CUgrep: A GPU-based High Performance Multi-string Matching System
String matching is one of the oldest and most pervasive problems in computer science. Nowadays applications related to string matching can be found everywhere. Meanwhile, the heterogeneous processing of CPU+GPU has become the popular parallel platform in solving high performance computing applications. This paper proposes a GPU-based multi-string matching algorithm, CUgrep, and uses this algorithm to implement the webpage matching system, which is almost 40 times peak performance to the original BNDM algorithm used in Nrgrep1.
GPU CUDA parallel multi-string matching webpage matching system BNDM
Jiangfeng Peng Hu Chen
School of Computer Science and Engineering South China University of Technology Guangzhou, China School of Software Engineering South China University of Technology Guangzhou, China
国际会议
武汉
英文
77-81
2010-05-21（万方平台首次上网日期，不代表论文的发表时间）