Sciweavers

Share
CORR
2011
Springer

Fast Sparse Matrix-Vector Multiplication on GPUs: Implications for Graph Mining

9 years 9 months ago
Fast Sparse Matrix-Vector Multiplication on GPUs: Implications for Graph Mining
Scaling up the sparse matrix-vector multiplication kernel on modern Graphics Processing Units (GPU) has been at the heart of numerous studies in both academia and industry. In this article we present a novel non-parametric, selftunable, approach to data representation for computing this kernel, particularly targeting sparse matrices representing power-law graphs. Using real web graph data, we show how our representation scheme, coupled with a novel tiling algorithm, can yield significant benefits over the current state of the art GPU efforts on a number of core data mining algorithms such as PageRank, HITS and Random Walk with Restart.
Xintian Yang, Srinivasan Parthasarathy, Ponnuswamy
Added 13 May 2011
Updated 13 May 2011
Type Journal
Year 2011
Where CORR
Authors Xintian Yang, Srinivasan Parthasarathy, Ponnuswamy Sadayappan
Comments (0)
books