High-performance Processing of Covariance Matrices Using GPU Computations
- 作者: Erofeev K.1, Khramchenkov E.2, Biryal’tsev E.3
-
隶属关系:
- Kazan (Volga region) Federal University
- Kazan Branch of Joint Supercomputer Center
- Aff3
- 期: 卷 40, 编号 5 (2019)
- 页面: 547-554
- 栏目: Article
- URL: https://journals.rcsi.science/1995-0802/article/view/204340
- DOI: https://doi.org/10.1134/S1995080219050068
- ID: 204340
如何引用文章
详细
Practical applicability of many statistical algorithms is limited by large sizes of corresponding covariance matrices. These limitations can be significantly weakened due to effective use of the structure of covariance matrices, properties of the autocorrelation function, and advantages of the architecture of modern GPUs. This paper presents GPU implementations of the algorithms for inversion of a covariance matrix and solution of a system of linear equations whose coefficient matrix is a covariance matrix. Inversion of close to sparse covariance matrices is also considered in the work. For all the cases considered, significant accelerations were obtained in comparison with Octave mathematical software and ViennaCL computational library. For example, implemented algorithm of solution of a linear system was 6 times faster as compared with the implementation of Octave on the CPU and 3 times faster as compared with the ViennaCL implementation on the GPU for general matrices. The performance of inversion of a covariance matrix was 14 times faster than inversion algorithm of Octave on the CPU and 6 times faster than ViennaCL inversion algorithm on GPU.
作者简介
K. Erofeev
Kazan (Volga region) Federal University
编辑信件的主要联系方式.
Email: krllerof@gmail.com
俄罗斯联邦, Kazan, 420018
E. Khramchenkov
Kazan Branch of Joint Supercomputer Center
编辑信件的主要联系方式.
Email: ekhramch@gmail.com
俄罗斯联邦, Kazan, 420111
E. Biryal’tsev
Aff3
编辑信件的主要联系方式.
Email: igenbir@ya.ru
俄罗斯联邦, ZAO Gradient, Kazan, 420045
![](/img/style/loading.gif)