procossing and graph rendering work。
Summary of the invention
The present invention provides a kind of pattern process computer and construction method thereof, in order to solve the problem that professional workstation in prior art is bulky, price is high, power consumption is big。
A kind of pattern process computer, including:
At least two pieces of cpu central processing units, at least two pieces of mainboards, the switch of at least four ports or router and a nfs server;
Described at least two pieces of cpu central processing units are respectively arranged at least two pieces of mainboards;Described at least two pieces of mainboards are connected to described switch or router respectively with netting twine;Described nfs server netting twine is connected with described switch or router。
Described computer includes 6 pieces of CPU and 6 pieces of mainboards。
Described switch or switch that router is at least 8 ports or router。
Every piece of described mainboard supports at least 2G internal memory。
Every piece of described mainboard supports 8G internal memory。
Described nfs server installs ubuntu12.04 system, and every piece of described mainboard installs operating system by NFS NFS。
Described nfs server is installed and renders management software DrQueue in order to process view data。
A kind of pattern process computer construction method, including:
At least two pieces of cpu central processing units are respectively arranged at least two pieces of mainboards;At least two pieces of mainboards are connected to switch or router respectively with netting twine;One nfs server netting twine is connected with switch or router;
Described nfs server is installed ubuntu12.04 system, and installation renders management software DrQueue in order to process view data;Described mainboard installs operating system by NFS NFS。
Described mainboard at least supports 2G internal memory, it is preferred to 8G internal memory。
Described mainboard is 6 pieces, and described CPU is 6 pieces, and described switch or router are 8 ports。
In the embodiment of the present invention, processing view data by setting up a high performance pattern process computer, this pattern process computer includes: at least two pieces of cpu central processing units, at least two pieces of mainboards, the switch of at least four ports or router and a nfs server;At least two pieces of cpu central processing units are respectively arranged at least two pieces of mainboards;At least two pieces of mainboards are connected to switch or router respectively with netting twine;Nfs server netting twine is connected with switch or router。In the embodiment of the present invention, utilize conventional computer module to set up a high performance pattern process computer, have that volume is little, quiet, a feature of power saving and low cost, it is adaptable to various image procossing or other need the calculating process of intensive。
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from description, or understand by implementing the present invention。The purpose of the present invention and other advantages can be realized by structure specifically noted in the description write, claims and accompanying drawing and be obtained。
Below by drawings and Examples, technical scheme is described in further detail。
Accompanying drawing explanation
Accompanying drawing is for providing a further understanding of the present invention, and constitutes a part for description, is used for together with embodiments of the present invention explaining the present invention, is not intended that limitation of the present invention。In the accompanying drawings:
A kind of pattern process computer structural representation that Fig. 1 provides for the embodiment of the present invention 1;
A kind of pattern process computer structural representation that Fig. 2 provides for the embodiment of the present invention 2;
A kind of pattern process computer construction method principle flow chart that Fig. 3 provides for the embodiment of the present invention 3。
Detailed description of the invention
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are illustrated, it will be appreciated that preferred embodiment described herein is merely to illustrate and explains the present invention, is not intended to limit the present invention。
As it is shown in figure 1, a kind of pattern process computer structural representation provided for the embodiment of the present invention 1, including:
At least two pieces of cpu central processing units, at least two pieces of mainboards, the switch of at least four ports or router and a nfs server;
At least two pieces of cpu central processing units are respectively arranged at least two pieces of mainboards;At least two pieces of mainboards are connected to switch or router respectively with netting twine;Nfs server netting twine is connected with switch or router。
In the present embodiment, at least two pieces of described CPU, it is therefore intended that make multiple CPU collaborative work, thus at least need two pieces of CPU。CPU is The more the better in theory, it is possible to set the quantity of CPU according to the actual needs。
Set the quantity of CPU, it is clear that in order to coordinate the work of CPU, it is necessary to Cai there is corresponding mainboard passable。CPU must be mounted to just can play a role on corresponding mainboard。After the quantity set of CPU, the quantity of mainboard also just sets, the two be identical accordingly。
