Hi Joseph,
Thanks for this. I'll recompile with --with-debug and see what I get.
The funny thing is that I seem to get the right outputs, but with this
error- I suspect it could happen at MPI_Finalize but I do not see any
obvious problems.
In any case, I am compiling OpenMPI 4.1.0a1 with gcc 6.3.
Hi Joseph,
Thanks for this. I'll recompile with --with-debug and see what I get.
The funny thing is that I seem to get the right outputs, but with this
error- I suspect it could happen at MPI_Finalize but I do not see any
obvious problems.
In any case, I am compiling OpenMPI 4.1.0a1 with gcc 6.3.
Hi Luis,
My first step is usually to configure Open MPI with `--with-debug` and
recompile/install. Then use DDT (or gdb inside an xterm per rank if DDT
is not available and you have X-fowarding on the nodes). When the
segfault happens you at least get proper symbols inside Open MPI that
may h
Hi ompi devs,
Any idea where should I start debugging this kind of error from? This
comes from a plain "Hello World".
[r1i0n32:67074] *** Process received signal ***
[r1i0n32:67074] Signal: Segmentation fault (11)
[r1i0n32:67074] Signal code: Address not mapped (1)
[r1i0n32:67074] Failing at add
I know a number of us work on Mac, and many have suffered the frustrations of
losing gdb for core file debugging when Apple moved on to Yosemite. However, I
just found out that gdb is actually available again! You can read how to
install it here:
http://stackoverflow.com/questions/27680712/home
