CN107274471A - It is a kind of to dispatch system based on rendering parallel multipriority queue offline in real time - Google Patents

It is a kind of to dispatch system based on rendering parallel multipriority queue offline in real time Download PDF

Info

Publication number
CN107274471A
CN107274471A CN201710453490.4A CN201710453490A CN107274471A CN 107274471 A CN107274471 A CN 107274471A CN 201710453490 A CN201710453490 A CN 201710453490A CN 107274471 A CN107274471 A CN 107274471A
Authority
CN
China
Prior art keywords
rendering
offline
task
priority
render
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.)
Granted
Application number
CN201710453490.4A
Other languages
Chinese (zh)
Other versions
CN107274471B (en
Inventor
颜强华
胡少雄
鲁四喜
胡鹏
王国彬
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tubatu Group Co Ltd
Original Assignee
Shenzhen Bincent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Bincent Technology Co Ltd filed Critical Shenzhen Bincent Technology Co Ltd
Priority to CN201710453490.4A priority Critical patent/CN107274471B/en
Publication of CN107274471A publication Critical patent/CN107274471A/en
Application granted granted Critical
Publication of CN107274471B publication Critical patent/CN107274471B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/48Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806Task transfer initiation or dispatching
    • G06F9/4843Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T15/003D [Three Dimensional] image rendering
    • G06T15/005General purpose rendering architectures

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computer Graphics (AREA)
  • General Engineering & Computer Science (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The invention discloses a kind of based on parallel multipriority queue scheduling system is rendered offline in real time, the scheduling system includes:Type detection module is rendered, the render request type of detection rendering task is real-time rendering request or offline render request;Resource state detection module, when render request type is that real-time rendering is asked, the state for detecting current rendering resources is busy or idle and points out user's selection to render or real-time rendering offline, if offline render request, then without the state-detection of rendering resources;Rendering task receiving module, the priority that renders for receiving rendering task and the rendering task judges information;Priority judge module, judges the priority of user's rendering task, and is stored in corresponding priority query;Rendering module, rendering task is obtained according to priority and is rendered from high to low.The present invention dynamically distributes the priority of rendering task according to user's request and resource status, improves Consumer's Experience, improves resource utilization.

