• JSTS:Journal of Semiconductor Technology and Science
• /
• v.14 no.6
• /
• pp.760-767
• /
• 2014

This paper describes a high-radix crossbar switch design with low latency and power dissipation for Network-on-Chip (NoC) applications. The reduction in latency and power is achieved by employing a folded-clos topology, implementing the switch organized as three stages of low-radix switches connected in cascade. In addition, to facilitate the uniform placement of wires among the sub-switch stages, this paper proposes a Mux-Matrix-Mux structure, which implements the first and third switch stages as multiplexer-based crossbars and the second stage as a matrix-type crossbar. The proposed 256-radix, 8-bit crossbar switch designed in a 65nm CMOS has the simulated power dissipation of 1.92-W and worst-case propagation delay of 0.991-ns while operating at 1.2-V supply and 500-MHz frequency. Compared with the state-of-the-art designs in literature, the proposed crossbar switch achieves the best energy-delay-area efficiency of $0.73-fJ/cycle{\cdot}ns{\cdot}{\lambda}^2$.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.123-126
• /
• 2005

STP gets to have different network performance, depending on the configuration method of topology. Accordingly, for efficient network environment, it is necessary to make the optimum topology. This paper proposed a way to make the optimum topology for construction of efficient network among switches on ethernet: the optimum topology was made by calculating the time the switches in the same domain receive the frame transmitted from the root switch, using a mathematical model. And it analyzed the performance of the topology depending on the location of the root switch. As a result of analyzing the performance, this study came to the conclusion that it would be effective to locate the root switch in the center of the square network.

• ETRI Journal
• /
• v.43 no.5
• /
• pp.799-811
• /
• 2021

This paper considers a challenging problem: to simultaneously optimize the cost and the quality of service in opaque wavelength division multiplexing (WDM) networks. An optimization problem is proposed that takes the information including network topology, traffic between end nodes, and the target level of congestion at each link/ node in WDM networks. The outputs of this problem include routing, link channel capacities, and the optimum number of switch ports locally added/dropped at all switch nodes. The total network cost is reduced to maintain a minimum congestion level on all links, which provides an efficient trade-off solution for the network design problem. The optimal information is utilized for dynamic traffic in WDM networks, which is shown to achieve the desired performance with the guaranteed quality of service in different networks. It was found that for an average link blocking probability equal to 0.015, the proposed model achieves a net channel gain in terms of wavelength channels (𝛾_w) equal to 35.72 %, 39.09 %, and 36.93 % compared to shortest path first routing and 𝛾_w equal to 29.41 %, 37.35 %, and 27.47 % compared to alternate routing in three different networks.

• Journal of Korean Institute of Industrial Engineers
• /
• v.22 no.2
• /
• pp.277-302
• /
• 1996

The overall performance of BISDN depends significantly on the interconnection network or the switch fabric. Hence, it is extremely important to evaluate the performance of the network or the fabric. The well developed performance models also provide insight into the factors that determine design tradeoffs as well as quantitative estimates of their importance. The objective of this paper is to investigate and critically compare all the developed performance analysis models of FPS according to internal switch fabric structure, traffic assumptions, performance measures, methodologies, etc. FPSs are described according to their internal fabric structure. Brief history of FPS performance analysis is mentioned and performance analysis modeling is discussed.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.60-65
• /
• 2017

Network virtualization enables us to make efficient use of resources in a physical network by embedding multiple virtual networks in the physical network. In this paper, we develop a prototype of a virtual network embedding system. Our system consists of OpenStack, which is an open source cloud service platform, and shell scripts. Because OpenStack does not provide a quality of service control function, we realize bandwidth reservation for virtual links by making use of the ingress policing function of Open vSwitch, which is a virtual switch used in OpenStack. The shell scripts in our system automatically construct the required virtual network on the physical network using the OpenStack command-line interface, and they reserve bandwidth for virtual links using the Open vSwitch command. Experimental evaluation confirms that our system constructs the requested virtual network and appropriately allocates node and link resources to it.

