CN107479683B - Serial computing method oriented to configuration software - Google Patents
Serial computing method oriented to configuration software Download PDFInfo
- Publication number
- CN107479683B CN107479683B CN201710698009.8A CN201710698009A CN107479683B CN 107479683 B CN107479683 B CN 107479683B CN 201710698009 A CN201710698009 A CN 201710698009A CN 107479683 B CN107479683 B CN 107479683B
- Authority
- CN
- China
- Prior art keywords
- calculation
- configuration
- data
- queue
- logic data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F1/00—Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
- G06F1/26—Power supply means, e.g. regulation thereof
- G06F1/32—Means for saving power
- G06F1/3203—Power management, i.e. event-based initiation of a power-saving mode
- G06F1/3234—Power saving characterised by the action undertaken
- G06F1/3243—Power saving in microcontroller unit
Abstract
The invention provides a serial computing method facing configuration software, which stores logic data to be computed of multiple virtual control nodes in a computing queue in a specified data arrangement mode by adopting a data queue mode; and the configuration calculation executor calls the logic data to be calculated in sequence according to the calculation queue and stores the calculation result in the tail part of the calculation queue again. The serial computing method well solves the problems of high requirements of parallel computing on system computing resources, high CPU occupation rate and high power consumption in the prior art.
Description
Technical Field
The invention relates to the technical field of industrial control, in particular to a serial computing method oriented to configuration software.
Background
Currently, high-performance computing is widely used in high-tech research and many industrial fields, and the science of computing based on high-performance computing has been remarkably developed. At the same time, the ever-increasing demand and demanding performance requirements have created significant challenges in the research and design of new generations of high performance computing systems. Especially with the rapid increase in processor performance and system size, the dramatically increasing power consumption severely limits the design and use of high performance computing systems. In order to effectively manage the power consumption of the system, improve the reliability and the availability of the system and finally reduce the ownership cost of a high-performance computing system, a low-power-consumption technology becomes a key technology in the field of high-performance computing. Since the last 90 s, Massively Parallel Processing (MPP) and Cluster (Cluster) systems have become the dominant architectures for high performance computers. In the parallel computing system, the parallel resource management software selects proper jobs from the job queue according to a scheduling algorithm, distributes and releases computing nodes for the jobs, and runs in parallel by a plurality of configuration executors, so that the occupation rate of CPU computing resources is high. All the steps occupy huge system resources and generate a large amount of power consumption. However, once there is not enough job load and the job scheduling and resource allocation strategy cannot fully utilize the system resources, there are often situations where idle resources waste system energy consumption.
In view of this, the present invention provides a serial computing method for configuration software, and under the condition that system computing resources are limited, only one configuration executor calculates configuration data of different virtual control nodes in a serial manner by using a serial-based configuration computing method under the condition that there are many virtual control nodes, so that the operation of the configuration executor is reduced, that is, the CPU computing resource occupancy rate of the executor module itself is reduced. The method not only can effectively improve the utilization rate of the data computing resources, but also can reduce the influence of unnecessary resource occupation on the network load of the system and the performance of the controller.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a serial computing method oriented to configuration software, so as to solve the problems of high requirements of parallel computing on system computing resources, high CPU occupation rate and high power consumption in the prior art.
The invention is realized by the following steps: a serial computing method facing configuration software is characterized in that logic data to be computed of multiple virtual control nodes are stored in a computing queue in a specified data arrangement mode by adopting a data queue mode; and the configuration calculation executor sequentially calls the logic data to be calculated according to the calculation queue and writes the calculation result into the memory area for other virtual control nodes to call.
The specific process is as follows:
step S1, configuring a memory area for each virtual control node, where the memory area is used to store logic data to be calculated by the corresponding virtual control node, and the memory area includes logic data of configuration logic of all the virtual control nodes;
step S2, adding digital labels to the stored logic data according to a preset data arrangement mode, and adding the digital labels to a serial calculation queue;
step S3, the data transmission module sends the logic data of the serial calculation queue to the configuration calculation executor in sequence, and removes the logic data from the serial calculation queue;
step S4, the configuration calculation executor performs configuration calculation according to the logic data, and writes the configuration calculation result into the memory area for other virtual control nodes to call.
