Alfio --
We just released Open MPI v2.0.0, with lots of MPI RMA fixes. Would you mind
testing there?
> On Jul 12, 2016, at 1:33 PM, Alfio Lazzaro wrote:
>
> Dear OpenMPI developers,
> we found a strange behavior when using MPI-RMA passive target and OpenMPI
>
Thanks Jeff for your inputs.
‹
Murali
On 7/12/16, 12:12 PM, "devel on behalf of Jeff Squyres (jsquyres)"
wrote:
>Unfortunately, the Open MPI code base is quite large, and changes over
>time.
>
>There really is no overall diagram
Unfortunately, the Open MPI code base is quite large, and changes over time.
There really is no overall diagram describing the entire code base, sorry. The
OPAL-level doxygen docs are probably the best you'll get, but they're really
only the utility classes in the portability layer. They
Thanks Kawashima. This note is really helpful.
‹
Murali
On 7/7/16, 4:17 PM, "devel on behalf of KAWASHIMA Takahiro"
wrote:
>FWIW, I have my private notes on process and datatype -related structs.
>
>
Thanks Ralph.
The ‘doxygen’ command generated a bunch of html files along with few class
diagrams in “gif”. I think these figures cover only few classes/structs and
are not exhaustive. I am looking to generate a complete hierarchical diagram. I
will try to see if I can utilize the generated
Dear OpenMPI developers,
we found a strange behavior when using MPI-RMA passive target and OpenMPI
(versions 1.8.3 and 1.10.2). We don't see any problem when using MPICH.
This is a small example on what we want to do:
===
program rma_openmpi
use mpi
integer :: nproc, rank,
Hello Gilley, Howard,
I configured without disable dlopen - same error.
I test these classes on another cluster and: IT WORKS!
So it is a problem of the cluster configuration. Thank you all very much
for all your help! When the admin can solve the problem, i will let you
know, what he had
Instead of manually linking like this
gfortran -o a.out a.o -lmpi_usempi -lmpi_mpifh -lmpi
you can simply use the compiler wrapper
mpifort -o a.out a.o
so you do not have to worry about the Open MPI library names
/* i do not think mpifort was available back in 1.6.5, but mpif90 was */
Sorry but I didn't understand the relation between name changes and wrapper
compilers. I only used --enable-static in the configure process.
> -rw-r--r-- 1 root root 1029580 Jul 11 23:51 libmpi_mpifh.a
> -rw-r--r-- 1 root root 17292 Jul 11 23:51 libmpi_usempi.a
>These are the two for v1.10.x.