Designing Nonblocking Networks With a General Topology

Conventional theory for designing strictly nonblocking networks, such as crossbars or Clos networks, assumes that these networks have a centralized topology. Many new applications, however, require networks to have a distributed topology, like 2-D mesh or torus. In this paper, we present a new theor...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2022, Vol.10, p.8399-8408
Main Authors: Lin, Bey-Chi, Lea, Chin-Tau
Format: Article
Language:English
Subjects:
bufferless
Buffers
Costs
Finite element method
hose model
Integrated circuits
Linear programming
Network topologies
Network topology
networks-on-chip (NoCs)
Nonblocking networks
Optical switches
Performance evaluation
Power consumption
Routing
System on chip
System recovery
Topology
Toruses
Traffic control
Traffic models
Very large scale integration
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Conventional theory for designing strictly nonblocking networks, such as crossbars or Clos networks, assumes that these networks have a centralized topology. Many new applications, however, require networks to have a distributed topology, like 2-D mesh or torus. In this paper, we present a new theoretical framework for designing such nonblocking networks. The framework is based on a linear programming formulation originally proposed for solving the hose-model traffic routing problem. The main difference, however, is that the link bandwidths in our problem must be discrete. This makes the problem much more challenging. We show how to apply the developed theorems to tackle the problem of designing bufferless NoCs (networks-on-chip). The proposed bufferless NoCs are deadlock/livelock-free and consume significantly less power than their buffered counterparts. We also present a multi-slice technique to reduce node capacity variations. This can make the proposed NoC architecture more cost efficient in a VLSI (very large-scale integration) implementation. In addition, we offer a detailed delay/throughput performance evaluation of the proposed bufferless NoC in the paper.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2021.3139732