Adaptive fast multipole methods on the GPU

Authors:
Anders Goude;Stefan Engblom
Affiliations:
Division of Electricity, Department of Engineering Sciences, Uppsala University, Uppsala, Sweden 751 21;Division of Scientific Computing, Department of Information Technology, Uppsala University, Uppsala, Sweden 751 05
Venue:
The Journal of Supercomputing
Year:
2013

Citing 12
Cited 0

A fast algorithm for particle simulations

Journal of Computational Physics
Algorithms in C

Algorithms in C
Greengard's N-Body Algorithm is Not Order N

SIAM Journal on Scientific Computing
An Improved Fast Multipole Algorithm for Potential Fields

SIAM Journal on Scientific Computing
Fast multipole methods on graphics processors

Journal of Computational Physics
Bottom-Up Construction and 2:1 Balance Refinement of Linear Octrees in Parallel

SIAM Journal on Scientific Computing
Numerical Simulation in Molecular Dynamics: Numerics, Algorithms, Parallelization, Applications

Numerical Simulation in Molecular Dynamics: Numerics, Algorithms, Parallelization, Applications
Parallel accelerated cartesian expansions for particle dynamics simulations

IPDPS '09 Proceedings of the 2009 IEEE International Symposium on Parallel&Distributed Processing
On the limits of GPU acceleration

HotPar'10 Proceedings of the 2nd USENIX conference on Hot topics in parallelism
On well-separated sets and fast multipole methods

Applied Numerical Mathematics
CUDA Application Design and Development

CUDA Application Design and Development
A tuned and scalable fast multipole method as a preeminent algorithm for exascale systems

International Journal of High Performance Computing Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a highly general implementation of fast multipole methods on graphics processing units (GPUs). Our two-dimensional double precision code features an asymmetric type of adaptive space discretization leading to a particularly elegant and flexible implementation. All steps of the multipole algorithm are efficiently performed on the GPU, including the initial phase, which assembles the topological information of the input data. Through careful timing experiments, we investigate the effects of the various peculiarities of the GPU architecture.