CN106447755A - Animation rendering system - Google Patents
Animation rendering system Download PDFInfo
- Publication number
- CN106447755A CN106447755A CN201610856424.7A CN201610856424A CN106447755A CN 106447755 A CN106447755 A CN 106447755A CN 201610856424 A CN201610856424 A CN 201610856424A CN 106447755 A CN106447755 A CN 106447755A
- Authority
- CN
- China
- Prior art keywords
- task
- node apparatus
- unit
- tasks carrying
- carrying node
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/005—General purpose rendering architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/28—Indexing scheme for image data processing or generation, in general involving image processing hardware
Abstract
The invention provides an animation rendering system based on a distributed computer system. The animation rendering system comprises at least one main task node device connected through a computer network and multiple task executing node devices, wherein the main task node devices are configured to divide a rendering task into multiple task units and distributing the task to the executing node devices, and the executing node devices are configured to complete the task units. The invention further provides a rendering method based on cloud computing, namely distributed processing of cloud computing and storage advantages are utilized to divide one or more rendering tasks, rendering is performed through the nodes in a cluster simultaneously, and the purposes of rapidly rendering, shortening the manufacturing time and reducing the cost are achieved.
Description
Technical field
The present invention relates to animation field is and in particular to a kind of animation rendering system.
Background technology
The specially good effect of 3D film makes our admirations, and the animation effect that these are extremely dazzled is behind, but has extremely complex technology
Constitute and the calculating of magnanimity and storage resource consumption, be either all very high to artificial or the requirement to equipment.With
Data illustrating, a specially good effect film perfect in workmanship, the resolution about 2k-4k of every frame, processed big using the unit of 8 core CPU
General need 2 hours, and whole movie render time of getting off needs 2800000 hours, nearly 300 years, if it is desired to by Production Time
Control in 1 year, then need the machine of 300 same performances and 300 qualified designers of tool, the big threshold of its cost
Height have some idea of.
Meanwhile, it is how to appoint relatively independent complete rendering based on the matter of utmost importance facing that renders of cloud environment
Business is cut into several pieces, work compound on multiple stage machine.The mode of cutting has a lot, is such as cut according to animation duration
Point, or divide equally according to number of machines, but these high-performance, high efficiency and the dynamic scalable that cannot meet parallel rendering.For example
According to animation duration cutting, the frame number that animation is comprised each second is different, and a simple scene may only need to
Several pictures, and a scene extremely dazzled will switch tens pictures in 1 second, if so carrying out cutting by animation duration,
Load imbalance and frequent communication between node certainly will be led to.And the effect that cannot embody work compound is divided equally according to number of machines
Really, as broad as long with hundreds of unit execution.
Content of the invention
It is an object of the invention to provide a kind of animation rendering scheme based on Distributed Computer System,
According to the present invention, a kind of animation rendering system, it is used for completing rendering task, this system includes at least one main task
Node apparatus and multiple tasks execution node apparatus, wherein this main task node apparatus and this tasks carrying node apparatus pass through meter
Calculation machine network connection,
This main task node apparatus includes task cutting unit and task allocation unit, wherein this task cutting unit configuration
It is that this rendering task is divided into multiple TU task units comprising one or more number picture, this task allocation unit is configured to
The plurality of TU task unit is separately dispensed into the plurality of tasks carrying node apparatus,
This tasks carrying node apparatus includes rendering performance element and communication unit, and wherein this renders performance element and is configured to
Execution is configured to after this TU task unit completes to this master by the TU task unit of this main task node apparatus distribution, this communication unit
Task node device transmits completion signal.
Wherein, this communication unit is further configured to during executing this TU task unit, at interval of a period of time to this
Main task node apparatus send cue.
Wherein, this main task node apparatus is configured to distribute to this TU task unit and is sent to complete signal and contact letter
Number tasks carrying node apparatus.
Wherein, this main task node apparatus is configured to work as and does not receive this contact letter from tasks carrying node apparatus
Number when, this tasks carrying node apparatus will be distributed to and be reassigned to other tasks carrying node apparatus.
Wherein, this task cutting unit is configured to determine that each TU task unit is comprised according to the complexity of this rendering task
Number of pictures, wherein said complexity determines according to executing the unit resource consumption needed for this rendering task.
