Computer networks
Performance Analysis of k-ary n-cube Interconnection Networks
IEEE Transactions on Computers
A Router Architecture for Real-Time Communication in Multicomputer Networks
IEEE Transactions on Computers
On-chip communication architecture for OC-768 network processors
Proceedings of the 38th annual Design Automation Conference
Interconnection Networks: An Engineering Approach
Interconnection Networks: An Engineering Approach
Embedded DRAM: more than just a memory
IEEE Communications Magazine
System-level modeling of a network switch SoC
Proceedings of the 15th international symposium on System Synthesis
A fully-programmable memory management system optimizing queue handling at multi gigabit rates
Proceedings of the 40th annual Design Automation Conference
Guaranteeing the quality of services in networks on chip
Networks on chip
An Interconnect Channel Design Methodology for High Performance Integrated Circuits
Proceedings of the conference on Design, automation and test in Europe - Volume 2
NoC Synthesis Flow for Customized Domain Specific Multiprocessor Systems-on-Chip
IEEE Transactions on Parallel and Distributed Systems
Queue Management in Network Processors
Proceedings of the conference on Design, Automation and Test in Europe - Volume 3
Implementing DSP Algorithms with On-Chip Networks
NOCS '07 Proceedings of the First International Symposium on Networks-on-Chip
Hi-index | 0.00 |
Moving high bandwidth (10Gb/s+) network switches from the large scale, rack mount design space to the single chip design space requires a re-evaluation of the overall design requirements. In this paper, we explore the design space for these single chip devices by evaluating the ITRS. We find that unlike ten years ago when interconnect was scarce, the limiting factor in today's designs is on-chip memory. We then discuss an architectural technique for maximizing the effectiveness of queue memory in a single chip switch. Next, we show simulation results that indicate that a more than two order of magnitude improvement in dropped packet probability can be achieved by re-distributing memory and allowing sharing between the switch's ports. Finally, we evaluate the cost of the optimized architecture in terms of other on-chip resources.