In the selection of mainboard, usual IQ needs to support the internal memory of 2G。Owing in the present embodiment, requirement for mainboard sets according to the actual needs, so this is not limited。
Set the quantity of CPU and mainboard, in order to be linked together by all of cpu motherboard, it will usually connected by netting twine。A switch or router is needed to connect to do total exchange between netting twine。The selection of switch or router, minimum needs are satisfied to be actually needed, and the mainboard quantity namely included according to real system selects。Such as, if real system includes 6 mainboards, then at least to select switch or the router of 8 mouthfuls。
In addition, in order to realize the actual control to system, in addition it is also necessary to a station server, for practical OS's。Nfs server can meet the demand of reality。
NFS is the abbreviation of NetworkFileSystem, i.e. NFS。A kind of agreement being used in decentralized file system, is developed by Sun Microsystems, outwards announces in 1984。Function is to allow different machines, different operating system can share an other data each other by network, allow application program be accessed the data being arranged in server disk by network in client, be between class Unix system, realize a kind of method that disk file is shared。
The basic principle of NFS is " allowing that different clients and service end share identical file system by one group of RPC ", and it is independently of operating system, allows that the system of different hardware and operating system carries out sharing of file jointly。
NFS depends on RPC agreement in file transmission or information transfer process。RPC, remote procedure call (RemoteProcedureCall) is a kind of mechanism that can make client executing other system Program。NFS itself is the agreement and function that do not provide information to transmit, but NFS can carry out sharing of data by network by let us, this is because NFS employs some other host-host protocol。And these host-host protocols use this RPC function。It may be said that NFS inherently uses a program of RPC。NFS is also a RPCSERVER in other words。As long as so the place using NFS will start RPC service, whether NFSSERVER or NFSCLIENT。Such SERVER and CLIENT could realize the correspondence of PROGRAMPORT by RPC。Can so understand the relation of RPC and NFS: NFS is a file system, and RPC is responsible for the transmission of information of being responsible for。
NFS promotes the archives on Servers can by other machine mount, and reach resource-sharing, the machine enjoying these archives just can be described as Client, one client can from mono-shelves of mount server or the catalogue (filehierarchies) of a level. but in fact any machine can be NFSserverorNFSclient, and even simultaneously can also for NFSserverandNFSclient。
Nfs server institute export archives out or catalogue all record in/these shelves of etc/exports, when we start NFSserver, this script at/etc/rc.local can start this formula of exportfs automatically, whether these shelves of search/etc/exports exist, and give correct authority to all export filehierarchies gone out。
The target of NFS is to allow the different machines can the identical Archive Resource of cross-platform sharing。In simple terms, it is possible to regard the archives economy of a kind of far-end as。Also because cross-platform target, so NFS all supported by almost all of UnixLike platform, such as IBMAIX, SunSolaris, HPUnix, GNU/Linux and FreeBSD etc., NFS can be passed through and share archives and resource of catalog。Although having NFSClient to install on MSWindows at present, but it it is almost business software。So everybody is everlasting, UnixLike system use NFS to share Archive Resource。Perhaps reader can wonder, why not shares with Samba net virtue, and such MSWindows and Unix can line mutually?This is because NFS efficiency ratio Samba is well a lot, so usually on the super computer of parallel calculation or business large scale system, using a NFSServer, other Server to be wired to NFS archive server through optical-fibre channel and obtain data。
Usually one NFSServer of frame in practice, and be fitted with magnetic tape controller can the backup archives of timing。Other server just gets up NFSServershare catalogue carry out, and the archives such as actually all webpages and data are all placed on NFSServer, these Server just only a simple computing with respond client request。Safeguard a archives economy as long as such benefit is for we, and backup and resource distribution also can be easier。Also because NFSServer generally uses Raid disc array system, so whole framework can reach high-effect and high reliability service。
So in the system of composition, it is possible to the operational capability making full use of multiple cpu motherboard carries out the image procossing of reality, or, it is also possible to doing other any work needing macrooperation amount, concrete application scenarios is not limited by the present embodiment。
