Abstract | ||
---|---|---|
We present PacketShader, a high-performance software router frame- work for general packet processing with Graphics Processing Unit (GPU) acceleration. PacketShader exploits the massively-parallel processing power of GPU to address the CPU bottleneck in current software routers. Combined with our high-performance packet I/O engine, PacketShader outperforms existing software routers by more than a factor of four, forwarding 64B IPv4 packets at 39 Gbps on a single commodity PC. We have implemented IPv4 and IPv6 for- warding, OpenFlow switching, and IPsec tunneling to demonstrate the flexibility and performance advantage of PacketShader. The eval- uation results show that GPU brings significantly higher throughput over the CPU-only implementation, confirming the effectiveness of GPU for computation and memory-intensive operations in packet processing. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1145/1851275.1851207 | ACM SIGCOMM Conference |
Keywords | Field | DocType |
massively-parallel processing power,general packet processing,cuda,current software routers,high-performance packet,ipv4 packet,gpu-accelerated software router,packet processing,ipv6 forwarding,high-performance software router framework,software routers,software router,cpu bottleneck,gpu,massively parallel processing | Computer science,CUDA,Network packet,Parallel computing,OpenFlow,Packet processing,Software,General-purpose computing on graphics processing units,Throughput,Graphics processing unit | Conference |
Volume | Issue | ISSN |
40 | 4 | 0146-4833 |
Citations | PageRank | References |
298 | 17.45 | 26 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sang-Jin Han | 1 | 655 | 35.59 |
Keon Jang | 2 | 768 | 37.56 |
KyoungSoo Park | 3 | 1198 | 73.47 |
Sue B. Moon | 4 | 6806 | 485.52 |