CN102592315B - 3D rendering platform based on GPU cloud cluster - Google Patents
3D rendering platform based on GPU cloud cluster Download PDFInfo
- Publication number
- CN102592315B CN102592315B CN201110005379.1A CN201110005379A CN102592315B CN 102592315 B CN102592315 B CN 102592315B CN 201110005379 A CN201110005379 A CN 201110005379A CN 102592315 B CN102592315 B CN 102592315B
- Authority
- CN
- China
- Prior art keywords
- rendering
- file
- unit
- rendered
- real
- 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.)
- Active
Links
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention provides a 3D rendering platform based on a GPU cloud cluster, which is applied to an internet system constructed by a client end and a remote servo end. A 3D model making software used for carrying out 3D modeling and animation designing is pre-installed in the client end. The 3D rendering platform comprises a real-time monitoring transmission module which is used for transmitting file packages to be rendered to the remote servo end in batches and establishing a mapping association with the remote servo end, a rendering management module positioned in the remote servo end, a database and a cloud cluster rendering node set, wherein the rendering management module receives the file packages to be rendered in real time and transmits the file packages to the database for backup, the file packages to be rendered are segmented and are dynamical distributed the cloud cluster rendering node set for carrying out cloud cluster rendering, and finally the rendered files are received and then are integrated to form files with preset formats, and then the files with the preset formats are retransmitted to the client end, thus the problems of overlow 3D model rendering speed or overhigh 3D model rendering cost and the like of three-dimensional animation, film and television production, furniture design and the like of a user under the condition of a single machine are solved.
Description
Technical field
The present invention relates to a kind of 3D graphics rendering technology, particularly relate to a kind of to be applied in the internet system built by client and remote servo end and based on the 3D rendering platform of GPU cloud cluster.
Background technology
Computer animation is so process: the still image of a sequence assembles by it, and shows in order, thus produces the effect of motion continuously.The animation of each frame should fusion seamless with next frame in playing process, so just can reach the level and smooth effect play.
Playing up is process 3-D geometric model being changed journey graph image.A process very consuming time to playing up of a cartoon scene, because an animation is generally all made up of thousands of frame.Along with the requirement of people to visual effect is more and more higher, the resolution of each frame is also more and more higher, and pixel is also more and more higher, and a width picture is taken several hours possibly and just can have been played up.Generally, the time controling playing up film is just considered to accept at every frame for 1 ~ 2 hour.Certainly, also have and need to play up tens hours.Suppose to wake up with a start to play up by 4k resolution to be that if every frame is with 5 hours, then every 1 minute projection amount render time of needing 300 days, complete digital movie needs nearly 100 years of a 120 minutes length, this is God-awful.To have no idea practical requirement so depend merely on unit to improve rendering efficiency.Because, it is utilize the arithmetic section of CPU to carry out rendering operation that traditional CPU plays up, but the arithmetic element of a CPU only accounts for 20%, even if the multi-core CPU of main flow is also the same at present, multi-core CPU just can run multiple program simultaneously, but in the animation render process of reality, above-mentioned situation has no to help for computing.
So how overcoming personal user and carry out the 3D model rendering speed such as three-dimensional cartoon, production of film and TV, furniture design cross slow or play up the shortcomings such as high cost in unit situation, has been the problem expecting in the industry to need to solve.
Summary of the invention
The shortcoming of prior art in view of the above, the object of the present invention is to provide a kind of 3D rendering platform based on GPU cloud cluster, distributed parallel cloud Rendering is built to utilize GPU, complete new experience is brought to user, to make user dynamically can submit rendering task on the remote servo end of cloud cluster, and then solve personal user in prior art and in unit situation, carry out the 3D model rendering speed such as three-dimensional cartoon, production of film and TV, furniture design cross slow or play up the problems such as high cost.
