Smoothed-Particle Hydrodynamics Models: Implementation Features on GPUs

Abstract

Parallel implementation features of self-gravitating gas dynamics modeling on multiple GPUs are considered applying the GPU-Direct technology. The parallel algorithm for solving of the self-gravitating gas dynamics problem based on hybrid OpenMP-CUDA parallel programming model has been described in detail. The gas-dynamic forces are calculated by the modified SPH-method (Smoothed Particle Hydrodynamics) while the N-body problem gravitational interaction is obtained by the direct method (so-called Particle-Particle algorithm). The key factor in the SPH-method performance is creation of the neighbor lists of the particles which contribute into the gas-dynamic forces calculation. Our implementation is based on hierarchical grid sorting method using a cascading algorithm for parallel computations of partial sums at CUDA block. The parallelization efficiency of the algorithm for various GPUs of the Nvidia Tesla line (K20, K40, K80) is studied in the framework of galactic' gaseous halos collisions models by the SPH-method.

arXiv comment12 pages, 5 figures. arXiv admin note: text overlap with arXiv:0810.3579 by other authors

References in corpus (5)

• Gasoline: An adaptable implementation of TreeSPH
• Resolution requirements for Smoothed Particle Hydrodynamics simulations of self-gravitating accretion discs
• Dark matter in galaxies
• GMCs scaling relations: role of the cloud definition
• N-Body Simulations of Collective Effects in Spiral and Barred Galaxies

Cited by in corpus (4)

• Extreme kinematic misalignment in IllustrisTNG galaxies: the origin, structure and internal dynamics of galaxies with a large-scale counterrotation
• New features of parallel implementation of N-body problems on GPU
• Lagrange-Eulerian method for numerical integration of the gas dynamics equations: parallel implementation on GPUs
• Dynamics of unstable sound waves in a non-equilibrium medium at the nonlinear stage