Looking for a solution?

Where there's a problem there's a solution

  • When launching FLUENT in parallel I get this error:
    fluent_mpi.6.3.26: Rank 0:0: MPI_Init: Can't initialize RDMA device
    fluent_mpi.6.3.26: Rank 0:0: MPI_Init: MPI BUG: Cannot initialize RDMAComments:

  • Can't initialize RDMA device error indicates an incompatible HPMPI or OFED version with FLUENT.

    OFED 1.2 needs HPMPI 2.2.5.1 so you will need to be running Fluent 6.3.35

    Determining what OFED version you are running:

    "cat /usr/ofed/BUILD_ID" will give us this info or % find /usr -name BUILD_ID

    Determining the Software Version

    If InfiniBand drivers are already installed on the host, they may be installed in one of several locations.

    To determine the version of the Cisco InfiniBand host drivers, log in to the host and enter the following commands at the shell prompt. If the first command produces output, the Cisco Commercial InfiniBand host drivers are installed. If the second or third commands produce a version number, OFED host drivers are installed.

    host$ rpm -qa | grep topspin
    topspin-ib-mpi-rhel4-3.2.0-118
    topspin-ib-mod-rhel4-2.6.9-34.ELsmp-3.2.0-118
    topspin-ib-rhel4-3.2.0-118
    host$ ofed_info | grep OFED
    OFED-1.1
    host$ grep OFED /usr/local/ofed/BUILD_ID
    OFED-1.1

    Cisco Documentation
    http://www.cisco.com/en/US/docs/server_nw_virtual/open_fabrics_enterprise_distribution/ofed_host_driver/release1.2/release_note/rn11537.html#wp16932



  • Show Form
    No comments yet. Be the first to add a comment!