For achieving the above object and other relevant objects, the invention provides a kind of 3D rendering platform based on GPU cloud cluster, be applied in the internet system built by client and remote servo end, and described client is preinstalled with the 3D modelling software carrying out 3D modeling and animation, it is characterized in that, described 3D rendering platform at least comprises: monitor transport module in real time, be installed on described client and embed in described 3D modelling software with the form of plug-in unit, in order at described 3D modelling software Modling model, arrange light, and after establishment material, these document scenes are packaged as file bag to be rendered, and by its bulk transfer to described remote servo end, and set up mapping association with it, play up administration module, be positioned at described remote servo end, be connected with described real-time monitoring transport module by internet, after real-time reception to the file bag to be rendered of described real-time monitoring transport module transmission, described file bag to be rendered is carried out backup to export, then export giving dynamic assignment after described file bag segmentation to be rendered, and play up file for what finish receiving, and be carry out backup after predetermined format file again to export by respectively this plays up integrating documents, then this predetermined format file is returned to described client, database, is positioned at described remote servo end, is connected with described administration module of playing up, and stores after playing up the backup file of administration module output described in receiving, cloud cluster rendering node group, be positioned at described remote servo end, be connected with described administration module of playing up, there is multiple rendering unit, respectively this rendering unit is mounted with the Rendering software accelerated based on GPU, after playing up the divided file of administration module dynamic assignment described in receiving, respectively this rendering unit performs respectively and plays up operation, and complete play up operation after generate and play up file play up administration module described in returning to.
Of the present invention based in the 3D rendering platform of GPU cloud cluster, described real-time monitoring transport module has an identification authenticating unit and expense computing unit, wherein, described identification authenticating unit is connected with described administration module of playing up by internet, keeps mechanism for carrying out certification to the identity of described client and setting up secured session; Described expense computing unit is connected with described administration module of playing up by internet, in order to calculated described file bag to be rendered rendering task needed for expense, in concrete embodiment, described real-time monitoring transport module is a client plug-in.
Of the present invention based in the 3D rendering platform of GPU cloud cluster, described administration module of playing up has a mapping association unit, be connected with described real-time monitoring transport module by internet, in order to the file bag to be rendered of monitoring transport module transmission in real time described in real-time reception, real time data renewal is carried out in amendment according to described real-time monitoring transport module, and passback plays up process to described real-time monitoring transport module.
Of the present invention based in the 3D rendering platform of GPU cloud cluster, described administration module of playing up has a backup units, with described DataBase combining, in order to copy the transmission of described real-time monitoring transport module file bag to be rendered and by respectively this exports to described database after playing up the predetermined format file that integrating documents becomes.
Of the present invention based in the 3D rendering platform of GPU cloud cluster, described in play up administration module there is a detecting unit, be connected with described cloud cluster rendering node group, in order to the load of each this rendering unit of detecting, and draw feed back to described in play up administration module.
Of the present invention based in the 3D rendering platform of GPU cloud cluster, described administration module of playing up has a dynamic allocating unit, be connected with described cloud cluster rendering node group, and according to the feedback information that described detecting unit draws, described file bag to be rendered is split, and those divided files are carried out being dynamically assigned to respectively this rendering unit.
Of the present invention based in the 3D rendering platform of GPU cloud cluster, described administration module of playing up has an integral unit, be connected with described cloud cluster rendering node group, play up file for what receive that respectively this rendering unit completes, and be predetermined format file by respectively this plays up integrating documents.
Of the present invention based in the 3D rendering platform of GPU cloud cluster, each rendering unit in described cloud cluster rendering node group at least comprises a CPU and the many groups GPU by this cpu monitor.
As mentioned above, 3D rendering platform based on GPU cloud cluster of the present invention compared with prior art, GPU is utilized to build distributed parallel cloud Rendering, and adopt the strategy of dynamic assignment, make user dynamically can submit rendering task on the supervisor of cloud cluster, use and play up mode based on the cloud of GPU, improve rendering speed significantly, save and played up cost, and the present invention's employing monitors transport module in real time in client installation, file bag real-time Transmission to be rendered is set up mapping association to remote servo end with it, and then in transfer rate, faster 8 ~ 9 times than traditional farm of playing up, the 3D model rendering speed such as three-dimensional cartoon in prior art, production of film and TV, furniture design that efficiently solve are crossed slow or are played up the problems such as high cost.
Accompanying drawing explanation
Fig. 1 is shown as the 3D rendering platform configuration diagram based on GPU cloud cluster of the present invention.