Description

It is a kind of to dispatch system based on rendering parallel multipriority queue offline in real time
Technical field
The present invention relates to 3D Renderings field, more particularly to it is a kind of based on rendering parallel multipriority team offline in real time Row scheduling system.
Background technology
The current high speed development with virtual reality technology, produces a large amount of calculating tasks related based on virtual reality. Virtual Decoration Industry, generates a large amount of 3D house ornamentation design softwares that What You See Is What You Get is realized using virtual reality technology.Produce therewith Raw substantial amounts of image rendering mission requirements, but the substantial amounts of demand that renders can't be evenly distributed to different time sections, thus produce A large amount of situations for rendering user's wait are given birth to.Such software does not all divide different priorities to carry out task processing on current market, But the implementation first rendered first is used, cause very poor Consumer's Experience.
The content of the invention
To solve above-mentioned technical problem, the invention provides a kind of based on rendering parallel multipriority team offline in real time Row scheduling system, method proposed by the present invention solves rendering resources under prior art and wasted, the problem of rendering experience difference.
The present invention realizes that the technical scheme that above-mentioned technique effect is used is:
A kind of to dispatch system based on rendering parallel multipriority queue offline in real time, the scheduling system includes:
Type detection module is rendered, for detecting that the render request type for the rendering task that rendering task pond is sent is real-time Render request or offline render request;
Resource state detection module, is connected with the type detection module that renders, and described type detection is rendered for receiving The feedback information of module, when the render request type of the rendering task for rendering type detection module feedback please for offline render Ask, then the offline mark offline that the resource state detection module is put in the rendering task data is 1, without rendering money The rendering task data after processing, are then sent to task recipient, type detection are rendered when described by the state-detection in source The render request type of the rendering task of module feedback is asked for real-time rendering, then the resource state detection module detection is current The state of rendering resources is busy or idle and points out user's selection to render or real-time rendering offline, then the wash with watercolours after processing Dye task data is sent to task recipient;
Rendering task receiving module, as task recipient, is connected, for receiving wash with watercolours with the resource state detection module Dye task and the priority that renders of the rendering task judge information;
Priority judge module, is connected with the rendering task receiving module, for judging that the rendering task receives mould The priority of user's rendering task in block, and according to the priority in deposit priority query pond;
Rendering module, is connected with the priority query pond, obtains rendering task from high to low according to priority and carries out wash with watercolours Dye.
It is above-mentioned to dispatch system, in addition to reminding module based on rendering parallel multipriority queue offline in real time, it is described It is that real-time rendering is asked or offline that prompting template, which is used in the render request type that detection rendering task pond sends rendering task, Before render request, the prompt message of Primary Stage Data preparation is sent.
It is above-mentioned to dispatch system, the resource state detection module based on rendering parallel multipriority queue offline in real time Including detection request transmitting unit, the state-detection for sending rendering resources is asked, and the rendering task receiving module is received The state-detection is asked and counts the rendering resources quantity of current idle, when the quantity of idle rendering resources is more than 0, is returned Idle condition gives the detection request transmitting unit, when idle rendering resources are equal to 0, returns to busy state to the detection Request transmitting unit.
It is above-mentioned to dispatch system based on rendering parallel multipriority queue offline in real time, send single in the detection request Member is sent before the state-detection request of rendering resources, and system is initialized to all machine resources that render, and acquiescence is all It is the free time to render machine resources, and preserves current all idle conditions for rendering machine, is appointed when rendering machine and obtaining to render After business, the state for rendering machine is set to busy state, and preserve the busy state for rendering machine.
It is above-mentioned to dispatch system, the resource state detection module based on rendering parallel multipriority queue offline in real time Detect the states of current rendering resources to be busy or idle and point out user's selection is offline to render or real-time rendering is specifically included Step:
If the resource state detection module return for busy state, point out the current rendering resources of user busy, The mode that can be rendered offline carries out task processing, if user's selection is rendered offline, in rendering task data The offline mark offline that renders is revised as 1, if user selects real-time rendering, rendering task data are not processed;
Return if idle condition, then rendering task data are not processed.
