Optimization strategies for parallel CPU and GPU implementations of a meshfree particle method
Preprint
Abstract
Much of the current focus in high performance computing (HPC) for computational fluid dynamics (CFD) deals with grid based methods. However, parallel implementations for new meshfree particle methods such as Smoothed Particle Hydrodynamics (SPH) are less studied. In this work, we present optimizations for both central processing unit (CPU) and graphics processing unit (GPU) of a SPH method. These optimization strategies can be further applied to many other meshfree methods. The obtained performance for each architecture and a comparison between the most efficient implementations for CPU and GPU are shown.Keywords
All Related Versions
This publication has 21 references indexed in Scilit:
- Importance of explicit vectorization for CPU and GPU software performanceJournal of Computational Physics, 2011
- Neighbour lists in smoothed particle hydrodynamicsInternational Journal for Numerical Methods in Fluids, 2010
- Smoothed Particle Hydrodynamics (SPH): an Overview and Recent DevelopmentsArchives of Computational Methods in Engineering, 2010
- A new 3D parallel SPH scheme for free surface flowsComputers & Fluids, 2009
- Modeling Dam Break Behavior over a Wet Bed by a SPH TechniqueJournal of Waterway, Port, Coastal, and Ocean Engineering, 2008
- 3D SPH Simulation of large waves mitigation with a dikeJournal of Hydraulic Research, 2007
- Numerical modeling of water waves with the SPH methodCoastal Engineering, 2006
- Green water overtopping analyzed with a SPH modelOcean Engineering, 2005
- SPH without a Tensile InstabilityJournal of Computational Physics, 2000
- Solitary Waves on a Cretan BeachJournal of Waterway, Port, Coastal, and Ocean Engineering, 1999