QCD simulations with staggered fermions on GPUs
Dipartimento di Fisica, Universita di Pisa and INFN, Largo Pontecorvo 3, I-56127 Pisa, Italy
arXiv:1106.5673v1 [hep-lat] (28 Jun 2011)
@article{2011arXiv1106.5673B,
author={Bonati}, C. and {Cossu}, G. and {D’Elia}, M. and {Incardona}, P.},
title={"{QCD simulations with staggered fermions on GPUs}"},
journal={ArXiv e-prints},
archivePrefix={"arXiv"},
eprint={1106.5673},
primaryClass={"hep-lat"},
keywords={High Energy Physics – Lattice, Physics – Computational Physics},
year={2011},
month={jun},
adsurl={http://adsabs.harvard.edu/abs/2011arXiv1106.5673B},
adsnote={Provided by the SAO/NASA Astrophysics Data System}
}
We report on our implementation of the RHMC algorithm for the simulation of lattice QCD with two staggered flavors on Graphics Processing Units, using the NVIDIA CUDA programming language. The main feature of our code is that the GPU is not used just as an accelerator, but instead the whole Molecular Dynamics trajectory is performed on it. After pointing out the main bottlenecks and how to circumvent them, we discuss the obtained performances. We present some preliminary results regarding OpenCL and multiGPU extensions of our code and discuss future perspectives.
June 29, 2011 by hgpu