It is above-mentioned to dispatch system based on rendering parallel multipriority queue offline in real time, initiate accurate before rendering task request Standby Primary Stage Data includes the house type data being embodied obtained after house house type is completed:House layout structure, model pendulum Put, furred ceiling is put, the regulation of intensity of light and color.
Above-mentioned to dispatch system based on rendering parallel multipriority queue offline in real time, the data of rendering task include: Layout structure data, model data, furred ceiling data, light information data and offline render identify offline, described to render offline Mark offline is defaulted as 0, is designated not offline.
It is above-mentioned to dispatch system based on rendering parallel multipriority queue offline in real time, carry out rendering priority judgement User profile has:User type type, user gradation level.
It is above-mentioned to dispatch system based on rendering parallel multipriority queue offline in real time, receive the data of rendering task Afterwards, judging the reference value of the priority of the rendering task is:User type type, user gradation level and offline mark offline。
It is above-mentioned to dispatch system, the create-rule of priority query based on rendering parallel multipriority queue offline in real time For:
The offline mark offline of S1, first detection;
If S2, offline mark offline are equal to 1, the rendering task is put into lowest priority queue quene_ offline;
If S3, offline mark offline are 0, carried out rendering team according to user type type and user gradation level The judgement of row priority, wherein, user type type has value 0 and 1, and user gradation level has value 0 and 1, priority query's form For:Quene_type_level, it is prioritized to be respectively:Quene_0_0, quene_0_1, quene_1_0 and quene_1_1。
It is above-mentioned to dispatch system based on rendering parallel multipriority queue offline in real time, according to rendering resources state, use Family demand comprehensive descision, can achieve 5 rendering task priority queries, prioritized to be respectively:quene_0_ 0、quene_0_1、quene_1_0、quene_1_1、quene_offline。
Above-mentioned to dispatch system based on rendering parallel multipriority queue offline in real time, the priority query is according to wash with watercolours Dye demand and user's request are provided with expansible attribute, the priority class for extending priority query.
The beneficial effects of the invention are as follows:The present invention is used based on multipriority task scheduling approach that is real-time, rendering offline, The priority of rendering task can be dynamically distributed according to user's request and resource status, there is provided money while lifting Consumer's Experience Source utilization rate.
Brief description of the drawings
Fig. 1 is module connection figure of the invention;
Fig. 2 renders scheduling flow figure for the present invention's;
Fig. 3 is priority query's form schematic diagram of the invention;
Fig. 4 is priority query's form schematic diagram of the invention.
Embodiment
More clearly intactly illustrate to be made to the present invention, below in conjunction with the accompanying drawings with the specific embodiment pair of the present invention Technical scheme is further illustrated.
First, two technical terms of the present invention are made explanations explanation, wherein, real-time rendering task refers to user Requirement height to render time is, it is necessary to being rendered within the shortest time for task.Offline rendering task refers to user to rendering The requirement of time is low, being rendered after machine resources idle is rendered for task.With reference to embodiment one and in fact Two pairs of concrete technical schemes of the invention of example are applied to be described in detail.
Embodiment one:
Concrete technical scheme combination Fig. 1 module connection figure, Fig. 2 render priority flow chart and Fig. 3 priority team Shown in column format schematic diagram, it is proposed by the present invention it is a kind of dispatch system based on rendering parallel multipriority queue offline in real time, The scheduling system includes:
Type detection module 200 is rendered, this renders type detection module 200 and is connected with rendering task pond 100, for detecting The render request type for the rendering task that rendering task pond 100 is sent, render request type includes real-time rendering request and offline Two kinds of forms of render request.It is described that real-time rendering asks the definition with offline render request to see above.
Resource state detection module 300, the resource state detection module 300 connects with the type detection module 200 that renders Connect, for receiving the feedback information for rendering type detection module 200, render what type detection module 200 was fed back when described The render request type of rendering task is offline render request, then the resource state detection module 300 puts the rendering task number Offline mark offline in is 1, without the state-detection of rendering resources, then the rendering task number after processing According to being sent to task recipient.When it is described render type detection module 200 feedback rendering task render request type be for Real-time rendering is asked, then the resource state detection module 300 first detects the state of current rendering resources, if currently rendering money The state in source is busy, then points out user's selection to render offline;If the state of current rendering resources is the free time, user is pointed out Real-time rendering is selected, the rendering task data after processing are then sent to task recipient.
Rendering task receiving module 400, the rendering task receiving module 400 is examined as task recipient with resource status Module 300 is surveyed to connect, it is preferential for receiving rendering for rendering task that resource state detection module 300 sends and the rendering task Level judges information.
