An OpenCL Implementation of Sketch-based Network Traffic Change Detection on GPU

被引：1

作者：

Wellem, Theophilus ^{[1
]}

Lai, Yu-Kuen ^{[2
]}

机构：

[1] Satya Wacana Christian Univ, Dept Informat Syst, Salatiga, Indonesia

[2] Chung Yuan Christian Univ, Dept Elect Engn, Chungli, Taiwan

来源：

2012 FIFTH INTERNATIONAL SYMPOSIUM ON PARALLEL ARCHITECTURES, ALGORITHMS AND PROGRAMMING (PAAP) | 2012年

关键词：

Sketch; Change detection; OpenCL; GPU;

D O I：

10.1109/PAAP.2012.46

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

GPU and other SIMD stream architecture have been used for accelerating packet processing applications. This paper explores the design space on GPU for sketch-based network traffic change detection application by using OpenCL parallel programming framework. Due to the parallel nature of sketch data structure, the computations can be mapped to OpenCL execution model on GPU efficiently. The sketch data structure is mapped to buffer object in device's global memory, and work-items are executed on the sketch in parallel. Compared to the sequential CPU implementation, the experiment results on Radeon HD 5870 GPU show that the hash computation and ESTIMATE operation achieved about 15 times and 9 times speedup, respectively.

引用

页码：279 / 286

页数：8

共 20 条

[11]

Gao Yan., 2006, Proc. IEEE International Conference on Distributed Computing Systems (ICDCS'06), P39, DOI DOI 10.1109/ICDCS.2006.6

[12]

Gilbert A., 2001, 200143 CTR DISCR MAT

[13]

Lai Y.-K., 2010, P 1 AS NETFPGA DEV W

[14] Diagnosing network-wide traffic anomalies [J].

Lakhina, A ;

Crovella, M ;

Diot, C .

ACM SIGCOMM COMPUTER COMMUNICATION REVIEW, 2004, 34 (04) :219-230

[15]

Li Xin, 2006, P 6 ACM SIGCOMM C IN, P147, DOI DOI 10.1145/1177080.1177099

[16]

Munshi A., 2011, OPENCL SPECIFICATION

[17]

Schweller R., 2004, P ACM USENIX INT MEA

[18]

Tang J., 2009, GLOBECOM 2009-2009 IEEE Global Telecommunications Conference, P1, DOI DOI 10.1109/CAS-ICTD.2009.4960778

[19]

Thorup M., 2004, P 15 ANN ACM SIAM S, P615

[20]

Yang Liu, 2009, Performance Evaluation Review, V37, P81, DOI 10.1145/1639562.1639596

← 1 2 →