In the embodiment of the present invention, processing view data by setting up a high performance pattern process computer, this pattern process computer includes: at least two pieces of cpu central processing units, at least two pieces of mainboards, the switch of at least four ports or router and a nfs server;At least two pieces of cpu central processing units are respectively arranged at least two pieces of mainboards;At least two pieces of mainboards are connected to switch or router respectively with netting twine;Nfs server netting twine is connected with switch or router。In the embodiment of the present invention, utilize conventional computer module to set up a high performance pattern process computer, have that volume is little, quiet, a feature of power saving and low cost, it is adaptable to various image procossing or other need the calculating process of intensive。
As in figure 2 it is shown, the pattern process computer structural representation provided for the embodiment of the present invention 2, wherein,
This system includes 4 core processors of 6 pieces of Core2,6 pieces of Jijia's S series GA-G33M-DS2R/S2 mainboards, every piece of maximum 8GB internal memory of mainboard, it is placed in a big cabinet (six pieces of mainboards of system can be filled), fit together, form image procossing computer system。6 pieces of mainboards connect with 8 mouthfuls of 3com gigabit switch, then look for a computer to do nfs server。Thus achieve concrete pattern process computer hardware composition。
Then needing installation ubuntu12.04 system on nfs server, each mainboard passes through NFS NFS installation system。Installing type renders management software DrQueue in systems。
Drqueue is the Cluster Rendering management software of an open source code, supports that the task of Maya8 is submitted at present, and other support that software includes mentalray, shake, Renderman, and Blender3D。Drqueue has the Drkeewee service routine situation for the transmission rendering task that communicates, and these operate the stopping of rendering task such as through Drqman graphical interfaces, restart, priority level etc.。DrQueue can run on various platform (Linux, FreeBSD, Irix, MacOS-X&Windows) can also with the collaborative work under the graphic user interface of GUI of a lot of rendering engines (Maya, MentalRay, Blender, XSI, Lightwave, Mantra, Turtle, BMRT, Shake, AfterEffects, Aqsis, Nuke, Terragen, 3Delight and Pixie)。The script of DrQueue can be write。This software includes a little server DrKeewee, and by web browser, it can help you to check the situation of the pending data such as current。
DrQueue is a powerful Distributed Rendering Environment farm management software of increasing income, and for a series of application program at visual effect industry and general batch processing job, is applied to science, engineering, finance, animation, film etc.。User submits an operation to DrQueue, and DrQueue is distributed on renderer node distributed for operation。
Concrete installation is as follows:
Download up-to-date DrQueue source code bag:
wgethttp://www.drqueue.org/files/drqueue.0.64.4c3.tgz-P/opt
cd/opt/
tarzxvfdrqueue.0.64.4c3.tgz
cdDrQueue-0.64.4c3
SconsinstallPREFIX=/opt
The words that do not report an error when sconsinstall can normal mounting under/opt/drqueue catalogue。
Amendment configuration file。
Amendment master.conf:
vim/opt/drqueue/etc/master.conf
Logs=/opt/drqueue/logs
Tmp=/opt/drqueue/tmp
Db=/opt/drqueue/db
Bin=/opt/drqueue/bin
Etc=/opt/drqueue/etc
Amendment slave.conf:
vim/opt/drqueue/etc/slave.conf
Logs=/opt/drqueue/logs
Tmp=/opt/drqueue/tmp
Pool=test1, test2, test3
Amendment drqman.conf:
vim/opt/drqueue/etc/drqman.conf
Logs=/opt/drqueue/logs
Tmp=/opt/drqueue/tmp
Db=/opt/drqueue/db
Set
/ etc/profile adds following variable:
PATH=$ { PATH}:/opt/drqueue/bin
exportPATH
ExportDRQUEUE_ROOT=/opt/drqueue
ExportDRQUEUE_TMP=/opt/drqueue/tmp
ExportDRQUEUE_OS=LINUX
ExportDRQUEUE_BIN=/opt/drqueue/bin
ExportDRQUEUE_ETC=/opt/drqueue/etc
ExportDRQUEUE_DB=/opt/drqueue/db
ExportDRQUEUE_LOGS=/opt/drqueue/logs
ExportDRQUEUE_MASTER=192.168.8.123
ExportRAILS_ENV=production
Perform source/etc/profile so as to come into force。
Next can performing master.Linux.x86_64, slave.Linux.x86_64 and drqman.Linux.x86_64 order, drqman needs to call figure, it is possible to submit rendering task to by drqman client。
In the embodiment of the present invention, processing view data by setting up a high performance pattern process computer, this pattern process computer includes: at least two pieces of cpu central processing units, at least two pieces of mainboards, the switch of at least four ports or router and a nfs server;At least two pieces of cpu central processing units are respectively arranged at least two pieces of mainboards;At least two pieces of mainboards are connected to switch or router respectively with netting twine;Nfs server netting twine is connected with switch or router。In the embodiment of the present invention, utilize conventional computer module to set up a high performance pattern process computer, have that volume is little, quiet, a feature of power saving and low cost, it is adaptable to various image procossing or other need the calculating process of intensive。
As it is shown on figure 3, a kind of pattern process computer construction method principle flow chart provided for the embodiment of the present invention 3, wherein,
