Intel® MPI Library Developer Guide for Windows* OS

Download PDF
ID 768730
Date 3/31/2023
Public

A newer version of this document is available.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

Document Table of Contents
Document Table of Contents x
Intel® MPI Library Developer Guide for Windows* OS
Intel® MPI Library Developer Guide for Windows* OS x
Introduction Installation and Prerequisites Compiling and Linking Running Applications Debugging Applications Analysis and Tuning Troubleshooting Notices and Disclaimers
Introduction x
Introducing Intel® MPI Library Conventions and Symbols Related Information
Installation and Prerequisites x
Installation Prerequisite Steps User Authorization
Compiling and Linking x
Compiling an MPI Program Configuring a Microsoft Visual Studio* Project
Running Applications x
Running Intel® MPI Library in Containers Selecting a Library Configuration Running an MPI Program Running an MPI/OpenMP* Program MPMD Launch Mode Fabrics Control Job Schedulers Support Microsoft HPC Pack* Altair* PBS Pro* Controlling Per-Host Process Placement Controlling Process Placement Java* MPI Applications Support
Running Intel® MPI Library in Containers x
Build a Singularity* Container for an MPI Application Run the Application with a Container
Fabrics Control x
Selecting Fabrics Libfabric* Support OFI* Providers Support
Debugging Applications x
Debugging Using -gtool for Debugging
Analysis and Tuning x
Displaying MPI Debug Information Tracing Applications MPI Tuning
Troubleshooting x
Error Message: Bad Termination Error Message: No such file or Directory Error Message: Permission Denied Error Message: Fatal Error Error Message: Bad File Descriptor Error Message: Too Many Open Files Problem: MPI Application Hangs Problem: Password Required Problem: Cannot Execute Binary File Problem: MPI limitation for Docker*
Intel® MPI Library Developer Guide for Windows* OS

Job Schedulers Support

The Intel® MPI Library supports the majority of commonly used job schedulers in the HPC field.

The following job schedulers are supported on Windows* OS:

  • Microsoft HPC Pack*
  • Altair PBS Pro*

Microsoft HPC Pack*

The Intel MPI Library job startup command mpiexec can be called out of Microsoft HPC Job Scheduler to execute an MPI application. In this case, the mpiexec command automatically inherits the host list, process count, and the working directory allocated to the job.

Use the following command to submit an MPI job: 

> job submit /numprocessors:4 /stdout:test.out mpiexec -delegate test.exe

Make sure the mpiexec and dynamic libraries are available in PATH.

Altair* PBS Pro*

The Intel MPI Library job startup command mpiexec can be called out of PBS Pro job scheduler to execute an MPI application. In this case, the mpiexec command automatically inherits the host list, process count allocated to the job if they were not specified manually by the user. mpiexec reads %PBS_NODEFILE% environment variable to count a number of processes and uses it as a machine file.

Example of a job script contents: 

REM PBS -l nodes=4:ppn=2
REM PBS -l walltime=1:00:00
cd %PBS_O_WORKDIR%
mpiexec test.exe

Use the following command to submit the job: 

> qsub -C "REM PBS" job

mpiexec will run two processes on each of four nodes for this job.

Controlling Per-Host Process Placement

When using a job scheduler, by default the Intel MPI Library uses per-host process placement provided by the scheduler. This means that the -ppn option has no effect. To change this behavior and control process placement through -ppn (and related options and variables), use the I_MPI_JOB_RESPECT_PROCESS_PLACEMENT environment variable: 

> set I_MPI_JOB_RESPECT_PROCESS_PLACEMENT=off
Parent topic: Running Applications
Level Two Title