Wherein, each described tasks carrying node apparatus also includes load balancing unit, each described tasks carrying node
This load balancing unit of device is constructed by described computer network communication, and wherein, each this load balancing unit includes：
Loading information module, is configured to obtain the load data of this tasks carrying node apparatus, and can be according to other tasks carrying sections
This load data is transmitted to the tasks carrying node apparatus sending this request by the request of point device by this computer network；Appoint
Business shift module, is configured to when the load data of this tasks carrying node apparatus is less than first threshold, will be apart from this this task
Execution node apparatus are recently and load data renders work more than the part of another tasks carrying node of Second Threshold and transfers to
Described tasks carrying node apparatus execution.
Wherein, this tasks carrying node apparatus is configured to send preparatory signal to notify this master to this main task node apparatus
Task node distributes TU task unit.
Thus, the present invention proposes a kind of rendering intent based on cloud computing, that is, utilize cloud computing distributed treatment and
Storage advantage, one or more rendering task is carried out being divided into the essentially identical TU task unit of multiple complexities, and each is appointed
Resource consumption needed for business unit is essentially identical, it is to avoid in prior art, rendering task distributes unbalanced shortcoming.According to this
Bright system, is rendered by each node in cluster simultaneously, thus reaching the purpose of Fast rendering, shortening Production Time and cost.
In addition, can balancing the load between each task node, allocating rendering task, it is to avoid host node substantial amounts of input/output expense,
Simultaneously also can system for recycling resource, accelerate render process.
Brief description
Below by the way of clearly understandable, preferred implementation is described with reference to the drawings, to above-mentioned characteristic, technical characteristic,
Advantage and its implementation are further described.
Fig. 1 is the schematic diagram of the animation rendering system according to one embodiment of the invention.
Drawing reference numeral explanation：
100 main task node apparatus
110 task cutting units
120 task allocation unit
200,200-1,200-2 tasks carrying node apparatus
210 communication units
220 render performance element
230 load balancing unit
232 loading information module
234 task shift modules
300 computer networks
Specific embodiment
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, brief description will be compareed below
The specific embodiment of the present invention.It should be evident that drawings in the following description are only some embodiments of the present invention, for
For those of ordinary skill in the art, on the premise of not paying creative work, other can also be obtained according to these accompanying drawings
Accompanying drawing, and obtain other embodiments.
A kind of animation rendering system, executes node apparatus including at least one main task node apparatus 100 and multiple tasks
200, wherein this main task node apparatus 100 and this tasks carrying node apparatus 200 are connected by computer network.Show in Fig. 1
In the embodiment going out, for illustrative purpose, main task node apparatus and two tasks carrying node apparatus are only shown,
But those skilled in the art will appreciate that, in other examples, can more main task node apparatus and tasks carrying
Node apparatus.
In addition, described computer network can be any suitable computer network, it can be in this main task node
Transmission information between device and tasks carrying node apparatus.For example, this computer network can be, including but not limited to, local
Net, wide area network, cable network, wireless network.
As shown in figure 1, this main task node apparatus 100 includes task cutting unit 110 and task allocation unit 120, should
Being configured between task cutting unit 110 and this task allocation unit 120 can be with exchange data information.
According to the embodiment shown in Fig. 1, for a rendering task, this task cutting unit 110 is configured to render this
Task is divided into multiple tasks unit, and the data of the picture wherein rendering required for each TU task unit is identical.Further, for
One specific rendering task, the image data that each TU task unit is comprised determines according to the complexity of this rendering task.
The complexity of rendering task is to be determined by the unit resource consumption executing required for this rendering task.Unit resource consumption is got over
Greatly, complexity is higher, and the number of pictures that each TU task unit is comprised is lower, and vice versa.
The purpose of segmentation is rendering task to be decomposed into most unit assignments divide equally and size to fit, therefore, ability
Field technique personnel will appreciate that, for some rendering tasks it is possible to not be that each TU task unit has identical figure
Piece number.For example, if a rendering task comprising 430 pictures is divided into 20 TU task units, most tasks
The number of pictures of unit is all 21, but also the number of pictures of a TU task unit is 10.