After detecting that the configuration calculation executor completes configuration calculation of a group of logic data, the data transmission module sends the next group of logic data to the configuration calculation executor to perform a new round of configuration calculation until the serial calculation queue is empty.
The logic data to be calculated of each virtual control node is firstly packaged into a data block and then stored into the corresponding memory area.
The invention has the following advantages: the method is different from a common parallel computing method, adopts a serial computing-based mode, can meet the general requirements of the operation of configuration software to the maximum extent, has lower requirements on an operating system, can orderly complete computing tasks even under the configuration computing requirements of multiple virtual control nodes, reduces the CPU resource occupancy rate of a configuration computing actuator module, and greatly reduces the energy consumption in the computing process.
Drawings
The invention will be further described with reference to the following examples with reference to the accompanying drawings.
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The serial computing method facing the configuration software stores logic data to be computed of multiple virtual control nodes in a computing queue in a specified data arrangement mode by adopting a data queue mode; and the configuration calculation executor sequentially calls the logic data to be calculated according to the calculation queue and writes the calculation result into the memory area for other virtual control nodes to call. The predetermined data arrangement manner may be the order of each virtual control node, or may be the arrangement of the order tags included in the logical data of each virtual control node.
As shown in fig. 1, the specific process is as follows:
step S1, configuring a memory area for each virtual control node, where the memory area is used to store logic data to be calculated by the corresponding virtual control node, and the memory area includes logic data of configuration logic of all the virtual control nodes; the virtual control nodes have the function of simulating a physical control station to execute a control program, and the logic data to be calculated of each virtual control node is firstly respectively packaged into a data block and then stored in the corresponding memory area.
Step S2, adding digital labels to the stored logic data according to a preset data arrangement mode, and adding the digital labels to a serial calculation queue;
step S3, the data transmission module sends the logic data of the serial calculation queue to the configuration calculation executor in sequence, and removes the logic data from the serial calculation queue;
step S4, the configuration calculation executor performs configuration calculation according to the logic data, and writes the configuration calculation result into the memory area for other virtual control nodes to call.
The data transmission module transmits the logic data positioned at the first bit of the serial calculation queue to the configuration calculation executor at the beginning, removes the logic data from the serial calculation queue, and transmits the next group of logic data to the configuration calculation executor to perform a new round of configuration calculation when the data transmission module detects that the configuration calculation executor completes the configuration calculation after the configuration calculation of the group of logic data is completed by the calculation executor until the serial calculation queue is empty.
The method is different from a common parallel computing method, adopts a serial computing-based mode, can meet the general requirements of the operation of configuration software to the maximum extent, has lower requirements on an operating system, can orderly complete computing tasks even under the configuration computing requirements of multiple virtual control nodes, reduces the CPU resource occupancy rate of a configuration computing actuator module, and greatly reduces the energy consumption in the computing process.
Although specific embodiments of the invention have been described above, it will be understood by those skilled in the art that the specific embodiments described are illustrative only and are not limiting upon the scope of the invention, and that equivalent modifications and variations can be made by those skilled in the art without departing from the spirit of the invention, which is to be limited only by the appended claims.
Claims (3)
1. A serial computing method oriented to configuration software is characterized in that: storing logic data to be calculated of multiple virtual control nodes in a calculation queue in a specified data arrangement mode by adopting a data queue mode; the configuration calculation executor sequentially calls logic data to be calculated according to the calculation queue, and writes calculation results into a memory area for other virtual control nodes to call:
step S1, configuring a memory area for each virtual control node, where the memory area is used to store logic data to be calculated by the corresponding virtual control node, and the memory area includes logic data of configuration logic of all the virtual control nodes;
step S2, adding digital labels to the stored logic data according to a preset data arrangement mode, and adding the digital labels to a serial calculation queue;
step S3, the data transmission module sends the logic data of the serial calculation queue to the configuration calculation executor in sequence, and removes the logic data from the serial calculation queue;
step S4, the configuration calculation executor performs configuration calculation according to the logic data, and writes the configuration calculation result into the memory area for other virtual control nodes to call.
2. The serial computing method for configuration software according to claim 1, wherein: after detecting that the configuration calculation executor completes configuration calculation of a group of logic data, the data transmission module sends the next group of logic data to the configuration calculation executor to perform a new round of configuration calculation until the serial calculation queue is empty.
