Getting an account

New users have to ask the PIs (Eric Larour or Mathieu Morlighem) to request a NASA account for them if they don't have one already:

• go to ​https://www.nas.nasa.gov/hecc/portal/accounts select option 3 ("I want to request a NASA identity for one of my new users")
• provide the information requested

Then, a NAS account has to be created by the new user:

• go to ​https://www.nas.nasa.gov/hecc/portal/accounts select option 2 ("I want to request and account for myself")
• provide the information requested using either GID = s5692 for Eric's group or GID = s1507 for Mathieu's group
• the PI will receive an email to approve the request
• All users must complete NASA-mandatory Basic IT Security Training (This year's training is called "FY21 CYBERSECURITY AND SENSITIVE UNCLASSIFIED INFORMATION AWARENESS COURSE").
• Dartmouth Security officer: Sean McNamara, Sean.R.McNamara@… ​https://itc.dartmouth.edu/about/who-we-are/itc-leadership
• UCI IT Security officer: Josh Drummond jdrummon@…
• JPL IT Security officer: Tomas Soderstrom Tomas.J.Soderstrom@…

Password-less ssh

Follow the steps outlined here ​http://www.nas.nasa.gov/hecc/support/kb/Setting-Up-SSH-Passthrough_232.html

Environment

Since you will be using bash, add the following to your ~/.bashrc:

#ISSM
export ISSM_DIR="/u/username/trunk-jpl"
source $ISSM_DIR/etc/environment.sh

#Packages
module load mpi-hpe/mpt
module load comp-intel
module load petsc/3.17.3_intel_mpt_py

#Set compilers
export MPICXX_CXX=icpc
export MPICC_CC=icc
export MPIF90_F90=ifort
export CC="mpicc"
export CXX="mpicxx"
export F77="mpif77"

And replace ISSM_DIR with your actual trunk. Log out and log back in to apply this change.

Note that if your bashrc is not loaded when you logging, you will have to add a new file: ~/.bash_login with the following content:

if [ -f ~/.bashrc ]; then . ~/.bashrc; fi

Installing ISSM on Pleiades

Do NOT install mpich. We have to use the one provided by NAS. Pleiades will only be used to run the code, you will use your local machine for pre- and post- processing, you will never use Pleiades' copy of MATLAB. You can check out ISSM and install the following packages:

• m1qn3
• that's it because we now use Pleiades' PETSc

For documentation on the Pleiades cluster, see here: ​http://www.nas.nasa.gov/hecc/support/kb/

You will need to run the following command before configuring ISSM:

cd $ISSM_DIR
autoreconf -ivf

Use the following configuration script for ISSM (adapt to your needs):

export CXXFLAGS="-g -Ofast"
export CFLAGS="-g -Ofast"
./configure \
   --prefix=$ISSM_DIR \
   --with-wrappers=yes \
   --with-matlab-dir="/nasa/matlab/2022b/" \
   --with-mpi-include="-I${MPI_ROOT}/include " \
   --with-mpi-libflags="-L${MPI_ROOT}/lib -lmpi" \
   --with-petsc-dir=${PETSC_DIR} \
   --with-parmetis-dir=${PETSC_DIR} \
   --with-metis-dir=${PETSC_DIR} \
   --with-mumps-dir=${PETSC_DIR} \
   --with-mkl-libflags="-L${MKLROOT}/lib/intel64 -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread -lm" \
   --with-m1qn3-dir="${ISSM_DIR}/externalpackages/m1qn3/install" \
    --with-fortran-lib="-L${MKLROOT}/../compiler/lib/intel64_lin -lifcore -lifport -lgfortran" \
   --with-cxxoptflags="-g -Ofast -axCORE-AVX2,AVX -xSSE4.2" \
   --enable-development

Installing ISSM on Pleiades with Dakota

You will not need to remake PETSc and m1qn3, as long as you made them using the Intel MPI libraries and compilers, as described above.