The TU task unit split is distributed to this tasks carrying node apparatus 200 by this task allocation unit 120, in order to complete
Become rendering task.It will be appreciated by those skilled in the art that in one example, can be by the data is activation of TU task unit to accordingly
Tasks carrying node apparatus 200.Or, in another example, TU task unit may be located at a single storage device
On, for example, it is connected in the storage server of computer network, the labelling of TU task unit is sent to phase by task allocation unit 120
The tasks carrying node apparatus 200 answered, then, tasks carrying node apparatus 200 are using this labeled data removing TU task unit.
Here, in order to make it easy to understand, the data of described TU task unit refers to the data that the needs execution that TU task unit is comprised renders.
Each tasks carrying node apparatus 200 includes each other can the communication unit 210 of data exchange and render performance element
220.For convenience of description, in the following description, will stress to describe task executing units 200-1, other tasks are held
Row unit also has identical configuration and function.
After the TU task unit obtaining the distribution of this main task node apparatus, this renders performance element 220 and starts execution and renders
Work.Meanwhile, this communication unit 210 sends cue at interval of certain time to this main task node apparatus 100, shows this
Tasks carrying node apparatus 200 are gone out active state.
Complete after rendering work of described TU task unit when this renders performance element 220, this communication unit 210 is to this director
Business node apparatus 100 send idle signal signal, then, another TU task unit is distributed to this by this main task node apparatus 100
Business execution node apparatus 200-1.
The transmission interval of described cue can determine according to concrete application, for example, in seconds, or with millisecond meter.
If this main task node unit 100 does not receive tasks carrying node apparatus 200-1 and sends cue, will
Originally the TU task unit distributing to tasks carrying node apparatus 200-1 is reassigned to another tasks carrying node apparatus, for example,
200-2, again to complete this TU task unit.
One tasks carrying node apparatus accessing this computer network can send to this main task execution node apparatus
Preparatory signal, thus accelerate this rendering system.So, TU task unit can be distributed to this task and hold by this main task node apparatus
Row node apparatus.On the other hand, if tasks carrying node apparatus can actively stop sending out to this main task node apparatus
Send cue, such main task node apparatus just no longer distribute TU task unit to this tasks carrying node apparatus.
Based on such mechanism, can flexibly increase or minimizing system in tasks carrying node unit quantity.One side
Face is adapted to the rendering task of multiple loads, and for example, when the complexity of rendering task is higher, that is, unit consumption resource is more
When, the quantity of node can be increased, faster to complete rendering task, and when rendering task is fairly simple, it is possible to reduce participate in
Number of nodes, thus save resources, improve the resource utilization of individual node.
In some examples, this preparatory signal and this idle signal can be same signals it is therefore an objective to notify main task
Node apparatus can receive TU task unit at any time.And in other examples, preparatory signal is different signals from idle signal,
Tasks carrying node apparatus send preparatory signal and show newly to add this rendering system can receive TU task unit, and send idle letter
Number show to complete a TU task unit.
Each tasks carrying node apparatus 200 also includes load balancing unit 230, is constructed by this computer network and leads to
News.Each load balancing unit 230 includes loading information module 232 and task shift module 234.
Loading information module 232 can obtain tasks carrying node apparatus 200 load data of itself, and can basis
The request of other tasks carrying node apparatus and be sent to this load data of itself sends the tasks carrying node dress of request
Put.For example, the loading information module of tasks carrying node apparatus 200-1 obtains the load data of this node apparatus 200-1 itself,
When the load data of tasks carrying node apparatus 200-2 acquisition request node apparatus 200-1, this loading information module can be by
The load data of node apparatus 200-1 is sent to node apparatus 200-2.
One tasks carrying node apparatus, such as 200-1, on task shift module 234 this node TU task unit
When will complete, that is, load data is reduced to below the first threshold of setting, and such as CPU usage is reduced to 20%, then obtains
Nearby multiple tasks execute the load data of node apparatus, and check whether their load data is more than Second Threshold, example
As CPU usage is more than 60%, if it exceeds this Second Threshold, then by that closest tasks carrying node apparatus
Part renders work and transfers to the execution of this node apparatus.
