OpenACC acceleration for the PN–PN-2 algorithm in Nek5000

Otero E, Gong J, Min M, Fischer P, Schlatter P, Laure E (2019)

Publication Type: Journal article

Publication year: 2019

Journal

Journal of Parallel and Distributed Computing Elsevier

Book Volume: 132

Pages Range: 69-78

DOI: 10.1016/j.jpdc.2019.05.010

Abstract

Due to its high performance and throughput capabilities, GPU-accelerated computing is becoming a popular technology in scientific computing, in particular using programming models such as CUDA and OpenACC. The main advantage with OpenACC is that it enables to simply port codes in their “original” form to GPU systems through compiler directives, thus allowing an incremental approach. An OpenACC implementation is applied to the CFD code Nek5000 for simulation of incompressible flows, based on the spectral-element method. The work follows up previous implementations and focuses now on the PN−PN−2 method for the spatial discretization of the Navier–Stokes equations. Performance results of the ported code show a speed-up of up to 3.1 on multi-GPU for a polynomial order N>11.

Authors with CRIS profile

Philipp Schlatter

Involved external institutions

Royal Institute of Technology / Kungliga Tekniska Högskolan (KTH) SE Sweden (SE) Argonne National Laboratory US United States (USA) (US)

How to cite

APA:

Otero, E., Gong, J., Min, M., Fischer, P., Schlatter, P., & Laure, E. (2019). OpenACC acceleration for the PN–PN-2 algorithm in Nek5000. Journal of Parallel and Distributed Computing, 132, 69-78. https://doi.org/10.1016/j.jpdc.2019.05.010

MLA:

Otero, Evelyn, et al. "OpenACC acceleration for the PN–PN-2 algorithm in Nek5000." Journal of Parallel and Distributed Computing 132 (2019): 69-78.

BibTeX: Download