Accelerating the Fourier split operator method via graphics processing units

@article{Bauke2011AcceleratingTF,
  title={Accelerating the Fourier split operator method via graphics processing units},
  author={Heiko Bauke and Christoph H. Keitel},
  journal={Comput. Phys. Commun.},
  year={2011},
  volume={182},
  pages={2454-2463}
}
  • H. Bauke, C. Keitel
  • Published 2011
  • Computer Science, Mathematics, Physics
  • Comput. Phys. Commun.
Abstract Current generations of graphics processing units have turned into highly parallel devices with general computing capabilities. Thus, graphics processing units may be utilized, for example, to solve time dependent partial differential equations by the Fourier split operator method. In this contribution, we demonstrate that graphics processing units are capable to calculate fast Fourier transforms much more efficiently than traditional central processing units. Thus, graphics processing… Expand
A New Framework of GPU-Accelerated Spectral Solvers: Collocation and Glerkin Methods for Systems of Coupled Elliptic Equations
  • F. Chen
  • Computer Science, Mathematics
  • J. Sci. Comput.
  • 2015
TLDR
An order-of-magnitude speedup is obtained for solving 2-D and 3-D systems using a Kepler 20 GPU over a high-end multi-core processor, with two popular spectral methods, namely, the spectral collocation method and the spectral-Galerkin method. Expand
A GPU parallelized spectral method for elliptic equations in rectangular domains
TLDR
A polynomial-based spectral method applicable to elliptic equations in rectangular domains with general boundary condition that shows remarkable speedups of up to 15 times and more than 35 times in the 2-D and 3-D cases. Expand
Solution of relativistic quantum optics problems using clusters of graphical processing units
TLDR
The relativistic ionization rate is computed for an ion illuminated by a laser field near the usual barrier suppression threshold, and the ionizing wavefunction is displayed. Expand
Numerical solution of the time-dependent Dirac equation in coordinate space without fermion-doubling
TLDR
It is shown that this numerical method for the solution of the time-dependent Dirac equation is free from spurious solutions related to the fermion-doubling problem and that it can be parallelized very efficiently. Expand
Pseudospectral computational methods for the time-dependent Dirac equation in static curved spaces
TLDR
The numerical schemes are derived using a pseudodifferential representation of the Dirac equation along with a simple Fourier-basis technique and are applied to the dynamics of charge carriers in strained graphene to verify the convergence. Expand
A Spacetime Finite Elements Method to Solve the Dirac Equation
TLDR
A fully implicit numerical approach based on space-time finite element method to solve the Dirac equation in 1 (space) + 1 (time), 2 + 1, and 3 + 1 dimensions is presented. Expand
An OpenCL implementation for the solution of TDSE on GPU and CPU architectures
Open Computing Language (OpenCL) is a parallel processing l a uage that is ideally suited for running parallel algorit hms on Graphical Processing Units (GPUs). In the present work we re port on theExpand
Computational performance of simple and efficient sequential and parallel Dirac equation solvers
TLDR
The computational performance of basic and efficient pseudo-spectral methods and a Quantum Lattice Boltzmann-like approach for solving the Time Dependent Dirac Equation (TDDE) modeling the interaction of classical electromagnetic fields with quantum relativistic particles is studied. Expand
Krylov subspace methods for the Dirac equation
TLDR
It is demonstrated that the Lanczos algorithm can yield very precise eigenenergies and allows very precise time propagation of relativistic wave packets and the excellent parallelization capabilities are demonstrated by a parallel implementation of the Dirac Lanczos propagator utilizing the Message Passing Interface standard. Expand
A split-step numerical method for the time-dependent Dirac equation in 3-D axisymmetric geometry
TLDR
The time evolution of Gaussian wave packets is studied, and the eigenstates of hydrogen-like systems are evaluated by using a spectral method, and three-dimensional simulations of relativistic laser–matter interactions are presented, using the Dirac equation. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 68 REFERENCES
Parallel option pricing with Fourier Space Time-stepping method on Graphics Processing Units
  • V. Surkov
  • Computer Science
  • 2008 IEEE International Symposium on Parallel and Distributed Processing
  • 2008
TLDR
Algorithms, based on the Fourier space time-stepping (FST) method, for pricing single and multi-asset European and American options with Levy underliers on a GPU are presented. Expand
High performance discrete Fourier transforms on graphics processors
TLDR
This work implemented their algorithms using the NVIDIA CUDA API and compared their performance with NVIDIA's CUFFT library and an optimized CPU-implementation (Intel's MKL) on a high-end quad-core CPU. Expand
Parallel solver for the time-dependent linear and nonlinear Schrödinger equation.
TLDR
An approach in which the finite-element discrete variable representation (FEDVR) is combined with the real-space product (RSP) algorithm to generate an efficient and highly accurate method for the solution of the time-dependent linear and nonlinear Schrödinger equation is described. Expand
GPU Computing
TLDR
The background, hardware, and programming model for GPU computing is described, the state of the art in tools and techniques are summarized, and four GPU computing successes in game physics and computational biophysics that deliver order-of-magnitude performance gains over optimized CPU applications are presented. Expand
FFT-split-operator code for solving the Dirac equation in 2+1 dimensions
TLDR
This work represents an implementation of the split-operator method, combined with fast Fourier transforms (FFT) for calculating any occurring spatial derivatives, to solve the given problem of relativistic time evolution of wave functions according to the Dirac equation. Expand
Complex integration steps in decomposition of quantum exponential evolution operators
Abstract We generalize previous high-order exponential split operator methods for solving time-dependent Schroedinger equations [A.D. Bandrauk, H. Shen, Chem. Phys. Lett. 176 (1991) 428] byExpand
A real space split operator method for the Klein-Gordon equation
TLDR
The fact that the kinetic energy operator b K in the two-component representation of the Klein–Gordon equation is a nilpotent operator, that is b K 2 1⁄4 0, allows us to implement the split operator method for the Klein-Gordon equation entirely in real space. Expand
The Design and Implementation of FFTW3
TLDR
It is shown that such an approach can yield an implementation of the discrete Fourier transform that is competitive with hand-optimized libraries, and the software structure that makes the current FFTW3 version flexible and adaptive is described. Expand
Symbolic calculation in development of algorithms: split-step methods for the Gross–Pitaevskii equation
We employ symbolic calculation to perform a systematic study of the accuracy of split-step Fourier transform methods for the time dependent Gross-Pitaevskii equation (GPE). Provided the most recentExpand
The discrete variable method for the solution of the time-dependent Schrödinger equation
A solution of the time-dependent Schrodinger equation (TDSE) is required in a variety of problems in physics and chemistry. These include atoms and molecules in time dependent electromagnetic fields,Expand
...
1
2
3
4
5
...