• Proceedings of the Korea Institute of Applied Superconductivity and Cryogenics Conference
• /
• 2003.10a
• /
• pp.146-149
• /
• 2003

In this Work, we have studied about an RSFQ 2$\times$2 crossbar switch. The circuit was designed, simulated, and laid out for mask fabrication The switch cell was composed of a splitter a confluence buffer, and a switch core. An RSFQ 2$\times$2 crossbar switch was composed of 4 switch cells, a switch control input to select the cross and bar, data input, and data outputs. When a pulse was input to the switch control input to select the cross or bar the route of the input data was determined, and the data was output at the proper output port. We simulated and optimized the switch-element circuit and 2$\times$2 crossbar switch, by using Xic and Julia. We also performed the mask layout of the circuit by using Xic and Lmeter.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.1
• /
• pp.1-8
• /
• 1997

A wide class of networking application services, such as video teleconferencing, VOD, LAN bridging, and distributed data processing require multipoint communications. The essential component inteh network to achieve this is a multicast packet switch which is capable of packet replication and switching. In this paper, we propose an efficient mukticast addressing scheme using the smallest number of routing bits which is deterministic lower bound. The new scheme performs all point-to-multipoint connection in radix-2 tree ATM switch like banyan network. Also, we provide a simple radix-2 switch block diagram for achieving our algorithm. And we investigate several addressing schemes for implementing multicasting in radix-r tree ATM switch and evaluate several performance factors, such as complexity of the additional header bits, requirement of the internal speedup and complexity of the major hardware.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.5
• /
• pp.1037-1050
• /
• 2000

A goal of a BISDN network is to provided integrated transport for a wide range of applications such as teleconferencing, Video On Demand etc. There require multipoint communications in addition to conventional point-to-point connections. Therefore multicast capabilities are very essential in multimedia communications. In this paper, we propose a new multicast cell scheduling method on the Parallel Multicast Packet Switch with Ring network: PMRN which are based on separated HOL. In this method, we place two different HOLs, one for unicast cells and the other for multicast cells. Then using non-FIFO scheduling, we can schedule both unicast cells and multicast cells which are available at the time in the input buffer. The simulation result shows that this method reduces the delay in the input buffer and increases the efficiency of both point-to-point network and ring network and finally enhances the bandwidth of the overall packet switch. A goal of a BISDN network is to provided integrated transport for a wide range of applications such as teleconferencing, Video On Demand etc. There require multipoint communications in addition to conventional point-to-point connections. Therefore multicast capabilities are very essential in multimedia communications. In this paper, we propose a new multicast cell scheduling method on the Parallel Multicast Packet Switch with Ring network: PMRN which are based on separated HOL. In this method, we place two different HOLs, one for unicast cells and the other for multicast cells. Then using non-FIFO scheduling, we can schedule both unicast cells and multicast cells which are available at the time in the input buffer. The simulation result shows that this method reduces the delay in the input buffer and increases the efficiency of both point-to-point network and ring network and finally enhances the bandwidth of the overall packet switch.

• Journal of KIISE:Information Networking
• /
• v.30 no.4
• /
• pp.520-534
• /
• 2003

In this paper, a performance evaluation model of the Fat-tree Network with the multiple-buffered crossbar switches is proposed and examined. Buffered switch technique is well known to solve the data collision problem of the switch network. The proposed evaluation model is developed by investigating the transfer patterns of data packets in a switch with output-buffers. Two important parameters of the network performance, throughput and delay, are then evaluated. The proposed model takes simple and primitive switch networks, i.e., no flow control and drop packet, to demonstrate analysis procedures clearly. It, however, can not only be applied to any other complicate modern switch networks that have intelligent flow control but also estimate the performance of any size networks with multiple-buffered switches. To validate the proposed analysis model, the simulation is carried out on the various sizes of Fat-tree networks that uses the multiple buffered crossbar switches. Less than 2% differences between analysis and simulation results are observed.

• The KIPS Transactions:PartC
• /
• v.12C no.3 s.99
• /
• pp.449-456
• /
• 2005

Optical burst switching (OBS) overcomes the inefficient resource usage of optical circuit switching and minimizes the optical buffering requirement of optical packet switching. General switch management protocol (GSMP) is an open interface between a label switch and a controller, and it provides connection, configuration, performance, event management and synchronization. GSMP open interface in the OBS network allows the implementation of OBS switch to be simple by separating the data forward plane from the control plane. We defined managed objects to support connection, configuration, performance, and fault management for the management of OBS network in the GSMP open interface. We proposed the network management model, in which the above managed objects are distributed in a controller and an OBS switch according to network management functions. We verified the possibility of connection management using distributed network management model in the GSMP open interface of OBS network by implementing GSMP and network management functions with managed objects of OBS.