Performance Evaluation of Some Inverse Iteration Algorithms on PowerXCell^<i>TM</i> 8i Processor

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, we compare with the inverse iteration algorithms on PowerXCellTM 8i processor, which has been known as a heterogeneous environment. When some of all the eigenvalues are close together or there are clusters of eigenvalues, reorthogonalization must be adopted to all the eigenvectors associated with such eigenvalues. Reorthogonalization algorithms need a lot of computational cost. The Classical Gram-Schmidt (CGS) algorithm, the modified Gram-Schmidt (MGS) algorithm, and the Householder orthogonalization algorithm in terms of the compact WY representation have been known as reorthogonalization algorithms. These algorithms can be computed using BLAS level-1 and level-2. Since synergistic processor elements in PowerXCellTM 8i processor archive the high performance of BLAS level-2 and level-3, the orthogonalization algorithms except the MGS algorithm can be computed high-speed on parallel computers.

• 2012-07-09

著者

• Kinji Kimura

  Kyoto University

• Yoshimasa Nakamura

  Kyoto University

• Masami Takata

  Nara Women's University

• Hiroyuki Ishigami

  Graduate school of Informatics, Kyoto University

• Hiroyuki Ishigami

  Graduate School Of Informatics Kyoto University

• Hiroyuki Ishigami

  Kyoto University

関連論文

• Algebraic Approaches to Underdetermined Experiments in Biology
• Resultant-factorization Technique for Obtaining Solutions to Ordinary Differential Equations
• An Improved Shift Strategy for the Modified Discrete Lotka-Volterra with Shift Algorithm
• Implementation and performance evaluation of new inverse iteration algorithm with Householder transformation in terms of the compact WY representation
• Performance Evaluation of Some Inverse Iteration Algorithms on PowerXCellTM 8i Processor
• AR based Spatial Reasoning Capacity Training for Students
• Real Time Spatiotemporal Biological Stress Level Checking
• Improved Computation of Bounds for Positive Roots of Polynomials
• Implementation of the Orthogonal QD Algorithm for Lower Tridiagonal Matrices
• On Implementation and Evaluation of Inverse Iteration Algorithm with Compact WY Orthogonalization
• Accelerating the Numerical Computation of Positive Roots of Polynomials using Improved Bounds

もっと見る 閉じる

スポンサーリンク