Embodiment
Below by way of specific instantiation, embodiments of the present invention are described, those skilled in the art can understand other advantages of the present invention and effect easily by content disclosed in the present specification.The present invention can also be implemented or be applied by embodiments different in addition, and the every details in this instructions also can based on different viewpoints and application, carries out various modification or change not deviating under spirit of the present invention.
Refer to Fig. 1, Fig. 1 is shown as the 3D rendering platform configuration diagram based on GPU cloud cluster of the present invention; It should be noted that, the diagram provided in the present embodiment only illustrates basic conception of the present invention in a schematic way, then only the assembly relevant with the present invention is shown in graphic but not component count when implementing according to reality and arbitrary shape, it is actual when implementing, and the kenel of each assembly and quantity can be a kind of change arbitrarily, and its assembly layout kenel also may be more complicated.
As shown in the figure, the invention provides a kind of 3D rendering platform based on GPU cloud cluster, be applied in the internet system built by client 1 and remote servo end 3, and described client 1 is preinstalled with the 3D modelling software carrying out 3D modeling and animation, it should be noted that, because 3D rendering platform of the present invention is applied in internet system, really as is known to the person skilled in the art, numerous client will be had in internet system, thus in FIG, also a label n (i.e. client n in diagram) has been used to show this actual conditions, but, for convenience of the principle setting forth the present invention, in the present embodiment, below by single client 1 for example is described, hereby state clearly.
The 3D rendering platform based on GPU cloud cluster of the present invention at least comprises: monitoring transport module 11 in real time, plays up administration module 31, database 32, cloud cluster rendering node group 33.
Described real-time monitoring transport module 11 is installed on described client 1, particularly, described real-time monitoring transport module 11 embeds in described 3D modelling software with the form of plug-in unit, in order to after described 3D modelling software Modling model, layout light and establishment material, these document scenes are packaged as file bag to be rendered, and by its bulk transfer to described remote servo end 3, and set up mapping association with described remote servo end 3;
In the present embodiment, described real-time monitoring transport module 11 has an identification authenticating unit 111 and expense computing unit 112, wherein, described identification authenticating unit 111 is connected with described administration module 31 of playing up by internet, keeps mechanism for carrying out certification to the identity of described client 1 and setting up secured session; Described expense computing unit 112 is connected with described administration module 31 of playing up by internet, in order to calculated described file bag to be rendered rendering task needed for expense.In the present embodiment, described real-time monitoring transport module 11 is a client plug-in.In concrete embodiment, the form of described client plug-in directly extends the 3D modeling softwares such as Maya, 3DsMax, Archi CAD, Digital Fusion, After Effects, Combustion, described client plug-in can submit rendering task in above-mentioned 3D Software for producing inside, facilitate the submission of appointing rendering task, decrease the time cost of user to greatest extent.
In concrete embodiment, in described identification authenticating unit 111, there is user and register login feature, after that is only having user to complete authentication, can do and submit file bag to be rendered to, check the progress of playing up, obtain the operations such as rendering result.
In concrete embodiment, described expense computing unit 112 in order to calculated described file bag to be rendered this rendering task needed for expense.Particularly, described expense computing unit 112 adopts following mode to provide the expense of this time transaction: in conjunction with GPU use number and GPU render time (by minute in units of) two factors, described expense computing unit 112 comprises an on-line payment function, when user accepts this time transaction, after completing on-line payment deposit, file bag to be rendered can be submitted to, check the progress of playing up, obtain the operations such as rendering result.
Described administration module 31 of playing up is positioned at described remote servo end 3, particularly, described administration module 31 of playing up is such as a high performance computing machine, described administration module 31 of playing up is connected with described real-time monitoring transport module 11 by internet, after file bag to be rendered in order to monitoring transport module 11 transmission in real time described in real-time reception, described file bag to be rendered being carried out backup to export, then exporting giving dynamic assignment after described file bag segmentation to be rendered.
Described administration module 31 of playing up also plays up file for what receive that respectively this rendering unit 331 or 33n complete, and be carry out backup after predetermined format file again to export by respectively this plays up integrating documents, then this predetermined format file is returned to described client 1, so that the user of client 1 obtains rendering result.
