CN105320660A - Method and device for automatic task submitting in numerical simulation parallel computing - Google Patents

Method and device for automatic task submitting in numerical simulation parallel computing Download PDF

Info

Publication number
CN105320660A
CN105320660A CN201410245400.9A CN201410245400A CN105320660A CN 105320660 A CN105320660 A CN 105320660A CN 201410245400 A CN201410245400 A CN 201410245400A CN 105320660 A CN105320660 A CN 105320660A
Authority
CN
China
Prior art keywords
file
information
user
numerical simulation
module
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
CN201410245400.9A
Other languages
Chinese (zh)
Other versions
CN105320660B (en
Inventor
马鸣
车慧翠
傅瑞军
卞法敏
肖从毅
孟宪民
王智勇
周虹
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.)
China Petroleum and Chemical Corp
Sinopec Shengli Geological Scientific Reserch Institute
Original Assignee
China Petroleum and Chemical Corp
Sinopec Shengli Geological Scientific Reserch Institute
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 China Petroleum and Chemical Corp, Sinopec Shengli Geological Scientific Reserch Institute filed Critical China Petroleum and Chemical Corp
Priority to CN201410245400.9A priority Critical patent/CN105320660B/en
Publication of CN105320660A publication Critical patent/CN105320660A/en
Application granted granted Critical
Publication of CN105320660B publication Critical patent/CN105320660B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Computer And Data Communications (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The invention provides a method and device for automatic task submitting in numerical simulation parallel computing. The method comprises the steps of automatically mounting a user personal space distributed to a user in a server memory space to a local client, and generating a user information packet; scanning .DAT files in the user personal space, and sorting and screening data files already existing in the user personal space; endowing priority to the screened data files, making computing waiting marks, and generating a file information packet; transmitting the file information packet and the user information packet to a parallel computing server, writing information in the file information packet, such as file states, into a database; acquiring information from the database, performing sensible resource allocation and then performing computing, and computing a submitted task. According to the method and device, the numerical simulation parallel computing efficiency can be improved, the network quality influence is lowered, and the time and human cost in the numerical simulation parallel computing process is reduced.

