Hello guys,
I try to do the first steps with Open MPI and I finally got it work on
Cygwin64(Windows 7 64bit).
I am able to compile plain C code without any issues via "mpicc ..." but
when I try to initialize MPI the program is getting stuck within
"MPI_INIT" without creating CPU load. Example
Hans,
here is attached a simplified version of your second.c test program that
works.
i noticed that anz variable is not initialized,
also, your program is incorrect from an MPI point of view.
the program fails on my RHEL7 like box, with both OpenMPI and MPICH.
Cheers,
Gilles
On 3/5/2016 7:
Folks,
Here is attached a simplified C only version of the test program.
it can be ran with two or one task.
on rhel7, valgrind complains about an invalid read when accessing the
recv buffer after MPI_Recv.
this is pretty odd since :
- the buffer is initialized *before* MPI_Recv is invoked
- M
Gilles,
memchecker is intended to be used together with some suppression rules.
For the receive the rationale of making the buffer unaccessible after the
unpack was to ensure that nobody is touching the memory until we return
from the receive. The buffer was supposed to be made available during t
Thanks George,
is valgrind able to mark memory as read only ?
i checked quickly but could not find such a feature
Cheers,
Gilles
On 3/7/2016 11:40 AM, George Bosilca wrote:
Gilles,
memchecker is intended to be used together with some suppression rules.
For the receive the rationale of maki
Hi everyone,
I have tried everything to compile openmpi. It used to compile on my system,
and I’m not sure what has changed in my c++ libraries to get this error. I get
the following when trying to compile contrib/vt/vt/extlib/otf/tools/otfprofile
make[8]: Entering directory
`/dnas/apps/openm