3. The serial computing method for configuration software according to claim 1, wherein: the logic data to be calculated of each virtual control node is firstly packaged into a data block respectively and then stored into the corresponding memory area.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710698009.8A CN107479683B (en) | 2017-08-15 | 2017-08-15 | Serial computing method oriented to configuration software |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710698009.8A CN107479683B (en) | 2017-08-15 | 2017-08-15 | Serial computing method oriented to configuration software |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107479683A CN107479683A (en) | 2017-12-15 |
CN107479683B true CN107479683B (en) | 2019-12-20 |
Family
ID=60599639
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710698009.8A Active CN107479683B (en) | 2017-08-15 | 2017-08-15 | Serial computing method oriented to configuration software |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107479683B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105487930A (en) * | 2015-12-01 | 2016-04-13 | 中国电子科技集团公司第二十八研究所 | Task optimization scheduling method based on Hadoop |
CN105610972A (en) * | 2016-02-01 | 2016-05-25 | 中博信息技术研究院有限公司 | Clustered task dispatching system |
CN106528288A (en) * | 2015-09-10 | 2017-03-22 | 中兴通讯股份有限公司 | Resource management method, device and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9578081B2 (en) * | 2011-02-02 | 2017-02-21 | Imvu, Inc. | System and method for providing an actively invalidated client-side network resource cache |
-
2017
- 2017-08-15 CN CN201710698009.8A patent/CN107479683B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106528288A (en) * | 2015-09-10 | 2017-03-22 | 中兴通讯股份有限公司 | Resource management method, device and system |
CN105487930A (en) * | 2015-12-01 | 2016-04-13 | 中国电子科技集团公司第二十八研究所 | Task optimization scheduling method based on Hadoop |
CN105610972A (en) * | 2016-02-01 | 2016-05-25 | 中博信息技术研究院有限公司 | Clustered task dispatching system |
Also Published As
Publication number | Publication date |
---|---|
CN107479683A (en) | 2017-12-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8893145B2 (en) | Method to reduce queue synchronization of multiple work items in a system with high memory latency between processing nodes | |
CN107038069B (en) | Dynamic label matching DLMS scheduling method under Hadoop platform | |
CN110442451B (en) | Deep learning-oriented multi-type GPU cluster resource management scheduling method and system | |
US9747132B2 (en) | Multi-core processor using former-stage pipeline portions and latter-stage pipeline portions assigned based on decode results in former-stage pipeline portions | |
CN104714785A (en) | Task scheduling device, task scheduling method and data parallel processing device | |
CN104137075A (en) | Resource allocation method and apparatus of gpu | |
CN107656813A (en) | The method, apparatus and terminal of a kind of load dispatch | |
CN111104211A (en) | Task dependency based computation offload method, system, device and medium | |
US9471387B2 (en) | Scheduling in job execution | |
CN114741207A (en) | GPU resource scheduling method and system based on multi-dimensional combination parallelism | |
CN103218329A (en) | Digital signal processing data transfer | |
CN104123304A (en) | Data-driven parallel sorting system and method | |
CN104094235A (en) | Multithreaded computing | |
CN104199739A (en) | Speculation type Hadoop scheduling method based on load balancing | |
CN102004664A (en) | Scheduling method of embedded real-time operating system of space vehicle | |
CN108446180A (en) | A kind of data center dynamic method for scheduling task based on Data Migration | |
CN105808346A (en) | Task scheduling method and device | |
WO2023082575A1 (en) | Graph execution pipeline parallelism method and apparatus for neural network model computation | |
WO2016024508A1 (en) | Multiprocessor device | |
WO2022160628A1 (en) | Command processing apparatus and method, electronic device, and computer-readable storage medium | |
US20210390405A1 (en) | Microservice-based training systems in heterogeneous graphic processor unit (gpu) cluster and operating method thereof | |
CN103677959A (en) | Virtual machine cluster migration method and system based on multicast | |
CN103309734A (en) | Embedded task scheduling method based on priority grouping | |
CN116069480B (en) | Processor and computing device | |
CN107479683B (en) | Serial computing method oriented to configuration software |
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 |