Re: [OMPI users] Open MPI - Signal: Segmentation fault (11) Problem

2007-04-18 Thread Michael Gauckler
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

Re: [OMPI users] Open MPI - Signal: Segmentation fault (11) Problem

2007-04-16 Thread Michael Gauckler
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

Re: [OMPI users] Open MPI - Signal: Segmentation fault (11) Problem

2007-04-11 Thread George Bosilca
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

[OMPI users] Open MPI - Signal: Segmentation fault (11) Problem

2007-04-11 Thread Michael Gauckler
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,