Matrix Multiplication in Multiphysics Systems Using CUDA
Document Type
Conference Proceeding
Publication Date
2014
Publication Title
Proceedings of the 18th International Conference on Systems Science (ICSS 2013), Advances in Intelligent Systems and Computing
Publisher
Springer Verlag
Volume
240
First page number:
493
Last page number:
502
Abstract
Multiphysics systems are used to simulate various physics phenomena given byPartial Differential Equations (PDEs). The most popular method of solving PDEs is Finite Element method. The simulations require large amount of computational power, that is mostly caused by extensive processing of matrices. The high computational requirements have led recently to parallelization of algorithms and to utilization of Graphic Processing Units (GPUs). To take advantage of GPUs, one of GPU programming models has to be used. In this paper, CUDA model developed by nVidia is used to implement two parallel matrix multiplication algorithms. To evaluate the effectiveness of these algorithms, several experiments have been performed. Results have been compared with results obtained by classic Central Processing Unit (CPU) matrix multiplication algorithm. The comparison shows that matrix multiplication on GPU significantly outperforms classic CPU approach.
Keywords
CUDA; libMesh; Matrix Multiplication; Multiphysics Simulations
Disciplines
Electrical and Computer Engineering
Language
English
Permissions
Use Find in Your Library, contact the author, or interlibrary loan to garner a copy of the item. Publisher policy does not allow archiving the final published version. If a post-print (author's peer-reviewed manuscript) is allowed and available, or publisher policy changes, the item will be deposited.
Repository Citation
Krol, D.,
Zydek, D. M.,
Selvaraj, H.
(2014).
Matrix Multiplication in Multiphysics Systems Using CUDA.
Proceedings of the 18th International Conference on Systems Science (ICSS 2013), Advances in Intelligent Systems and Computing, 240
493-502.
Springer Verlag.