×

Development of an overset grid computational fluid dynamics solver on graphical processing units. (English) Zbl 1365.76242

Summary: General Purpose computation on Graphics Processing Units (GPGPUs) has gained popularity recently. Graphics Processing Units (GPUs) are being used for computationally intensive and data intensive problems to obtain orders of magnitude speed up in wide range of domains like molecular dynamics, bio-physics, geo-physics and CFD [E. Elsen et al., J. Comput. Phys. 227, No. 24, 10148–10161 (2008; Zbl 1218.76035), E. H. Phillips et al., “Rapid aerodynamic performance prediction on a cluster of graphics processing units”, in: Proceedings of the 47th Aerospace sciences meeting, AIAA 2009. Reston, VA: AIAA. Article ID 2009-565, 11 p. (2009; doi:10.2514/6.2009-565), T. Brandvik and G. Pullan, “Acceleration of a 3D Euler solver using commodity graphics hardware”, in: Proceedings of the 46th Aerospace sciences meeting and exhibit, AIAA 2008. Reston, VA: AIAA. Article ID 2008-607, 10 p. (2008; doi:10.2514/6.2008-607), T. R. Hagen et al., Lect. Notes Comput. Sci. 3994, 220–227 (2006; Zbl 1157.76358)]. In this paper we discuss the development of a two-dimensional overset grid CFD solver on GPUs for moving body problems and demonstrate orders of magnitude speed-up on single GPU unit as compared to C/FORTRAN solver on a single CPU core. The two-dimensional overset grid CFD solver consists of three modules. A near-body solver module which solves the fluid conservation laws on structured and unstructured mesh systems, an off-body solver module which solves the fluid-conservation laws on an isotropic Cartesian mesh, and the domain connectivity module which manages the interaction between these two mesh systems. The GPU acceleration is extended to all the three modules. We expect this work to be the fore-runner for future development efforts for full three-dimensional Navier-Stokes solutions capable of executing in a heterogeneous parallel environment. Here “heterogeneous parallelism” refers to combination of Message Passing Interface (MPI) based communication for distributed memory systems, and large scale multi-threading using GPUs for shared memory systems.

MSC:

