ATM SWITCH: As an Application of VLSI in Telecommunication System

Size: px
Start display at page:

Download "ATM SWITCH: As an Application of VLSI in Telecommunication System"

Transcription

1 Volume-6, Issue-6, November-December 2016 International Journal of Engineering and Management Research Page Number: ATM SWITCH: As an Application of VLSI in Telecommunication System Shubh Prakash 1, Amita Verma 2 1 M.Tech Student, Electronics and Communication Engineering Department, Maharishi University of Information Technology, Lucknow, Uttar Pradesh, INDIA 2 Assistant Professor, Electronics and Communication Engineering Department, Maharishi University of Information Technology, Lucknow, Uttar Pradesh, INDIA ABSTRACT Thus the paper proposes a new asynchronous transfer mode (ATM) switch architecture also known as barrel switch. It is made from n/2*n identical element switches which are kept around a cylindrical pattern and connected with each other. The switch has following smart features The switch architecture suites for high speed (<2.4 Gbps) cell switching. It is non blocking and multistage self routing in nature. The connections copied can be realized by the switch. For switch implementation, building block method is applicable thus full scalability is achieved. The cell loss rate and delay characteristic has been discussed by use of computer simulation result. Under random traffic, simulator result proves that 64*64 barrel switch has adequate cell loss rate and mean delay characteristics to an actual ATM switching system. Key words: ATM; cell; ATM switch; copy con I. INTRODUCTION An electronic switch is essentially just a switch that uses an electrical current, to turn on, usually turning off when the current is turned off. Some applications of switches can be quite inconvenient for someone to go and press a button to turn on or off, such as for the starter motor in a car, or the "turn off nuclear meltdown" button inside a nuclear reactor, or in an electronics project, a small low power device such as a receiver, must somehow power a large energy guzzling component, like the motor in a garage door opener. And others just want to control their houses with their computer's, which could never possible supply the 240v/120v mains needed to run some appliances. To construct future B-ISDN systems, considerable research has been conducted. Asynchronous transfer mode (ATM) switches are one of the basic technologies of B- ISDN and much of the research has focused on constructing an ATM switch. ATM switches for 150 Mbps/600 Mbps cell switching have already been implemented [1, 2], and the interest of many researchers has turned to higher-speed ATM switches that would lead to the development of a more flexible B-ISDN. In this paper, an ATM switch architecture for highspeed switching called "barrel switch" is proposed and its characteristic is discussed. In section 2, the characteristics of this switch architecture to be satisfied for high-speed ATM switches is described. The barrel switch itself is proposed in section 3. Topology, two self-routing algorithms, the non blocking condition, and a buildingblock method also are discussed in this section. In section 4, the cell loss rate and the delay characteristics of this switch are discussed using computer simulation results. II. CHARACTERISTICS OF HIGH- SPEED ATM SWITCHES An architecture for a high-speed ATM switch must satisfy the following two criteria to alleviate bottlenecks in high-speed ATM switch implementation. Cell buffer criterion. Alleviating the speed limitations of RAM devices A cell buffer, which holds some cells for a while to avoid cell losses due to cell conflicts at an output port, is one of the most important components of an ATM switch. 87 Copyright Vandana Publications. All Rights Reserved.

