Hi Terry,
> How does the stack for the non-SM BTL run look, I assume it probably is the
> same? Also, can you dump the message queues for rank 1? What's interesting
> is you have a bunch of pending receives, do you expect that to be the case
> when the MPI_Gatherv occurred?
It turns out we
Can you provide a small chunk of code that replicates the problem, perchance?
On Apr 27, 2010, at 9:22 AM, Terry Dontje wrote:
> How does the stack for the non-SM BTL run look, I assume it probably is the
> same? Also, can you dump the message queues for rank 1? What's interesting
> is you ha
How does the stack for the non-SM BTL run look, I assume it probably is
the same? Also, can you dump the message queues for rank 1? What's
interesting is you have a bunch of pending receives, do you expect that
to be the case when the MPI_Gatherv occurred?
--td
Teng Lin wrote:
Hi,
We rece
On Apr 26, 2010, at 9:07 PM, Trent Creekmore wrote:
> You are going to have to debug and trace the program to find out where it is
> stopping.
> You may want to try using KDbg, a graphical front end for the command line
> debugger dbg, which makes it a LOT easier, or use Eclipse.
As a matter of
-boun...@open-mpi.org] On
Behalf Of Teng Lin
Sent: Monday, April 26, 2010 6:49 PM
To: Open MPI Users
Subject: [OMPI users] deadlock when calling MPI_gatherv
Hi,
We recently ran into deadlock when calling MPI_gatherv with Open MPI 1.3.4.
It seems to have something to do with sm at first. However
Hi,
We recently ran into deadlock when calling MPI_gatherv with Open MPI 1.3.4. It
seems to have something to do with sm at first. However, it still hangs even
after turning off sm btl.
Any idea how to track down the problem?
Thanks,
Teng
#
Stac