Description

The automatic commit method of operation of numerical simulation parallel computation and device
Technical field
The present invention relates to oil reservoir development areas of information technology, particularly relate to a kind of automatic commit method of operation and device of numerical simulation parallel computation.
Background technology
The operation of numerical simulation parallel computation submits to main function to divide two large divisions automatically.A part is positioned at client, when user opens local, namely monitors the user profile of module last time transmission according to server end, confirms, validated user information is broken into user profile bag to user profile.In addition, immediately to the .DATA file scan in the personal space of automatic carry, the logging timestamp of module last time transmission is monitored backward according to server end after sequence, screening file, and logging timestamp again, be recorded in fileinfo, calculation document gives priority according to information such as user rights, enter and treat job queue, finally needing the associated documents information of calculation document to break into fileinfo bag; A part is positioned at server end, monitors user profile bag and fileinfo bag that module obtains client, is delivered to parallel computation server end together, and write into Databasce.Parallel computation server end resource reasonable distribution, computing is carried out in operation, during computing, client provides calculating process impression window directly perceived, and real time inspection computing situation, after finally having calculated, operation relevant information write into Databasce, monitor module and transmit user profile and fileinfo to client, client ejects result information, checks operation result in user to personal space.
The present invention is that large server is more and more applied in research and production, to accelerate the progress of oil reservoir research project based at present in oil reservoir development field, but simultaneously, although hardware configuration improves year by year, most of the time superior resources are left unused, and utilization factor is not high.When hardware centralized configuration, user faces and compares outstanding problem and have: 1. a machine one with or special computer for special use pattern cause sometime in section hardware resource nervous, and other times superior resources are left unused in a large number, overall hardware resource advantage does not embody, in addition, sometimes due to the shake of network, cause user to connect parent process and interrupt, server end subprocess and user job calculate and stop; 2. storage resources aspect: user uses the network data stand-by period long, because user fails effective use core space computing machine, storage and Internet resources at present, only use local hard disk to make buffer memory, actual read and write, all through network transmission repeatedly, causes all adding one section of network delay at every turn; It is direct-connected with private server again that data are stored in particular storage device, memory device, very big limited subscriber is to the use of data, this has just occurred when software and hardware resources can be used, cannot realize market demand " floating ", also just mean that user cannot use other computational resource, and the clear area of particular storage device is difficult to be used by other users, cause storage resources waste.We have invented a kind of automatic commit method of operation and device of new numerical simulation parallel computation for this reason, solve above technical matters.
Summary of the invention
The object of this invention is to provide a kind of automatic commit method of operation and the device that can improve numerical simulation concurrent operation efficiency and reduce the numerical simulation parallel computation that network quality affects.
Object of the present invention realizes by following technical measures: the automatic commit method of operation of numerical simulation parallel computation, the automatic commit method of operation of this numerical simulation parallel computation comprises: step 1, after user's local is opened, individual subscriber space automatic hanging user distributed on server storage is loaded onto local client, and confirms rear generating user information bag in user profile; Step 2, the .DAT file in scanning individual subscriber space, and data file already present in individual subscriber space is carried out sorting and screening; Step 3, gives priority by the data file filtered out, stamps wait calculation flag, spanned file packets of information; Step 4, passes to parallel computation server end by fileinfo bag and user profile bag, and by information write into Databasces such as file statuss wherein; And step 5, obtaining information from database, carries out computing after resource reasonable distribution according to the information in fileinfo bag and user profile bag, carries out computing to the operation submitted in step 4.
Object of the present invention also realizes by following technical measures:
In step 1, when by automatic for individual subscriber space carry, will set up the information channel of client and server simultaneously, and this information channel is defined as the highest information channel of priority, individual subscriber space is preset without access limit, and space file does not show.
