We present our implementation of the RHMC algorithm for staggered fermions on Graphics Processing Units using the NVIDIA CUDA programming language. While previous studies exclusively deal with the Dirac matrix inversion problem, our code performs the complete MD trajectory on the GPU. After pointing out the main bottlenecks and how to circumvent them, we discuss the performance of our code.
@article{arxiv.1010.5433,
title = {Staggered fermions simulations on GPUs},
author = {Claudio Bonati and Guido Cossu and Massimo D'Elia and Adriano Di Giacomo},
journal= {arXiv preprint arXiv:1010.5433},
year = {2010}
}
Comments
Poster presented at the XXVIII International Symposium on Lattice Field Theory, June 14-19, 2010, Villasimius, Sardinia Italy