>> Then you have to simplify your problem as much as possible until we
>> can reproduce it.
>
> I am not sure of the best way to do it, as a have a rather large program and
> I need it to build the system matrix. In your experience, saving the
> matrices
> to files and then just load them would be
Deal all,
Sorry for the late reply. I had some urgent matters to solve, and had to
put this investigation to a halt for a while.
> Then you have to simplify your problem as much as possible until we
> can reproduce it.
I am not sure of the best way to do it, as a have a rather large program
and
> It shows the same issues, as expected. I will follow your advice and try to
> use a different solver.
Then you have to simplify your problem as much as possible until we
can reproduce it.
> Still, would it be possible for you to comment a bit more on those
> MPI_Op_free errors?
This can happ
On 11/17/2017 07:37 AM, Lucas Campos wrote:
Invalid MPI_Op, error stack:
MPI_Op_free(111): MPI_Op_free(op=0x7ffcf6298dac) failed
MPI_Op_free(75).: Null Op pointer
If this error would lead the the issues I am having, is up to discussion.
I tried using PETSc's SolverPr
Dear Timo,
Also, do you have recommendations for Valgrind flags other
than --track-origins=yes --leak-check=full?
Lucas
On 17 November 2017 at 15:37, Lucas Campos wrote:
> Dear Timo,
>
> Thanks for you advice. I am running the program in three different
> computers -- my notebook, my research
Dear Timo,
Thanks for you advice. I am running the program in three different
computers -- my notebook, my research group's server and the local cluster.
In all of them I have this (small) change to suddenly find the nan.
According to MUST, there is clearly a problem inside deal.II, MUMPS or
PETS
Lucas,
those kind of bugs are hard to find. Honestly, the bug could still be
in your code, inside deal.II, inside PETSc, inside MUMPS, or related
to the software/hardware you are running on.
I know this won't be of much help, but I would suggest you try a
different solver to see if MUMPS is the p
Sorry, I forgot to include the link to MUST. Here it
is: https://doc.itc.rwth-aachen.de/display/CCP/Project+MUST
On Friday, 17 November 2017 14:12:18 UTC+1, Lucas Campos wrote:
>
> Dear all,
>
> First of all, a bit of context:
> I am trying to debug an error in my application where randomly I sta