2 Such cell buffers generally are implemented using RAM devices, and these devices have access speed limitations. These speed limitations impose a limit on the throughput of cell buffers. Therefore, it is desirable that an ATM switch architecture for high-speed switching has the characteristic that the required throughput of RAMs, i.e., the required throughput of cell buffers, is as slow as possible. Cell switching algorithm criterion. Alleviating clock skew problems in ATM switches There are some cell switching algorithms for ATM switches which require that cells are input through all input ports at the same time and that all element switches operate synchronously (e.g., the Batcher sorting network [3]). In this type of algorithm, it is assumed that system clock for the ATM switch can be distributed to cell buffers located on all the input ports and to every element switch with no clock skew. Unfortunately, clock distribution with zero skew is impractical and clock skew limits the maximum bit rate for this type of ATM switch. By contrast, in other cell switching algorithms, the element switches do not need to operate synchronously (e.g., the buffered Banyan network [4]). Cell buffers on the element switches can be used as elastic stores in this type of architecture, and the clock skew problem is avoided. The latter type of algorithm is more suitable than the former for high-speed cell switching. An ATM switch architecture which satisfies the fore mentioned criteria is considered suitable for high-speed switching because such architecture can operate at higher speed than that architecture which does not satisfy such criteria. The buffered Banyan network is one architecture which satisfies the two fore mentioned criteria. Thus, the author has been discussing the possibility of an ATM switch using the buffered Banyan network [5, 6]. However, the buffered Banyan network has the following three disadvantages: 1. The buffered Banyan network is a blocking network at connection level. Therefore, a connection setup procedure must manage the total bit rate for all connections on each internal link. This adds no negligible overhead to the connection set-up procedure, especially in the case of a large ATM switch. 1 Interconnections between stages form a perfect shuffle [7], thus the interconnection pattern becomes more complex when the switch size is increased. This makes it difficult to adopt a building-block method in constructing an ATM switch system. 2 Copy connections cannot be realized using the buffered Banyan network only. An additional component, such as the copy network in [8], must be added to the buffered Banyan network. In this paper, an ATM switch which satisfies the two fore mentioned criteria while also overcoming the three foregoing disadvantages of the buffered Banyan network is proposed. III. BARREL SWITCH 3.1. Barrel switch topology The barrel switch is an ATM switch architecture designed to satisfy the five requirements given in the foregoing. The topology of the switch is shown in Fig. 1. This figure shows a barrel switch which has eight input ports and eight output ports. The barrel switch is constructed from n stages, each of which has «/2 element switches with two inlets and two outlets. Here, n is the switch size. These element switches are laid out around a cylinder and connected to each other by internal links following the rule described below. This shape gives the 12 "barrel switch' its name. Each input port or output port is given a number as shown in this figure. Each stage also is g}\ea a stage number as shown in this figure. The interconnections between stages of the barrel switch are now defined. In this definition, the inlet of each element switch at each stage is given a number, i.e., /(O), /(I), -, /(/i-l), in order from top to bottom in Fig. 1, matching the input/output port numbers. In the same manner, the outlet of each element switch is given a number, i.e., 0(0), 0(1),, O{n-l). Using these inlet/outlet numbers, the interconnections between stages can be defmed as follows. Connection between an outlet in stage i x 2-1 and an inlet in stage / X 2 Connect from an outlet 0(7) to an inlet /((/ + 1) modn). Connection between an outlet in stage k x 2 and an inlet in stage A: x 2 -*-1 Connect from an outlet 0((/ + 1) mod n) to an inlet /(/). (Here, 1 < i < n/2, 0 < j < n -I, I < k < n/21.) 3.2 Self-routing algorithm for the barrel switch outing tags for the barrel switch The barrel switch is a self-routing switch. Each element switch routes each input cell to one of two outlets. 88 Copyright Vandana Publications. All Rights Reserved.