Step 31, at least two pieces of cpu central processing units are respectively arranged at least two pieces of mainboards;At least two pieces of mainboards are connected to switch or router respectively with netting twine;One nfs server netting twine is connected with switch or router;
Step 32, nfs server is installed ubuntu12.04 system, and installation renders management software DrQueue in order to process view data;Mainboard installs operating system by NFS NFS。
In the present embodiment, at least two pieces of described CPU, it is therefore intended that make multiple CPU collaborative work, thus at least need two pieces of CPU。CPU is The more the better in theory, it is possible to set the quantity of CPU according to the actual needs。
Set the quantity of CPU, it is clear that in order to coordinate the work of CPU, it is necessary to Cai there is corresponding mainboard passable。CPU must be mounted to just can play a role on corresponding mainboard。After the quantity set of CPU, the quantity of mainboard also just sets, the two be identical accordingly。
In the selection of mainboard, usual IQ needs to support the internal memory of 2G。Owing in the present embodiment, requirement for mainboard sets according to the actual needs, so this is not limited。
Set the quantity of CPU and mainboard, in order to be linked together by all of cpu motherboard, it will usually connected by netting twine。A switch or router is needed to connect to do total exchange between netting twine。The selection of switch or router, minimum needs are satisfied to be actually needed, and the mainboard quantity namely included according to real system selects。Such as, if real system includes 6 mainboards, then at least to select switch or the router of 8 mouthfuls。Similarly, for, in the selection of mainboard, at least needing to support 2G internal memory, it is preferred to maximum support 8G internal memory。
In addition, in order to realize the actual control to system, in addition it is also necessary to a station server, for practical OS's。Nfs server can meet the demand of reality。
NFS is the abbreviation of NetworkFileSystem, i.e. NFS。A kind of agreement being used in decentralized file system, is developed by Sun Microsystems, outwards announces in 1984。Function is to allow different machines, different operating system can share an other data each other by network, allow application program be accessed the data being arranged in server disk by network in client, be between class Unix system, realize a kind of method that disk file is shared。
The basic principle of NFS is " allowing that different clients and service end share identical file system by one group of RPC ", and it is independently of operating system, allows that the system of different hardware and operating system carries out sharing of file jointly。
NFS depends on RPC agreement in file transmission or information transfer process。RPC, remote procedure call (RemoteProcedureCall) is a kind of mechanism that can make client executing other system Program。NFS itself is the agreement and function that do not provide information to transmit, but NFS can carry out sharing of data by network by let us, this is because NFS employs some other host-host protocol。And these host-host protocols use this RPC function。It may be said that NFS inherently uses a program of RPC。NFS is also a RPCSERVER in other words。As long as so the place using NFS will start RPC service, whether NFSSERVER or NFSCLIENT。Such SERVER and CLIENT could realize the correspondence of PROGRAMPORT by RPC。Can so understand the relation of RPC and NFS: NFS is a file system, and RPC is responsible for the transmission of information of being responsible for。
NFS promotes the archives on Servers can by other machine mount, and reach resource-sharing, the machine enjoying these archives just can be described as Client, one client can from mono-shelves of mount server or the catalogue (filehierarchies) of a level. but in fact any machine can be NFSserverorNFSclient, and even simultaneously can also for NFSserverandNFSclient。
Nfs server institute export archives out or catalogue all record in/these shelves of etc/exports, when we start NFSserver, this script at/etc/rc.local can start this formula of exportfs automatically, whether these shelves of search/etc/exports exist, and give correct authority to all export filehierarchies gone out。
The target of NFS is to allow the different machines can the identical Archive Resource of cross-platform sharing。In simple terms, it is possible to regard the archives economy of a kind of far-end as。Also because cross-platform target, so NFS all supported by almost all of UnixLike platform, such as IBMAIX, SunSolaris, HPUnix, GNU/Linux and FreeBSD etc., NFS can be passed through and share archives and resource of catalog。Although having NFSClient to install on MSWindows at present, but it it is almost business software。So everybody is everlasting, UnixLike system use NFS to share Archive Resource。Perhaps reader can wonder, why not shares with Samba net virtue, and such MSWindows and Unix can line mutually?This is because NFS efficiency ratio Samba is well a lot, so usually on the super computer of parallel calculation or business large scale system, using a NFSServer, other Server to be wired to NFS archive server through optical-fibre channel and obtain data。
