Sparse matrix multiplication algorithm based on MapReduce
Zheng Jian-hu · Zhongkai Nongye Gongcheng Xueyuan xuebao · 2013
To suitable for computing of big data sets and overcome the low efficiencies of existing algorithms for sparse matrix multiplication,a matrix multiplication processing scheme based on vector linear combination( VLC) was proposed,and then a parallel matrix multiplication algorithm was realized base on VLC scheme using MapReduce( MR). Two jobs of MR about this new algorithm were explained in detail. The experimental data showed that new algorithm needed less execution time and had higher efficiency. The result verified the correctness and effectiveness of the new algorithm.