Hi George,
Some more investigation on the Segmentation fault done with valgrind is
shown below.
There seems to be uninitialized parameters and finally a read at address
0x1, which
causes the segfault. I have checked whether one of my members appear to be
at that
address when constructing th
or >(const std::vector
&var)
{
if (var.size() > 0)
memoryMap_.push_back(MemoryMapDescr(DataTypeConverter::type,
(void*)&var[0], var.size()));
}
-------------
Message: 1
List-Post: users@lists.open-mpi.org
Michael,
The MPI standard is quite clear. In order to have a correct and
portable MPI code, you are not allowed to use (void*)0. Use
MPI_BOTTOM instead.
We have plenty of tests which test the exact behavior you describe in
your email. And they all pass. I will take a look at what's happen
Dear Open MPI User's and Developers,
I encountered a problem with Open MPI when porting an application, which
successfully ran with LAM MPI and MPICH.
The program produces a segmentation fault (see [1] for the stack trace) when
doing the MPI_Send with the following arguments:
MPI_Send((void *)0,