3 A routing tag is used for this routing in each element switch. The self-routing algorithm for the barrel switch is a form of Input-to-Output address difference routing [9]. Each cell input has a "difference number" as the routing tag. The difference numbers for the barrel switch are defined as follows. It is assumed that the number of the output ports carrying the output from the cell is A and the number of the input port carrying input to the cell is B. For input from an input port which has an event number: A - 5-1; if negative, add n. For input from an input p)ort which has an odd number B - i4 + 1; if negative, add n; if this result equals n, set to 0. Note that this difference number would be simpler in a version of the barrel switch with n -I stages [10]. However, the n-stage barrel switch is considered in this paper since this version can be constructed using the building-block method described later. Also, it should be noted that the difference numbers for cells from different input ports to the same output port are not the same, although routing tags to the same output port are identical in the buffered Banyan network. In an ATM switching system, however, this difference number is calculated only once at the connection set-up; thus, the calculation is not a heavy load on the connection set-up procedure Self-routing algorithm for point-to-point connections There are two versions of the self-routing algorithm for the barrel switch: one is for point-to-point connections only, and the other is for point-to-multipoint connections. The algorithm for point-to-point connections, called P-P routing, is described first. The routing tag for input cells with P-P routing is the difference number. Each element switch determines the direction for each input cell according to the following rules: The difference number of an input cell is not zero. That cell is routed to cross dir. When the cell is output, the difference number is decreased by one. The difference number of an input cell is equal to zero. That cell is routed to straight dir. (Here, cross_dir means that a cell from the upper inlet is routed to the lower outlet and vice versa; straightjdir Figure 2 gives an example of cell switching using P- P routing. The sequence of difference number changes also is shown in this figure. Figure 2 also shows a route of a cell means that a cell from the upper inlet is routed to the upper outlet and vice versa.) which comes from the input port 2 and is destined to the output port 7. By the foregoing definition, the difference number of the cell when it comes in is 4. At the first stage, the difference number is not zero. Then an element switch outputs the cell to cross_dir. At the same time, the element switch decreases the difference number by one. At the following stage, the cell is output to the cross_dir while the difference number is not zero. After the difference number becomes zero, the cell is output to straight_dir. By executing the foregoing operation at each element switch, the routing from any input port to any output port can be realized on the barrel switch Self-routing algorithm for point-to-multipoint connections Next, the self-routing algorithm for point-to-multipoint connections, called COPY routing, is described. The routing tag for COPY routing is depicted in Fig. 3. This routing tag is made up from a bit corresponding to each stage and an additional bit called a "routing end bit." Each bit corresponding to a stage also is related to the difference number by the rule "the difference number plus 89 Copyright Vandana Publications. All Rights Reserved.

4 one is the stage number." To set up a point-to-multipoint connection, the difference numbers corresponding to output ports to which copied cells should be routed are calculated. Then a bit related to each calculated difference number is set to one. Other bits not related to these difference numbers are set to zero. The routing end bit is set to zero when a cell enters the barrel switch. Each element switch selects the direction of the input cells using the following rules. At each stage except the last The routing end bit is zero. The input cell is routed to cross_dir. When this cell is output, the routing end bit of this cell is still zero. If a bit corresponding to the stage is one, a copied cell is made from the input cell and the copied cell is output to straight_dir. The routing end bit of the copied cell is rewritten to one. The routing end bit is one. The input cell is routed to straight dir. The routing end bit of this cell is still one. At the last stage The routing end bit is zero. If a bit corresponding to the last stage is one, the input cell is routed to straight_dir. The routing end bit of this cell is rewritten to one. If that bit is zero, then the input cell is discarded. The routing end bit is one. The input cell is routed to straight_dir. The routing end bit is still one. bit is one. In this figure, the route of a cell from the input port 2 to output ports 5 and 7 is shown. By the foregoing definition, the routing tag of the cell is " " at the input port (here, the leftmost bit is the routing end bit). At the first and second stages, the cell is output to cross_dir only because the corresponding bit in the routing tag is zero. At the third stage, the cell is output to crossdir (the dotted line) and a copy cell is made to distend to straight dir (the dashed-dotted line) because the corresponding bit is one. The routing end bit of the copy cell is set to one. At the following stages, the copy cell is routed to straight_dir and output to the desired output port 5. In Fig. 4, an example of cell switching using COPY routing is shown. The dotted line shows the route for cells whose routing end bit is zero, and the dashed-dotted line shows the route for cells whose routing end The cell which is output to cross dir at the third stage is input to the element switch at the fourth stage and output to cross_dir. Then the cell is handled at the element switch in the fifth stage. Because the corresponding bit in the routing tag is one, the element switch outputs the cell to cross dir and makes a copy cell to be destined to straight dir as in the third stage. At the following stages, the copy cell is routed to straight dir and output to the desired output port. The cell which is output to cross_dir at the fifth stage is routed to cross dir at the following stages. At the last stage, this cell is discarded because the routing end bit of this cell is zero. By executing the foregoing operation at each element switch, the copy connection from any input port to any output port can be realized. 90 Copyright Vandana Publications. All Rights Reserved.

