Overview
FluTAS (Fluid Transport Accelerated Solver) is an open-source code targeting multiphase fluid dynamics simulations. The key feature of FluTAS is the ability to efficiently run both on many-CPUs and many-GPUs in a single and unified framework.
This framework is also designed to be modular so that it can be extended in a sustainable manner.
Downloading and compiling FluTAS
Download the application:
git clone https://github.com/Multiphysics-Flow-Solvers/FluTAS.git
Builld FFTW library
Choose a built script from src/targets and build the application.
cd FluTAS BASE=$PWD # Edit src/targets/target.generic-intel with your fftw path module load intel/2022.1.2 module load compiler/2022.1.0 module load mkl/2022.0.2 module load hpcx/2.13.0 export CXX=mpicxx export FC=mpif90 export FFTW_DIR=$BASE/fftw-3.3.10 make clean APP=single_phase make ARCH=generic-intel APP=single_phase DO_DBG=0 -j 16
Running Example
# Copy one of examples mkdir run cp -r examples/two_phase_ht/dhc run cd run/dhc # Edit the following line in dns.in to change the process grid. Below will work with 128 cores (2x64 cores) 2 64 ! dims(1:2) EXE=<path>/flutas.two_phase_ht /usr/bin/time mpirun -np 128 $MPIFLAGS $EXE"
Task and submission
Use the input under <TBD>.
Profile the input
Use any of the remote clusters to run an MPI profile (such as IPM profile or any other profiler) over 4 nodes, full PPN to profile the given input.Submit the profile as PDF to the team's folder.
Add to your presentation the 3 main MPI calls that are being used plus the MPI time being used.
Run the FluTAS on both PSC bridges-2 and FAU Fritz CPU clusters.
Submission and Presentation:
- Submit all the build scripts, run scripts and stdout/logs.
- Do not submit the data output.
- Prepare slides for the team’s interview based on your work for this application
0 Comments