Priority judge module 500, is connected with the rendering task receiving module 400, for judging the rendering task The priority of user's rendering task in receiving module 400, and according to the priority in deposit priority query pond 600.It is excellent The user's rendering task being stored in first level queue pond 600 is arranged from high to low according to priority level, when rendering, according to being used in queue The priority height of family rendering task is arranged.
Rendering module 700, is connected with the priority query pond 600, appoints to being stored in rendering in priority query pond 600 Business is rendered from high to low according to priority.
Preferably, it is of the invention also to include prompting mould based on rendering parallel multipriority queue scheduling system offline in real time Block, it is real-time rendering request that the prompting template, which is used to send the render request type of rendering task in detection rendering task pond 100, Or before offline render request, send the prompt message of Primary Stage Data preparation.Specifically, initiating what is prepared before rendering task request Primary Stage Data includes the house type data being embodied obtained after house house type is completed:House layout structure, model are put, hung Top is put, the regulation of intensity of light and color.
Preferably, the resource state detection module 300 also includes detection request transmitting unit, and detection request sends single Member is used for the state-detection request for sending rendering resources.The rendering task receiving module 400 receives state-detection request simultaneously The rendering resources quantity of current idle is counted, when the quantity of idle rendering resources is more than 0, idle condition is returned and gives the detection Request transmitting unit, when idle rendering resources are equal to 0, returns to busy state to the detection request transmitting unit.
Before detection request transmitting unit sends the state-detection request of rendering resources, system renders machine to all Resource is initialized, and it is the free time to give tacit consent to all machine resources that render, and preserves current all idle shapes for rendering machine The state for rendering machine, after rendering machine and obtaining rendering task, is set to busy state, and preserves this to render machine by state Busy state.The resource state detection module detects the state of current rendering resources to be busy or idle and point out user Selection is rendered offline or real-time rendering detailed process is:
If the resource state detection module return for busy state, point out the current rendering resources of user busy, The mode that can be rendered offline carries out task processing, if user's selection is rendered offline, in rendering task data The offline mark offline that renders is revised as 1, if user selects real-time rendering, rendering task data are not processed;Return If idle condition, then rendering task data are not processed.Specifically, the data of rendering task include:Layout structure data, Model data, furred ceiling data, light information data and offline render identify offline, and the offline mark offline that renders writes from memory Think 0, be designated not offline.
Preferably, in the present invention based on the embodiment one for rendering parallel multipriority queue scheduling system offline in real time Kind, the priority that renders that rendering task receiving module 400 receives rendering task judges that information is specifically included:User type type, User gradation level.The create-rule of priority query is:
The offline mark offline of S1, first detection;
If S2, offline mark offline are equal to 1, the rendering task is put into lowest priority queue quene_ offline;
If S3, offline mark offline are 0, carried out rendering team according to user type type and user gradation level The judgement of row priority, wherein, user type type has value 0 and 1, and user gradation level has value 0 and 1, priority query's form For:Quene_type_level, it is prioritized to be respectively:Quene_0_0, quene_0_1, quene_1_0 and quene_1_1。
It is above-mentioned to dispatch system based on rendering parallel multipriority queue offline in real time, in step s 4, receive wash with watercolours After the data of dye task, judging the reference value of the priority of the rendering task is:User type type, user gradation level and Offline mark offline.Expansible attribute also can be set according to the demand that renders and user's request in priority query, excellent for extending The priority class of first level queue.
Embodiment two:
Concrete technical scheme combination Fig. 1 module connection figure, Fig. 2 render priority flow chart and Fig. 4 priority team Shown in column format schematic diagram, it is proposed by the present invention it is a kind of dispatch system based on rendering parallel multipriority queue offline in real time, The scheduling system includes:
Type detection module 200 is rendered, this renders type detection module 200 and is connected with rendering task pond 100, for detecting The render request type for the rendering task that rendering task pond 100 is sent, render request type includes real-time rendering request and offline Two kinds of forms of render request.It is described that real-time rendering asks the definition with offline render request to see above.
