Dear All

I am trying to get openmpi-1.1.2 to work on AIX 5.3 / power5.

:: Compilation seems to have worked with the following sequence:

====================================================================

setenv OBJECT_MODE 64

setenv CC xlc

setenv CXX xlC

setenv F77 xlf

setenv FC xlf90

setenv CFLAGS "-qthreaded -O3 -qmaxmem=-1 -qarch=pwr5x -qtune=pwr5 -q64"

setenv CXXFLAGS "-qthreaded -O3 -qmaxmem=-1 -qarch=pwr5x -qtune=pwr5 -q64"

setenv FFLAGS "-qthreaded -O3 -qmaxmem=-1 -qarch=pwr5x -qtune=pwr5 -q64"

setenv FCFLAGS "-qthreaded -O3 -qmaxmem=-1 -qarch=pwr5x -qtune=pwr5 -q64"

setenv LDFLAGS "-Wl,-brtl"

./configure --prefix=/ist/openmpi-1.1.2 \

  --disable-mpi-cxx \

  --disable-mpi-cxx-seek \

  --enable-mpi-threads \

  --enable-progress-threads \

  --enable-static \

  --disable-shared \

  --disable-io-romio

====================================================================

:: After the compilation I ran make check and all 11 tests passed successfully.

:: Now I'm trying to run the following command just for test:

# mpirun -hostfile /gpfs/MICHAEL/MPI_hostfiles/mpinodes_b41-b44_1.asc -np 2 /usr/bin/hostname

- The file /gpfs/MICHAEL/MPI_hostfiles/mpinodes_b41-b44_1.asc contains 4 hosts:

    r1blade041 slots=1

    r1blade042 slots=1

    r1blade043 slots=1

    r1blade044 slots=1

- The mpirun command eventually hangs with the following message:

    [r1blade041:418014] poll failed with errno=25

    [r1blade041:418014] opal_event_loop: ompi_evesel->dispatch() failed.

- In this state mpirun cannot be killed by hitting <ctrl-c> only a kill -9 will do the trick.

- While the mpirun still hangs I can see that the "orted" has been launched on both requested hosts.

:: I turned on all debug options in openmpi-mca-params.conf. The output for the same call of mpirun is in the file mpirun-debug.txt.gz.