5 3.2.4 Nonblocking condition for the barrel switch The barrel switch has a function such that, if the bit rate for the internal links is set to twice that of the input/output ports, then this switch is nonblocking at the connection level, i.e., the total bit rate for all connections on an internal link does not exceed the capacity of the internal link. In Fig. 5, cell paths for all input and output port pairs in P-P or COPY routing are shown. The dotted lines show paths for cells whose difference number is not zero or routing end bit is zero. The dashed-dotted lines show paths for cells whose difference number is zero or routing end bit is one. Solid circles show the points where a cell whose High-speed cell switching with the barrel switch The barrel switch has a suitable architecture for high-speed cell switching for two reasons. First, the barrel switch is nonblocking if the bit rate of the internal links is doubled. Therefore, for example, if the element switches are identical input buffer switches and are implemented using the technique that can realize a 2.5 Gbps 8x 8 shared buffer ATM switch [11], the barrel switch constructed with these element switches can operate at 10 Gbps difference number is zero is input to an element switch first or the routing end bit is rewritten from zero to one. From this figure, it can be seen that a (virtual) crossbar switch is realized in a barrel switch if the solid circles are regarded as the crosspoints. Moreover, one input line (a dotted line) and one output line (a dashed-dotted line) of the crossbar switch are mapped onto one internal link of the barrel switch. Therefore, at any switch size, the barrel switch is nonblocking if the bit rate for the internal links is twice that of the input/output ports. The second reason results from the forementioned routing algorithms. Each element switch in a barrel switch can decide on the direction of the input cells from the routing tag only. Both P-P routing and COPY routing have this feature. The cell buffers on the element switch are used as elastic stores; and some cell data signals, i.e., a bit clock for sampling the cell data signals and a signal showing the head of cells, are used in the cell transfer path between element switches; then the clock skew problem is alleviated. If this method is applied to the barrel switch, the clock phase in each portion need not be controlled. By contrast, an ATM switch architecture in which the clock phase should be controlled is difficult to implement. Assuming that the speed is 10 Gbps per port and cells are handled in an 8-bit parallel form, the line length difference in the clock distribution circuit in the ATM switch should be less than about 2 cm to suppress the clock skew below quarter cycle (transmission speed of electrical signal = 15 cm/ns). The forementioned difficulty can be disregarded in the barrel switch. It should be noted that the total amount of hardware should be reduced because the number of the element switch is large in the barrel switch. Reducing the length of the cell buffer is efficient in reducing the total hardware size. In this case, the backpressure (the flow control in [5]) can be applied to reduce the cell loss rate. It is assumed that the backpressure is as follows. The destination cell buffer, which receives a cell, outputs a signal called flow control signal to show whether or not it can receive a cell. The source cell buffer, which outputs a cell to the destination cell buffer, refers the flow control signal at each cell output. If the destination cell buffer can receive a cell, the source cell buffer outputs a cell. The forementioned simple backpressure can be implemented at a high bit rate. The barrel switch is nonblocking at the connection level because a virtual crossbar switch is in the barrel switch. The crosspoint buffer switch [12] is another architecture based on the crossbar switch. The required throughput of cell buffers of this type is lower than that of the barrel switch. However, the barrel switch has the following advantage over the cross-point buffer switch. In the case of the crosspoint buffer switch, the cell buffers connected to the same output ports should output 91 Copyright Vandana Publications. All Rights Reserved.

6 cells synchronized to one clock. To prevent the clock skew problem, an architecture based on cascade-connected elastic stores is proposed in [12]. However, this architecture is disadvantageous in that the operation speed of the cell output control depends on the switch size, i.e., the cell output control is a bottleneck to implement a large-scale ATM switch. In the case of the barrel switch, this problem does not occur Building-block method to construct the barrel switch The barrel switch has a topology which is easy to construct using a building-block method. One buildingblock method is described in Fig. 6. This method uses a 2 x 2 module, as shown in Fig. 6(a). This module incorporates two element switches, i.e., one fixed internal link, three inputs, and three outputs. To form the topology of the barrel switch, these inputs and outputs are connected to other modules. Figures 6(b) and (c) show 4x 4 and 8x 8 barrel switches using identical 2x 2 modules shown in Fig. 6(a), respectively. The 4x 4 switch is made from four 2x 2 modules, and the 8 x 8 switch consists of eight 2x 2 modules. In general, the n x n switch consists of tp/4 2x 2 modules. As shown in these figures, interconnections between the stages of the barrel switch are almost the same for any switch size, whereas interconnections of the Banyan network are different if the switch size is varied. Thus, various switch sizes can be implemented by connecting identical modules. Moreover, the number of modules to which the outputs of each module are connected is fixed (there are only three) in any switch and module sizes and interconnections between stages are not intertwined. Input Buffers Output Buffers (2 cells long) (32 cells long) It should be noted that the length of one internal link is longer than that of other internal links at one interstage interconnection. However, this is not a restriction to implement if the cell buffer in the element switch operates as an elastic store. The flow control signal can be a difficulty for high-speed implementation. However, this can be avoided by changing the condition of "backpressure is on." The backpressure turns to on when the remain storage in the destination buffer is less than the number of the cell on the internal link. This problem can be disregarded. 92 Copyright Vandana Publications. All Rights Reserved.

