Doh!

This is a problem that was fixed on the trunk long ago and it somehow never 
made it over to the v1.0 branch.  Brian ported it over earlier today; it'll be 
in the 1.0.2a13 that should be on the web site in a few hours.

Thanks for bringing it to our attention.


> -----Original Message-----
> From: users-boun...@open-mpi.org 
> [mailto:users-boun...@open-mpi.org] On Behalf Of Francoise Roch
> Sent: Wednesday, March 29, 2006 7:08 AM
> To: us...@open-mpi.org
> Subject: [OMPI users] openmpi-1.0.2a12 on solaris opteron
> 
> 
> Hello,
> 
> I am attempting to run openmpi-1.0.2a12 on solaris opteron.
> I compile in 64 bit mode, with Studio11 compilers
> 
> The configure and the make run fine.
> 
> I compile my application with :
> mpicc -o myapp myapp.c
> 
> 1/ I have the following hieroglyphs and error message when launching 
> mpirun :
> 
> icare> mpirun -np 4 -host icare ./myapp
> T0<ú²þÿÿ+½T0<ú²þÿÿ4½T0<ú²þÿÿ=½T0<ú²þÿÿF½ld.so.1: myapp: fatal: 
> relocation error: file 
> /users/roch/lib/openmpi-1.0.2a12/lib/libmca_common_sm.so.0: symbol 
> nanosleep: referenced symbol not found
> ld.so.1: all2all: fatal: relocation error: file 
> /users/roch/lib/openmpi-1.0.2a12/lib/libmca_common_sm.so.0: symbol 
> nanosleep: referenced symbol not found
> ld.so.1: all2all: fatal: relocation error: file 
> /users/roch/lib/openmpi-1.0.2a12/lib/libmca_common_sm.so.0: symbol 
> nanosleep: referenced symbol not found
> ld.so.1: all2all: fatal: relocation error: file 
> /users/roch/lib/openmpi-1.0.2a12/lib/libmca_common_sm.so.0: symbol 
> nanosleep: referenced symbol not found
> 
> The problem is fixed by compiling with -lrt option :
> mpicc -lrt -o myapp myapp.c
> 
> 2/ I attempted to force interface exclusion without success :
> 
> n14 > mpirun --mca btl_tcp_if_exclude bge1 -np 2 -host p14,p39 myapp
> 9ÿÿÿÿÿýD $ ½T Ö¡¸ÿÿÿÿý $ ½Process 0 is alive on n14
> Process 1 is alive on n39
> [n39:26824] *** An error occurred in MPI_Barrier
> [n39:26824] *** on communicator MPI_COMM_WORLD
> [n39:26824] *** MPI_ERR_INTERN: internal error
> [n39:26824] *** MPI_ERRORS_ARE_FATAL (goodbye)
> 
> 
> Best Regards,
> Francoise
> 
> -- 
> 
> _______________________________________________
> users mailing list
> us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users
> 

Reply via email to