Length-bounded hybrid CPU/GPU pattern matching algorithm for deep packet inspection

Yi Shan Lin; Chun Liang Lee; Yaw Chung Chen

doi:10.1145/3033288.3033346

Length-bounded hybrid CPU/GPU pattern matching algorithm for deep packet inspection

Yi Shan Lin, Chun Liang Lee, Yaw Chung Chen

Department of Computer Science and Information Engineering

National Yang Ming Chiao Tung University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Since frequent communication between the applications took place in high speed networks, deep packet inspection (DPI) plays an important role to the network application awareness. The signature-based network intrusion detection system (NIDS) contains the DPI technique that examines the incoming packet payloads by employing the pattern matching algorithm, which dominates the overall inspection performance. Existing studies focused on implementing efficient pattern matching algorithms by parallel programming on software platform because of the advantages of lower cost and higher scalability. Either the central processing unit (CPU) or the graphic processing unit (GPU) was involved. Our studies focused on designing a pattern matching algorithm based on the cooperation between both CPU and GPU. In this paper, we present an enhanced design for our previous work and introduce this novel method, a length-bounded hybrid CPU/GPU pattern matching algorithm (LHPMA). In the preliminary experiment, the performance and comparison with the previous work are displayed, and the results show that the LHPMA achieves higher throughput than other tested algorithms.

Original language	English
Title of host publication	Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016
Publisher	Association for Computing Machinery
Pages	63-67
Number of pages	5
ISBN (Electronic)	9781450347938
DOIs	https://doi.org/10.1145/3033288.3033346
State	Published - 17 12 2016
Event	5th International Conference on Network, Communication and Computing, ICNCC 2016 - Kyoto, Japan Duration: 17 12 2016 → 21 12 2016

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	5th International Conference on Network, Communication and Computing, ICNCC 2016
Country/Territory	Japan
City	Kyoto
Period	17/12/16 → 21/12/16

Bibliographical note

Publisher Copyright:
© 2016 ACM.

Keywords

Compute Unified Device Architecture (CUDA)
Deep Packet Inspection (DPI)
GeneralPurpose Graphics Processing Unit (GPGPU)
Intrusion Detection System (IDS)
Network Security
Pattern Matching Algorithm

Access to Document

10.1145/3033288.3033346

Cite this

Lin, Y. S., Lee, C. L., & Chen, Y. C. (2016). Length-bounded hybrid CPU/GPU pattern matching algorithm for deep packet inspection. In Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016 (pp. 63-67). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3033288.3033346

@inproceedings{3e83081156174f2d8a1bd98e9e767e22,

title = "Length-bounded hybrid CPU/GPU pattern matching algorithm for deep packet inspection",

abstract = "Since frequent communication between the applications took place in high speed networks, deep packet inspection (DPI) plays an important role to the network application awareness. The signature-based network intrusion detection system (NIDS) contains the DPI technique that examines the incoming packet payloads by employing the pattern matching algorithm, which dominates the overall inspection performance. Existing studies focused on implementing efficient pattern matching algorithms by parallel programming on software platform because of the advantages of lower cost and higher scalability. Either the central processing unit (CPU) or the graphic processing unit (GPU) was involved. Our studies focused on designing a pattern matching algorithm based on the cooperation between both CPU and GPU. In this paper, we present an enhanced design for our previous work and introduce this novel method, a length-bounded hybrid CPU/GPU pattern matching algorithm (LHPMA). In the preliminary experiment, the performance and comparison with the previous work are displayed, and the results show that the LHPMA achieves higher throughput than other tested algorithms.",

keywords = "Compute Unified Device Architecture (CUDA), Deep Packet Inspection (DPI), GeneralPurpose Graphics Processing Unit (GPGPU), Intrusion Detection System (IDS), Network Security, Pattern Matching Algorithm",

