Singular value decomposition on GPU using CUDA

Authors:
Sheetal Lahabar;P. J. Narayanan
Affiliations:
Center for Visual Information Technology, International Institute of Information Technology, Hyderabad, India;Center for Visual Information Technology, International Institute of Information Technology, Hyderabad, India
Venue:
IPDPS '09 Proceedings of the 2009 IEEE International Symposium on Parallel&Distributed Processing
Year:
2009

Citing 0
Cited 9

Solving quadratic assignment problems by genetic algorithms with GPU computation: a case study

Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking Papers
A parallel immune algorithm for traveling salesman problem and its application on cold rolling scheduling

Information Sciences: an International Journal
Implementing random indexing on GPU

Proceedings of the 19th High Performance Computing Symposia
Introducing scalable quantum approaches in language representation

QI'11 Proceedings of the 5th international conference on Quantum interaction
A GPU-based approximate SVD algorithm

PPAM'11 Proceedings of the 9th international conference on Parallel Processing and Applied Mathematics - Volume Part I
Parallel perfusion imaging processing using GPGPU

Computer Methods and Programs in Biomedicine
Accelerating text mining workloads in a MapReduce-based distributed GPU environment

Journal of Parallel and Distributed Computing
A divide-and-conquer approach for solving singular value decomposition on a heterogeneous system

Proceedings of the ACM International Conference on Computing Frontiers
Extended Kalman filter-based Elman networks for industrial time series prediction with GPU acceleration

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Linear algebra algorithms are fundamental to many computing applications. Modern GPUs are suited for many general purpose processing tasks and have emerged as inexpensive high performance co-processors due to their tremendous computing power. In this paper, we present the implementation of singular value decomposition (SVD) of a dense matrix on GPU using the CUDA programming model. SVD is implemented using the twin steps of bidiagonalization followed by diagonalization. It has not been implemented on the GPU before. Bidiagonalization is implemented using a series of Householder transformations which map well to BLAS operations. Diagonalization is performed by applying the implicitly shifted QR algorithm. Our complete SVD implementation outperforms the MATLAB and Intel ®Math Kernel Library (MKL) LAPACK implementation significantly on the CPU. We show a speedup of upto 60 over the MATLAB implementation and upto 8 over the Intel MKL implementation on a Intel Dual Core 2.66GHz PC on NVIDIA GTX 280 for large matrices. We also give results for very large matrices on NVIDIA Tesla S1070.