Intel Software Network articles feed http://software.intel.com/en-us/articles/intel-mpi-library-for-windows-kb/tips-and-techniques/ en-us Tips and tricks - FAQ
  • Are there any DAPL* implementations available for Microsoft* Windows*?
  • How do you run an Intel® MPI Library application located on a network resource?
  • How do you pin processes to prevent undesired process migration?

    • Are there any DAPL* implementations available for Microsoft* Windows*?

    Yes. Find Windows OpenFabrics* (WinOF*) at OpenFabrics* Alliance website http://www.openfabrics.org/downloads/WinOF/ †

     

    How do you run an Intel® MPI Library application located on a network resource?

    Use the mpiexec -gwdir or -wdir options to specify a working directory for the application.

    For instance: mpiexec.exe -machinefile machine_file -n 4 -wdir \\host\share_folder IMB-MPI1.exe

     

    How do you pin processes to prevent undesired process migration?

    The Intel MPI Library automatically pins processes to CPUs to prevent undesired process migration. Use the I_MPI_PIN, I_MPI_PIN_MODE and I_MPI_PIN_PROCESSOR_LIST environment variables to control process pinning.

    For example: mpiexec -env I_MPI_DEVICE shm -env I_MPI_PIN enable -np 4 ./prog

    See the Intel® MPI Library for Windows Reference Manual for more details.

     

    † This link will take you off of the Intel Web site. Intel does not control the content of the destination Web Site.

    ]]>     http://software.intel.com/en-us/articles/tips-and-tricks-faq Thu, 18 Jun 2009 12:32:59 -0700 http://software.intel.com/en-us/articles/tips-and-tricks-faq#comments http://software.intel.com/en-us/articles/tips-and-tricks-faq Intel® MPI Library for Windows* Knowledge Base     Hybrid applications: Intel MPI Library and OpenMP* I have a mixed application which uses both MPI and OpenMP* calls. Does the Intel® MPI Library support this type of hybrid functionality?

    Yes, Intel MPI does support mixed MPI/OpenMP applications. To make sure your hybrid code runs correctly, follow these steps:

    1. Use the thread safe version of the Intel MPI Library by using the -mt_mpi compiler driver option
    2. Set the I_MPI_PIN_DOMAIN environment variable to select the desired process pinning scheme. The recommended setting is omp:
      $ export I_MPI_PIN_DOMAIN=omp

      This will set the process pinning domain size to be equal to OMP_NUM_THREADS. Therefore, each MPI process can create $OMP_NUM_THREADS number of children threads for running within the corresponding domain. If OMP_NUM_THREADS is not set, each node is treated as a separate domain (which will allow as many threads per MPI processes as there are cores).

      NOTE: In order to pin OpenMP threads inside the domain, use the corresponding OpenMP feature by setting the KMP_AFFINITY environment variable.

    3. See the “Interoperability with OpenMP*” section in the Intel® MPI Library for Linux* Reference Manual for more details
    ]]>     http://software.intel.com/en-us/articles/hybrid-applications-intelmpi-openmp Thu, 21 May 2009 07:42:27 -0700 http://software.intel.com/en-us/articles/hybrid-applications-intelmpi-openmp#comments http://software.intel.com/en-us/articles/hybrid-applications-intelmpi-openmp Intel® MPI Library for Linux* Knowledge Base Intel® MPI Library for Windows* Knowledge Base     Does Intel® MPI Library limit the number of procs on a node Question

    Does Intel® MPI Library limit the number of processes run on a single node?

    Answer

    No, it does not. Intel MPI has no internal restrictions on the number of MPI processes started on a node.

    NOTE: Be careful when running a large number of processes on a single machine. At some point, you might start oversubscribing the processor (meaning starting more processes than there are cores). This could lead to performance degradation.

    ]]>     http://software.intel.com/en-us/articles/does-intel-mpi-library-limit-the-number-of-procs-on-a-node Thu, 26 Feb 2009 07:53:14 -0800 http://software.intel.com/en-us/articles/does-intel-mpi-library-limit-the-number-of-procs-on-a-node#comments http://software.intel.com/en-us/articles/does-intel-mpi-library-limit-the-number-of-procs-on-a-node Intel® MPI Library for Linux* Knowledge Base Intel® MPI Library for Windows* Knowledge Base     Release notes Note: This web page refers to the entire set of Intel® Cluster Tools.

    Operating System:

    SUSE* Linux Enterprise Server 9.0, SUSE* Linux Enterprise Server 10, Red Hat* Enterprise Linux 4.0, Red Hat* Enterprise Linux 5.0, Windows* Compute Cluster Server 2003, Windows* HPC Server 2008
    ]]>     http://software.intel.com/en-us/articles/intel-cluster-tools-release-notes Fri, 16 Jan 2009 15:04:12 -0800 http://software.intel.com/en-us/articles/intel-cluster-tools-release-notes#comments http://software.intel.com/en-us/articles/intel-cluster-tools-release-notes Intel® Cluster Toolkit for Linux* Knowledge Base Intel® Cluster Toolkit for Windows* Knowledge Base Intel® MPI Library for Linux* Knowledge Base Intel® MPI Library for Windows* Knowledge Base Intel® Trace Analyzer and Collector for Linux* Knowledge Base Intel® Trace Analyzer and Collector for Windows* Knowledge Base