author = "Lin, {Yi Shan} and Lee, {Chun Liang} and Chen, {Yaw Chung}",

note = "Publisher Copyright: {\textcopyright} 2016 ACM.; 5th International Conference on Network, Communication and Computing, ICNCC 2016 ; Conference date: 17-12-2016 Through 21-12-2016",

year = "2016",

month = dec,

day = "17",

doi = "10.1145/3033288.3033346",

language = "英语",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "63--67",

booktitle = "Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016",

}

Lin, YS, Lee, CL & Chen, YC 2016, Length-bounded hybrid CPU/GPU pattern matching algorithm for deep packet inspection. in Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 63-67, 5th International Conference on Network, Communication and Computing, ICNCC 2016, Kyoto, Japan, 17/12/16. https://doi.org/10.1145/3033288.3033346

Length-bounded hybrid CPU/GPU pattern matching algorithm for deep packet inspection. / Lin, Yi Shan; Lee, Chun Liang; Chen, Yaw Chung.
Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016. Association for Computing Machinery, 2016. p. 63-67 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Length-bounded hybrid CPU/GPU pattern matching algorithm for deep packet inspection

AU - Lin, Yi Shan

AU - Lee, Chun Liang

AU - Chen, Yaw Chung

PY - 2016/12/17

Y1 - 2016/12/17

N2 - Since frequent communication between the applications took place in high speed networks, deep packet inspection (DPI) plays an important role to the network application awareness. The signature-based network intrusion detection system (NIDS) contains the DPI technique that examines the incoming packet payloads by employing the pattern matching algorithm, which dominates the overall inspection performance. Existing studies focused on implementing efficient pattern matching algorithms by parallel programming on software platform because of the advantages of lower cost and higher scalability. Either the central processing unit (CPU) or the graphic processing unit (GPU) was involved. Our studies focused on designing a pattern matching algorithm based on the cooperation between both CPU and GPU. In this paper, we present an enhanced design for our previous work and introduce this novel method, a length-bounded hybrid CPU/GPU pattern matching algorithm (LHPMA). In the preliminary experiment, the performance and comparison with the previous work are displayed, and the results show that the LHPMA achieves higher throughput than other tested algorithms.

AB - Since frequent communication between the applications took place in high speed networks, deep packet inspection (DPI) plays an important role to the network application awareness. The signature-based network intrusion detection system (NIDS) contains the DPI technique that examines the incoming packet payloads by employing the pattern matching algorithm, which dominates the overall inspection performance. Existing studies focused on implementing efficient pattern matching algorithms by parallel programming on software platform because of the advantages of lower cost and higher scalability. Either the central processing unit (CPU) or the graphic processing unit (GPU) was involved. Our studies focused on designing a pattern matching algorithm based on the cooperation between both CPU and GPU. In this paper, we present an enhanced design for our previous work and introduce this novel method, a length-bounded hybrid CPU/GPU pattern matching algorithm (LHPMA). In the preliminary experiment, the performance and comparison with the previous work are displayed, and the results show that the LHPMA achieves higher throughput than other tested algorithms.

KW - Compute Unified Device Architecture (CUDA)

KW - Deep Packet Inspection (DPI)

KW - GeneralPurpose Graphics Processing Unit (GPGPU)

KW - Intrusion Detection System (IDS)

KW - Network Security

KW - Pattern Matching Algorithm

UR - http://www.scopus.com/inward/record.url?scp=85018323404&partnerID=8YFLogxK

U2 - 10.1145/3033288.3033346

DO - 10.1145/3033288.3033346

M3 - 会议稿件

AN - SCOPUS:85018323404

T3 - ACM International Conference Proceeding Series

SP - 63

EP - 67

BT - Proceedings of 2016 5th International Conference on Network, Communication and Computing, ICNCC 2016

PB - Association for Computing Machinery

T2 - 5th International Conference on Network, Communication and Computing, ICNCC 2016

Y2 - 17 December 2016 through 21 December 2016

ER -

Length-bounded hybrid CPU/GPU pattern matching algorithm for deep packet inspection

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this