@inproceedings{38de125854f24f3abcb74d36e00644f9,
title = "OpenACC-based GPU acceleration of a 3-D unstructured discontinuous galerkin method",
abstract = "A GPU-accelerated discontinuous Galerkin (DG) method is presented for the solution of compressible flows on 3-D unstructured grids. The present work has employed two of the most attractive features in a new programming standard of parallel computing \{ OpenACC: 1) multi-platform/compiler support and 2) descriptive directive interface to upgrade a legacy CFD solver with the capacity of GPU computing, without significant extra cost in recoding, resulting in a highly portable and extensible GPU-accelerated code. In addition, a face renumbering/grouping scheme is proposed to overcome the \textbackslash{}race condition{"} in face- based flux calculations that occurs on GPU vectorization. Performance of the developed double-precision solver is assessed for both simple and complex geometries. Speedup factors up to but not limited to 24× and 1.6× were achieved by comparing the measured computing time of the OpenACC program running on an NVIDIA Tesla K20c GPU to that of the equivalent MPI program running on one single core and full sixteen cores of an AMD Opteron-6128 CPU respectively, indicating a great potential to port more features of the underlying DG solver into the OpenACC framework.",
author = "Yidong Xia and Hong Luo and Lixiang Luo and Jack Edwards and Jialin Lou and Frank Mueller",
year = "2014",
doi = "10.2514/6.2014-1129",
language = "English",
isbn = "9781624102561",
series = "52nd AIAA Aerospace Sciences Meeting - AIAA Science and Technology Forum and Exposition, SciTech 2014",
publisher = "American Institute of Aeronautics and Astronautics Inc.",
booktitle = "52nd AIAA Aerospace Sciences Meeting - AIAA Science and Technology Forum and Exposition, SciTech 2014",
note = "52nd AIAA Aerospace Sciences Meeting - AIAA Science and Technology Forum and Exposition, SciTech 2014 ; Conference date: 13-01-2014 Through 17-01-2014",
}