In the present embodiment, play up administration module 31 described in and at least include following unit: mapping association unit 311, backup units 312, detecting unit 313, dynamic allocating unit 314, and integral unit 315.
Described mapping association unit 311 is connected with described real-time monitoring transport module 11 by internet, in order to the file bag to be rendered of monitoring transport module 11 transmission in real time described in real-time reception, real time data renewal is carried out in amendment according to described real-time monitoring transport module 11, and passback plays up process to described real-time monitoring transport module 11.In other words, described real-time monitoring transport module 11 by with described mapping association unit 311 mapping association, carrying out submitting file bag to be rendered to, check the progress of playing up, obtain the operations such as rendering result.
Described backup units 312 is connected with described database 32, in order to copy the file bag to be rendered that described real-time monitoring transport module 11 transmits, described backup units 312 also for by respectively this exports to described database 32 after playing up the predetermined format file of integrating documents one-tenth, stores to make it.
Described detecting unit 313 is connected with described cloud cluster rendering node group 33, in order to the load of detecting respectively this rendering unit 331 or 33n, and draw feed back to described in play up administration module 31.In other words, described feedback information refers to the loading condition of respectively this rendering unit 331 or 33n, and rendering unit 331 few for load or 33n inventory are supplied to dynamic allocating unit 314 described above by described detecting unit 313, to make its dynamic assignment.
Described dynamic allocating unit 314 is connected with each rendering unit 33 to the 33n in described cloud cluster rendering node group 33, and according to the feedback information (loading condition of namely above-mentioned respectively this rendering unit 331 or 33n) that described detecting unit 313 draws, described file bag to be rendered is split, and carries out those divided files to be dynamically assigned to respectively this rendering unit 331 or 33n.In the present embodiment, described dynamic allocating unit 314 is split file bag to be rendered, then the file after segmentation is dynamically assigned to respectively this rendering unit 331 or 33n to get on, in a particular embodiment, described dynamic allocating unit 314 has two kinds to the mode that file bag to be rendered is split: one on a frame-by-frame basis carries out random division; Another kind divides in units of the successive frame of some.Just as above-mentioned, its dynamic allocation scheme is distributed according to the load of respectively this rendering unit 331 or 33n.
Described integral unit 315 is connected with described cloud cluster rendering node group 33, plays up file, and be predetermined format file by respectively this plays up integrating documents for what receive that respectively this rendering unit 331 or 33n complete.In the present embodiment, described predetermined format file is MID formatted file.
Described database 32 is positioned at described remote servo end 3, be connected with described administration module 31 of playing up, particularly, described database 32 is such as a high performance computing machine, it is connected with the described backup units 312 playing up administration module 31, store after playing up the backup file of backup units 312 output of administration module 31 described in receiving, extract in order to above-mentioned File lose or after damaging.In the present embodiment, its backup file stored is at least two kinds, a kind of file bag to be rendered being real-time monitoring transport module 11 and transmitting, another kind of for respectively this plays up the predetermined format file of integrating documents one-tenth.
Described cloud cluster rendering node group 33 is positioned at described remote servo end 2, particularly, described cloud cluster rendering node group 33 is such as a high performance computing machine group, it is connected with described administration module 31 of playing up, described cloud cluster rendering node group 33 has n many rendering unit 331 to 33n, in a particular embodiment, each rendering unit 331 or 33n are high performance computing machines, and this computing machine at least comprises a CPU and the many groups GPU by this cpu monitor.In other words, each rendering unit 331 or 33n are made up of a monokaryon or the CPU of multinuclear and the GPU of multi-set parallel, and each GPU has the concurrent operation unit being greater than 128 cores, such as, can adopt the GPU of NVidian.
Respectively this rendering unit 331 or 33n are mounted with the Rendering software accelerated based on GPU, such as based on the Rendering software nRay that GPU accelerates, this Rendering software nRay is based on the programming technique of CUDA, and its calculated amount automatically estimating every frame is played up to adopt the many GPU of single frames or multiframe list GPU.Respectively this rendering unit 331 or 33n are for after playing up the divided file of dynamic allocating unit 314 dynamic assignment of administration module 31 described in receiving, respectively this rendering unit 331 or 33n perform respectively and play up operation, and complete play up operation after generate and play up file to play up the integral unit 315 of administration module 31 described in returning to, to make after described integral unit 315 is integrated into MID formatted file, return to described client 1.