Resource state detection module 300, the resource state detection module 300 connects with the type detection module 200 that renders Connect, for receiving the feedback information for rendering type detection module 200, render what type detection module 200 was fed back when described The render request type of rendering task is offline render request, then the resource state detection module 300 puts the rendering task number Offline mark offline in is 1, without the state-detection of rendering resources, then the rendering task number after processing According to being sent to task recipient.When it is described render type detection module 200 feedback rendering task render request type be for Real-time rendering is asked, then the resource state detection module 300 first detects the state of current rendering resources, if currently rendering money The state in source is busy, then points out user's selection to render offline;If the state of current rendering resources is the free time, user is pointed out Real-time rendering is selected, the rendering task data after processing are then sent to task recipient.
Rendering task receiving module 400, the rendering task receiving module 400 is examined as task recipient with resource status Module 300 is surveyed to connect, it is preferential for receiving rendering for rendering task that resource state detection module 300 sends and the rendering task Level judges information.
Priority judge module 500, is connected with the rendering task receiving module 400, for judging the rendering task The priority of user's rendering task in receiving module 400, and according to the priority in deposit priority query pond 600.It is excellent The user's rendering task being stored in first level queue pond 600 is arranged from high to low according to priority level, when rendering, according to being used in queue The priority height of family rendering task is arranged.
Rendering module 700, is connected with the priority query pond 600, appoints to being stored in rendering in priority query pond 600 Business is rendered from high to low according to priority.
Preferably, it is of the invention also to include prompting mould based on rendering parallel multipriority queue scheduling system offline in real time Block, it is real-time rendering request that the prompting template, which is used to send the render request type of rendering task in detection rendering task pond 100, Or before offline render request, send the prompt message of Primary Stage Data preparation.Specifically, initiating what is prepared before rendering task request Primary Stage Data includes the house type data being embodied obtained after house house type is completed:House layout structure, model are put, hung Top is put, the regulation of intensity of light and color.
Preferably, the resource state detection module 300 also includes detection request transmitting unit, and detection request sends single Member is used for the state-detection request for sending rendering resources.The rendering task receiving module 400 receives state-detection request simultaneously The rendering resources quantity of current idle is counted, when the quantity of idle rendering resources is more than 0, idle condition is returned and gives the detection Request transmitting unit, when idle rendering resources are equal to 0, returns to busy state to the detection request transmitting unit.
Before detection request transmitting unit sends the state-detection request of rendering resources, system renders machine to all Resource is initialized, and it is the free time to give tacit consent to all machine resources that render, and preserves current all idle shapes for rendering machine The state for rendering machine, after rendering machine and obtaining rendering task, is set to busy state, and preserves this to render machine by state Busy state.The resource state detection module detects the state of current rendering resources to be busy or idle and point out user Selection is rendered offline or real-time rendering detailed process is:
If the resource state detection module return for busy state, point out the current rendering resources of user busy, The mode that can be rendered offline carries out task processing, if user's selection is rendered offline, in rendering task data The offline mark offline that renders is revised as 1, if user selects real-time rendering, rendering task data are not processed;Return If idle condition, then rendering task data are not processed.Specifically, the data of rendering task include:Layout structure data, Model data, furred ceiling data, light information data and offline render identify offline, and the offline mark offline that renders writes from memory Think 0, be designated not offline.
Preferably, in the present invention based on the embodiment one for rendering parallel multipriority queue scheduling system offline in real time Kind, the priority that renders that rendering task receiving module 400 receives rendering task judges that information is specifically included:User type type, User gradation level and offline mark offline.The create-rule of priority query is:
The offline mark offline of S1, first detection;
If S2, offline mark offline are equal to 1, the rendering task is put into lowest priority queue quene_ offline;
If S3, offline mark offline are 0, carried out rendering team according to user type type and user gradation level The judgement of row priority, wherein, user type type has value 0 and 1, and user gradation level has value 0 and 1, priority query's form For:Quene_type_level, it is prioritized to be respectively:Quene_0_0, quene_0_1, quene_1_0 and quene_1_1.Along with lowest priority queue quene_offline, 5 rendering task priority queries can be achieved, are pressed Priority orders are arranged:quene_0_0、quene_0_1、quene_1_0、quene_1_1、quene_offline. In other embodiment, expansible attribute can be set according to the demand that renders and user's request in priority query, for further expanding The priority class of priority query.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention Any modifications, equivalent substitutions and improvements made within refreshing and principle etc., should be included in the scope of the protection.

