Intel® MPI Library Developer Guide for Linux* OS

ID 768728
Date 10/31/2024
Public
Document Table of Contents

Prerequisite Steps

Before you start using any of the Intel® MPI Library functionality, make sure to establish the proper environment settings:

  1. Set up the Intel MPI Library environment by sourcing the setvars.sh script, which is found in your installation directory (by default, /opt/intel/oneapi/mpi/<version> ).

    NOTE:
    You must run setvars at the start of each session. See the Intel HPC Toolkit Get Started Guide for more details, including options for automatic setup of environment settings.
    NOTE:
    If you are using Intel MPI in a Unified Directory Layout, set the environment variables using the /opt/intel/oneapi/<toolkit-version-number>/oneapi_vars.sh script instead. To understand more about the Unified Directory Layout, including how the environment is initialized and the advantages of using the layout, see Use the setvars and oneapi-vars Scripts with Linux* .
  2. To run an MPI application on a cluster, the Intel MPI Library needs to know names of all its nodes. Create a text file listing the cluster node names. The format of the file is one name per line, and the lines starting with # are ignored. To get the name of a node, use the hostname utility.

    A sample host file may look as follows:

    $ cat ./hosts
    # This line is ignored
    clusternode1
    clusternode2
    clusternode3
    clusternode4

  3. For communication between cluster nodes, in most cases the Intel MPI Library uses the SSH protocol. You need to establish a passwordless SSH connection to ensure proper communication of MPI processes.

After completing these steps, you are ready to use the Intel MPI Library.