In the present invention, new data layout MID is taked to transmit.The result of calculation of the render farm that it is different from the past is certain image, and MID formatted file is the individual set close to the data representation of final image.After described real-time monitoring transport module 11 accepts MID formatted file, resolve final image result by existing modeling software.The length dimension of MID formatted file only has 10% of the length dimension of final image result, is very beneficial for, in transmission over networks, decreasing client bandwidth significantly.
And, play up administration module 31 in the present invention, cloud cluster rendering node group 33, database 32 adopt gigabit switch (not shown) to couple together, constitute the Ethernet of a gigabit.Whole network adopts distributed management mode, uses cloud computing technology to reduce offered load, realizes task scheduling.
In sum, 3D rendering platform based on GPU cloud cluster of the present invention utilizes GPU to build distributed parallel cloud Rendering, and adopt the strategy of dynamic assignment, make user dynamically can submit rendering task on the supervisor of cloud cluster, use and play up mode based on the cloud of GPU, improve rendering speed significantly, save and played up cost, and the present invention's employing monitors transport module in real time in client installation, file bag real-time Transmission to be rendered is set up mapping association to remote servo end with it, and then in transfer rate, faster 8 ~ 9 times than traditional farm of playing up, the 3D model rendering speed such as three-dimensional cartoon in prior art, production of film and TV, furniture design that efficiently solve are crossed slow or are played up the problems such as high cost.So the present invention compared with prior art, effectively overcomes various shortcoming of the prior art and tool high industrial utilization.
Above-described embodiment is illustrative principle of the present invention and effect thereof only, but not for limiting the present invention.Any personage haveing the knack of this technology all without prejudice under spirit of the present invention and category, can modify above-described embodiment or changes.Therefore, such as have in art usually know the knowledgeable do not depart from complete under disclosed spirit and technological thought all equivalence modify or change, must be contained by claim of the present invention.
Claims (3)
1. the 3D rendering platform based on GPU cloud cluster, be applied in the internet system built by client and remote servo end, and described client is preinstalled with the 3D modelling software carrying out 3D modeling and animation, it is characterized in that, it at least comprises:
Real-time monitoring transport module, be installed on described client and embed in described 3D modelling software with the form of plug-in unit, in order to after described 3D modelling software Modling model, layout light and establishment material, these document scenes are packaged as file bag to be rendered, and by its bulk transfer to described remote servo end, and set up mapping association with it;
Described real-time monitoring transport module has an identification authenticating unit and expense computing unit, wherein, described identification authenticating unit by internet with play up administration module and be connected, keep mechanism for carrying out certification to the identity of described client and setting up secured session; Described expense computing unit is connected with described administration module of playing up by internet, in order to calculated described file bag to be rendered rendering task needed for expense;
Play up administration module, be positioned at described remote servo end, be connected with described real-time monitoring transport module by internet, after real-time reception to the file bag to be rendered of described real-time monitoring transport module transmission, described file bag to be rendered is carried out backup to export, then export giving dynamic assignment after described file bag segmentation to be rendered, and play up file for what finish receiving, and be carry out backup after predetermined format file again to export by respectively this plays up integrating documents, then this predetermined format file is returned to described client;
Described administration module of playing up at least comprises: mapping association unit, backup units, detecting unit, dynamic allocating unit, and integral unit;
