Hey all,
Has anyone got the error “collective abort of all ranks killed by signal 9” or 11
while running loops of different run ?
And maybe know what the reason is ?
Hey all,
wen,
if you want useful help, you have to give useful information.
the message below is pretty much useless, since there is
no information about context or how to reproduce it. it is
*really* difficult to give any kind of help on such non-descriptive
reports.
Has anyone got the error "collective abort of all ranks killed by signal 9"
or 11
while running loops of different run ?
this error message is a generic error message from the MPI
library that you have used, thus it doesn't say much more than
that one of your MPI tasks stopped unexpectedly. signal 11
is a segmentation fault and signal 9 is a "kill -KILL" signal,
but that means very little with a library like MPICH.
i suggest you try running in serial and try to identify the
location of the real problem.
And maybe know what the reason is ?
sorry, i left my crystal ball at home...
cheers,
axel.