Performance Analysis of Multicore and Multinodal Implementation of SpMV Operation

• Autorzy: Beata Bylina , Jarosław Bylina , Przemysław Stpiczyński , Dominik Szałkowski
• Języki publikacji: EN

Abstrakty

EN

In this paper the authors present new algorithms for performing sparse matrix-dense vector multiplication (known as SpMV operation). They show parallel version of algorithm, which can be efficiently implemented on the contemporary multicore architectures. Next, they 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 known MKL library.(original abstract)

Słowa kluczowe

PL

Macierze; Algorytmy; Klastry

EN

Matrix; Algorithms; Business cluster

• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2014
• Tom: 2
• Strony: 569-576

Twórcy

autor

Beata Bylina

• Maria Curie-Skłodowska University in Lublin, Poland

autor

Jarosław Bylina

• Maria Curie-Skłodowska University in Lublin, Poland

autor

Przemysław Stpiczyński

• Maria Curie-Skłodowska University in Lublin, Poland

autor

Dominik Szałkowski

• Maria Curie-Skłodowska University in Lublin, Poland

Bibliografia

• Basic Linear Algebra Communication Subprograms, http://www.netlib.org/blacs/
• Bylina B., Bylina J., Karwacki M.: Computational Aspects of GPU-accelerated Sparse Matrix-Vector Multiplication for Solving MarkovModels; Theoretical and Applied Informatics, 23 (2011), no. 2, ISSN 1896-5334, pp. 127-145.
• Davis T. A., Hu Y., The University of Florida Sparse Matrix Collection, ACM Transactions on Mathematical Software, Vol 38, 2011, pp.1-25, http://www.cise.ufl.edu/research/sparse/matrices.
• Golub G. H., van Van Loan C. F.: Matrix Computations, Johns Hopkins Studies in Mathematical Sciences, 3rd Edition, 2013.
• Intel Math Kernel Library, http://software.intel.com/en-us/articles/intel-mkl/
• MATLAB. The Language of Technical Computing, http://www.mathworks.com/products/matlab/
• Matrix Market Exchange Formats, http://math.nist.gov/MatrixMarket/formats.html
• Saad Y., Iterative Methods for Sparse Linear Systems: Second Edition, SIAM, 2003.
• Saad Y., SPARSKIT: A basic tool kit for sparse computations; Version 2, June 1994.
• The OpenMP API specification for parallel programming, http://openmp.org/
• Williams S., Oliker L., Vuduc R., Shalf J., Yelick K., Demmel J., Optimization of sparse matrix-vector multiplication on emerging multicore platforms, Parallel Computing 35 (2009), pp. 178-194.
• Yang, B., Gu, S., Gu, T.-X., Zheng, C. and Liu, X.-P. (2014) Parallel Multicore CSB Format and Its Sparse Matrix Vector Multiplication. Advances in Linear Algebra & Matrix Theory, 4, 1-8.