Described mapping association unit is connected with described real-time monitoring transport module by internet, in order to the file bag to be rendered of monitoring transport module transmission in real time described in real-time reception, real time data renewal is carried out in amendment according to described real-time monitoring transport module, and passback plays up process to described real-time monitoring transport module; Described backup units and DataBase combining, in order to copy the file bag to be rendered of described real-time monitoring transport module transmission, described backup units also for by respectively this exports to described database after playing up the predetermined format file of integrating documents one-tenth, stores to make it; Described detecting unit is connected with cloud cluster rendering node group, in order to detect the load of each rendering unit in cloud cluster rendering node group, and draw feed back to described in play up administration module; In described dynamic allocating unit and described cloud cluster rendering node group
each rendering unitconnect, and according to the feedback information that described detecting unit draws, described file bag to be rendered is split, and those divided files are carried out being dynamically assigned to respectively this rendering unit, it is on a frame-by-frame basis carry out random division that described dynamic allocating unit carries out segmentation to file bag to be rendered, or divides in units of the successive frame of some; Described integral unit is connected with described cloud cluster rendering node group, and play up file for what receive that respectively this rendering unit completes, and be predetermined format file by respectively this plays up integrating documents, described predetermined format file is MID formatted file;
Database, be positioned at described remote servo end, be connected with described administration module of playing up, store after playing up the backup file of administration module output described in receiving, described database is a high performance computing machine, it is connected with the described backup units playing up administration module, store after playing up the backup file of the backup units output of administration module described in receiving, lose in order to described backup file or extract after damage, the described backup file stored is two kinds, a kind of is the file bag to be rendered monitoring transport module transmission in real time, another kind of for respectively this plays up the predetermined format file of integrating documents one-tenth, and
Cloud cluster rendering node group, be positioned at described remote servo end, be connected with described administration module of playing up, there is multiple rendering unit, respectively this rendering unit is mounted with the Rendering software accelerated based on GPU, after playing up the divided file of administration module dynamic assignment described in receiving, respectively this rendering unit performs respectively and plays up operation, and complete play up operation after generate and play up file play up administration module described in returning to; Respectively this rendering unit is mounted with the Rendering software accelerated based on GPU, and this Rendering software is based on the programming technique of CUDA, and its calculated amount automatically estimating every frame is played up to adopt the many GPU of single frames or multiframe list GPU; Respectively this rendering unit is for after playing up the divided file of dynamic allocating unit dynamic assignment of administration module described in receiving, respectively this rendering unit performs respectively and plays up operation, and complete play up operation after generate and play up file to play up the integral unit of administration module described in returning to
,to make after described integral unit is integrated into MID formatted file, return to described client;
After described real-time monitoring transport module accepts described MID formatted file, resolve final image result by modeling software.
2. the 3D rendering platform based on GPU cloud cluster according to claim 1, is characterized in that: described real-time monitoring transport module is a client plug-in.
3. the 3D rendering platform based on GPU cloud cluster according to claim 1, is characterized in that: many groups GPU that each rendering unit in described cloud cluster rendering node group at least comprises a GPU and monitored by this GPU.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110005379.1A CN102592315B (en) | 2011-01-12 | 2011-01-12 | 3D rendering platform based on GPU cloud cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110005379.1A CN102592315B (en) | 2011-01-12 | 2011-01-12 | 3D rendering platform based on GPU cloud cluster |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102592315A CN102592315A (en) | 2012-07-18 |
