Intel® MPI Library Developer Guide for Linux* OS

ID 768728
Date 12/16/2022

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents
Give Feedback

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 script, which is found in your installation directory (by default, /opt/intel/oneapi/mpi/<version> ).

    You must run setvars at the start of each session. See the Intel oneAPI HPC Toolkit Get Started Guide for more details, including options for automatic setup of environment settings.
  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

  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.

IntelMPI uses PowerShell bootstrap by default. It is available by default and does not require any extra steps. If you need more fine-grain setup information, refer to Microsoft PowerShell Setup Guide (, Security Guide (, and Troubleshooting Guide ( You can also consider domain-based authorization as an alternative to the default mechanism. However, this method requires additional configuration. See User Authorization.

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