DocumentCode :
130386
Title :
Performance analysis of multicore and multinodal implementation of SpMV operation
Author :
Bylina, Beata ; Bylina, Jaroslaw ; Stpiczynski, Przemyslaw ; Szalkowski, Dominik
Author_Institution :
Inst. of Math., Maria Curie-Sklodowska Univ., Lublin, Poland
fYear :
2014
fDate :
7-10 Sept. 2014
Firstpage :
569
Lastpage :
576
Abstract :
In this paper we present two algorithms for performing sparse matrix-dense vector multiplication (known as SpMV operation). We show parallel (multicore) version of algorithm, which can be efficiently implemented on the contemporary multicore architectures. Next, we show distributed (so-called multinodal) version targeted at high performance clusters. Both versions are thoroughly tested using different architectures, compiler tools and sparse matrices of different sizes. Considered matrices comes from The University of Florida Sparse Matrix Collection. The performance of the algorithms is compared to the performance of SpMV routine from widely used Intel Math Kernel Library.
Keywords :
mathematics computing; matrix multiplication; multiprocessing systems; vectors; Intel math kernel library; SpMV operation; high performance clusters; multicore implementation; multinodal implementation; sparse matrix-dense vector multiplication; Algorithm design and analysis; Arrays; Clustering algorithms; Libraries; Multicore processing; Sparse matrices; Vectors; SpMV operation; computer cluster; multicore platforms; parallel matrix-vector multiplication; sparse matrix-dense vector multiplication;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Science and Information Systems (FedCSIS), 2014 Federated Conference on
Conference_Location :
Warsaw
Type :
conf
DOI :
10.15439/2014F313
Filename :
6933066
Link To Document :
بازگشت