7 IV. BARREL SWITCH PERFORMANCE EVALUATION Computer simulations have been done with the barrel switch, and the cell loss rate and delay characteristics were obtained from these simulations. The simulation results are given in this section Simulation model The model used for these simulations is shown in Fig. 7. Input buffers are located on every input port of the barrel switch. This buffer speeds up the bit rate from normal to double, and the buffers are two cells long; that is, the buffer can hold two cells. Also, output buffers are located on every output port of the barrel switch. These buffers reduce the bit rate to normal and the buffers are 32 cells long. The backpressure discussed in section is adopted from the output buffers through every element switch to the input buffers. Each element switch is 2 X 2 the input buffer switch to keep the throughput of the cell buffers in the element switch low. The cell buffers in the element switch are four cells long. The offered load is random traffic, i.e., cells arrive with a Poisson distribution and the destinations for the arriving cells are selected randomly among all output ports with the same probability. on the barrel switch than a point-to-multipoint connection if the total bit rates for all connections on all input and output ports do not exceed the capacity of the input and output ports. If a point-to-multipoint connection is set up instead of a point-to-point connection, the load of some input ports and some internal links decreases. Therefore, considering point-to-point connections only gives a worst 4.2. Performance comparison between P-P routing and COPY routing The cell loss rate of 8 x 8 barrel switch is shown in Fig. 8. The X-axis is the offered load and the F-axis is the cell loss rate. In this figure, the performance of P-P and COPY routing is shown by curves marked "P-P" and "COPY," respectively. Note that only point-to-point connections are made with COPY routing in these simulations. In case of COPY routing, input cells are always transferred to the last stage and some copy cells are made at desired points. A point-to-point connection places a heavier load 18 COPY: Copy routing case scenario for COPY routing. Figure 8 shows that the cell loss rate for P-P routing is acceptable for an ATM switching system, whereas that for COPY routing is not so good. Following COPY routing and the simulation model, input load on the last stage for COPY routing is two times as heavy as that for P-P routing due to these copied cells. Input load on other stages for COPY routing also is heavier than that for P-P routing. The cell losses in this model are due mainly to the cell buffers of the element switches located near the input ports that become full. This may occur frequently under the conditions in which the barrel switch load is heavy which is why the cell loss rate for COPY routing is worse than that for P-P routing. The cell loss characteristic below lo"* is not apparent in this figure because this result has been obtained from computer simulations. To obtain the cell loss characteristic in this range, the queueing theory may be applied for future work. However, it can be considered that this can be conjectured from the obtained characteristic. 93 Copyright Vandana Publications. All Rights Reserved.

