Intel® MPI Library

Intel® MPI Library 5.0 Update 2 Readme

The Intel® MPI Library is a high-performance interconnect-independent multi-fabric library implementation of the industry-standard Message Passing Interface, v3.0 (MPI-3.0) specification. This package is for MPI users who develop on and build for Intel® 64 architectures on Linux* and Windows*, as well as customers running on the Intel® Xeon Phi™ coprocessor on Linux*. You must have a valid license to download, install, and use this product.

  • Linux*
  • Microsoft Windows* (XP, Vista, 7)
  • Microsoft Windows* 8.x
  • Server
  • C/C++
  • Fortran
  • Intel® MPI Library
  • Message Passing Interface
  • Cluster Computing
  • HBM for the Intel® Xeon Phi™ Coprocessor

    Purpose

    This article provides instructions for code access, build, and run directions for the Baffin-Bay test cases for the HBM code, running on Intel® Xeon® processors and Intel® Xeon Phi™ Coprocessors.

    Introduction

    Danish Meteorological Institute (DMI) operates a regional 3D ocean model HBM for the North Sea - Baltic, in order to provide information about the physical state of the Danish and nearby waters in the near future.

  • Developers
  • Linux*
  • Server
  • Intel® MPI Library
  • Danish Meteorological Institute
  • Intel(R) Xeon Phi(TM) Coprocessor
  • Intel® Many Integrated Core Architecture
  • Hydra Incompatibility with Certain gdb* Versions

    There is a known compatibility problem between Hydra and versions 7.2 and 7.3 of the GNU* Debugger (gdb*).  When running Hydra under one of these versions, Hydra will hang.

    Please use a different version of gdb in order to run Hydra under gdb.

    This has only been seen in Linux* at this time.

  • Developers
  • Linux*
  • Beginner
  • Intel® MPI Library
  • debugging
  • GNU* GDB
  • MPI
  • message passing interface
  • hang
  • intel mpi library
  • Message Passing Interface
  • Cluster Computing
  • Compiler Wrapper Scripts Returning 0 Incorrectly

    There is currently a known issue in the Intel® MPI Library for Linux*, affecting Version 5.0 and Version 5.0 Update 1.  The compiler wrapper scripts will always return 0, even if the compile or link failed.  This can lead to errors in makefiles or any job checking the return code.  The error is corrected and a fix is available in Version 5.0 Update 2.

    There are currently three workarounds for this issue:

  • Developers
  • Linux*
  • Beginner
  • Intel® MPI Library
  • Intel® MPI Library
  • known issue
  • Message Passing Interface
  • Cluster Computing
  • Timer Driven Checkpoint

    Timer Driven Checkpoint

    In the following example, a checkpoint is taken every 3600 seconds (=1hour). The checkpoints are stored in a directory called ckptdir. Each node generates one checkpoint which is named by the node number and number of that checkpoint.

    Subscribe to Intel® MPI Library