You say:
> one possiblity is use different mpif90 and mpicc, but I
> checked in my case they all use gcc 4.3.4
Do you really mean gcc for both,
or is it gfortran for mpif90 perhaps?
What is the output of:
mpif90 --show
and
mpicc --show
for each OMPI version?
Maybe other list subscribers can
No. I didn't mix environment variables. I run two editions seperately. I
searched online, one possiblity is use different mpif90 and mpicc, but I
checked in my case they all use gcc 4.3.4
From: Gus Correa
To: Open MPI Users
Sent: Tuesday, June 18, 2013 8:
The root cause of the problem is that you are assigning your host name to
the loopback device. This is rather unusual, but not forbidden. Normally,
people would name that interface something like "localhost" since it cannot
be used to communicate off-node.
Doing it the way you have could cause pro
Ed,
Im not sure but there might be a case where the BTL is getting overwhelmed by
the nob-blocking operations while trying to setup the connection. There is a
simple test for this. Add an MPI_Alltoall with a reasonable size (100k) before
you start posting the non-blocking receives, and let's se
Hello,
On 26 June 2013 03:11, Ralph Castain wrote:
> I've been reviewing the code, and I think I'm getting a handle on
> the issue.
>
> Just to be clear - your hostname resolves to the 127 address? And you are on
> a Linux (not one of the BSD flavors out there)?
Yes (but resolves to 127.0.1.1 --
Sorry about that - it has been fixed in the upcoming 1.7.2, which should be
released in the immediate future. For now, you can grab the 1.7.2 tarball
from the web site.
On Tue, Jun 25, 2013 at 8:25 PM, Jeff Hammond wrote:
> I observe this error with the OpenMPI 1.7.1 "feature":
>
> Making all i