In step 1, when carrying out user profile and confirming, catch existing user profile key word, contrast with the user profile key word deposited in individual subscriber space in the .DAT file of last user profile and fileinfo, if the two is consistent, then user is legal, source document in the individual subscriber space of display carry; As the two is inconsistent, user is illegal, and individual subscriber space Self-tipping, cancels the information channel that priority is the highest.
In step 2, when being carried out sorting and screening by file, according to the timestamp information in .DAT file, calculation document sorted, according to last registration timestamp backward, screening file, and logging timestamp again, be recorded in fileinfo; Exist as met file, then enter into step 3; File does not exist, then EOP (end of program).
In step 3, priority is given file according to the user gradation in .DAT file; Timestamp and operation are marked these fileinfos and breaks into fileinfo bag
Step 3 also comprises, and according to the empirical value of Activity Calculation time, in conjunction with job size, defines CPU check figure, determines to participate in parallel computation CPU check figure, shortens the Activity Calculation time.
The automatic commit method of operation of this numerical simulation parallel computation also comprises, and after step 5, client provides calculating process impression window directly perceived, computing situation in real time inspection step 5, and after having calculated, National Information Infrastructure is cancelled; And after step is shown in computing, by operation relevant information write into Databasce, transmit user profile, fileinfo to client, form new .DAT file, cover the old .DAT file in personal space; Client ejects result information.
Object of the present invention also realizes by following technical measures: the automatic issuing means of operation of numerical simulation parallel computation, the automatic issuing means of operation of this numerical simulation parallel computation comprises the line module and first being positioned at client and monitors module, and the scheduler module and second being positioned at server end monitors module, this line module is after user's local is opened, individual subscriber space automatic hanging user distributed on server storage is loaded onto local client, and relevant user information catches and breaks into user profile bag by this line module after user profile confirms, .DAT file in this line module scanning individual subscriber space, and data file already present in individual subscriber space is carried out sorting and screening, and give priority by the data file filtered out, stamp wait calculation flag, spanned file packets of information, this the first monitoring model calling is in this line module, this the second monitoring model calling is in this first monitoring module, fileinfo bag and user profile bag are passed to this second monitoring module by this first monitoring module, and this second monitoring module is by information write into Databasces such as file statuss wherein, this scheduler module is connected to this and second monitors module, and from database obtaining information, carry out computing after resource reasonable distribution according to the information in fileinfo bag and user profile bag, this second monitored to operation that module submits to and carry out computing.
Object of the present invention also realizes by following technical measures:
When this line module is by automatic for individual subscriber space carry, this the first monitoring module will set up the information channel of client and server, and this information channel is defined as the highest information channel of priority, individual subscriber space is preset without access limit, and space file does not show.
This line module is when carrying out user profile and confirming, this line module catches existing user profile key word, contrast with the user profile key word deposited in individual subscriber space in the .DAT file of last user profile and fileinfo, if the two is consistent, then user is legal, source document in the individual subscriber space of display carry; As the two is inconsistent, user is illegal, and this first monitoring module, by individual subscriber space Self-tipping, cancels the information channel that priority is the highest.
Calculation document, when being carried out sorting and screening by file, according to the timestamp information in .DAT file, sorts by this line module, and according to last registration timestamp backward, screening file, and logging timestamp again, be recorded in fileinfo.
File is given priority according to the user gradation in .DAT file by this line module; This line module, also according to the empirical value of Activity Calculation time, in conjunction with job size, defines CPU check figure, determines to participate in parallel computation CPU check figure, shortens the Activity Calculation time; Timestamp and operation are also marked these fileinfos and break into fileinfo bag by this line module.
This line module also provides calculating process impression window directly perceived, real time inspection computing situation, after calculating completes, this the first monitoring module information high-speed channel is cancelled, this scheduler module is by operation relevant information write into Databasce, this the second monitoring module transmits user profile, fileinfo by this first monitoring module to client, forms new .DAT file, covers the old .DAT file in personal space; This line module of client ejects result information.
