Communication Optimal Parallel Multiplication of Sparse Random Matrices
作者：Grey Ballard；Aydin Buluc；James Demmel；Laura Grigori；Benjamin Lipshitz；Oded Schwartz；Sivan Toledo 作者单位：University of California at Berkeley；Lawrence Berkeley National Laboratory；INRIA Paris - Rocquencourt；Tel-Aviv University 加工时间：2013-11-22 信息来源：EECS 索取原文[17 页]
关键词：通信优化；并行算法；稀疏矩阵乘法；通信成本；处理器 摘 要：Parallel algorithms for sparse matrix-matrix multiplication typically spend most of their time on inter-processor communication rather than on computation, and hardware trends predict the relative cost of communication will only increase. Thus, sparse matrix multiplication algorithms must minimize communication costs in order to scale to large processor counts.
索取原文[17 页]
027-87841330