Dataset for "Fmmgen: Automatic Code Generation of Operators for Cartesian Fast Multipole and Barnes-Hut Methods"

This repository provides the dataset, build and run scripts for the paper "Fmmgen: Automatic Code Generation of Cartesian Fast Multipole and Barnes-Hut Operators", by Ryan Alexander Pepper and Hans Fangohr.

Organisation
The repository is organised as follows:

sim-scripts

sim-scripts/ contains the source code, build and run scripts for running the FMM calculations described in the paper. To reproduce the results from the paper, you need as prerequisites:
* An installation and license of the Intel Compiler (Parallel Studio 2019 Update 3 was used for the paper).
* An installation of the GNU compiler suite.
* GNU Make
* Python 3.6
* A copy of fmmgen v1.0 (available at https://github.com/rpep/fmmgen or https://zenodo.org/record/3842591)
* An installation of Fidimag v3.0 (available at http://github.com/computationalmodelling/fidimag or http://dx.doi.org/10.5281/zenodo.3841935)

With these prerequisites, simply run from the sim-scripts directory:
```
# To build the executables
make build
# To run the studies
make run
```

The four scripts are:
* run-harmonic-cse-comparison.sh - Runs the Fast Multipole Method for 50000 Coulomb particles, varying the order of expansion, and evaluating the performance benefits of various optimisation strategies introduced in the code generation stage.

* run-scaling-comparison.sh - Runs comparisons between the Barnes-Hut and Fast Multipole Methods for different expansion orders and values of theta, the 'opening angle' parameter.

* run-error-comparison.sh - Runs the FMM and Barnes-Hut calculations, saving the fields and performing the direct calculation, allowing evaluation of the errors for the two methods.

* run-fidimag-tests.sh - Runs the Fidimag scaling tests for a series of magnetic dipoles placed on a lattice.

results

results contains the output data from the sim-scripts scripts. Note: running the scripts will overwrite this data!

figure-scripts

This contains Python scripts needed to reproduce the figures from the paper. These generated figures are included in the repository for convenience. To run these scripts, you require:

* Python >= 3.6
* Matplotlib >= 3.1.1
* Seaborn >= 0.9.1
* NumPy >= 1.17.1

figures

This contains the output figures included in the paper.