The automatic issuing means of operation of this numerical simulation parallel computation also comprises time block, and this time block is positioned at server end and is connected to this second monitors module, for every the schedule time or detect individual subscriber space when needed.
The automatic commit method of operation of this numerical simulation parallel computation and device, by the operation automatic screening of required calculating out, in conjunction with information such as user rights, priority definition is carried out to user job again, be pushed to parallel computation server end and carry out computing after resource reasonable distribution, thus realize the automatic submit job computing of client.Application the present invention can improve numerical simulation concurrent operation efficiency and reduce network quality impact, and the time reduced in numerical simulation parallel computation process and human cost.
Accompanying drawing explanation
Fig. 1 is the structural drawing of the automatic issuing means of operation of numerical simulation parallel computation of the present invention;
Fig. 2 is the process flow diagram of the specific embodiment of the automatic commit method of operation of numerical simulation parallel computation of the present invention.
Embodiment
For making above and other object of the present invention, feature and advantage can become apparent, cited below particularly go out preferred embodiment, and coordinate institute's accompanying drawings, be described in detail below.
As shown in Figure 2, Fig. 2 is the process flow diagram of a specific embodiment of the automatic commit method of operation of numerical simulation parallel computation of the present invention.
Step 201: line module is that each user distributes personal space on server storage, after user's local is opened, automatic hanging is loaded onto local client by the personal space that far-end server end and client are shared.
The individual subscriber space automatic hanging that server storage distributes is loaded onto user this locality, and the read-write of user to the data file in space is equivalent to local operation.The amendment of server storage file is also directly reflected into user this locality.User gradation is distributed by system manager, is present in the list item of .DAT file in individual subscriber space and background data base.The empirical value table of Activity Calculation is the stealthy file in individual subscriber space, is to be formed after historical data statistics, by keeper after user's space is opened, deposits in individual subscriber space.
Individual subscriber space is preset without access limit, and space file does not show, and monitors module client end and will set up the information channel of client and server simultaneously.Switch carries out QOS setting, and different data streams adopts corresponding different priority, and the information channel of client and server is defined as the highest passage of priority.Flow process enters into step 202.
Step 202: individual subscriber space internal memory is with or without the .DAT file of access limit, and file does not show, transmits user profile and fileinfo for depositing the last module server of monitoring end.Line module catches existing user profile key word, contrast with user profile key word in .DAT file, if the two is unanimously, then user is legal, in step display 201 carry personal space in source document, and will step 203 and step 204 be proceeded to.Otherwise as the two is inconsistent, user is illegal, monitoring module client end will personal space Self-tipping, and National Information Infrastructure is cancelled, EOP (end of program).
Step 203: relevant user information catches and breaks into packets of information by line module.Flow process enters into step 208.
Step 204: the .DATA file in line module scanning step 201 in carry personal space, to All Files in user's space, comprise source document and new file carries out classifying type scanning, flow process enters into step 205.
Step 205: the file ordering that step 204 scans by line module.According to the timestamp information in .DAT file, calculation document sorted, according to last registration timestamp backward, screening file, and logging timestamp again, be recorded in fileinfo; Exist as met file, then proceed to step 206 and step 207.File does not exist, then EOP (end of program).
Step 206: file is given job run priority according to the user gradation in .DAT file by line module, stamps mark to be calculated.Flow process enters into step 208.
Step 207: line module, according to the empirical value table of Activity Calculation, in conjunction with job size, defines CPU check figure.Flow process enters into step 208.
Step 208: the fileinfos such as timestamp and operation mark are broken into fileinfo bag by line module.Flow process enters into step 209.
Step 209: step 203 and step 208 fileinfo bag and user profile bag are passed to parallel computation server end by monitoring module client end by line module, and write into Databasce.Line module is after information packet transmissions, and namely eject calculating process impression window directly perceived, flow process enters into step 210.
Step 210: scheduler module obtains user profile and fileinfo from database, after resource reasonable distribution, carry out computing to the operation submitted in step 209, and modify to job run state in database, flow process enters into step 211.
