FSB (University of Zagreb) · 2011 · 36 citations · 16 references
ComputingComputer ScienceHigh-performance ComputingComputer GraphicsParallel ComputingScientific ComputingHyperbolic GeometryMatrix ComputationNumerical AlgorithmsNumerical AnalysisNumerical Linear AlgebraVector GraphicsScientific Computing On GpusStructured Matrix Computation
A one-sided Jacobi hyperbolic singular value decomposition (HSVD) algorithm, using a massively parallel graphics processing unit (GPU), is developed. The algorithm also serves as the final stage of solving a symmetric indefinite eigenvalue problem. Numerical testing demonstrates the gains in speed and accuracy over sequential and MPI-parallelized variants of similar Jacobi-type HSVD algorithms. Finally, possibilities of hybrid CPU--GPU parallelism are discussed.
16
Singular value decomposition on GPU using CUDA
Sheetal Lahabar, P. J. Narayanan · 2009 · 130 citations