Reprogrammable network packet processing on the field programmable port extender (FPX)
FPGA '01 Proceedings of the 2001 ACM/SIGDA ninth international symposium on Field programmable gate arrays
FPGA '02 Proceedings of the 2002 ACM/SIGDA tenth international symposium on Field-programmable gate arrays
A framework for reconfigurable computing: task scheduling and context management
IEEE Transactions on Very Large Scale Integration (VLSI) Systems - System Level Design
Computer Networks: The International Journal of Computer and Telecommunications Networking - Special issue on programmable networks
The MOLEN Polymorphic Processor
IEEE Transactions on Computers
A Reconfiguration Manager for Dynamically Reconfigurable Hardware
IEEE Design & Test
Framework for supporting multi-service edge packet processing on network processors
Proceedings of the 2005 ACM symposium on Architecture for networking and communications systems
CommBench-a telecommunications benchmark for network processors
ISPASS '00 Proceedings of the 2000 IEEE International Symposium on Performance Analysis of Systems and Software
FCCM '06 Proceedings of the 14th Annual IEEE Symposium on Field-Programmable Custom Computing Machines
Characterization of power-aware reconfiguration in FPGA-based networking hardware
NETWORKING'11 Proceedings of the IFIP TC 6th international conference on Networking
Hi-index | 0.00 |
A main feature of current FPGAs is that they can be dynamically reconfigured to meet the network traffic requirements. In this paper we present a case study for a multi-service edge router in which the number of processors and co-processors is dynamically reconfigured to meet the network traffic workload. The system targets the Xilinx Virtex4 FPGA platform and uses the MicroBlaze soft processors for header processing and hardware acceleration units for payload processing. Furthermore, two schemes are compared for the reconfiguration of the system. The first one has fast response time but is prone to network burst traffic while the second one has slower response time but is more robust to burst traffic. The performance evaluation shows that the reconfigurable platform can achieve up to 1.5x speedup compared to a static system.