Efficient CSR-Based Sparse Matrix-Vector Multiplication on GPU
Joint Authors
Gao, Jiaquan
Qi, Panpan
He, Guixia
Source
Mathematical Problems in Engineering
Issue
Vol. 2016, Issue 2016 (31 Dec. 2016), pp.1-14, 14 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2016-10-30
Country of Publication
Egypt
No. of Pages
14
Main Subjects
Abstract EN
Sparse matrix-vector multiplication (SpMV) is an important operation in computational science and needs be accelerated because it often represents the dominant cost in many widely used iterative methods and eigenvalue problems.
We achieve this objective by proposing a novel SpMV algorithm based on the compressed sparse row (CSR) on the GPU.
Our method dynamically assigns different numbers of rows to each thread block and executes different optimization implementations on the basis of the number of rows it involves for each block.
The process of accesses to the CSR arrays is fully coalesced, and the GPU’s DRAM bandwidth is efficiently utilized by loading data into the shared memory, which alleviates the bottleneck of many existing CSR-based algorithms (i.e., CSR-scalar and CSR-vector).
Test results on C2050 and K20c GPUs show that our method outperforms a perfect-CSR algorithm that inspires our work, the vendor tuned CUSPARSE V6.5 and CUSP V0.5.1, and three popular algorithms clSpMV, CSR5, and CSR-Adaptive.
American Psychological Association (APA)
Gao, Jiaquan& Qi, Panpan& He, Guixia. 2016. Efficient CSR-Based Sparse Matrix-Vector Multiplication on GPU. Mathematical Problems in Engineering،Vol. 2016, no. 2016, pp.1-14.
https://search.emarefa.net/detail/BIM-1112203
Modern Language Association (MLA)
Gao, Jiaquan…[et al.]. Efficient CSR-Based Sparse Matrix-Vector Multiplication on GPU. Mathematical Problems in Engineering No. 2016 (2016), pp.1-14.
https://search.emarefa.net/detail/BIM-1112203
American Medical Association (AMA)
Gao, Jiaquan& Qi, Panpan& He, Guixia. Efficient CSR-Based Sparse Matrix-Vector Multiplication on GPU. Mathematical Problems in Engineering. 2016. Vol. 2016, no. 2016, pp.1-14.
https://search.emarefa.net/detail/BIM-1112203
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1112203