Finite temperature lattice QCD with GPUs
Abstract
Graphics Processing Units (GPUs) are being used in many areas of physics, since the performance versus cost is very attractive. The GPUs can be addressed by CUDA which is a NVIDIA's parallel computing architecture. It enables dramatic increases in computing performance by harnessing the power of the GPU. We present a performance comparison between the GPU and CPU with single precision and double precision in generating lattice SU(2) configurations. Analyses with single and multiple GPUs, using CUDA and OPENMP, are also presented. We also present SU(2) results for the renormalized Polyakov loop, colour averaged free energy and the string tension as a function of the temperature.
Cite
@article{arxiv.1104.5432,
title = {Finite temperature lattice QCD with GPUs},
author = {Nuno Cardoso and Marco Cardoso and Pedro Bicudo},
journal= {arXiv preprint arXiv:1104.5432},
year = {2012}
}
Comments
6 pages, 3 figures and 1 table, contribution presented at the International Meeting "Excited QCD", Les Houches, France, 20 - 25 February, 2011