Octagon architecture for low power and high performance NoC design

Reehal, Gursharan; Ghany, Mohamed A. Abd El; Ismail, Mohammed

doi:10.1109/naecon.2012.6531030

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A key element to address these challenges is a Network-on-Chip (NoC) topology that can manage the large volume of packets generated by Neural Networks. There are several topologies available, such as Tree topology [18], Butterfly Fat-tree [19], Octagon [20], Mesh topology, etc. The Mesh topology is the most widely used [21,22], due to its several advantages.…”

Section: Related Workmentioning

confidence: 99%

A Novel NoC-Based Neural Networks Design for Implementation of A Biosensor Solution

et al. 2023

View full text Add to dashboard Cite

Graphene-based nanosensors are used in many applications to monitor and survey physical or chemical phenomena. The use of Graphene improves the mechanical, electrochemical, optical, and magnetic properties of nanosensors due to its properties such as physical properties. But there are some characteristics and measurements that must be taken to manufacture such sensors. In this work, a Neural Network (NN) has been proposed that can predict the values of UV (ultraviolet) measurements, which are wavelength and absorption, based on XRD (X Ray Diffraction) measurements, namely diameter (in millimeters) and angle (theta in degrees). The proposed NN was developed on Network-on-Chip (NoC) to take advantage of the high level of parallelism and computing power provided by NoC. In addition, we used an adaptive XY routing algorithm due to its simplicity and allows exploiting multiple paths to route packets to their destination which reduces the number of lost packets due to the high injection rate without introducing any latency. Moreover, we proposed a mapping algorithm to extract maximum performance from the adaptive XY algorithm. The obtained results show the efficiency of the proposed architecture, as it allows packets to take different paths. Thus, the traffic is distributed across the network and significantly reduces packet loss. Moreover, the equal length of these paths allows avoidance of latency. HIGHLIGHTS Network-on-chip (NoC) is a powerful tool for implementing artificial neural networks, thanks to its high level of parallelism and computing power The Adaptive XY algorithm eliminates the need for a routing table and allows traffic to be distributed over the NoC The proposed mapping algorithm allows for better traffic management within the NoC, thereby enhancing performance in terms of reducing lost packets GRAPHICAL ABSTRACT

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel NoC-Based Neural Networks Design for Implementation of A Biosensor Solution

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The router can support several topologies [2], [3], [4], [24], [27], [28], [29], [30] such as Ring, Octagon, Spidergon, 2D mesh plus a family of customized topologies that can be derived from them. Each topology has some advantages and disadvantages, briefly reviewed hereafter.…”

Section: Topology and Routing Strategymentioning

confidence: 99%

Configurable network-on-chip router macrocells

Saponara

Fanucci

2016

Microprocessors and Microsystems

View full text Add to dashboard Cite

“…An important direction for the NoC design is the use of circular topologies. So, Spidergon topology is used in STNoC software developed by ST Microelectronix [ 2 , 3 ]; there are examples of the usage of the Octagon topology [ 4 ] and its 3D version Octagon for Ubiquitous Computing (OUC) [ 5 ], Midimew [ 6 ], etc. All of them are related to circulant topologies whose optimal configurations in the context of the application as a topological basis in the design of NoCs are still little studied.…”

Section: Introductionmentioning

confidence: 99%

Ring-Split: Deadlock-Free Routing Algorithm for Circulant Networks-on-Chip

Romanov

Myachin²,

Lezhnev

et al. 2023

Micromachines

View full text Add to dashboard Cite

This article considers the usage of circulant topologies as a promising deadlock-free topology for networks-on-chip (NoCs). A new high-level model, Newxim, for the exploration of NoCs with any topology is presented. Two methods for solving the problem of cyclic dependencies in circulant topologies, which limit their applications for NoCs due to the increased possibility of deadlocks, are proposed. The first method of dealing with deadlocks is universal and applicable to any topology; it is based on the idea of bypassing blocked sections of the network on an acyclic subnetwork. The second method—Ring-Split—takes into account the features of circulant topologies. The results of high-level modeling and comparison of the peak throughput of NoCs for circulant and mesh topologies using deadlock-free routing algorithms are presented. It was shown that a new approach for routing in circulants (compared to mesh topology) shows up to 59% better network throughput with a uniform distribution of network load.

show abstract

Octagon architecture for low power and high performance NoC design

Cited by 4 publications

References 12 publications

A Novel NoC-Based Neural Networks Design for Implementation of A Biosensor Solution

A Novel NoC-Based Neural Networks Design for Implementation of A Biosensor Solution

Configurable network-on-chip router macrocells

Ring-Split: Deadlock-Free Routing Algorithm for Circulant Networks-on-Chip

Contact Info

Product

Resources

About