The invalid writes in uGNI are nothing. I suggest adding any GNI_ call to a
suppression file. The RB tree invalid write looks like a bug. I will take a
look and see what might be causing it.
BTW, you can add --with-valgrind(=DIR) to configure. This will suppress some
uninitialized value errors
Gilles,
Adding ess component that excludes slurm and slurmd.
I run into trouble about connection issue. I guess I need slurm and slurmd
in my runtime context ! Anyway, as you mentioned that not a good solution
regarding remaining mpi process when using scancel and I guess i will also
lose some pro
"mpirun takes the #slots for each node from the slurm allocation."
Yes this is my issue and what I was not expected. But I will stick with
--bynode solution.
Thanks a lot for your help.
Regards,
Nicolas
2018-05-17 14:33 GMT+02:00 r...@open-mpi.org :
> mpirun takes the #slots for each node from
mpirun takes the #slots for each node from the slurm allocation. Your hostfile
(at least, what you provided) retained that information and shows 2 slots on
each node. So both the original allocation _and_ your constructed hostfile are
both telling mpirun to assign 2 slots on each node.
Like I s
Nicolas,
This looks odd at first glance, but as stated before, 1.6 is an obsolete
series.
A workaround could be to
mpirun—mca ess ...
And replace ... with a comma separated list of ess components that excludes
both slurm and slurmd.
An other workaround could be to remove SLURM related environment
Hi all,
Thanks for your feedback,
about using " mpirun --mca ras ^slurm --mca plm ^slurm --mca ess
^slurm,slurmd ...". I am a bit confused since syntax sounds good, but I
keep getting following error at run time :
*-
Nathan,
I am trying to track down some memory corruption that leads to crashes
in my application running on the Cray system using Open MPI
(git-6093f2d). Valgrind reports quite some invalid reads and writes
inside Open MPI when running the benchmark that I sent you earlier.
There are plenty
yes, you are right..I didn't know MPI_scan and I finally jumped into, thanks
Le Lun 14 Mai 2018 20:11, Nathan Hjelm a écrit :
> Still looks to me like MPI_Scan is what you want. Just need three
> additional communicators (one for each direction). With a recurive doubling
> MPI_Scan inplementatio
