On Dec 28, 2005, at 4:50 AM, Graziano Giuliani wrote:
Hi all,
can confirm this bug also on Linux Debian testing with kernel
2.6.14 and
gcc (GCC) 4.0.3 20051201 (prerelease) (Debian 4.0.2-5) running WRF
atmospheric
model compiled with portland pgf90. For who cares about this, it
needs just a
little patch in the RSL layer of the model to convert fortran
integer comms
to C comms (MPICH uses integer for boths, just a matter of using
MPI_Comm_f2c).
Shame on the developers of the atmospheric code for not using
MPI_Comm_{f2c,c2f} in the first place ;).
It is not limited to FC4.
Interesting thing is that it works if pls_rsh_debug is set....
Could you generate a stack trace from a core file? It would be good
to verify that this is the startup bug we are seeing with FC4 and not
another bug somewhere else. Or, I think you are using a recent
enough version of Open MPI that you should see a stack trace printed
when a SIGSEGV or SIGBUS occurs. Finally, could you let me know what
options you passed to configure and send the config.out file
generated by configure (this is probably unrelated to the error with
sm, but I'm curious why you ended up with the malloc_hooks component
-- it shouldn't be automatically chosen in any circumstance).
Thanks,
Brian
--
Brian Barrett
Open MPI developer
http://www.open-mpi.org/