Dakota will require that you have a python that is of version python2. The easiest way to do this is create a link for a python call to /usr/bin/python2. One way to do this is to add a path to a new bin folder in your ~/.bashrc:

export PATH="$PATH:${HOME}/bin"

Then, create a bin folder in your home directory (if you do not have one already). In your home directory, type mkdir bin. Then cd bin, and finally type ln -s /usr/bin/python2 python.

Then, log out and log back in and build the following external packages:

• gsl, install-pleiades.sh
• boost, install-1.55-pleiades.sh
• dakota, install-6.2-pleiades_toss4.sh

Finally, you will need to use the following configuration script (i.e. adding the "with" lines for dakota and boost):

#/
./configure \
 --prefix=$ISSM_DIR \
 --enable-standalone-libraries \
 --with-wrappers=no \
 --with-m1qn3-dir=$ISSM_DIR/externalpackages/m1qn3/install \
 --with-metis-dir=$PETSC_ROOT \
 --with-petsc-dir=$PETSC_ROOT \
 --with-scalapack-lib="-L/nasa/intel/Compiler/2018.3.222/compilers_and_libraries_2018.3.222/linux/mkl/lib/intel64/libmkl_scalapack_lp64.so" \
 --with-boost-dir=$ISSM_DIR/externalpackages/boost/install \
 --with-dakota-dir=$ISSM_DIR/externalpackages/dakota/install \
 --with-mpi-include=" " \
 --with-mpi-libflags=" -lmpi" \
 --with-mkl-libflags="-L/nasa/intel/Compiler/2018.3.222/compilers_and_libraries_2018.3.222/linux/mkl/lib/intel64 -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread -lm" \
 --with-mumps-dir=$PETSC_ROOT \
 --with-fortran-lib="-L/nasa/intel/Compiler/2018.3.222/compilers_and_libraries_2018.3.222/linux/compiler/lib/intel64_lin/ -lifcore -lifport -lgfortran" \
 --with-cxxoptflags="-O3 " \
 --with-vendor="intel-pleiades-mpi" \
 --enable-development

Remember, you will need to run the following command before configuring ISSM:

cd $ISSM_DIR
autoreconf -ivf

Note, if you would like to use the python 3 version that loads in the environment, you will need to call python3 to do so, as long as the python alias is set to python2.

NOTE: Refer to jenkins/pleiades-dakota for external packages and configuration updates that may not yet be listed here.

Installing ISSM on Pleiades with Solid Earth Capabilities

The required external packages and configuration of ISSM with Solid Earth capabilities is similar to building ISSM with Dakota. You will not need to remake PETSc and m1qn3, as long as you made them using the Intel MPI libraries and compilers, as described above.

Then, build the following external packages:

• zlib, install-1.sh
• hdf5, install-1-parallel.sh
• gsl, install-pleiades.sh
• boost, install-1.55-pleiades.sh
• dakota, install-6.2-pleiades.sh
• curl, install-7-linux.sh
• netcdf, install-4.7-parallel.sh
• sqlite, install.sh
• proj, install-6.sh
• gdal, install-3.sh
• gshhg, install.sh
• gmt, install-6-linux.sh
• gmsh, install-4.sh

Finally, you will need to use the following configuration script (i.e. adding the "with" lines for the needed packages):

