An OpenCL implementation for the solution of TDSE on GPU and CPU architectures
School of Physical Sciences, Dublin City University, Collins Ave and National Center for Plasma Science & Technology, Collins Ave, Dublin 9, Ireland
arXiv:1201.6062v1 [physics.comp-ph] (29 Jan 2012)
@article{2012arXiv1201.6062O,
author={O’Broin}, C. and {Nikolopoulos}, L.~A.~A.},
title={"{An OpenCL implementation for the solution of TDSE on GPU and CPU architectures}"},
journal={ArXiv e-prints},
archivePrefix={"arXiv"},
eprint={1201.6062},
primaryClass={"physics.comp-ph"},
keywords={Physics – Computational Physics, Physics – Atomic Physics, Quantum Physics},
year={2012},
month={jan},
adsurl={http://adsabs.harvard.edu/abs/2012arXiv1201.6062O},
adsnote={Provided by the SAO/NASA Astrophysics Data System}
}
Open Computing Language (OpenCL) is a parallel processing language that is ideally suited for running parallel algorithms on Graphical Processing Units (GPUs). In the present work we report the development of a generic parallel single-GPU code for the numerical solution of a system of first-order ordinary differential equations (ODEs) based on the openCL model. We have applied the code in the case of the time-dependent Schr"{o}dinger equation of atomic hydrogen in a strong laser field and studied its performance to the two basic kinds of compute units (GPUs and CPUs) . We found an excellent scalability and a significant speed-up of the GPU over the CPU device tending to a value of about 40.
January 31, 2012 by hgpu
