Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Implementation of algebraic procedures on the GPU using CUDA architecture on the example of generalized eigenvalue problem

Implementation of algebraic procedures on the GPU using CUDA architecture on the example of... AbstractThe ready to use set of functions to facilitatesolving a generalized eigenvalue problem for symmetricmatrices in order to efficiently calculate eigenvalues andeigenvectors, using Compute Unified Device Architecture(CUDA) technology from NVIDIA, is provided. An integralpart of the CUDA is the high level programming environmentenabling tracking both code executed on Central ProcessingUnit and on Graphics Processing Unit. The presentedmatrix structures allow for the analysis of the advantagesof using graphics processors in such calculations. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Open Computer Science de Gruyter

Implementation of algebraic procedures on the GPU using CUDA architecture on the example of generalized eigenvalue problem

Syrocki, Łukasz; Pestka, Grzegorz
Open Computer Science , Volume 6 (1): 12 – Jan 1, 2016
Download PDF
12 pages

Loading next page...
 
/lp/de-gruyter/implementation-of-algebraic-procedures-on-the-gpu-using-cuda-zftEljaF0g
Publisher
de Gruyter
Copyright
© 2016 Ł. Syrocki and G. Pestka
eISSN
2299-1093
DOI
10.1515/comp-2016-0006
Publisher site
See Article on Publisher Site

Abstract

AbstractThe ready to use set of functions to facilitatesolving a generalized eigenvalue problem for symmetricmatrices in order to efficiently calculate eigenvalues andeigenvectors, using Compute Unified Device Architecture(CUDA) technology from NVIDIA, is provided. An integralpart of the CUDA is the high level programming environmentenabling tracking both code executed on Central ProcessingUnit and on Graphics Processing Unit. The presentedmatrix structures allow for the analysis of the advantagesof using graphics processors in such calculations.

Journal

Open Computer Science – de Gruyter

Published: Jan 1, 2016

References

  • Solving dense generalized eigenproblems on multi - threaded architectures Mathematics and Computation
    Aliaga
  • CULA : Hybrid GPU Accelerated Linear Algebra Routines SPIE Defense and Security April
    Humphrey
  • Experiments with QL / QR methods for the symmetric tridiagonal eigenproblem Computer Dept Technical Report CS University of Tennessee Knoxville TN
    Greenbaum
  • Numerical linear algebra on emerging architectures : the PLASMAandMAGMAprojects Journal of Physics :
    Agullo