A High-Throughput Distributed Shared-Buffer NoC Router

Authors:
Vassos Soteriou;Rohit Sunkam Ramanujam;Bill Lin;Li-Shiuan Peh
Affiliations:
Cyprus University of Technology, Cyprus;University of California San Diego, La Jolla;University of California San Diego, San Diego;Princeton University, Princeton
Venue:
IEEE Computer Architecture Letters
Year:
2009

Citing 0
Cited 6

Design of a High-Throughput Distributed Shared-Buffer NoC Router

NOCS '10 Proceedings of the 2010 Fourth ACM/IEEE International Symposium on Networks-on-Chip
Design of High-Radix Clos Network-on-Chip

NOCS '10 Proceedings of the 2010 Fourth ACM/IEEE International Symposium on Networks-on-Chip
A deadlock-free routing algorithm for dynamically reconfigurable Networks-on-Chip

Microprocessors & Microsystems
Design of a performance enhanced and power reduced dual-crossbar Network-on-Chip (NoC) architecture

Microprocessors & Microsystems
Analytical modeling for multi-transaction bus on distributed systems

ICA3PP'12 Proceedings of the 12th international conference on Algorithms and Architectures for Parallel Processing - Volume Part II
Gana: A novel low-cost conflict-free NoC architecture

ACM Transactions on Embedded Computing Systems (TECS) - Special Section on Wireless Health Systems, On-Chip and Off-Chip Network Architectures

Quantified Score

Hi-index	0.00

Visualization

Abstract

Microarchitectural configurations of buffers in routers have a significant impact on the overall performance of an on-chip network (NoC). This buffering can be at the inputs or the outputs of a router, corresponding to an input-buffered router (IBR) or an output-buffered router (OBR). OBRs are attractive because they have higher throughput and lower queuing delays under high loads than IBRs. However, a direct implementation of OBRs requires a router speedup equal to the number of ports, making such a design prohibitive given the aggressive clocking and power budgets of most NoC applications. In this letter, we propose a new router design that aims to emulate an OBR practically based on a distributed shared-buffer (DSB) router architecture. We introduce innovations to address the unique constraints of NoCs, including efficient pipelining and novel flow control. Our DSB design can achieve significantly higher bandwidth at saturation, with an improvement of up to 20% when compared to a state-of-the-art pipelined IBR with the same amount of buffering, and our proposed microarchitecture can achieve up to 94% of the ideal saturation throughput.