76M25 Other numerical methods (fluid mechanics) (MSC2010)
76-04 Software, source code, etc. for problems pertaining to fluid mechanics
65Y10 Numerical algorithms for specific classes of architectures
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] LeGresley, P.; Elsen, E.; Darve, E., Large calculation of the flow over a hypersonic vehicle using a GPU, J Comput Phys, 227, 24, 10148-10161 (2008) · Zbl 1218.76035
[2] Phillips EH, Zhang Y, Davis RL, Owens JD. Rapid aerodynamic performance prediction on a cluster of graphics processing units. In: 47th Aerospace sciences meeting and exhibit, AIAA-2009-065, Orlando, FL; 2009.; Phillips EH, Zhang Y, Davis RL, Owens JD. Rapid aerodynamic performance prediction on a cluster of graphics processing units. In: 47th Aerospace sciences meeting and exhibit, AIAA-2009-065, Orlando, FL; 2009.
[3] Brandvik T, Pullan G. Acceleration of a 3D Euler solver using commodity graphics hardware. In: 46th AIAA aerospace sciences meeting and exhibit, AIAA-2008-0607, Reno, NV; 2008.; Brandvik T, Pullan G. Acceleration of a 3D Euler solver using commodity graphics hardware. In: 46th AIAA aerospace sciences meeting and exhibit, AIAA-2008-0607, Reno, NV; 2008.
[4] Hagen, T. R.; Lie, K-. A.; Natvig, J. R., Solving the Euler equations on graphics processing units, Lect Notes Comput Sci, 3994, 220-227 (2006) · Zbl 1157.76358
[5] Flynn, M., Some computer organizations and their effectiveness, IEEE Trans Comput, C21, 9, 948-960 (1972) · Zbl 0241.68020
[6] Sitaraman J, Katz A, Jayaraman B, Wissink AM, Sankaran V. Evaluation of multi-solver paradigm for CFD using overset unstructured and structured adaptive Cartesian grids. In: 46th AIAA aerospace sciences meeting and exhibit, AIAA-2008-660, Reno, Nevada; 2008.; Sitaraman J, Katz A, Jayaraman B, Wissink AM, Sankaran V. Evaluation of multi-solver paradigm for CFD using overset unstructured and structured adaptive Cartesian grids. In: 46th AIAA aerospace sciences meeting and exhibit, AIAA-2008-660, Reno, Nevada; 2008.
[7] http://gpgpu.org; http://gpgpu.org
[8] NVIDIA, NVIDIA CUDA programming guide version 3.2.; NVIDIA, NVIDIA CUDA programming guide version 3.2.
[9] Fermi. NVIDIA’s next generation CUDA compute architecture. <http://www.nvidia.com/object/fermi_architecture.html; Fermi. NVIDIA’s next generation CUDA compute architecture. <http://www.nvidia.com/object/fermi_architecture.html
[10] Micikevicius P. 3D finite difference computation on GPUs using CUDA, GPGPU-2. In: Proceedings of the 2nd workshop on general purpose processing on graphics processing units; 2009. p. 79-84.; Micikevicius P. 3D finite difference computation on GPUs using CUDA, GPGPU-2. In: Proceedings of the 2nd workshop on general purpose processing on graphics processing units; 2009. p. 79-84.
[11] Roe, P. L., Approximate Riemann solvers, parameter vectors, and difference schemes, J Comput Phys, 135, 250-258 (1997) · Zbl 0890.65094
[12] Vatsa, V. N.; Thomas, J. L.; Wedan, B. W., Navier Stokes computations of a prolate spheroid at an angle of attack, J Aircraft, 26, 11, 986-993 (1989)
[13] Kennedy Chistopher A, Carpenter Mark H, Michael Lewis R. Low-storage, explicit Runge-Kutta schemes for the compressible Navier-Stokes equations. NASA/CR 1999-209349; 1999.; Kennedy Chistopher A, Carpenter Mark H, Michael Lewis R. Low-storage, explicit Runge-Kutta schemes for the compressible Navier-Stokes equations. NASA/CR 1999-209349; 1999. · Zbl 0986.76060
[14] Jameson, A., Analysis and design of numerical schemes for gas dynamics 2 artificial diffusion and discrete shock structure, Int J Comput Fluid Dynam, 5, 1-38 (1995)
[15] Buning PG et al. OVERFLOW users manual. NASA Langley Research Center, July 2003.; Buning PG et al. OVERFLOW users manual. NASA Langley Research Center, July 2003.
[16] Petersson, N. A., An algorithm for assembling overlapping grid systems, SIAM J Sci Comput, 20, 1995-2022 (1999) · Zbl 0939.65110
[17] Brown DL, Henshaw WD, Quinlan DJ. Overture: object-oriented tools for overset grid applications. In: AIAA 17th conference on applied aerodynamics, AIAA 1999-3130, Norfolk, VA; 1999.; Brown DL, Henshaw WD, Quinlan DJ. Overture: object-oriented tools for overset grid applications. In: AIAA 17th conference on applied aerodynamics, AIAA 1999-3130, Norfolk, VA; 1999.
[18] Henshaw WD. OGEN: an overlapping grid generator for overture. Research Report LA-UR-96-3466. Los Alamos National Laboratory; 1996.; Henshaw WD. OGEN: an overlapping grid generator for overture. Research Report LA-UR-96-3466. Los Alamos National Laboratory; 1996.
[19] Rogers, S. E.; Suhs, N. E.; Dietz, W. E., PEGASUS 5: an automated preprocessor for overset-grid computational fluid dynamics, AIAA J, 41, 6, 1037-1045 (2003)
[20] Noack RW. SUGGAR: a general capability for moving body overset grid assembly. In: 17th AIAA computational fluid dynamics conference, AIAA-2005-5117, Toronto, ON; 2005.; Noack RW. SUGGAR: a general capability for moving body overset grid assembly. In: 17th AIAA computational fluid dynamics conference, AIAA-2005-5117, Toronto, ON; 2005.
[21] Alonso JJ, Hahn S, Ham F, Herrmann M, Iaccarino G, Kalitzin G, et al. CHIMPS: a high-performance scalable module for multi-physics simulations. In: 42nd AIAA/ASME/SAE/ASEE joint propulsion conference, AIAA-2006-5274, Sacramento, CA; 2006.; Alonso JJ, Hahn S, Ham F, Herrmann M, Iaccarino G, Kalitzin G, et al. CHIMPS: a high-performance scalable module for multi-physics simulations. In: 42nd AIAA/ASME/SAE/ASEE joint propulsion conference, AIAA-2006-5274, Sacramento, CA; 2006.
[22] Belk DM, Maple RC. Automated assembly of structured grids for moving body problems. In: 12th AIAA computational fluid dynamics conference. Part 1, AIAA-1995-1680, Washington, DC; 1995. p. 381-90.; Belk DM, Maple RC. Automated assembly of structured grids for moving body problems. In: 12th AIAA computational fluid dynamics conference. Part 1, AIAA-1995-1680, Washington, DC; 1995. p. 381-90.
[23] Wang, Z. J.; Parthasarathy, V.; Hariharan, N., A fully automated chimera methodology for multiple moving body problems, Int J Numer Methods Fluids, 33, 7, 919-938 (2000) · Zbl 0984.76073
[24] Sitaraman, J.; Floros, M.; Wissink, A.; Potsdam, M., Parallel domain connectivity algorithm for unsteady flow computations using overlapping and adaptive grids, J Comput Phys, 229, 12, 4703-4723 (2010) · Zbl 1305.76058
[25] Lee Y, Baeder JD. Implicit hole cutting—a new approach to overset grid connectivity. In: 16th AIAA computational fluid dynamics conference, AIAA-2003-4128, Orlando, FL; 2003.; Lee Y, Baeder JD. Implicit hole cutting—a new approach to overset grid connectivity. In: 16th AIAA computational fluid dynamics conference, AIAA-2003-4128, Orlando, FL; 2003.
[26] Sankaran V, Sitaraman J, Wissink A, Datta A, Jayaraman B, Potsdam M, et al. Application of HELIOS computational platform to rotorcraft flowfields. In: 48th AIAA aerospace sciences meeting and exhibit, AIAA-2010-1230 Orlando, FL; 2010.; Sankaran V, Sitaraman J, Wissink A, Datta A, Jayaraman B, Potsdam M, et al. Application of HELIOS computational platform to rotorcraft flowfields. In: 48th AIAA aerospace sciences meeting and exhibit, AIAA-2010-1230 Orlando, FL; 2010.
[27] Bonet, J.; Peraire, J., An alternating digital tree algorithm for 3D geometric searching and intersection problems, Int J Numer Methods Eng, 31, 1, 1-17 (1991) · Zbl 0825.73958
[28] Morinishi, K., A finite difference solution of the Euler equations on non-body-fitted Cartesian grids, Comput Fluids, 21, 3, 331-344 (1992) · Zbl 0753.76121
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.