NOTE: Defects and feature requests described below represent specific issues with specific test cases. It is difficult to succinctly describe an issue and how it impacted the specific test case. Some of the issues listed may impact multiple architectures, operating systems, and/or languages. If you have any questions about the issues discussed in this report, please post on the user forums, http://software.intel.com/en-us/forums or submit an issue to Intel® Premier Support, https://premier.intel.com.
If you have a previous version of the Intel® MPI Library for Linux* OS installed, you do not need to uninstall it before installing the latest version.
Extract the l_mpi[-rt]_p_<version>.<package_num>.tar.gz package by using following command:
tar –xvzf l_mpi[-rt]_p_<version>.<package_num>.tar.gz
This command creates the subdirectory l_mpi[-rt]_p_<version>.<package_num>.
Environment variable I_MPI_DEBUG provides a very convenient way to get information from an MPI application at runtime. You can set value of this variable from 0 (the default value) to 1000. The higher the value, the more debug information you get.
$ mpirun -genv I_MPI_DEBUG 5 -n 8 ./my_application
To limit the number of processes running on one node, you can use the perhost-range min:max option. For example: the following command defines the number of MPI ranks on each node, between 4 and 8:
$ mpitune --perhost-range 4:8
When faced with errors or failures during usage of the Intel® MPI Library, take the following general troubleshooting steps:
Check the System Requirements section and the Known Issues section in Intel® MPI Library Release Notes.
Check accessibility of the hosts. Run a simple non-MPI application (for example, the hostname utility) on the problem hosts using mpirun.
This document reflects the updates for Intel® MPI Library 5.1 Update 2 for Linux* OS:
The following latest changes in this document were made:
-n <# of processes> or -np <# of processes>
Use this option to set the number of MPI processes to run with the current argument set.
-env <ENVVAR> <value>
Use this option to set the <ENVVAR> environment variable to the specified <value> for all MPI processes in the current arg-set.
This topic concentrates on the Intel® MPI Library specifics related to the support of the Intel® Xeon Phi™ Coprocessor (codename: Knights Corner) based on Intel® Many Integrated Core Architecture (Intel® MIC Architecture).
Choose the network interface for MPI communication over TCP-capable network fabrics.
Define the network interface (string parameter)