Claims (12)

1. a kind of dispatch system based on rendering parallel multipriority queue offline in real time, it is characterised in that the scheduling system Including:
Type detection module is rendered, for detecting that the render request type for the rendering task that rendering task pond is sent is real-time rendering Request or offline render request;
Resource state detection module, is connected with the type detection module that renders, and described type detection module is rendered for receiving Feedback information, when the rendering task for rendering type detection module feedback render request type be offline render request, The offline mark offline that then the resource state detection module is put in the rendering task data is 1, without rendering resources The rendering task data after processing, are then sent to task recipient, type detection module are rendered when described by state-detection The render request type of the rendering task of feedback is asked for real-time rendering, then the resource state detection module detection is currently rendered The state of resource is busy or idle and points out user's selection to render or real-time rendering offline, and then rendering after processing is appointed Business data are sent to task recipient;
Rendering task receiving module, as task recipient, is connected with the resource state detection module, appoints for receiving to render The priority that renders of business and the rendering task judges information;
Priority judge module, is connected with the rendering task receiving module, for judging in the rendering task receiving module User's rendering task priority, and according to the priority in deposit priority query pond;
Rendering module, is connected with the priority query pond, obtains rendering task from high to low according to priority and is rendered.
2. according to claim 1 based on parallel multipriority queue scheduling system is rendered offline in real time, its feature exists In, in addition to reminding module, render request type of the prompting template for sending rendering task in detection rendering task pond Before real-time rendering request or offline render request, the prompt message of Primary Stage Data preparation is sent.
3. according to claim 2 based on parallel multipriority queue scheduling system is rendered offline in real time, its feature exists In the resource state detection module includes detection request transmitting unit, and the state-detection for sending rendering resources is asked, institute State rendering task receiving module and receive the rendering resources quantity that the state-detection is asked and counts current idle, when idle renders When the quantity of resource is more than 0, idle condition is returned to the detection request transmitting unit, when idle rendering resources are equal to 0, Busy state is returned to the detection request transmitting unit.
4. according to claim 3 based on parallel multipriority queue scheduling system is rendered offline in real time, its feature exists In before the detection request transmitting unit sends the state-detection request of rendering resources, system renders machine to all Resource is initialized, and it is the free time to give tacit consent to all machine resources that render, and preserves current all idle shapes for rendering machine The state for rendering machine, after rendering machine and obtaining rendering task, is set to busy state, and preserves this to render machine by state Busy state.
5. according to claim 1 based on parallel multipriority queue scheduling system is rendered offline in real time, its feature exists In the resource state detection module detects that the state of current rendering resources is busy or idle and points out user's selection offline Render or real-time rendering specifically includes step:
If the resource state detection module return for busy state, point out the current rendering resources of user busy, can be with The mode rendered offline carries out task processing, if user's selection is rendered offline, offline in rendering task data Render mark offline and be revised as 1, if user selects real-time rendering, rendering task data are not processed;
Return if idle condition, then rendering task data are not processed.
6. according to claim 2 based on parallel multipriority queue scheduling system is rendered offline in real time, its feature exists In the Primary Stage Data for initiating to prepare before rendering task request includes the house type number being embodied obtained after house house type is completed According to:House layout structure, model are put, furred ceiling is put, the regulation of intensity of light and color.
7. according to claim 1 based on parallel multipriority queue scheduling system is rendered offline in real time, its feature exists In the data of rendering task include:Layout structure data, model data, furred ceiling data, light information data and render mark offline Know offline, the offline mark offline that renders is defaulted as 0, is designated not offline.
8. according to claim 1 based on parallel multipriority queue scheduling system is rendered offline in real time, its feature exists In render the user profile of priority judgement has:User type type, user gradation level.
9. according to claim 7 based on parallel multipriority queue scheduling system is rendered offline in real time, its feature exists In after the data for receiving rendering task, judging the reference value of the priority of the rendering task is:User type type, user Grade level and offline mark offline.
10. according to claim 9 based on parallel multipriority queue scheduling system is rendered offline in real time, its feature exists In the create-rule of priority query is:
The offline mark offline of S1, first detection;
If S2, offline mark offline are equal to 1, the rendering task is put into lowest priority queue quene_ offline;
If S3, offline mark offline are 0, it is excellent to carry out render-ahead queue according to user type type and user gradation level First level judgement, wherein, user type type has value 0 and 1, and user gradation level has value 0 and 1, and priority query's form is: Quene_type_level, it is prioritized to be respectively:Quene_0_0, quene_0_1, quene_1_0 and quene_ 1_1。
11. according to claim 10 dispatch system, its feature based on rendering parallel multipriority queue offline in real time It is, according to rendering resources state, user's request comprehensive descision, 5 rendering task priority queries can be achieved, according to priority Order is arranged:quene_0_0、quene_0_1、quene_1_0、quene_1_1、quene_offline.
12. according to claim 11 dispatch system, its feature based on rendering parallel multipriority queue offline in real time It is, the priority query is provided with expansible attribute according to the demand that renders and user's request, for extending priority query Priority class.
CN201710453490.4A 2017-06-15 2017-06-15 Multi-priority queue scheduling system based on real-time offline rendering parallelism Active CN107274471B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710453490.4A CN107274471B (en) 2017-06-15 2017-06-15 Multi-priority queue scheduling system based on real-time offline rendering parallelism