With reference to Fig. 1, for example, if the CPU usage of tasks carrying node apparatus 200-1 is less than 20%, therein
Business shift module obtains the CPU usage of other neighbouring tasks carrying node apparatus.For node apparatus 200-2, therein
The request that the load data of node apparatus 200-2 answers node apparatus 200-1 is sent to this node apparatus by loading information module
200-1.If the CPU usage of node apparatus 200-2 is more than 60%, the task shift module of node apparatus 200-1 just will
The part of node apparatus 200-2 renders work and transfers to node apparatus 200-1 execution.
This mechanism can balance the load between each node.Because the performance of node apparatus is different, it completes complexity
The time spending essentially identical TU task unit is different with resource consumption, especially for Distributed Computer System, wherein each
The hardware performance of node has differences.The strong node of performance can be rapidly completed task, conversely, the weak node needs of performance are longer
Time complete same TU task unit.
Under normal circumstances, high performance tasks carrying node apparatus can be to new the appointing of main task node apparatus acquisition request
Business unit.But, when TU task unit is distributed by main task node, or, the request that main task unit receives too many and
When having little time to process, high performance node is practically at idle state, has both caused the waste of resource, nor it is whole to improve system
The processing speed of body.Using this load balancing unit, high performance tasks carrying node apparatus can complete more to render work
Make, improve the overall processing speed of system.
It should be noted that above-described embodiment all can independent assortment as needed.The above is only the preferred of the present invention
Embodiment it is noted that for those skilled in the art, in the premise without departing from the principle of the invention
Under, some improvements and modifications can also be made, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (7)
1. a kind of animation rendering system, is used for completing rendering task it is characterised in that including at least one main task node apparatus
Execute node apparatus with multiple tasks, wherein this main task node apparatus and this tasks carrying node apparatus pass through computer network
Connect,
Wherein, this main task node apparatus includes task cutting unit and task allocation unit, and wherein this task cutting unit is joined
It is set to and this rendering task is divided into multiple TU task units comprising one or more number picture, this task allocation unit configures
It is that the plurality of TU task unit is separately dispensed into the plurality of tasks carrying node apparatus,
Wherein, this tasks carrying node apparatus includes rendering performance element and communication unit, and wherein this renders performance element configuration
The TU task unit being distributed by this main task node apparatus for execution, this communication unit is configured to after this TU task unit completes to this
Main task node apparatus transmit completion signal.
2. animation rendering system according to claim 1 is it is characterised in that this communication unit is further configured in execution
During this TU task unit, send cue at interval of a period of time to this main task node apparatus.
3. animation rendering system according to claim 2 is it is characterised in that this main task node apparatus is configured to this
Business unit distributes to the tasks carrying node apparatus being sent to complete signal and cue.
4. animation rendering system according to claim 2 is it is characterised in that this main task node apparatus is configured to when not having
When tasks carrying node apparatus receive this cue, this tasks carrying node apparatus will be distributed to and be reassigned to
Other tasks carrying node apparatus.
5. animation rendering system according to claim 1 is it is characterised in that this task cutting unit is configured to according to this wash with watercolours
The complexity of dye task determines the number of pictures that each TU task unit is comprised, and wherein said complexity renders according to executing this
The unit resource consumption of required by task determines.
6. animation rendering system according to claim 1 is it is characterised in that each described tasks carrying node apparatus also wraps
Include load balancing unit, this load balancing unit of each described tasks carrying node apparatus is constructed by described computer network
Network communicates, and wherein, each this load balancing unit includes：
Loading information module, is configured to obtain the load data of this tasks carrying node apparatus, and can be held according to other tasks
This load data is transmitted by this computer network and fills to the tasks carrying node sending this request by the request of row node apparatus
Put；
Task shift module, is configured to when the load data of this tasks carrying node apparatus is less than first threshold, will be apart from this
This tasks carrying node apparatus are recently and load data renders work more than the part of another tasks carrying node of Second Threshold
Transfer to described tasks carrying node apparatus execution.
