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

@article{atalyrek1999HypergraphPartitioningBasedDF,
  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.},
  year={1999},
  volume={10},
  pages={673-693}
}
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

Topics

Statistics

0204060'98'00'02'04'06'08'10'12'14'16'18
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.