stack (overflow ?) issue with cosmomc on a cluster :

[Patrice Okouma]

Hi,
I am getting the error message pasted below on a cluster where I've been running a version of cosmomc (May 2010 ver). I get it quite quickly whenever I run - say - 5 chains over 5 nodes (1 chain per node). According to the post at
http://cosmocoffee.info/viewtopic.php?t=1074
I should be able to fix it with : ulimit -s unlimited
or by changing declarations of ninvplninv2 in wmap7 likelihood code
(It seems to have been done already in this May 2010 version of cosmomc)

Unfortunately
ulimit -s unlimited does not seem to help at all.

Would you please have any hint for me ?

Thanks & regards,
Patrice
--------------------------Here's the error message --------------------

forrtl: severe (174): SIGSEGV, segmentation fault occurred
Image PC Routine Line Source
. FFFFE410 Unknown Unknown Unknown
Unknown 0000000B Unknown Unknown Unknown
libiomp5.so F7708F38 Unknown Unknown Unknown
libpthread.so.0 F78B12AB Unknown Unknown Unknown
libc.so.6 F7629B9E Unknown Unknown Unknown
--------------------------------------------------------------------------
mpirun has exited due to process rank 3 with PID 29230 on
node cnode-3-50 exiting without calling "finalize". This may
have caused other processes in the application to be
terminated by signals sent by mpirun (as reported here).
--------------------------------------------------------------------------