Usually one NFSServer of frame in practice, and be fitted with magnetic tape controller can the backup archives of timing。Other server just gets up NFSServershare catalogue carry out, and the archives such as actually all webpages and data are all placed on NFSServer, these Server just only a simple computing with respond client request。Safeguard a archives economy as long as such benefit is for we, and backup and resource distribution also can be easier。Also because NFSServer generally uses Raid disc array system, so whole framework can reach high-effect and high reliability service。
So in the system of composition, it is possible to the operational capability making full use of multiple cpu motherboard carries out the image procossing of reality, or, it is also possible to doing other any work needing macrooperation amount, concrete application scenarios is not limited by the present embodiment。
In the embodiment of the present invention, processing view data by setting up a high performance pattern process computer, this pattern process computer includes: at least two pieces of cpu central processing units, at least two pieces of mainboards, the switch of at least four ports or router and a nfs server;At least two pieces of cpu central processing units are respectively arranged at least two pieces of mainboards;At least two pieces of mainboards are connected to switch or router respectively with netting twine;Nfs server netting twine is connected with switch or router。In the embodiment of the present invention, utilize conventional computer module to set up a high performance pattern process computer, have that volume is little, quiet, a feature of power saving and low cost, it is adaptable to various image procossing or other need the calculating process of intensive。
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program。Therefore, the present invention can adopt the form of complete hardware embodiment, complete software implementation or the embodiment in conjunction with software and hardware aspect。And, the present invention can adopt the form at one or more upper computer programs implemented of computer-usable storage medium (including but not limited to disk memory and optical memory etc.) wherein including computer usable program code。
The present invention is that flow chart and/or block diagram with reference to method according to embodiments of the present invention, equipment (system) and computer program describe。It should be understood that can by the combination of the flow process in each flow process in computer program instructions flowchart and/or block diagram and/or square frame and flow chart and/or block diagram and/or square frame。These computer program instructions can be provided to produce a machine to the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device so that the instruction performed by the processor of computer or other programmable data processing device is produced for realizing the device of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame。
These computer program instructions may be alternatively stored in and can guide in the computer-readable memory that computer or other programmable data processing device work in a specific way, the instruction making to be stored in this computer-readable memory produces to include the manufacture of command device, and this command device realizes the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame。
These computer program instructions also can be loaded in computer or other programmable data processing device, make on computer or other programmable devices, to perform sequence of operations step to produce computer implemented process, thus the instruction performed on computer or other programmable devices provides for realizing the step of function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame。
Obviously, the present invention can be carried out various change and modification without deviating from the spirit and scope of the present invention by those skilled in the art。So, if these amendments of the present invention and modification belong within the scope of the claims in the present invention and equivalent technologies thereof, then the present invention is also intended to comprise these change and modification。
Claims (10)
1. a pattern process computer, it is characterised in that including:
At least two pieces of cpu central processing units, at least two pieces of mainboards, the switch of at least four ports or router and a nfs server;
Described at least two pieces of cpu central processing units are respectively arranged at least two pieces of mainboards;Described at least two pieces of mainboards are connected to described switch or router respectively with netting twine;Described nfs server netting twine is connected with described switch or router。
2. pattern process computer as claimed in claim 1, it is characterised in that described computer includes 6 pieces of CPU and 6 pieces of mainboards。
3. pattern process computer as claimed in claim 1, it is characterised in that described switch or switch that router is at least 8 ports or router。
4. pattern process computer as claimed in claim 1, it is characterised in that every piece of described mainboard supports at least 2G internal memory。
5. pattern process computer as claimed in claim 4, it is characterised in that every piece of described mainboard supports 8G internal memory。
