Directionally Unsplit Hydrodynamic Schemes with Hybrid MPI/OpenMP/GPU Parallelization in AMR
Department of Physics, National Taiwan University, 10617, Taipei, Taiwan
arXiv:1103.3373v1 [astro-ph.IM] (17 Mar 2011)
@article{2011arXiv1103.3373S,
author={Schive}, {H.-Y.} and {Zhang}, {U.-H.} and {Chiueh}, T.},
title={“{Directionally Unsplit Hydrodynamic Schemes with Hybrid MPI/OpenMP/GPU Parallelization in AMR}”},
journal={ArXiv e-prints},
archivePrefix={“arXiv”},
eprint={1103.3373},
primaryClass={“astro-ph.IM”},
keywords={Astrophysics – Instrumentation and Methods for Astrophysics},
year={2011},
month={mar},
adsurl={http://adsabs.harvard.edu/abs/2011arXiv1103.3373S},
adsnote={Provided by the SAO/NASA Astrophysics Data System}
}
We present the implementation and performance of a class of directionally unsplit Riemann-solver-based hydrodynamic schemes on Graphic Processing Units (GPU). These schemes, including the MUSCL-Hancock method, a variant of the MUSCL-Hancock method, and the corner-transport-upwind method, are embedded into the adaptive-mesh-refinement (AMR) code GAMER. Furthermore, a hybrid MPI/OpenMP model is investigated, which enables the full exploitation of the computing power in a heterogeneous CPU/GPU cluster and significantly improves the overall performance. Performance benchmarks are conducted on the Dirac GPU cluster at NERSC/LBNL using up to 32 Tesla C2050 GPUs. A single GPU achieves speed-ups of 101(25) and 84(22) for uniform-mesh and AMR simulations, respectively, as compared with the performance using one(four) CPU core(s), and the excellent performance persists in multi-GPU tests. In addition, we make a direct comparison between GAMER and the widely-adopted CPU code Athena (Stone et al. 2008) in adiabatic hydrodynamic tests and demonstrate that, with the same accuracy, GAMER is able to achieve two orders of magnitude performance speed-up.
March 18, 2011 by hgpu
