Evaluating GPUs for network packet signature matching

Smith, Randy; Goyal, Neelam; Ormont, Justin; Sankaralingam, Karthikeyan; Estan, Cristian

doi:10.1109/ispass.2009.4919649

Cited by 97 publications

(52 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Huang et al [4] do network intrusion detection on a GPU based on the multipattern search algorithm of Wu and Manber [15]. Smith et al [12] use deterministic finite automata and extended deterministic finite automata to do regular expression matching on a GPU for intrusion detection applications. Marziale et al [7] propose the use of GPUs and massive parallelism for in-place file carving.…”

Section: Introductionmentioning

confidence: 99%

Multipattern string matching on a GPU

Zha

Sahni

2011

2011 IEEE Symposium on Computers and Communications (ISCC)

View full text Add to dashboard Cite

Abstract-We develop GPU adaptations of the Aho-Corasick string matching algorithm for the two cases GPU-to-GPU and host-to-host. For the GPU-to-GPU case, we consider several refinements to a base GPU implementation and measure the performance gain from each refinement. For the host-to-host case, we analyze two strategies to communicate between the host and the GPU and show that one is optimal with respect to run time while the other requires less device memory. Experiments conducted on an NVIDIA Tesla GT200 GPU that has 240 cores running off of a Xeon 2.8GHz quad-core host CPU show that, for the GPU-to-GPU case, our Aho-Corasick GPU adaptation achieves a speedup between 8.5 and 9.5 relative to a singlethread CPU implementation and between 2.4 and 3.2 relative to the best multithreaded implementation. For the host-to-host case, the GPU AC code achieves a speedup of 3.1 relative to a singlethreaded CPU implementation. However, the GPU is unable to deliver any speedup relative to the best multithreaded code running on the quad-core host. In fact, the measured speedups for the latter case ranged between 0.74 and 0.83.

show abstract

Section: Introductionmentioning

confidence: 99%

Multipattern string matching on a GPU

Zha

Sahni

2011

2011 IEEE Symposium on Computers and Communications (ISCC)

View full text Add to dashboard Cite

show abstract

“…In [4], an architecture for packet signature matching is examined and implemented in a GPU. A comparison between Deterministic Finite Automata (DFA) and eXtended Finite Automata (XFA) based architectures is provided.…”

Section: Gpusmentioning

confidence: 99%

“…T h i ss t r u c t u r ea l l o w st of a s tc h e c k w h e t h e ra nI Pa d d r e s sb e l o n g st ot h e s e to fs u s p i c i o u sI P ss t o r e d i nt h ea r r a y ,j u s tb yc om p u t i n gt h ek 4 h a s h e sa n d c h e c k i n gt h ea s s o c i a t e dp o s i t i o n s .…”

Section: Fpgas/asicsmentioning

confidence: 99%

A Bloom Filter-Based Monitoring Station for a Lawful Interception Platform

Santos

Hernández

Urueña

et al. 2014

Communications in Computer and Information Science

View full text Add to dashboard Cite

Abstract. Lawful Interception (LI) is a fundamental tool in today's Police investigations.Therefore, it is important to make it as quickly and securely as possible as well as a reasonable cost per suspect. This makes traffic capture in aggregation links quite attractive, although this implies high wirespeeds which require the use of specific hardware-based architectures. This paper proposes a novel Bloom Filter-based monitoring station architecture for efficient packet capture in aggregation links. With said Bloom filter, we filter out most of the packets in the link and capture only those belonging to lawful interception wiretaps. Next, we present an FPGA-based implementation of said architecture and obtain the maximum capture rate achievable by injecting traffic through four parallel Gigabit Ethernet lines. Finally, we identify the limitations of our current design and suggest the possibility of further extending it to higher wirespeeds.

show abstract

“…Naghmouchi et al [18] investigated using GPUs for regular expression matching. Smith et al [19] evaluate GPUs as a platform for network packet inspection.…”

Section: Related Workmentioning

confidence: 99%

GPUs as an opportunity for offloading garbage collection

Maas

Reames

Morlan

et al. 2012

Proceedings of the 2012 International Symposium on Memory Management

View full text Add to dashboard Cite

GPUs have become part of most commodity systems. Nonetheless, they are often underutilized when not executing graphicsintensive or special-purpose numerical computations, which are rare in consumer workloads. Emerging architectures, such as integrated CPU/GPU combinations, may create an opportunity to utilize these otherwise unused cycles for offloading traditional systems tasks. Garbage collection appears to be a particularly promising candidate for offloading, due to the popularity of managed languages on consumer devices.We investigate the challenges for offloading garbage collection to a GPU, by examining the performance trade-offs for the mark phase of a mark & sweep garbage collector. We present a theoretical analysis and an algorithm that demonstrates the feasibility of this approach. We also discuss a number of algorithmic design trade-offs required to leverage the strengths and capabilities of the GPU hardware. Our algorithm has been integrated into the Jikes RVM and we present promising performance results.

show abstract

Evaluating GPUs for network packet signature matching

Abstract: Modern network devices employ deep packet inspection to

Cited by 97 publications

References 22 publications

Multipattern string matching on a GPU

Multipattern string matching on a GPU

A Bloom Filter-Based Monitoring Station for a Lawful Interception Platform

GPUs as an opportunity for offloading garbage collection

Contact Info

Product

Resources

About