Step 211: line module, according to the job state list item in database, provides calculating process impression window directly perceived in client, computing situation in real time inspection step 210.After calculating completes, monitor module server and hold revocation information high-speed channel.Flow process enters into step 212.
Step 212: scheduler module is after the calculating in step 211 completes, by information write into Databasces such as operation deadline, working times, monitor module server end and transmit user profile, fileinfo to client user's module, line module forms new .DAT file and covers old .DAT file.Line module has ejected prompting, and flow process terminates.
Fig. 1 is the structural drawing of the automatic issuing means of operation of numerical simulation parallel computation of the present invention.The automatic commit method of operation of this numerical simulation parallel computation and device are made up of line module, monitoring module (server holds and client holds), scheduler module, time block (can select).
Module 101: run in client, is responsible for judging that whether user is legal, screen calculation document, generating user information bag and fileinfo bag, provide visualization window.
Module 101 catches existing user profile, determines that whether user is legal, according to the timestamp screening calculation document in .DAT file, forms user profile bag and fileinfo bag.In addition, also provide ruuning situation monitor window according to the information in .DAT file and terminate to remind.
Module 102: run in client, is responsible for setting up the .DAT file in individual subscriber space, application and revocation information high-speed channel, transmits module 101 information generated bag.
Once module 101 packets of information generates, then National Information Infrastructure between client and server is set up in application, and user profile bag module 101 formed and fileinfo bag pass to module 104, after outstanding message transmits, and revocation information high-speed channel.As module 104 has packets of information to pass over, then generate new .DAT file to cover old .DAT file.
Module 103: run at server end, is responsible for running on Hand up homework to parallel server.
According to the information in database, resource is distributed, drop into computing.Carry out read operation to database table 2, database table 1 has read-write operation.
Module 104: run at server end, is responsible for module 102 transmission of information write into Databasce, application and revocation information high-speed channel, timing being generated new packets of information according to database information and passing to module 102.
Write in each database table by module 102 transmission of information, job task table in database is checked in timing, and National Information Infrastructure between client and server is set up in certain interval of time application, transmits user and fileinfo bag to client modules 102.
As shown in Figure 1, wherein module 305--time block is optional to the automatic issuing means structure of operation of above-mentioned numerical simulation parallel computation.
Time block, for detecting individual subscriber space every the schedule time, specifically can set according to the actual requirements, such as 1 hour, also can start at any time when needed.
Table 1 task status table
Chinese describes Field name Type Width Whether non-NULL
Task identification taskid mediumint 8 NOT NULL
User ID userid mediumint 8 NOT NULL
Project label projectid mediumint 8 NOT NULL
Task deposits path taskcatalog VARchar 100 NOT NULL
Job state taskstate VARchar 6 NULL
Software type software int 2 NULL
Uplink time committime int 10 NULL
The Hand up homework time starttime int 10 NULL
Priority pri smallint 5 NULL
Process ID pid int 10 NULL
CPU quantity cpunumber smallint 5 NULL
Operation progress runplan VARchar 10 NULL
Task identification database provides automatically, for unique identification and major key; User ID, project label, job state, priority, provides initial value states by monitoring module, priority, runs progress, uplink time, the Hand up homework time, detects amendment by scheduler module.
Table 2 user right table
Field name Field name Type Width Non-NULL field
User right identifies ujpid mediumint 8 NOT NULL
User ID userid mediumint 8 NOT NULL
Project label projectid mediumint 8 NOT NULL
Read right read tinyint 1 NULL
Write permission write tinyint 1 NULL
Erase right delete tinyint 1 NULL
Memory allocation spaceasgn varchar 5 NULL
Capability identification, read right, write permission, erase right, memory allocation, examination & approval situation, date of approval, all by keeper's distributively generated.
The automatic commit method of operation of a kind of numerical simulation parallel computation that the embodiment of the present invention provides and device, computational resource and storage resources waste and centralized consumption can be eliminated and the phenomenon of depositing, reduce the dependence to network quality in oil reservoir research and production, and simplify the operation of professional and technical personnel, improve the efficiency of whole oil reservoir research work.
The above; be only the present invention's preferably embodiment; but protection scope of the present invention is not limited thereto; anyly be familiar with those skilled in the art in the technical scope that the embodiment of the present invention discloses; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.

Claims (14)

1. the automatic commit method of the operation of numerical simulation parallel computation, is characterized in that, the automatic commit method of operation of this numerical simulation parallel computation comprises:
Step 1, after user's local is opened, individual subscriber space automatic hanging user distributed on server storage is loaded onto local client, and confirms rear generating user information bag in user profile;
Step 2, the .DAT file in scanning individual subscriber space, and data file already present in individual subscriber space is carried out sorting and screening;
Step 3, gives priority by the data file filtered out, stamps wait calculation flag, spanned file packets of information;
Step 4, passes to parallel computation server end by fileinfo bag and user profile bag, and by information write into Databasces such as file statuss wherein; And
Step 5, obtaining information from database, carries out computing after resource reasonable distribution according to the information in fileinfo bag and user profile bag, carries out computing to the operation submitted in step 4.
2. the automatic commit method of operation of numerical simulation parallel computation according to claim 1, it is characterized in that, in step 1, when by automatic for individual subscriber space carry, the information channel of client and server will be set up simultaneously, and this information channel is defined as the highest information channel of priority, individual subscriber space is preset without access limit, and space file does not show.
3. the automatic commit method of operation of numerical simulation parallel computation according to claim 2, it is characterized in that, in step 1, when carrying out user profile and confirming, catch existing user profile key word, contrast, if the two is consistent with the user profile key word deposited in individual subscriber space in the .DAT file of last user profile and fileinfo, then user is legal, source document in the individual subscriber space of display carry; As the two is inconsistent, user is illegal, and individual subscriber space Self-tipping, cancels the information channel that priority is the highest.
4. the automatic commit method of operation of numerical simulation parallel computation according to claim 1, it is characterized in that, in step 2, when file is carried out sorting and screening, according to the timestamp information in .DAT file, calculation document is sorted, according to last registration timestamp backward, screening file, and logging timestamp again, be recorded in fileinfo; Exist as met file, then enter into step 3; File does not exist, then EOP (end of program).
5. the automatic commit method of operation of numerical simulation parallel computation according to claim 1, is characterized in that, in step 3, gives priority by file according to the user gradation in .DAT file; Timestamp and operation are marked these fileinfos and breaks into fileinfo bag.
6. the automatic commit method of operation of numerical simulation parallel computation according to claim 1, it is characterized in that, step 3 also comprises, according to the empirical value of Activity Calculation time, in conjunction with job size, CPU check figure is defined, determine to participate in parallel computation CPU check figure, shorten the Activity Calculation time.
7. the automatic commit method of operation of numerical simulation parallel computation according to claim 1, it is characterized in that, the automatic commit method of operation of this numerical simulation parallel computation also comprises, after step 5, client provides calculating process impression window directly perceived, computing situation in real time inspection step 5, after having calculated, National Information Infrastructure is cancelled; And
After step is shown in computing, by operation relevant information write into Databasce, transmit user profile, fileinfo to client, form new .DAT file, cover the old .DAT file in personal space; Client ejects result information.
8. the automatic issuing means of the operation of numerical simulation parallel computation, it is characterized in that, the automatic issuing means of operation of this numerical simulation parallel computation comprises the line module and first being positioned at client and monitors module, and the scheduler module and second being positioned at server end monitors module, this line module is after user's local is opened, individual subscriber space automatic hanging user distributed on server storage is loaded onto local client, and relevant user information catches and breaks into user profile bag by this line module after user profile confirms, .DAT file in this line module scanning individual subscriber space, and data file already present in individual subscriber space is carried out sorting and screening, and give priority by the data file filtered out, stamp wait calculation flag, spanned file packets of information, this the first monitoring model calling is in this line module, this the second monitoring model calling is in this first monitoring module, fileinfo bag and user profile bag are passed to this second monitoring module by this first monitoring module, and this second monitoring module is by information write into Databasces such as file statuss wherein, this scheduler module is connected to this and second monitors module, and from database obtaining information, carry out computing after resource reasonable distribution according to the information in fileinfo bag and user profile bag, this second monitored to operation that module submits to and carry out computing.
9. the automatic issuing means of operation of numerical simulation parallel computation according to claim 8, it is characterized in that, when this line module is by automatic for individual subscriber space carry, this the first monitoring module will set up the information channel of client and server, and this information channel is defined as the highest information channel of priority, individual subscriber space is preset without access limit, and space file does not show.
10. the automatic issuing means of operation of numerical simulation parallel computation according to claim 8, it is characterized in that, this line module is when carrying out user profile and confirming, this line module catches existing user profile key word, contrast with the user profile key word deposited in individual subscriber space in the .DAT file of last user profile and fileinfo, if the two is consistent, then user is legal, source document in the individual subscriber space of display carry; As the two is inconsistent, user is illegal, and this first monitoring module, by individual subscriber space Self-tipping, cancels the information channel that priority is the highest.
The automatic issuing means of operation of 11. numerical simulation parallel computations according to claim 8, it is characterized in that, this line module is when being undertaken sorting and screening by file, according to the timestamp information in .DAT file, calculation document is sorted, according to last registration timestamp backward, screening file, and logging timestamp again, be recorded in fileinfo.
The automatic issuing means of operation of 12. numerical simulation parallel computations according to claim 8, is characterized in that, file is given priority according to the user gradation in .DAT file by this line module; This line module, also according to the empirical value of Activity Calculation time, in conjunction with job size, defines CPU check figure, determines to participate in parallel computation CPU check figure, shortens the Activity Calculation time; Timestamp and operation are also marked these fileinfos and break into fileinfo bag by this line module.
The automatic issuing means of operation of 13. numerical simulation parallel computations according to claim 8, it is characterized in that, this line module also provides calculating process impression window directly perceived, real time inspection computing situation, after calculating completes, this the first monitoring module information high-speed channel is cancelled, this scheduler module is by operation relevant information write into Databasce, this the second monitoring module transmits user profile, fileinfo by this first monitoring module to client, form new .DAT file, cover the old .DAT file in personal space; This line module of client ejects result information.
The automatic issuing means of operation of 14. numerical simulation parallel computations according to claim 8, it is characterized in that, the automatic issuing means of operation of this numerical simulation parallel computation also comprises time block, this time block is positioned at server end and is connected to this second monitors module, for every the schedule time or detect individual subscriber space when needed.
CN201410245400.9A 2014-06-05 2014-06-05 Method and device is submitted in the operation of numerical simulation parallel computation automatically Active CN105320660B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410245400.9A CN105320660B (en) 2014-06-05 2014-06-05 Method and device is submitted in the operation of numerical simulation parallel computation automatically