| CN102592315B true CN102592315B (en) | 2015-04-08 |
Family
ID=46480899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110005379.1A Active CN102592315B (en) | 2011-01-12 | 2011-01-12 | 3D rendering platform based on GPU cloud cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102592315B (en) |
Families Citing this family (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103023959B (en) * | 2012-08-09 | 2015-10-28 | 江苏科技大学 | A kind of distribution rendering system and method |
| CN103106680B (en) * | 2013-02-16 | 2015-05-06 | 赞奇科技发展有限公司 | Implementation method for three-dimensional figure render based on cloud computing framework and cloud service system |
| CN103400415B (en) * | 2013-08-07 | 2016-03-02 | 赞奇科技发展有限公司 | Plane space structure three-dimensional digital model generates and the implementation method of online interaction automatically |
| CN103617062B (en) * | 2013-12-05 | 2016-09-07 | 山东大学 | The render farm Dynamic Deployment System of a kind of flexibility and method |
| CN104052803A (en) * | 2014-06-09 | 2014-09-17 | 国家超级计算深圳中心(深圳云计算中心) | Decentralized distributed rendering method and system |
| CN105319985A (en) * | 2014-08-01 | 2016-02-10 | 北京航天智控监测技术研究院 | Cloud smart simulation monitoring and management platform |
| US9520002B1 (en) | 2015-06-24 | 2016-12-13 | Microsoft Technology Licensing, Llc | Virtual place-located anchor |
| CN105976420B (en) * | 2015-08-28 | 2019-02-05 | 深圳市彬讯科技有限公司 | A kind of online rendering method and system |
| CN105205851B (en) * | 2015-09-18 | 2019-01-22 | 深圳华侨城文化旅游科技股份有限公司 | A kind of extraordinary film rendering method and system based on GPU supercomputer |
| CN105224325B (en) * | 2015-09-30 | 2019-03-12 | 传线网络科技（上海）有限公司 | Rendering method and device |
| US10292247B2 (en) | 2015-10-16 | 2019-05-14 | Delight Innovative Technologies Limited | Intelligent installation method of indoor lighting system |
| CN105597314B (en) * | 2015-10-29 | 2020-07-10 | 网易（杭州）网络有限公司 | Rendering system and method of 2D game and terminal equipment |
| CN105263050B (en) * | 2015-11-04 | 2018-01-12 | 山东大学 | Mobile terminal real-time rendering system and method based on cloud platform |
| CN105488837B (en) * | 2015-11-24 | 2019-06-04 | 成都云创互联信息技术有限公司 | Real-time off screen rendering method based on cloud computing, apparatus and system |
| US10304247B2 (en) | 2015-12-09 | 2019-05-28 | Microsoft Technology Licensing, Llc | Third party holographic portal |
| CN107526623B (en) * | 2016-06-22 | 2020-06-16 | 腾讯科技（深圳）有限公司 | Data processing method and device |
| CN109544670B (en) * | 2018-11-26 | 2023-06-06 | 深圳市瑞云科技有限公司 | Cloud rendering method for improving lost graph |
| CN110660118A (en) * | 2019-09-25 | 2020-01-07 | 网易（杭州）网络有限公司 | Game asset processing method, device, equipment and readable storage medium |
| CN111494936A (en) * | 2020-02-12 | 2020-08-07 | 阿里巴巴集团控股有限公司 | Picture rendering method, device, system and storage medium |
| CN111352243A (en) * | 2020-03-31 | 2020-06-30 | 北京塞傲时代信息技术有限公司 | AR remote rendering system and method based on 5G network |
| CN111739141B (en) * | 2020-08-12 | 2021-02-09 | 绿漫科技有限公司 | 3D cloud rendering method for light terminal |
| CN112163986A (en) * | 2020-09-28 | 2021-01-01 | 山东黄金矿业(莱州)有限公司三山岛金矿 | Distributed processing method for underground logging and mining three-dimensional data of metal mine |
| CN112669428B (en) * | 2021-01-06 | 2024-06-25 | 南京亚派软件技术有限公司 | BIM model rendering method based on cooperation of server and client |
| CN113269856A (en) * | 2021-05-12 | 2021-08-17 | 南京邮电大学 | Data parallel visualization graph rendering method and system based on distributed cloud storage |
| CN114077508B (en) * | 2022-01-19 | 2022-10-11 | 维塔科技(北京)有限公司 | Remote image rendering method and device, electronic equipment and medium |
| CN114998500B (en) * | 2022-07-20 | 2022-11-18 | 南京芯驰半导体科技有限公司 | Rendering system and method based on SOC platform |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101087297A (en) * | 2006-06-06 | 2007-12-12 | 华为技术有限公司 | Method and device for transmitting billing information |
| CN101587583A (en) * | 2009-06-23 | 2009-11-25 | 长春理工大学 | The farm of playing up based on the GPU cluster |
| CN101686458A (en) * | 2008-09-28 | 2010-03-31 | 华为技术有限公司 | Terminal configuration, management method and terminal device |
| CN101933041A (en) * | 2008-02-01 | 2010-12-29 | 微软公司 | Graphics remoting architecture |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8253732B2 (en) * | 2008-01-03 | 2012-08-28 | International Business Machines Corporation | Method and system for remote visualization client acceleration |
-
2011