./configure \
--prefix=$ISSM_DIR \
--enable-development \
--enable-standalone-libraries \
--with-wrappers=no \
--with-vendor="intel-pleiades-mpi" \
--with-cxxoptflags="-O3 " \
--with-petsc-dir="${ISSM_DIR}/externalpackages/petsc/install" \
--with-m1qn3-dir="${ISSM_DIR}/externalpackages/m1qn3/install" \
--with-boost-dir="${ISSM_DIR}/externalpackages/boost/install" \
--with-dakota-dir="${ISSM_DIR}/externalpackages/dakota/install" \
--with-gsl-dir=${ISSM_DIR}/externalpackages/gsl/install \
--with-mpi-include=" " \
--with-mpi-libflags=" -lmpi" \
--with-mkl-libflags="-L/nasa/intel/Compiler/2018.3.222/compilers_and_libraries_2018.3.222/linux/mkl/lib/intel64 -lmkl_intel_lp64 -lmkl_sequential -lmkl_core -lpthread -lm" \
--with-metis-dir="${ISSM_DIR}/externalpackages/petsc/install" \
--with-parmetis-dir=${ISSM_DIR}/externalpackages/petsc/install \
--with-mumps-dir="${ISSM_DIR}/externalpackages/petsc/install" \
--with-scalapack-lib="-L/nasa/intel/Compiler/2018.3.222/compilers_and_libraries_2018.3.222/linux/mkl/lib/intel64/libmkl_scalapack_lp64.so" \
--with-graphics-lib="/usr/lib64/libX11.so" \
--with-fortran-lib="-L/nasa/intel/Compiler/2018.3.222/compilers_and_libraries_2018.3.222/linux/compiler/lib/intel64_lin/ -lifcore -lifport -lgfortran" \

Again, you will need to run the following command before configuring ISSM:

cd $ISSM_DIR
autoreconf -ivf

NOTE: Refer to jenkins/pleiades-solid_earth for external packages and configuration updates that may not yet be listed here.

Installing ISSM on Pleiades with CoDiPack

You will need to build these additional external package:

• medipack, install.sh
• codipack, install.sh

Your configuration script should look like this:

Error: Failed to load processor bashsh

No macro or processor named 'bashsh' found

You will get a lot of warnings while compiling (i.e. warning #2196: routine is both "inline" and "noinline"), which can be ignored.

pfe_settings.m

You have to add a file in $ISSM_DIR/src/m titled pfe_settings.m (on the machine you wish to access Pleiades) with your personal settings:

cluster.login='mmorligh';
cluster.queue='devel';
cluster.codepath='/u/mmorligh/issm/trunk/bin';
cluster.executionpath='/nobackup/mmorligh/execution/';
cluster.grouplist='s5692';
cluster.port=1099;

use your username for the login and enter your code path and execution path. Be sure to create the final execution directory (mkdir) within the nobackup folder. These settings will be picked up automatically by matlab when you do md.cluster=pfe().

Make sure your module list includes scicon/app-tools, comp-intel/2018.3.222, and /nasa/intel/impi/2021.3/modulefiles/mpi/2021.3.0. You can specify your own list of modules by adding to pfe_settings.m, for example:

cluster.modules = {'mpi-hpe/mpt', 'comp-intel', 'petsc/3.17.3_intel_mpt_py'};

To determine your grouplist, on Pleiades run:

%groups USERNAME

Running jobs on Pleiades

On Pleiades, the more nodes and the longer the requested time, the more you will have to wait in the queue. So choose your settings wisely:

md.cluster=pfe('numnodes',8,'time',30,'processor','bro','queue','devel');
md.cluster.time=10;

to have a maximum job time of 10 minutes and 8 broadwell nodes. If the run lasts longer than 10 minutes, it will be killed and you will not be able to retrieve your results.

Now if you want to check the status of your job and the queue you are using, use this command:

qstat -u USERNAME

You can delete your job manually by typing:

qdel JOBID

where JOBID is the ID of your job (indicated in the Matlab session). Matlab indicates too the directory of your job where you can find the files JOBNAME.outlog and JOBNAME.errlog. The outlog file contains the informations that would appear if you were running your job on your local machine and the errlog file contains the error information in case the job encounters an error.

If you want to load results from the cluster manually (for example if you have an error due to an internet interruption), you find in the informations Matlab gave you /home/srebuffi/trunk-jpl/execution//SOMETHING/JOBNAME.lock , you copy the SOMETHING and you type in Matlab:

md=loadresultsfromcluster(md,'runtimename','SOMETHING');