Multi-server parallel computing platform C# source code (realizing supercomputer) source code

The original code has been uploaded...

Multi-server parallel computing platform C# original code (realizing supercomputer), through .net remoting method and data slicing technology, only a certain number of servers or PCs, connecting network cables and 100-port switch networking can support 100 servers or PCs. Parallel computing, the data is sub-packaged on each server or PC and the results are summarized to the management terminal. It can simulate nuclear explosions, ballistic budgets, weather forecasts and other tasks that require huge computing power. On the basis of this original code, slight modifications can be made. As a parallel computing platform for projects that require large computing power.

Parallel computing refers to the process of using multiple computing resources to solve computing problems at the same time. It is an effective means to improve the computing speed and processing capacity of a computer system. It can be divided into parallel in time and parallel in space. Parallel in time refers to pipeline technology, while parallel in space refers to the concurrent execution of calculations with multiple processors.
Its basic idea is to use multiple processors to solve the same problem cooperatively, that is, to decompose the solved problem into several parts, and each part is calculated in parallel by an independent processor. A parallel computing system can be a specially designed supercomputer with multiple processors, or a cluster of several independent computers interconnected in a certain way. The data is processed through parallel computing clusters, and the results of the processing are returned to the user. Concurrency is a universal attribute of the material world. In many cases, computing problems with practical application background can be decomposed into multiple sub-components that can be calculated in parallel. Task . It should be noted that parallel computing is not equal to distributed computing. The former refers to processing or computing the same problem on multiple machines at the same time, while the latter refers to processing or computing different problems on multiple machines at the same time.

1. In order to make the framework of the entire parallel computing platform simple and easy to understand, and easy to modify for actual work, I did not use complex algorithms for the parallel algorithm examples. Readers can modify their own algorithms on the basis of this framework. The modified places are in the original code. Marked in.

2. The computing power of each machine participating in parallel computing is allocated in a task pool mode, or it can be changed to an average mode by itself.

3. Each machine participating in parallel computing returns the result value to the management PC (when all tasks are completed, the management machine adds up the total result)

Implementation method, all computers in the local area network install the parallel computing server server, the management PC calls the parallel algorithm on each parallel server server in the local multi-thread, and monitors the calculation of the parallel server server. If the calculation of the parallel server server is completed, Distribute new tasks, and manage the PC to sum up the total value of the local machine after all the computing tasks of the parallel server server are completed. (As the management PC needs to run multiple threads, a better multi-core CPU computer can be used)

4. The code contains the bhjsServer directory and the WindowsFormsbhjs directory, which are the parallel computing server side and the management PC side respectively. The bhjsServer directory must be deployed to all machines that want to participate in parallel computing and run bhjsServer.exe.

5. Just modify the algorithm public long Calculatebh() in the code of class ServerClass1 in the bhjsServer directory to recompile your own algorithm.

6. Enter the name of each machine participating in parallel computing on the LAN in the parallel computing client on the management PC.

7. The database in the DataBase directory is restored to SQLSERVER, storing configuration information and calculation results (SQLSERVER is placed on the management PC).

8. The environment is VS2015 C# and SQLSERVER 2014 or higher.

 

 

.

As shown in the figure above, two machines (supporting hundreds of machines) participate in parallel calculation, calculate at the same time, and return the calculated value

Link:   https://pan.baidu.com/s/1HLWQ9rbhW9WM01N6ohDsBw Extraction code: rktn

csdn download:  https://download.csdn.net/download/fanxiaoduo1/12309241

The source code will be constantly updated..... Please download the latest version

April 5, 2020 update

Update on April 13, 2020

Link: https://pan.baidu.com/s/1w3EfIga9sSJavfbhBoilyQ Extraction code: 35gt

Guess you like

Origin blog.csdn.net/fanxiaoduo1/article/details/105266867