Finite-element sparse matrix vector multiplication on graphic processing units

IEEE Transactions on Magnetics

Volumn 46, Issue 8, 2010, Pages 2982-2985

  Dehnavi, Maryam Mehri ^a   Fernández, David M ^a   Giannacopoulos, Dennis ^a  

^a MCGILL UNIVERSITY   (Canada)

Author keywords

Computer architecture; graphic processing units (GPUs); parallel processing; sparse matrix vector multiplication (SMVM)

Indexed keywords

COMPUTER ARCHITECTURE; FINITE ELEMENT METHOD; PROGRAM PROCESSORS;

ELECTROMAGNETIC APPLICATIONS; GRAPHIC PROCESSING UNITS; GRAPHIC PROCESSING UNITS (GPUS); LARGE SPARSE MATRIX; PARALLEL PROCESSING; PROGRAMMABILITY; SPARSE MATRIX-VECTOR MULTIPLICATION; SPARSITY PATTERNS;

GRAPHICS PROCESSING UNIT;

EID: 77954837026     PISSN: 00189464     EISSN: None     Source Type: Journal    
DOI: 10.1109/TMAG.2010.2043511     Document Type: Article

References (9)

1. NVIDIA CUDA [Onlineö. Available: http://developer.nvidia.com/object/ cuda.html
2. J. D. Owens et al., "A survey of general-purpose computation on graphics hardware.," Comput. Graphics Forum, pp. 80-113, 2007.
3. S. Yousef, Iterative Methods for Sparse Linear Systems. Philadelphia, PA: SIAM, 2003, p. 528.
4. L. Buatois, G. Caumon, and B. Lévy, "Concurrent number cruncher: An efficient sparse linear solver on the GPU," in High Performance Computing and Communications. Berlin, Germany: Springer-Verlag, 2007, vol.4782, Lecture Notes in Computer Science, pp. 358-371.
5. S. Sengupta, M. Harris, Y. Zhang, and J. D. Owens, "Scan primitives for GPU computing," in Proc. Graphics Hardw., 2007, pp. 97-106.
6. W. A. Wiggers, V. Bakker, A. B. J. Kokkeler, A. B. J., and G. J. M. Smit, "Implementing the conjugate gradient algorithm on multi-core systems," in Proc. Int. Symp. System-on-Chip, 2007, pp. 11-14.
7. S.Williams et al., "Optimization of sparse matrix vector multiplication on emerging multicore platforms," in Proc. ACM/IEEE Conf. Supercomput., 2007, Article no. 38.
8. D. Fernandez, D. Giannacopoulos, and W. Gross, "Efficient multicore sparse matrix-vector multiplication for FE electromagnetics," IEEE Trans. Magn., vol.45, no.3, pp. 1392-1395, Mar. 2009.
9. N. Bell and M. G. Fernandez, "Efficient sparse matrix-vector multiplication on CUDA," NVIDIA Tech. Rep., 2008.