7. animation rendering system according to claim 1 is it is characterised in that this tasks carrying node apparatus is configured to this
Main task node apparatus send preparatory signal to notify this main task node distribution TU task unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610856424.7A CN106447755A (en) | 2016-09-27 | 2016-09-27 | Animation rendering system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610856424.7A CN106447755A (en) | 2016-09-27 | 2016-09-27 | Animation rendering system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106447755A true CN106447755A (en) | 2017-02-22 |
Family
ID=58169455
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610856424.7A Pending CN106447755A (en) | 2016-09-27 | 2016-09-27 | Animation rendering system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106447755A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019006937A1 (en) * | 2017-07-04 | 2019-01-10 | 武汉斗鱼网络科技有限公司 | Virtual gift presentation method and apparatus, server, and storage medium |
| CN111142649A (en) * | 2019-12-25 | 2020-05-12 | 北京金山安全软件有限公司 | Wearable device performance optimization method and device and electronic device |
| CN114205359A (en) * | 2022-01-27 | 2022-03-18 | 腾讯科技（深圳）有限公司 | Video rendering coordination method, device and equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103023959A (en) * | 2012-08-09 | 2013-04-03 | 江苏科技大学 | Distributed rendering system and method |
| CN104468826A (en) * | 2014-12-25 | 2015-03-25 | 广东威创视讯科技股份有限公司 | Distributed rendering method, device and system |
-
2016
- 2016-09-27 CN CN201610856424.7A patent/CN106447755A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103023959A (en) * | 2012-08-09 | 2013-04-03 | 江苏科技大学 | Distributed rendering system and method |
| CN104468826A (en) * | 2014-12-25 | 2015-03-25 | 广东威创视讯科技股份有限公司 | Distributed rendering method, device and system |
Non-Patent Citations (3)
| Title |
|---|
| 廖宏建等: "基于云计算的动漫渲染实验平台研究与实现", 《实验室研究与探索》 * |
| 虞勤等: "基于云计算的三维动画渲染系统研究", 《中国有线电视》 * |
| 魏三强: "云计算技术在3D动画渲染中的应用", 《吉林师范大学学报(自然科学版)》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019006937A1 (en) * | 2017-07-04 | 2019-01-10 | 武汉斗鱼网络科技有限公司 | Virtual gift presentation method and apparatus, server, and storage medium |
| CN111142649A (en) * | 2019-12-25 | 2020-05-12 | 北京金山安全软件有限公司 | Wearable device performance optimization method and device and electronic device |
| CN114205359A (en) * | 2022-01-27 | 2022-03-18 | 腾讯科技（深圳）有限公司 | Video rendering coordination method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11477255B2 (en) | Hybrid network system, communication method and network node | |
| US10572290B2 (en) | Method and apparatus for allocating a physical resource to a virtual machine | |
| CN115328663B (en) | Method, device, equipment and storage medium for scheduling resources based on PaaS platform | |
| CN108519917B (en) | Resource pool allocation method and device | |
| CN114281521B (en) | Method, system, equipment and medium for optimizing deep learning heterogeneous resource communication efficiency | |
| CN114070739B (en) | Cluster deployment method, device, equipment and computer readable storage medium | |
| CN106447755A (en) | Animation rendering system | |
| CN105227489A (en) | A kind of bandwidth management method and electronic equipment | |
| CN103747107A (en) | Compatible cloud operating platform and realizing method thereof | |
| CN104598316A (en) | Storage resource distribution method and device | |
| CN111078516A (en) | Distributed performance test method and device and electronic equipment | |
| CN111427822A (en) | Edge computing system | |
| CN105786447A (en) | Method and apparatus for processing data by server and server | |
| CN106059940A (en) | Flow control method and device | |
| CN103108000A (en) | Task synchronization method and system and host node and work nodes in system | |
| CN108282526A (en) | Server dynamic allocation method and system between double clusters | |
| CN109729113A (en) | Manage method, server system and the computer program product of dedicated processes resource | |
| CN106325995A (en) | GPU resource distribution method and system | |
| AT512665B1 (en) | Method and apparatus for forming software fault containment units in a distributed real-time system | |
| CN112346980B (en) | Software performance testing method, system and readable storage medium | |
| CN106776014A (en) | Parallel acceleration method and system in Heterogeneous Computing | |
| CN106682198B (en) | Method and device for realizing automatic database deployment | |
| CN109714124B (en) | Time synchronization system and method for test system | |
| CN103973793A (en) | Distributed aviation electronic testing system | |
| CN109639599B (en) | Network resource scheduling method and system, storage medium and scheduling device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170222 |