Hypergraph-Partitioning-Based Decomposition for Parallel Sparse-Matrix Vector Multiplication

  title={Hypergraph-Partitioning-Based Decomposition for Parallel Sparse-Matrix Vector Multiplication},
  author={{\"U}mit V. Çataly{\"u}rek and Cevdet Aykanat},
  journal={IEEE Trans. Parallel Distrib. Syst.},
In this work, we show that the standard graph-partitioning based decomposition of sparse matrices does not reflect the actual communication volume requirement for parallel matrix-vector multiplication. We propose two computational hypergraph models which avoid this crucial deficiency of the graph model. The proposed models reduce the decomposition problem to the well-known hypergraph partitioning problem. The recently proposed successful multilevel framework is exploited to develop a multilevel… CONTINUE READING
Highly Influential
This paper has highly influenced 67 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 551 citations. REVIEW CITATIONS

14 Figures & Tables



Citations per Year

551 Citations

Semantic Scholar estimates that this publication has 551 citations based on the available data.

See our FAQ for additional information.