A GPU-based hyperbolic SVD algorithm |
| |
| Authors: | Vedran Novakovi? Sanja Singer |
| |
| Institution: | (1) Graduate School of Information Science & Technology, Hokkaido University, Sapporo, Japan;(2) Information Initiative Center, Hokkaido University, Sapporo, Japan |
| |
| Abstract: | 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. |
| |
| Keywords: | |
| 本文献已被 SpringerLink 等数据库收录！ |
|