- 2011-01-12 CN CN201110005379.1A patent/CN102592315B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101087297A (en) * | 2006-06-06 | 2007-12-12 | 华为技术有限公司 | Method and device for transmitting billing information |
| CN101933041A (en) * | 2008-02-01 | 2010-12-29 | 微软公司 | Graphics remoting architecture |
| CN101686458A (en) * | 2008-09-28 | 2010-03-31 | 华为技术有限公司 | Terminal configuration, management method and terminal device |
| CN101587583A (en) * | 2009-06-23 | 2009-11-25 | 长春理工大学 | The farm of playing up based on the GPU cluster |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102592315A (en) | 2012-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102592315B (en) | 3D rendering platform based on GPU cloud cluster | |
| CN103106680B (en) | Implementation method for three-dimensional figure render based on cloud computing framework and cloud service system | |
| US11227448B2 (en) | Cloud-centric platform for collaboration and connectivity on 3D virtual environments | |
| US8497865B2 (en) | Parallel graphics system employing multiple graphics processing pipelines with multiple graphics processing units (GPUS) and supporting an object division mode of parallel graphics processing using programmable pixel or vertex processing resources provided with the GPUS | |
| CN101587583A (en) | The farm of playing up based on the GPU cluster | |
| CN104952096A (en) | CPU and GPU hybrid cloud rendering method, device and system | |
| CN103021023A (en) | Three-dimensional scene construction method based on browser | |
| CN109086134A (en) | A kind of operation method and device of deep learning operation | |
| CN111932663B (en) | Parallel drawing method based on multi-level asymmetric communication management | |
| Behr et al. | webvis/instant3dhub: Visual computing as a service infrastructure to deliver adaptive, secure and scalable user centric data visualisation | |
| US20220101619A1 (en) | Cloud-centric platform for collaboration and connectivity on 3d virtual environments | |
| KR20170032333A (en) | Method and system for converting an existing 3d model into graphical data | |
| CN116977523B (en) | STEP format rendering method at WEB terminal | |
| Eilemann et al. | Equalizer 2.0–convergence of a parallel rendering framework | |
| CN109727376A (en) | Generate the method, apparatus and selling apparatus of configuration file | |
| CN113779040A (en) | Progressive online high-precision map service engine system | |
| Jung et al. | Declarative 3D Approaches for Distributed Web-based Scientific Visualization Services. | |
| CN116433818A (en) | Cloud CPU and GPU parallel rendering method | |
| Jensen et al. | An efficient system for collaboration in tele-immersive environments | |
| CN201845538U (en) | Multi-node image rendering synthesizer | |
| CN113129205A (en) | Electronic equipment and computer system | |
| Attila et al. | Surface models view designs with 3DS MAX software | |
| CN104616339A (en) | Scene data scheduling method of Web3D virtual reality system | |
| Ellis et al. | SVGPU: real time 3D rendering to vector graphics formats. | |
| Mwalongo | Interactive web-based visualization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| DD01 | Delivery of document by public notice |
Addressee: Shanghai Digital Information Technology Co., Ltd. Ye Minya Koorda Document name: Notification of Publication and of Entering the Substantive Examination Stage of the Application for Invention |
|
| ASS | Succession or assignment of patent right |
Owner name: CUDATEC DEVELOPMENT CO., LTD. Free format text: FORMER OWNER: SHANGHAI CUDA DIGITAL INFORMATION TECHNOLOGY CO., LTD. Effective date: 20130407 Free format text: FORMER OWNER: CUDATEC DEVELOPMENT CO., LTD. Effective date: 20130407 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 201101 XUHUI, SHANGHAI TO: 213022 CHANGZHOU, JIANGSU PROVINCE |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20130407 Address after: 213022 Jiangsu city of Changzhou province Taihu New District Road No. 23 building 9-2 Applicant after: Cudatec Development Co., Ltd. Address before: 201101, room 4, building 315, 403 West Guangyuan Road, Shanghai, Xuhui District Applicant before: Shanghai Cuda Digital Information Technology Co., Ltd Applicant before: Cudatec Development Co., Ltd. |
|
| DD01 | Delivery of document by public notice |
Addressee: Ye Minya Document name: Notification of Passing Examination on Formalities |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C56 | Change in the name or address of the patentee | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 213022 Jiangsu city of Changzhou province Taihu New District Road No. 23 building 9-2 Patentee after: JIANGSU CUDATEC CO., LTD. Address before: 213022 Jiangsu city of Changzhou province Taihu New District Road No. 23 building 9-2 Patentee before: Cudatec Development Co., Ltd. |