Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

We chose build_examples/build_cpu_mpi-only_intel_ubuntu20.04.sh (This is for CPU only runs).

  1. Copy build_examples/build_cpu_mpi-only_intel_ubuntu20.04.sh to root directory.

    • cp build_examples/build_cpu_mpi-only_intel_ubuntu20.04.sh rebuild.sh

  2. Build/load HDF5 and edit rebuild.sh with HDF5 location.

...

  1. 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.

  2. Run POT3D with isc2023 input on both PSC bridges-2 and FAU Fritz CPU clusters.

    Code Block
    Your job should converge and print outputs like below.
     ### The CG solver has converged.
     Iteration:    25112   Residual:   9.972489313728662E-13
  3. Run POT3D on the FAU Alex cluster using A100 GPU partition. Use only 4 GPUs for the run. Submit the results to the team's folder. It is required to build HDF5 and POT3D with the NV Compiler. A sample of POT3D scripts can be found in the “examples” folder.  Note that you do NOT need to build it with CUSPARSE enabled since they are only using preconditioner #1, so if you have issues with the build, you can just set that ENV in the build script to 0.

  4. Submission and Presentation:
    - Submit all the build scripts, run scripts and input & outputs (pot3d.dat, pot3d.out, timing.out)
    - Do not submit the output data or the source code.
    - Prepare slides for the team’s interview based on your work for this application.

...