Iterative-method performance evaluation for multiple vectors associated with a large-scale sparse matrix. Issue 6 (2nd July 2016)

• Record Type: Journal Article
• Authors: Imamura, Seigo; Ono, Kenji; Yokokawa, Mitsuo
• Is Part Of: International journal of computational fluid dynamics. Volume 30:Issue 6(2016)
• Page Start: 395
• Page End: 401
• Publication Date: 2016-07-02
• Subjects: Ensemble computation -- iterative solver -- capacity computing -- sparse matrix -- high-performance computing; Fluid dynamics -- Data processing -- Periodicals; 532.05
• DOI: 10.1080/10618562.2016.1234046
• Languages: English
• ISSNs: 1061-8562

Abstract

ABSTRACT: Ensemble computing, which is an instance of capacity computing, is an effective computing scenario for exascale parallel supercomputers. In ensemble computing, there are multiple linear systems associated with a common coefficient matrix. We improve the performance of iterative solvers for multiple vectors by solving them at the same time, that is, by solving for the product of the matrices. We implemented several iterative methods and compared their performance. The maximum performance on Sparc VIIIfx was 7.6 times higher than that of a naïve implementation. Finally, to deal with the different convergence processes of linear systems, we introduced a control method to eliminate the calculation of already converged vectors.