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410245400.9A CN105320660B (en) 2014-06-05 2014-06-05 Method and device is submitted in the operation of numerical simulation parallel computation automatically

Publications (2)

Publication Number Publication Date
CN105320660A true CN105320660A (en) 2016-02-10
CN105320660B CN105320660B (en) 2019-01-18

Family

ID=55248064

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410245400.9A Active CN105320660B (en) 2014-06-05 2014-06-05 Method and device is submitted in the operation of numerical simulation parallel computation automatically

Country Status (1)

Country Link
CN (1) CN105320660B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110968921A (en) * 2018-09-27 2020-04-07 中山市华盛家具制造有限公司 Automatic simulation board packaging process method in furniture industry
CN112764830A (en) * 2021-01-19 2021-05-07 长沙证通云计算有限公司 Data migration method and system applied to domestic substitution
CN113839977A (en) * 2020-06-24 2021-12-24 顺丰科技有限公司 Message pushing method and device, computer equipment and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101034362A (en) * 2007-02-05 2007-09-12 南京邮电大学 Method for implementing network job scheduling using mobile proxy
US20080229318A1 (en) * 2007-03-16 2008-09-18 Carsten Franke Multi-objective allocation of computational jobs in client-server or hosting environments
CN102521024A (en) * 2011-11-23 2012-06-27 北京市计算中心 Job scheduling method based on bioinformation cloud platform
CN102542103A (en) * 2011-12-21 2012-07-04 中国人民解放军国防科学技术大学 Simulation comprehensive integration system capable of supporting multiple tasks on basis of WEB
CN103237059A (en) * 2013-04-02 2013-08-07 西安翔迅科技有限责任公司 Method for interacting traffic information data and commands

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101034362A (en) * 2007-02-05 2007-09-12 南京邮电大学 Method for implementing network job scheduling using mobile proxy
US20080229318A1 (en) * 2007-03-16 2008-09-18 Carsten Franke Multi-objective allocation of computational jobs in client-server or hosting environments
CN102521024A (en) * 2011-11-23 2012-06-27 北京市计算中心 Job scheduling method based on bioinformation cloud platform
CN102542103A (en) * 2011-12-21 2012-07-04 中国人民解放军国防科学技术大学 Simulation comprehensive integration system capable of supporting multiple tasks on basis of WEB
CN103237059A (en) * 2013-04-02 2013-08-07 西安翔迅科技有限责任公司 Method for interacting traffic information data and commands

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
付云虹: ""基于BACKFILL的并行计算作业调度算法研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 *
陈苏: ""大型油藏数模软件网上共享管理系统设计与实现"", 《今日科苑》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110968921A (en) * 2018-09-27 2020-04-07 中山市华盛家具制造有限公司 Automatic simulation board packaging process method in furniture industry
CN110968921B (en) * 2018-09-27 2023-06-20 广东华盛家具集团有限公司 Automatic simulation board packaging process method in furniture industry
CN113839977A (en) * 2020-06-24 2021-12-24 顺丰科技有限公司 Message pushing method and device, computer equipment and storage medium
CN113839977B (en) * 2020-06-24 2024-04-19 顺丰科技有限公司 Message pushing method, device, computer equipment and storage medium
CN112764830A (en) * 2021-01-19 2021-05-07 长沙证通云计算有限公司 Data migration method and system applied to domestic substitution

Also Published As

Publication number Publication date
CN105320660B (en) 2019-01-18

Similar Documents

Publication Publication Date Title
Sayal et al. Business process cockpit
Sharma et al. Modeling and synthesizing task placement constraints in Google compute clusters
US20130096971A1 (en) Facilitation of Multi-Project Management Using Critical Chain Methodology
CN107885980B (en) Software management method and system
US20070299953A1 (en) Centralized work distribution management
CN103699693A (en) Metadata-based data quality management method and system
CN107665421A (en) The document measures and procedures for the examination and approval, device, storage medium and computer equipment
CN102169562A (en) Method and system for processing project plans
CN109658003A (en) A kind of property facility equipment management system and method
CN109284981A (en) A kind of employee satisfaction survey questionnaire information system and method
CN105320660A (en) Method and device for automatic task submitting in numerical simulation parallel computing
CN104933495A (en) Work task assessment system on Android-based mobile terminal
CN108268546A (en) A kind of method and device for optimizing database
CN106447157A (en) Product testing and supervision method and monitoring system thereof
CN109787807A (en) Self service system based on Openstack framework cloud platform workflow
CN107577748A (en) Building trade information acquisition system and its method based on big data
WO2010031699A1 (en) Governing service identification in a service oriented architecture ('soa') governance model
Lee et al. Simulation modeling for process reengineering in the telecommunications industry
CN107767061A (en) A kind of system of software test Amount of work
CN107480188B (en) Audit service data processing method and computer equipment
CN104866960A (en) Task flow management system for thermal power enterprise
Lu et al. Risk analysis in software development project with owners and contractors
Lami et al. A methodology to derive sustainability indicators for software development projects
CN105630580A (en) Scheduling platform based data summarizing method and data summarizing apparatus
CN105243490B (en) A kind of statistical system and method based on git software

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant