Indeed. In LAM, mpiexec is simply a perl wrapper around mpirun.
Check your $PATH, or use an absolute pathname to launch your
executable. The perl in mpiexec may be finding a different appName
than the one you expect...?
On Nov 10, 2005, at 12:14 PM, Michael Lees wrote:
> Yep you're test program seems to work for me too.
>
> I don't understand why with my real application I can't just swap the
> 'run' for 'exec'?
>
> Using mpirun, everything works fine - with mpiexec I get
>
> -----------------------------------------------------------------------
> ------
> It seems that [at least] one of the processes that was started with
> mpirun did not invoke MPI_INIT before quitting (it is possible that
> more than one process did not invoke MPI_INIT -- mpirun was only
> notified of the first one, which was on node n0).
>
> mpirun can *only* be used with MPI programs (i.e., programs that
> invoke MPI_INIT and MPI_FINALIZE). You can use the "lamexec" program
> to run non-MPI programs over the lambooted nodes.
> -----------------------------------------------------------------------
> ------
> mpirun failed with exit status 252
>
>
>
> Mike
>
>
>
> Jeff Squyres wrote:
>> What version of LAM are you using? This does not cause a problem for
>> me. For example:
>>
>> [16:57] eddie:~/mpi % cat hello.c
>> #include <stdio.h>
>> #include <mpi.h>
>> #include <stdlib.h>
>>
>> int main(int argc, char **argv)
>> {
>> int rank = 0, size = 0;
>> char hostname[BUFSIZ];
>>
>> MPI_Init(&argc, &argv);
>> MPI_Comm_rank(MPI_COMM_WORLD, &rank);
>> MPI_Comm_size(MPI_COMM_WORLD, &size);
>> gethostname(hostname);
>> printf("Hello, world! I am %d of %d (argv: %s)\n", rank, size,
>> argv[1]);
>>
>> MPI_Finalize();
>> return 0;
>> }
>> [16:57] eddie:~/mpi % mpicc hello.c -o hello
>> [16:57] eddie:~/mpi % mpirun -np 2 hello hfoo
>> Hello, world! I am 0 of 2 (argv: hfoo)
>> Hello, world! I am 1 of 2 (argv: hfoo)
>> [16:57] eddie:~/mpi % mpiexec -np 2 hello hfoo
>> Hello, world! I am 1 of 2 (argv: hfoo)
>> Hello, world! I am 0 of 2 (argv: hfoo)
>>
>>
>>
>>
>> On Nov 9, 2005, at 12:47 PM, Michael Lees wrote:
>>
>>
>>> Is there any reason why
>>>
>>> mpirun -np 1 appName arg1 arg2 arg3
>>> works and
>>>
>>> mpiexec -np 1 appName arg1 arg2 arg3
>>> does not?
>>>
>>> From the manual page any arguments after appName should be passed
>>> transparently to mpirun?
>>> Am I missing something? appName in the second case fails becuase it
>>> receives no command line arguments?
>>>
>>> Cheers
>>> --
>>> Mike
>>>
>>>
>>> This message has been checked for viruses but the contents of an
>>> attachment
>>> may still contain software viruses, which could damage your
>>> computer system:
>>> you are advised to perform your own checks. Email communications
>>> with the
>>> University of Nottingham may be monitored as permitted by UK
>>> legislation.
>>>
>>> _______________________________________________
>>> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>>>
>>
>>
>> _______________________________________________
>> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
> This message has been checked for viruses but the contents of an
> attachment
> may still contain software viruses, which could damage your computer
> system:
> you are advised to perform your own checks. Email communications with
> the
> University of Nottingham may be monitored as permitted by UK
> legislation.
>
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
--
{+} Jeff Squyres
{+} The Open MPI Project
{+} http://www.open-mpi.org/
|
