OpenACC acceleration of an unstructured CFD solver based on a reconstructed discontinuous Galerkin method for compressible flows
Abstract
Here, an OpenACC directive-based graphics processing unit (GPU) parallel scheme is presented for solving the compressible Navier–Stokes equations on 3D hybrid unstructured grids with a third-order reconstructed discontinuous Galerkin method. The developed scheme requires the minimum code intrusion and algorithm alteration for upgrading a legacy solver with the GPU computing capability at very little extra effort in programming, which leads to a unified and portable code development strategy. A face coloring algorithm is adopted to eliminate the memory contention because of the threading of internal and boundary face integrals. A number of flow problems are presented to verify the implementation of the developed scheme. Timing measurements were obtained by running the resulting GPU code on one Nvidia Tesla K20c GPU card (Nvidia Corporation, Santa Clara, CA, USA) and compared with those obtained by running the equivalent Message Passing Interface (MPI) parallel CPU code on a compute node (consisting of two AMD Opteron 6128 eight-core CPUs (Advanced Micro Devices, Inc., Sunnyvale, CA, USA)). Speedup factors of up to 24× and 1.6× for the GPU code were achieved with respect to one and 16 CPU cores, respectively. The numerical results indicate that this OpenACC-based parallel scheme is an effective and extensible approachmore »
- Authors:
-
- Idaho National Lab. (INL), Idaho Falls, ID (United States)
- North Carolina State Univ., Raleigh, NC (United States)
- Publication Date:
- Research Org.:
- Idaho National Laboratory (INL), Idaho Falls, ID (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1249553
- Report Number(s):
- INL/JOU-15-34041
Journal ID: ISSN 0271-2091
- Grant/Contract Number:
- AC07-05ID14517
- Resource Type:
- Accepted Manuscript
- Journal Name:
- International Journal for Numerical Methods in Fluids
- Additional Journal Information:
- Journal Volume: 78; Journal Issue: 3; Journal ID: ISSN 0271-2091
- Publisher:
- Wiley
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; GPU computing; OpenACC; CUDA; discontinuous Galerkin; WENO; compressible flow; Navier-Stokes equations
Citation Formats
Xia, Yidong, Lou, Jialin, Luo, Hong, Edwards, Jack, and Mueller, Frank. OpenACC acceleration of an unstructured CFD solver based on a reconstructed discontinuous Galerkin method for compressible flows. United States: N. p., 2015.
Web. doi:10.1002/fld.4009.
Xia, Yidong, Lou, Jialin, Luo, Hong, Edwards, Jack, & Mueller, Frank. OpenACC acceleration of an unstructured CFD solver based on a reconstructed discontinuous Galerkin method for compressible flows. United States. https://doi.org/10.1002/fld.4009
Xia, Yidong, Lou, Jialin, Luo, Hong, Edwards, Jack, and Mueller, Frank. Mon .
"OpenACC acceleration of an unstructured CFD solver based on a reconstructed discontinuous Galerkin method for compressible flows". United States. https://doi.org/10.1002/fld.4009. https://www.osti.gov/servlets/purl/1249553.
@article{osti_1249553,
title = {OpenACC acceleration of an unstructured CFD solver based on a reconstructed discontinuous Galerkin method for compressible flows},
author = {Xia, Yidong and Lou, Jialin and Luo, Hong and Edwards, Jack and Mueller, Frank},
abstractNote = {Here, an OpenACC directive-based graphics processing unit (GPU) parallel scheme is presented for solving the compressible Navier–Stokes equations on 3D hybrid unstructured grids with a third-order reconstructed discontinuous Galerkin method. The developed scheme requires the minimum code intrusion and algorithm alteration for upgrading a legacy solver with the GPU computing capability at very little extra effort in programming, which leads to a unified and portable code development strategy. A face coloring algorithm is adopted to eliminate the memory contention because of the threading of internal