6. pattern process computer as claimed in claim 1, it is characterised in that described nfs server installs ubuntu12.04 system, every piece of described mainboard installs operating system by NFS NFS。
7. pattern process computer as claimed in claim 1, it is characterised in that install on described nfs server and render management software DrQueue in order to process view data。
8. a pattern process computer construction method, it is characterised in that including:
At least two pieces of cpu central processing units are respectively arranged at least two pieces of mainboards;At least two pieces of mainboards are connected to switch or router respectively with netting twine;One nfs server netting twine is connected with switch or router;
Described nfs server is installed ubuntu12.04 system, and installation renders management software DrQueue in order to process view data;Described mainboard installs operating system by NFS NFS。
9. method as claimed in claim 8, it is characterised in that described mainboard at least supports 2G internal memory, it is preferred to 8G internal memory。
10. method as claimed in claim 8, it is characterised in that described mainboard is 6 pieces, and described CPU is 6 pieces, and described switch or router are 8 ports。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410685674.XA CN105703911A (en) | 2014-11-25 | 2014-11-25 | Image processing computer and formation method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410685674.XA CN105703911A (en) | 2014-11-25 | 2014-11-25 | Image processing computer and formation method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105703911A true CN105703911A (en) | 2016-06-22 |
Family
ID=56940923
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410685674.XA Pending CN105703911A (en) | 2014-11-25 | 2014-11-25 | Image processing computer and formation method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105703911A (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1447258A (en) * | 2003-04-22 | 2003-10-08 | 清华大学 | Networked computers with no local operation system |
US20060012822A1 (en) * | 2004-07-15 | 2006-01-19 | Ziosoft, Inc. | Image processing system for volume rendering |
CN1744047A (en) * | 2005-09-27 | 2006-03-08 | 浪潮电子信息产业股份有限公司 | Method for realizing dynamic layout of high-performance server based on group structure |
-
2014
- 2014-11-25 CN CN201410685674.XA patent/CN105703911A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1447258A (en) * | 2003-04-22 | 2003-10-08 | 清华大学 | Networked computers with no local operation system |
US20060012822A1 (en) * | 2004-07-15 | 2006-01-19 | Ziosoft, Inc. | Image processing system for volume rendering |
CN1744047A (en) * | 2005-09-27 | 2006-03-08 | 浪潮电子信息产业股份有限公司 | Method for realizing dynamic layout of high-performance server based on group structure |
Non-Patent Citations (2)
Title |
---|
唐双燕,: ""基于LSF平台的集群渲染可视化监控研究与实现"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
蔡靖,: ""动漫平台集群渲染系统的研究与实现"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103019802B (en) | A kind of virtual machine management method and platform | |
US9582904B2 (en) | Image composition based on remote object data | |
US10315110B2 (en) | Service for generating graphics object data | |
US20210049827A1 (en) | Cloud-centric platform for collaboration and connectivity on 3d virtual environments | |
DE102021129078A1 (en) | INTELLIGENT PUSH COUPLING ABOVE THE PLATFORM FOR COOLING SYSTEMS IN DATA CENTERS | |
US9230294B2 (en) | Preserving and reusing intermediate data | |
Wu et al. | Cloud-based image processing system with priority-based data distribution mechanism | |
US20190018687A1 (en) | Cognitive thread management in a multi-threading application server environment | |
DE102021125626A1 (en) | LIGHT RESAMPLING WITH AREA SIMILARITY | |
Raji et al. | Scalable web-embedded volume rendering | |
CN111932663A (en) | Parallel drawing method based on multi-level asymmetric communication management | |
Gooding et al. | Implementation of a distributed rendering environment for the TeraGrid | |
Mahmoudi et al. | Towards a smart selection of resources in the cloud for low‐energy multimedia processing | |
Ruan et al. | High performance photogrammetry for academic research | |
CN105703911A (en) | Image processing computer and formation method | |
DE112022003554T5 (en) | APPLICATION PROGRAMMING INTERFACE FOR CREATING AND MODIFYING GRAPHIC OBJECTS | |
DE112023000088T5 (en) | SELECTIVE COMMUNICATION INTERFACES FOR PROGRAMMABLE PARTS | |
KR20180008168A (en) | Holographic Content Creation System and Method using a Parallel Processing Environment | |
Wang et al. | Performance bottleneck analysis and resource optimized distribution method for IoT cloud rendering computing system in cyber-enabled applications | |
Huzaifa | Design and evaluation of extended reality systems | |
Kawaba et al. | Future Trends in Software Technology to Support Digital Innovations | |
Hagen | Interactive Visualization on High-Resolution Tiled Display Walls with Network Accessible Compute-and Display-Resources | |
Wang et al. | Research on 3D Terminal Rendering Technology Based on Power Equipment Business Features | |
US20240249464A1 (en) | Multi-factor prediction of computing resources for two-dimensional to three-dimensional modeling acceleration | |
US20230298132A1 (en) | Scene builder |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160622 |