[Users] Error in exe/cactus_sim

[Rishank Diwan]

Hello Roland and Ian,

I am attaching the build.log file. I have also tried running the simulation
after removing the MPICH with this I also attaching to file obtained from
"dpkg --list | grep -vi compile | grep -i mpi" command to compare from
previous one. I also did make changes in PATH and LD_Library_Path. The
current path are as follows:

LD_LIBRARY_PATH=:/usr/lib/x86_64-linux-gnu/openmpi/lib/

PATH=/home/rishank/miniconda2/bin:/home/rishank/anaconda2/bin:/home/rishank/anaconda2/condabin:/home/rishank/bin:/home/rishank/.local/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/usr/bin

and the previous one were:

LD_LIBRARY_PATH=:/home/rishank/.openmpi/lib/:/home/rishank/.openmpi/lib/

PATH=/home/rishank/miniconda2/bin:/home/rishank/anaconda2/bin:/home/rishank/anaconda2/condabin:/home/rishank/bin:/home/rishank/.local/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/home/rishank/.openmpi/bin:/home/rishank/.openmpi/bin

Yours Sincerely,
Rishank Diwan




On Thu, 23 Apr 2020 at 00:19, Roland Haas <rhaas at illinois.edu> wrote:

> Hello Rishank,
>
> > It's possible that you might have to uninstall mpich, but I'm not
> > sure.  There *shouldn't* be a fundamental reason why you can't have
> > both installed and just use one of them, but there might be technical
> > reasons why it doesn't work.
> It is possible to have both installed at the same time. However things
> then become fragile. Ubuntu will declare one as the "default" using
> either the "alternatives" system (which is why eg /usr/bin/mpi and
> /usr/bin/mpicc point to files in /etc/alternatives/). This however does
> not include things like eg hdf5 which come in flavor packages
> hdf5-openmpi, hdf5-mpich, hdf5-serial each of which has libraries
> libhdf5_{openmpi,mpich,serial}.so. Then there's always the possibility
> something being wrong in the package setup.
>
> Thus having multiple MPI stacks installed at the same time, while
> possible, is outside of the realm of cases easily supported by our
> automated setup and would likely require a hand-crafted option list
> similar to the ones used on clusters. Eg setting
>
> MPI_DIR = /usr/lib/x86_64-linux-gnu/openmpi
> MPI_INC_DIRS = /usr/lib/x86_64-linux-gnu/openmpi/include
> MPI_LIB_DIRS = /usr/lib/x86_64-linux-gnu/openmpi/lib
> MPI_LIBS = mpi
>
> *may* work (though see my note above about libraries that can use MPI).
> Note that this still assumes that the mpirun found in $PATH is the one
> that matches the used MPI stack, ie OpenMPI's so it may require changes
> to the run script as well.
>
> Thus the simplest solution is likely to make sure only one MPI stack
> (OpenMPI or MPICH) is installed and uninstall the other one.
>
> Yours,
> Roland
>
> --
> My email is as private as my paper mail. I therefore support encrypting
> and signing email messages. Get my PGP key from http://pgp.mit.edu .
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.einsteintoolkit.org/pipermail/users/attachments/20200426/9c6735cf/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: mpi.log
Type: text/x-log
Size: 1205 bytes
Desc: not available
Url : http://lists.einsteintoolkit.org/pipermail/users/attachments/20200426/9c6735cf/attachment-0002.bin 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: build.log
Type: text/x-log
Size: 1080674 bytes
Desc: not available
Url : http://lists.einsteintoolkit.org/pipermail/users/attachments/20200426/9c6735cf/attachment-0003.bin 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: mpi
Type: application/octet-stream
Size: 10076 bytes
Desc: not available
Url : http://lists.einsteintoolkit.org/pipermail/users/attachments/20200426/9c6735cf/attachment-0001.obj