and boundary face integrals. A number of flow problems are presented to verify the implementation of the developed scheme. Timing measurements were obtained by running the resulting GPU code on one Nvidia Tesla K20c GPU card (Nvidia Corporation, Santa Clara, CA, USA) and compared with those obtained by running the equivalent Message Passing Interface (MPI) parallel CPU code on a compute node (consisting of two AMD Opteron 6128 eight-core CPUs (Advanced Micro Devices, Inc., Sunnyvale, CA, USA)). Speedup factors of up to 24× and 1.6× for the GPU code were achieved with respect to one and 16 CPU cores, respectively. The numerical results indicate that this OpenACC-based parallel scheme is an effective and extensible approach to port unstructured high-order CFD solvers to GPU computing.},
doi = {10.1002/fld.4009},
journal = {International Journal for Numerical Methods in Fluids},
number = 3,
volume = 78,
place = {United States},
year = {Mon Feb 09 00:00:00 EST 2015},
month = {Mon Feb 09 00:00:00 EST 2015}
}
Web of Science
Works referenced in this record:
A Survey of General-Purpose Computation on Graphics Hardware
journal, March 2007
- Owens, John D.; Luebke, David; Govindaraju, Naga
- Computer Graphics Forum, Vol. 26, Issue 1
Acceleration of a 3D Euler Solver Using Commodity Graphics Hardware
conference, June 2012
- Brandvik, Tobias; Pullan, Graham
- 46th AIAA Aerospace Sciences Meeting and Exhibit
GPU acceleration of an unmodified parallel finite element Navier-Stokes solver
conference, June 2009
- Goddeke, Dominik; Buijssen, Sven H. M.; Wobker, Hilmar
- Simulation (HPCS), 2009 International Conference on High Performance Computing & Simulation
Rapid Aerodynamic Performance Prediction on a Cluster of Graphics Processing Units
conference, June 2012
- Phillips, Everett; Zhang, Yao; Davis, Roger
- 47th AIAA Aerospace Sciences Meeting including The New Horizons Forum and Aerospace Exposition
CUDA Implementation of a Navier-Stokes Solver on Multi-GPU Desktop Platforms for Incompressible Flows
conference, June 2012
- Thibault, Julien; Senocak, Inanc
- 47th AIAA Aerospace Sciences Meeting including The New Horizons Forum and Aerospace Exposition
An MPI-CUDA Implementation for Massively Parallel Incompressible Flow Computations on Multi-GPU Clusters
conference, June 2012
- Jacobsen, Dana; Thibault, Julien; Senocak, Inanc
- 48th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition
Porting of an Edge-Based CFD Solver to GPUs
conference, June 2012
- Corrigan, Andrew; Camelli, Fernando; Löhner, Rainald
- 48th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition
Acceleration of a CFD Code with a GPU
journal, January 2010
- Jespersen, Dennis C.
- Scientific Programming, Vol. 18, Issue 3-4
Unsteady CFD computations using vertex-centered finite volumes for unstructured grids on Graphics Processing Units
journal, May 2010
- Asouti, V. G.; Trompoukis, X. S.; Kampolis, I. C.
- International Journal for Numerical Methods in Fluids, Vol. 67, Issue 2
Semi-automatic porting of a large-scale Fortran CFD code to GPUs
journal, May 2011
- Corrigan, Andrew; Camelli, Fernando; Löhner, Rainald
- International Journal for Numerical Methods in Fluids, Vol. 69, Issue 2
Large calculation of the flow over a hypersonic vehicle using a GPU
journal, December 2008
- Elsen, Erich; LeGresley, Patrick; Darve, Eric
- Journal of Computational Physics, Vol. 227, Issue 24
Nodal discontinuous Galerkin methods on graphics processors
journal, November 2009
- Klöckner, A.; Warburton, T.; Bridge, J.
- Journal of Computational Physics, Vol. 228, Issue 21
Running unstructured grid-based CFD solvers on modern graphics hardware
journal, April 2011
- Corrigan, Andrew; Camelli, Fernando F.; Löhner, Rainald
- International Journal for Numerical Methods in Fluids, Vol. 66, Issue 2
High-Order Spectral Difference: Verification and Acceleration using GPU Computing
conference, June 2013
- Zimmerman, Ben J.; Wang, Zhi J.; Visbal, Miguel R.
