On Wednesday, August 6, 2003, at 12:58 PM, Jeff Squyres wrote:
> On Tue, 5 Aug 2003, galitz wrote:
>
>> When I compile the source RPM of the lam-7.0-1 with PGI 4.1 (portland
>> group compilers) my hello world application fails with a signal 11.
>> Here is the full output:
>
> I assume that you mean:
> - you rebuilt the LAM SRPM with the PGI 4.1 compilers
> - installed the resulting RPM
> - lambooted with the newly-installed lamboot
> - compiled your hello world application with the newly-installed mpicc
> - tried to run your hello world app with the newly-installed mpirun
>
> Is this correct?
>
Yes. This is correct.
In addition, after some more playing around, this problem does not
seem to occur with fortran compiled programs (compiled with the
newly-installed mpif77).
>> [galitz_at_univac galitz]$ mpirun C hello
>> ----------------------------------------------------------------------
>> -------
>> One of the processes started by mpirun has exited with a nonzero exit
>> code. This typically indicates that the process finished in error.
>> If your process did not finish in error, be sure to include a "return
>> 0" or "exit(0)" in your C code before exiting the application.
>>
>> PID 23094 failed on node n0 (127.0.0.1) due to signal 11.
>> ----------------------------------------------------------------------
>> -------
>
> Can you run it without mpirun? i.e., "./hello"?
>
> Can you compile it with -g and run it through a debugger to see where
> it
> is seg faulting?
>
> --
> {+} Jeff Squyres
> {+} jsquyres_at_[hidden]
> {+} http://www.lam-mpi.org/
|