PyBONDEM-GPU: A discrete element bonded particle Python research framework – Development and examples

Discrete element modelling (DEM) is widely used to simulate granular systems, nowadays routinely on graphical processing units. Graphics processing units (GPUs) are inherently designed for parallel computation, and recent advances in the architecture, compiler design and language development are allowing general-purpose computation to be computed on multiple GPUs. Application of DEM to bonded particle systems are much less common, with a number of open research questions remaining. This study outlines a Bonded-Particle Research DEM Framework, PyBONDEM-GPU, written in Python. This framework leverages the parallel nature of GPUs for computational speed-up and the rapid prototype flexibility of Python. Python is faster and easier to learn than classical compiled languages, making computational simulation development accessible to undergraduate and graduate engineers. PyBONDEMGPU leverages the Numba-CUDA module to compile Python syntax for execution on GPUs. The framework enables research of fibre pull-out from fibre-matrix embeddings. Bonds are simulated between all interacting particles. The performance of PyBONDEM-GPU is compared against Python CPU implementations of PyBONDEM using the Numpy and Numba-CPU Python modules. PyBONDEM-GPU was found to be 1000 times faster than the Numpy implementation and 4 times faster than the Numba-CPU implementation to resolve forces and to integrate the equations of motion.