Method and device for calling MPI function

Abstract

The application provides a method and device for calling the MPI function and relates to the technical field of testing. The device comprises a sequencing operation module, a calling execution module and a first preset module, wherein the sequencing operation module is used for conducting a uniform sequencing operation for all MPI calling requests when a computation server executes a task; the calling execution module is suitable for calling MPI functions corresponding to the MPI calling requests one by one for operation according to a sequence after the sequencing operation; the first preset module is suitable for constructing a queue and constructing a corresponding packaging function aiming at each MPI function in an OpenMPI library; when the computation server executes the task, if threads in the computation server send the respective MPI calling requests to call the MPI functions in the open MPI library, the queue and the packaging functions are used for conducting the uniform sequencing operation for all MPI calling requests. The MPI function calling method and the MPI function calling device have the beneficial effects that the MPI functions in the MPI library can be called by multiple threads, and in a cloud computing environment, the advantages of fine grit and high parallel performance of cloud computing can be fully exerted.

Description

technical field [0001] The present application relates to the technical field of testing, in particular to an MPI function calling method and device. Background technique [0002] The types of cloud computing (cloud computing: a computing model that provides dynamically scalable virtualized resources as a service through a computer network) programs can be divided into parallel programs without communication types and parallel programs with communication types. For the parallel program without communication type, each process (that is, each subtask) of the calculation (usually called a job) can be started at any time, and does not need to be started at the same time as other subtasks, because there is no need for communication between subtasks, each Each subtask can end directly after processing its own calculation. Therefore, the cloud computing platform scheduler can schedule different subtasks at different times, and the scheduling method to deal with this scheduling req...

AI Technical Summary

Problems solved by technology

In the strictly phased program, computing and network cannot be performed at the same time, and the advantages of fine-grained and high parallelism of cloud computing cannot be fully utilized.

[0010] 2. Program writers need to keep in mind that OpenMPI functions cannot be used in multiple threads. For cloud computing program writers, it is easy to make mistakes, resulting in undetectable problems in the program

Images