Hi,
     Attached is the output I got from using mpiexec.   Amos

On Wed, Dec 21, 2011 at 5:17 PM, Gustavo Correa <gus@ldeo.columbia.edu> wrote:
When I pushed "Send" on this email
I thought immediately: " ... hmm, Ralph or Jeff will say this is wrong ..."

Wow! Support to singletons!
I haven't read this word since long forgotten readings in Set Theory.
So, if you run a single process, you can do away with mpiexec,
and pretend that the code were serial, right?
Amazing. You guys think of all edge cases!

Happy Holidays!

Gus Correa
[standing corrected]

On Dec 21, 2011, at 4:44 PM, Ralph Castain wrote:

> Not  really - we support singletons, so that should work. The key is to have LD_LIBRARY_PATH set correctly in the environment.
>
> On Dec 21, 2011, at 1:08 PM, Gustavo Correa wrote:
>
>> You probably need also to launch the program with mpiexec (mpiexec -np 4 ./hello_c),
>> not just ./hello_c as your email suggests you did.
>>
>> On Dec 21, 2011, at 2:12 PM, Ralph Castain wrote:
>>
>>> Did you remember to set your LD_LIBRARY_PATH to include /opt/openmpi, per your configure line?
>>>
>>>
>>> On Dec 21, 2011, at 11:56 AM, amosleff@gmail.com wrote:
>>>
>>>> Dear OMPI Users,
>>>>        I have just read the messages from Martin Rushton and Jeff Squyres and have been having the same problem trying to get openmp-1.4.4 to work.  My specs are below:
>>>>                         Xeon(R) CPU 5335 2.00 GHz
>>>>                         Linux  SUSE 11.4 (x86_64)
>>>>                         Linux 2.6.371-1.2 desktop x86_64
>>>> I go through the compilation process with the commands:
>>>>                        ./configure --prefix=/opt/openmpi CC=icc CXX=icpc F77=ifort F90=ifort "FCFLAGS=-O3 -i8" "FFLAGS=-O3 -i8" 2>&1 | tee config.out
>>>>                         make -j 4 all 2>&1 | tee make.out
>>>>                         make install 2>&1 | tee install.out.
>>>> The entire process seems to go properly but when I try to use an example it doesn't work properly.
>>>>                         mpicc hello_c.c -o hello_c
>>>> compiles properly.  However,
>>>>                         "./hello_c" gives an error message that it cannot find the file libmpi_so.0.    There are at least 3 copies of the file present as found by the search command but none of these are found.  I have checked the permissions and they seem to be OK so I am at the same point as Martin Rushton.  I hope that somebody comes up with an anser soon.
>>>>                                                                                                        Amos Leffler
>>>> _______________________________________________
>>>> users mailing list
>>>> users@open-mpi.org
>>>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>>
>>>
>>> _______________________________________________
>>> users mailing list
>>> users@open-mpi.org
>>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>>
>>
>> _______________________________________________
>> users mailing list
>> users@open-mpi.org
>> http://www.open-mpi.org/mailman/listinfo.cgi/users
>
>
> _______________________________________________
> users mailing list
> users@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users


_______________________________________________
users mailing list
users@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users