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710453490.4A CN107274471B (en) 2017-06-15 2017-06-15 Multi-priority queue scheduling system based on real-time offline rendering parallelism

Publications (2)

Publication Number Publication Date
CN107274471A true CN107274471A (en) 2017-10-20
CN107274471B CN107274471B (en) 2020-10-09

Family

ID=60067606

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710453490.4A Active CN107274471B (en) 2017-06-15 2017-06-15 Multi-priority queue scheduling system based on real-time offline rendering parallelism

Country Status (1)

Country Link
CN (1) CN107274471B (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108288167A (en) * 2018-02-12 2018-07-17 平安科技(深圳)有限公司 Pay a return visit method, apparatus, computer equipment and storage medium
CN109981801A (en) * 2019-04-30 2019-07-05 深圳微新创世科技有限公司 A kind of Distributed Online rendering method
CN110990139A (en) * 2019-12-06 2020-04-10 安徽芯智科技有限公司 SMP scheduling method and system based on RTOS
CN112260952A (en) * 2020-10-20 2021-01-22 四川天邑康和通信股份有限公司 Wifi6 router rapid data access protection method
CN112860391A (en) * 2020-12-30 2021-05-28 佛山欧神诺云商科技有限公司 Dynamic cluster rendering resource management system and method
WO2022088082A1 (en) * 2020-10-30 2022-05-05 京东方科技集团股份有限公司 Task processing method, apparatus and device based on defect detection, and storage medium
CN114637581A (en) * 2022-01-26 2022-06-17 武汉艺画开天文化传播有限公司 Optimization system for submitting rendering model
CN116680086A (en) * 2023-07-25 2023-09-01 联通沃音乐文化有限公司 Scheduling management system based on offline rendering engine
US12020516B2 (en) 2019-12-20 2024-06-25 Boe Technology Group Co., Ltd. Method and device for processing product manufacturing messages, electronic device, and computer-readable storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102722549A (en) * 2012-05-28 2012-10-10 中国科学院遥感应用研究所 Cluster-based real-time rendering service of remote sensing data set
CN103426193A (en) * 2012-05-25 2013-12-04 上海幻维数码创意科技有限公司 Distributed animation rendering method and apparatus thereof
US20140040911A1 (en) * 2001-07-20 2014-02-06 Searchlite Advances Llc Dynamic job processing based on estimated completion time and specified tolerance time
CN104572305A (en) * 2015-01-26 2015-04-29 赞奇科技发展有限公司 Load-balanced cluster rendering task dispatching method
CN105959238A (en) * 2016-06-28 2016-09-21 深圳市彬讯科技有限公司 Dispatching method and system for multi-priority rendering resources based on message queues

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140040911A1 (en) * 2001-07-20 2014-02-06 Searchlite Advances Llc Dynamic job processing based on estimated completion time and specified tolerance time
CN103426193A (en) * 2012-05-25 2013-12-04 上海幻维数码创意科技有限公司 Distributed animation rendering method and apparatus thereof
CN102722549A (en) * 2012-05-28 2012-10-10 中国科学院遥感应用研究所 Cluster-based real-time rendering service of remote sensing data set
CN104572305A (en) * 2015-01-26 2015-04-29 赞奇科技发展有限公司 Load-balanced cluster rendering task dispatching method
CN105959238A (en) * 2016-06-28 2016-09-21 深圳市彬讯科技有限公司 Dispatching method and system for multi-priority rendering resources based on message queues

