Assessment of WENO schemes for numerical simulation of some hyperbolic equations using GPU. (English) Zbl 1284.76008
Summary: We study the implementation of WENO schemes on Graphic Processor Unit (GPU). The GPU implementation of the schemes are described for different test cases. The test cases are chosen from the linear and nonlinear and also one- and two-dimensional hyperbolic equations. Both the CPU and GPU versions of all the solvers are developed. The computational time of each test case using different schemes is obtained and the speedups are reported for different number of grid points. Also, two different GPUs are utilized and an occupancy analysis is performed for each of the GPUs. The numerical experiments show the speedups for the WENO schemes are more than that of the first-order upwind scheme and are very promising. Furthermore, the occupancy analysis indicates the occupancy is optimal for the presented simulations.
MSC:
| 76-04 | Software, source code, etc. for problems pertaining to fluid mechanics |
| 76M20 | Finite difference methods applied to problems in fluid mechanics |
| 65M06 | Finite difference methods for initial value and initial-boundary value problems involving PDEs |
| 65Y10 | Numerical algorithms for specific classes of architectures |
Software:
CUDAReferences:
| [1] | Ekaterinaris, J. A., High-order accurate low numerical diffusion methods for aerodynamics, Progr Aerospace Sci, 41, 192-300 (2005) |
| [2] | Lele, S. K., Compact finite difference schemes with spectral-like resolution, J Comput Phys, 103, 16-42 (1992) · Zbl 0759.65006 |
| [3] | Esfahanian, V.; Hejranfar, K.; Mahmoodi Darian, H., Implementation of high-order compact finite-difference method to parabolized Navier-Stokes schemes, Int J Numer Methods Fluids, 58, 659-685 (2008) · Zbl 1151.76023 |
| [4] | Hejranfar, K.; Esfahanian, V.; Mahmoodi Darian, H., On the use of high-order accurate solutions of PNS schemes as basic flows for stability analysis of hypersonic axisymmetric flows, J Fluids Eng, 129, 1328-1338 (2007) |
| [5] | Mahmoodi Darian, H.; Esfahanian, V.; Hejranfar, K., A shock-detecting sensor for filtering of high-order compact finite difference schemes, J Comput Phys, 230, 494-514 (2011) · Zbl 1283.76045 |
| [6] | Harten, A.; Engquist, B.; Osher, S.; Chakravarthy, S. R., Uniformly high order accurate essentially non-oscillatory schemes, III, J Comput Phys, 71, 231-303 (1987) · Zbl 0652.65067 |
| [7] | Harten, A.; Osher, S., Uniformly high-order accurate nonoscillatory schemes. I, SIAM J Numer Anal, 24, 2, 279-309 (1987) · Zbl 0627.65102 |
| [8] | Shu, C. W.; Osher, S., Efficient implementation of essentially non-oscillatory shock-capturing schemes, J Comput Phys, 77, 439-471 (1988) · Zbl 0653.65072 |
| [9] | Liu, X. D.; Osher, S.; Chan, T., Weighted essentially non-oscillatory schemes, J Comput Phys, 115, 200-212 (1994) · Zbl 0811.65076 |
| [10] | Jiang, G. S.; Shu, C. W., Efficient implementation of weighted ENO schemes, J Comput Phys, 126, 202-228 (1996) · Zbl 0877.65065 |
| [11] | Shen, Y.; Yang, G., Hybrid finite compact-WENO schemes for shock calculation, Int J Numer Methods Fluids, 53, 531-560 (2007) · Zbl 1104.76065 |
| [15] | Karantasis, K. I.; Polychronopoulos, E. D.; Ekaterinaris, J. A., Acceleration of a high order accurate method for compressible flows on SDSM based GPU clusters, (Proceedings of the 2010 IEEE 16th international conference on parallel and distributed systems, ICPADS ’10 (2010), IEEE Computer Society: IEEE Computer Society Washington (DC, USA)), 460-467 |
| [16] | Tutkun, B.; Edis, F. O., A GPU application for high-order compact finite difference scheme, Comput Fluids, 55, 29-35 (2012) · Zbl 1291.76232 |
| [17] | Sod, G., A survey of several finite difference methods for systems of nonlinear hyperbolic conservation laws, J Comput Phys, 27, 1-31 (1978) · Zbl 0387.76063 |
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.
