Page Comparison

...

SeisSol is a software package for simulating elastic wave propagation and dynamic rupture based on the arbitrary high-order accurate derivative discontinuous Galerkin method (ADER-DG). SeisSol can use (an)isotropic elastic, viscoelastic and viscoplastic material to approximate realistic geological subsurface properties.

Website: https://seissol.org/

...

The list of necessary dependencies to install and compile can be found under https://seissol.readthedocs.io/en/latest/compiling-seissol.html (TODO: The installation in the home directory, as described in there, is outdated). In particular, you will need to install:

• Python

• MPI

• Hdf5

• NetcdfNetCDF

• yaml-cpp

• easi https://github.com/SeisSol/easi

  • ASAGI https://github.com/TUM-I5/ASAGI

  • Lua

• Eigen

• ParMETIS

• libxsmm

• PSpaMM https://github.com/SeisSol/PSpaMM

...

For SeisSol itself, you will need to set the architecture you are going to will use—since our matrix kernel generators usually require that information. That can be done via the HOST_ARCH parameter. On x86 architectures without AVX512 support, choose either hsw , rome , or milan as host architecture. With AVX512 support, choose skx or bergamo . On ARM machines, we have the dummy targets neon , sve128 , sve256 , and sve512 , respectively. Setting these will enable the instruction generation for the respective SIMD architecture instructions. You should also set your CPU by using the -mcpu parameter.

For GPUs, you You will also need to set the DEVICE_ARCH and DEVICE_BACKEND parameters for GPUs.

Testing Your Installation

...

• Run SeisSol_proxy_Release_ARCH 100000 100 all . This command will give you an idealized performance figure , and also run through all kernels once.

• Run SeisSol_Release_ARCH with a parameter file. We provide reference values for all scenarios in the https://github.com/SeisSol/precomputed-seissol repository, which you could use to test your installation.

...

Furthermore, we recommend keeping one CPU core free per process free, to be used for the so-called communication thread. It will be used for advancing to advance MPI communication and IO I/O instead. To do so, you will need to set some environment variables, similar to the following snippet:

THREADS_PER_TASK=16 # TODO: set
CPU_HYPERTHREADING=2 #TODO: set
NUM_CORES=$(expr $CPUS_PER_TASK / $CPU_HYPERTHREADING)
NUM_COMPUTE_CORES=$(expr $NUM_CORES - 1)
export OMP_NUM_THREADS="$(expr $NUM_COMPUTE_CORES \* $CPU_HYPERTHREADING)"
export OMP_PLACES="cores($NUM_COMPUTE_CORES)"
export PROC_BIND=spread
export MP_SINGLE_THREAD=no
unset KMP_AFFINITY

Alternatively, you can also disable the communication thread , by setting SEISSOL_COMMTHREAD=0 .

...

2. Run MPI Profiler to profile the application, which . Which 3 MPI calls are mostly used? present your work in the teams team interview ppt slides

3. Visualize the results, and create a short video that demonstrate demonstrating the given input via paraview Paraview or any other tool.

4. <TBD>

5. <TBD> …

...