Implementing an architecture for efficient network traffic processing on modern graphics hardware

Lazaros Koromilas
Computer Science Department, School of Sciences and Engineering, University of Crete
University of Crete, 2012

   title={Implementing an architecture for efficient network traffic processing on modern graphics hardware},

   author={Koromilas, Lazaros},



Download Download (PDF)   View View   Source Source   



Network traffic processing is necessary in order to develop active components in the infrastructure of the network, such as routers, or passive applications, such as network intrusion detection systems. However, in today’s high-speed network links this has become a very challenging task in terms of computational resources. Custom hardware appliances that can handle high packet rates are rather expensive and offer limited programmability. This work presents the design and implementation of a high-performance software packet processing system using high-speed network interfaces, multi-core processors and many-core graphics hardware. The massive parallelism of modern graphics chips is exploited for efficient packet processing, which effectively frees cycles on the main processor. The development of the system focuses on high-throughput data movement techniques, memory access optimizations, domain specific data structures and the configuration of a large set of parameters that enables high processing rates. The evaluation of the system has shown that it can passively process real-world traffic at 18 Gbps, with latency in the order of few milliseconds. In active mode, where packets are forwarded, the system can achieve a 13.5 Gbps rate. There is an up to 15 times increase in throughput when compared to traditional approaches.
VN:F [1.9.22_1171]
Rating: 4.3/5 (4 votes cast)
Implementing an architecture for efficient network traffic processing on modern graphics hardware, 4.3 out of 5 based on 4 ratings

* * *

* * *

Follow us on Twitter

HGPU group

1666 peoples are following HGPU @twitter

Like us on Facebook

HGPU group

338 people like HGPU on Facebook

* * *

Free GPU computing nodes at hgpu.org

Registered users can now run their OpenCL application at hgpu.org. We provide 1 minute of computer time per each run on two nodes with two AMD and one nVidia graphics processing units, correspondingly. There are no restrictions on the number of starts.

The platforms are

Node 1
  • GPU device 0: nVidia GeForce GTX 560 Ti 2GB, 822MHz
  • GPU device 1: AMD/ATI Radeon HD 6970 2GB, 880MHz
  • CPU: AMD Phenom II X6 @ 2.8GHz 1055T
  • RAM: 12GB
  • OS: OpenSUSE 13.1
  • SDK: nVidia CUDA Toolkit 6.5.14, AMD APP SDK 3.0
Node 2
  • GPU device 0: AMD/ATI Radeon HD 7970 3GB, 1000MHz
  • GPU device 1: AMD/ATI Radeon HD 5870 2GB, 850MHz
  • CPU: Intel Core i7-2600 @ 3.4GHz
  • RAM: 16GB
  • OS: OpenSUSE 12.3
  • SDK: AMD APP SDK 3.0

Completed OpenCL project should be uploaded via User dashboard (see instructions and example there), compilation and execution terminal output logs will be provided to the user.

The information send to hgpu.org will be treated according to our Privacy Policy

HGPU group © 2010-2015 hgpu.org

All rights belong to the respective authors

Contact us: