Ok, I will do that as soon as possible.
Jörg
Am 18.12.2014 um 16:31 schrieb Jeff Squyres (jsquyres) :
> If it works with static builds and not dynamic, it might be worth reporting a
> problem on the Intel fortran compiler forums and see if this is a known
> problem.
>
>
> On Dec 18, 2014, at
If it works with static builds and not dynamic, it might be worth reporting a
problem on the Intel fortran compiler forums and see if this is a known problem.
On Dec 18, 2014, at 10:29 AM, Jörg Stiller wrote:
> Hi Jeff,
>
> with OS X I use ifort 15.0.1 20141022, which is the latest version, a
Hi Jeff,
with OS X I use ifort 15.0.1 20141022, which is the latest version, as far I
know.
I managed to get open-mpi 1.8.3 built properly when switching to static libs,
i.e.
> ./configure --prefix=/opt/openmpi-intel-static --disable-shared
> --enable-static \
F77=/opt/intel/composerxe/bi
Jorg --
I'm sorry for the giant delay in replying; the US holiday and the MPI Forum
meeting last week made a disaster out of my already-out-of-control INBOX. :-(
Hmm. This almost sounds like a bug in the intel compiler. Do you have the
latest version of their compiler, perchance?
On Dec 1,
Hi,
I am using the Open MPI 1.8.3 with gcc 4.9.2 and ifort 15.0.1 and the MPI_F08
module on Mac OS X 4.9.
With the latter, the == and /= operators are overloaded for MPI handles , e.g.
MPI_REQUEST_NULL /= MPI_REQUEST_NULL
should work and give the result .false. With gfortran 4.9.2 all is fin