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘伟: "WEB方式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》 *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108288167A (en) * 2018-02-12 2018-07-17 平安科技(深圳)有限公司 Pay a return visit method, apparatus, computer equipment and storage medium
CN109981801A (en) * 2019-04-30 2019-07-05 深圳微新创世科技有限公司 A kind of Distributed Online rendering method
CN109981801B (en) * 2019-04-30 2021-10-26 深圳微新创世科技有限公司 Distributed online rendering method
CN110990139B (en) * 2019-12-06 2020-11-24 安徽芯智科技有限公司 SMP scheduling method and system based on RTOS
CN110990139A (en) * 2019-12-06 2020-04-10 安徽芯智科技有限公司 SMP scheduling method and system based on RTOS
US12020516B2 (en) 2019-12-20 2024-06-25 Boe Technology Group Co., Ltd. Method and device for processing product manufacturing messages, electronic device, and computer-readable storage medium
CN112260952A (en) * 2020-10-20 2021-01-22 四川天邑康和通信股份有限公司 Wifi6 router rapid data access protection method
WO2022088082A1 (en) * 2020-10-30 2022-05-05 京东方科技集团股份有限公司 Task processing method, apparatus and device based on defect detection, and storage medium
US11982999B2 (en) 2020-10-30 2024-05-14 Beijing Zhongxiangying Technology Co., Ltd. Defect detection task processing method, device, apparatus and storage medium
CN112860391A (en) * 2020-12-30 2021-05-28 佛山欧神诺云商科技有限公司 Dynamic cluster rendering resource management system and method
CN114637581A (en) * 2022-01-26 2022-06-17 武汉艺画开天文化传播有限公司 Optimization system for submitting rendering model
CN114637581B (en) * 2022-01-26 2023-04-11 武汉艺画开天文化传播有限公司 Optimization system for submitting rendering model
CN116680086A (en) * 2023-07-25 2023-09-01 联通沃音乐文化有限公司 Scheduling management system based on offline rendering engine
CN116680086B (en) * 2023-07-25 2024-04-02 联通沃音乐文化有限公司 Scheduling management system based on offline rendering engine

Also Published As

Publication number Publication date
CN107274471B (en) 2020-10-09

Similar Documents

Publication Publication Date Title
CN107274471A (en) It is a kind of to dispatch system based on rendering parallel multipriority queue offline in real time
CN107274470A (en) It is a kind of based on rendering parallel multipriority queue dispatching method offline in real time
CN105320570B (en) Method for managing resource and system
CN102859492B (en) The method of assignment, equipment and the scheduler of Dispatching Drawings processing unit GPU order
CN103927225B (en) A kind of internet information processing optimization method of multi-core framework
CN108139935A (en) The extension of the resource constraint of service definition container
CN106502782A (en) Heterogeneous computing system and its method
CN106325976B (en) A kind of rendering task scheduling processing method and server
WO2023143151A1 (en) Code development methods, server and storage medium
CN109727376A (en) Generate the method, apparatus and selling apparatus of configuration file
CN103514048B (en) Participate in sensory perceptual system and method for allocating tasks thereof
WO2020177336A1 (en) Resource scheduling methods, device and system, and central server
CN109818810A (en) A kind of access server connection optimization method, access server and communication system
CN103973812A (en) Service interface providing method and system based on uniform resource locator in HTTP
CN104809126A (en) Business process engine system
CN106302368A (en) Transaction methods and device
CN105893160B (en) A kind of dispatching method of multi-interface data
CN107885589B (en) Job scheduling method and device
CN115361382B (en) Data processing method, device, equipment and storage medium based on data group
CN102013993A (en) Physical topology use management method and system
CN103685066A (en) Dynamic distributed scheduling method and system
CN107025126A (en) A kind of resource regulating method, NFVO and system
CN110161893A (en) The communication means and storage medium of slave device, control system, response data
US10104201B2 (en) Method for sharing microblog information
CN115291773A (en) Tree structure data display method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP03 Change of name, title or address

Address after: 518000 R & D room 3501, block a, building 7, Vanke Cloud City Phase I, Xingke 1st Street, Xili community, Xili street, Nanshan District, Shenzhen City, Guangdong Province

Patentee after: Tubatu Group Co.,Ltd.

Address before: 1001-a, 10th floor, bike technology building, No.9, Keke Road, high tech Zone, Nanshan District, Shenzhen, Guangdong 518000

Patentee before: SHENZHEN BINCENT TECHNOLOGY Co.,Ltd.

CP03 Change of name, title or address