- 21st AIAA Computational Fluid Dynamics Conference
Using Compiler Directives for Accelerating CFD Applications on GPUs
book, January 2012
- Jin, Haoqiang; Kellogg, Mark; Mehrotra, Piyush
- OpenMP in a Heterogeneous World
OpenCL: A Parallel Programming Standard for Heterogeneous Computing Systems
journal, May 2010
- Stone, John E.; Gohara, David; Shi, Guochun
- Computing in Science & Engineering, Vol. 12, Issue 3, p. 66-73
A Hermite WENO reconstruction-based discontinuous Galerkin method for the Euler equations on tetrahedral grids
journal, June 2012
- Luo, Hong; Xia, Yidong; Li, Shujie
- Journal of Computational Physics, Vol. 231, Issue 16
A reconstructed discontinuous Galerkin method based on a Hierarchical WENO reconstruction for compressible flows on tetrahedral grids
journal, March 2013
- Luo, Hong; Xia, Yidong; Spiegel, Seth
- Journal of Computational Physics, Vol. 236
A set of parallel, implicit methods for a reconstructed discontinuous Galerkin method for compressible flows on 3D hybrid grids
journal, July 2014
- Xia, Yidong; Luo, Hong; Frisbey, Megan
- Computers & Fluids, Vol. 98
An implicit Hermite WENO reconstruction-based discontinuous Galerkin method on tetrahedral grids
journal, June 2014
- Xia, Yidong; Luo, Hong; Nourgaliev, Robert
- Computers & Fluids, Vol. 96
Average-State Jacobians and Implicit Methods for Compressible Viscous and Turbulent Flows
journal, October 1997
- Batten, P.; Leschziner, M. A.; Goldberg, U. C.
- Journal of Computational Physics, Vol. 137, Issue 1
Discontinuous Galerkin solution of the Reynolds-averaged Navier–Stokes and k–ω turbulence model equations
journal, May 2005
- Bassi, Francesco; Crivellini, Andrea; Rebay, Stefano
- Computers & Fluids, Vol. 34, Issue 4-5
A discontinuous Galerkin method based on a Taylor basis for the compressible flows on arbitrary grids
journal, October 2008
- Luo, Hong; Baum, Joseph D.; Löhner, Rainald
- Journal of Computational Physics, Vol. 227, Issue 20
A reconstructed discontinuous Galerkin method for the compressible Navier–Stokes equations on arbitrary grids
journal, September 2010
- Luo, Hong; Luo, Luqing; Nourgaliev, Robert
- Journal of Computational Physics, Vol. 229, Issue 19
A Parallel, Reconstructed Discontinuous Galerkin Method for the Compressible Flows on Arbitrary Grids
journal, February 2011
- Luo, Hong; Luo, Luqing; Ali, Amjad
- Communications in Computational Physics, Vol. 9, Issue 2
A Reconstructed Discontinuous Galerkin Method for the Euler Equations on Arbitrary Grids
journal, November 2012
- Luo, Hong; Luo, Luqing; Nourgaliev, Robert
- Communications in Computational Physics, Vol. 12, Issue 5
A class of hybrid DG/FV methods for conservation laws II: Two-dimensional cases
journal, February 2012
- Zhang, Laiping; Wei, Liu; Lixin, He
- Journal of Computational Physics, Vol. 231, Issue 4
A p-multigrid discontinuous Galerkin method for the Euler equations on unstructured grids
journal, January 2006
- Luo, Hong; Baum, Joseph D.; Löhner, Rainald
- Journal of Computational Physics, Vol. 211, Issue 2
The Runge–Kutta Discontinuous Galerkin Method for Conservation Laws V
journal, April 1998
- Cockburn, Bernardo; Shu, Chi-Wang
- Journal of Computational Physics, Vol. 141, Issue 2
Directive-Based GPU Programming for Computational Fluid Dynamics
conference, January 2014
- Pickering, Brent P.; Roy, Christopher J.
- 52nd Aerospace Sciences Meeting
High-order CFD methods: current status and perspective: HIGH-ORDER CFD METHODS
journal, January 2013
- Wang, Z. J.; Fidkowski, Krzysztof; Abgrall, Rémi
- International Journal for Numerical Methods in Fluids, Vol. 72, Issue 8
High-Re solutions for incompressible flow using the Navier-Stokes equations and a multigrid method
journal, December 1982
- Ghia, U.; Ghia, K. N.; Shin, C. T.
- Journal of Computational Physics, Vol. 48, Issue 3
Works referencing / citing this record:
Nekbone performance on GPUs with OpenACC and CUDA Fortran implementations
journal, July 2016
- Gong, Jing; Markidis, Stefano; Laure, Erwin
- The Journal of Supercomputing, Vol. 72, Issue 11
Optimization and acceleration of flow simulations for CFD on CPU/GPU architecture
journal, June 2019
- Lei, Jiang; Li, Da-li; Zhou, Yun-long
- Journal of the Brazilian Society of Mechanical Sciences and Engineering, Vol. 41, Issue 7
High-Order Hyperbolic Navier-Stokes Reconstructed Discontinuous Galerkin Method for Unsteady Flows
conference, June 2019
- Li, Lingquan; Lou, Jialin; Luo, Hong
- AIAA Aviation 2019 Forum