Hi,
We're having a problem with the Intel MPI library crashing since we've updated to the latest Mellanox OFED 2.1. For example, the test program supplied with Intel MPI (test/test.f90) crashes with a segfault. I compiled it using
mpif90 -debug all /apps/intel-mpi/4.1.1.036/test/test.f90 -o test.x
and managed to get a back trace from the crash using idbc:
#0 0x00007fcb9418f078 in ?? () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #1 0x00007fcb94190bf7 in ?? () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #2 0x00007fcb94191543 in MPID_nem_dapl_rc_init_20 () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #3 0x00007fcb941de883 in MPID_nem_dapl_init () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #4 0x00007fcb94276fc6 in ?? () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #5 0x00007fcb9427547c in MPID_nem_init_ckpt () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #6 0x00007fcb94276ca7 in MPID_nem_init () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #7 0x00007fcb94128070 in MPIDI_CH3_Init () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #8 0x00007fcb94265bad in MPID_Init () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #9 0x00007fcb9423c38f in MPIR_Init_thread () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #10 0x00007fcb94230258 in PMPI_Init () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpi.so.4 #11 0x00007fcb946f331f in pmpi_init__ () from /apps/intel-mpi/4.1.1.036/intel64/lib/libmpigf.so.4 #12 0x0000000000403005 in main () at /apps/intel-mpi/4.1.1.036/test/test.f90:28 #13 0x0000000000402fbc in main ()
We are running CentOS 6.5.
Cheers,
Ben