Title :
A Modified Storage Format for Accelerating SPMV
Author :
Jin Tian ; Fei Wu ; Guohui Zeng ; Li Gong
Author_Institution :
Coll. of Electron. & Electr. Eng., Shanghai Univ. Of Eng. Sci., Shanghai, China
Abstract :
This paper aims to study how to choose an effective storage format to accelerate sparse matrix vector product (SMVP) occurring in different numerical methods. We discuss and analyze the storage formats of SMVP which implemented on a GPU. The formats are used for hastening the solution of equations arising from numerical methods. The research in this paper can provide fast selects, which allow low storage space and make memory accesses efficiency, for numerical methods to accelerate SMVP.
Keywords :
graphics processing units; mathematics computing; matrix multiplication; numerical analysis; sparse matrices; storage allocation; vectors; GPU; SMVP storage formats; equation solution; memory access efficiency; numerical methods; sparse matrix vector product; storage space; Joints; Optimization; Graphics Processing Unit (GPU); Sparse Matrix Vector Product (SMVP); Storage Format;
Conference_Titel :
Computational Sciences and Optimization (CSO), 2014 Seventh International Joint Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-5371-4
DOI :
10.1109/CSO.2014.106