8 4.3 Improvement of COPY routing performance The COPY routing performance can be improved if the CASO buffer [5] is used as the cell buffers in the element switch. The CASO buffer is a cell buffer which can select the destination of the output cell. When a conflict occurs on one of the outlets of the 2 X 2 element switch, a cell destined to another outlet is searched and outputted. Then the throughput of the element switch can be increased. The high-speed implementation method of the CASO buffer is discussed in [5] and [6]. V. CONCLUSION This paper proposed the concept and topology of a barrel switch, which has a suitable architecture for highspeed ATM switches. Two self-routing methods, i.e., for point-to-point connections only and for point-to-multipoint connections, can be implemented in a barrel switch. The topology of the switch is simple enough to allow construction by a building-block method leading to an excellent scalability. The nonblocking condition and cell loss rate/delay characteristics for the barrel switch also are addressed. Simulation results prove that less than a 64 X 64 REFERENCES [1] Y. Shobatake, M. Motoyama, E. Shobatake, T. Kamitake, S. Shimizu, M. Noda, and K. Sakaue.A one-chip scalable 8x 8 ATM switch LSI employing shared buffer architecture. IEEE J. on Sel. Area Commun., 9, 8, pp (Oct. 1991). [2] H. Kondoh, H. Nonaka, H. Yamanaka, T. Saito, Y. Matsuda, and M. Nakaya. Development of the Shared MuUibuffer-Type ATM Switch LSI Imple mentation Figure 9 shows the cell loss rate for a barrel switch applying the CASO buffer as the cell buffers in the element switch. The switch size for this result is eight. The cell loss rate for COPY routing has become closer to that for P-P routing in this case. 4.4 Performance of the large-scale barrel switch The last simulation result shown in this section is the characteristic of barrel switches greater than 8x 8 in size. Figure 10 shows the cell loss rate and mean delay characteristic of the 8 x 8, 16 x 16, 32 x 32, and 64 x 64 barrel switches with COPY routing. The cell buffer in the element switch is the CASO buffer. Simulation results under the random traffic prove that the 64 X 64 barrel switch has adequate cell loss rate to an actual ATM switching system (less than 10"* at 85- percent load). From the result of the mean delay characteristic, the following can be seen. At light load, few cells are held in the cell buffers in the element switches. At the load where the cell loss rate becomes greater, a large number of cells are held in the element switches. The mean delay characteristics calculated by the cell slot. This is a time interval in which a cell can transfer at the input/output port worse than that for e.g., the crosspoint buffer switch. However, this is not a serious problem because the absolute time of the cell slot is small at the application range of the barrel switch (200 ns for 2.4 Gbps). barrel switch has adequate cell loss rate to an actual ATM switching system. However, the mean delay characteristic is worse. This will not be a serious problem in high-speed ATM switches because the cell slot is short in the highspeed switching. More detailed performance evaluation, especially in the low cell-loss region by applying some analytical method, is a future work. Moreover, an applicable load under practical use also is a future work. The effect ofthe call admission control should also be considered. of the Buffer Switch LSI. In: 1992 Spring Nat'l Convention Record, I.E.I.C.E., Japan, Paper C-581 (March 1992). [3] K. E. Batcher. Sorting Networks and Their Applications. In: Proc. of AFIPS 1968 Spring JointComp. Conf., pp [4] D. M. Dias and J. R. Jump. Analysis and simulation of buffered delta networks. IEEE Trans, on Comput., C-30, 4, pp (April 1981). [5] Y. Shobatake and T. Kodama. A Cell SwitchingAlgorithm for the Buffered Banyan Network. In: Proc. of ICC'9O, Paper 316.4, pp (April 1990). 94 Copyright Vandana Publications. All Rights Reserved.

BROADBAND AND HIGH SPEED NETWORKS

BROADBAND AND HIGH SPEED NETWORKS BROADBAND AND HIGH SPEED NETWORKS ATM SWITCHING ATM is a connection-oriented transport concept An end-to-end connection (virtual channel) established prior to transfer of cells Signaling used for connection

More information

IV. PACKET SWITCH ARCHITECTURES

IV. PACKET SWITCH ARCHITECTURES IV. PACKET SWITCH ARCHITECTURES (a) General Concept - as packet arrives at switch, destination (and possibly source) field in packet header is used as index into routing tables specifying next switch in

More information

Introduction to ATM Technology

Introduction to ATM Technology Introduction to ATM Technology ATM Switch Design Switching network (N x N) Switching network (N x N) SP CP SP CP Presentation Outline Generic Switch Architecture Specific examples Shared Buffer Switch

More information

Switching. An Engineering Approach to Computer Networking

Switching. An Engineering Approach to Computer Networking Switching An Engineering Approach to Computer Networking What is it all about? How do we move traffic from one part of the network to another? Connect end-systems to switches, and switches to each other

More information

A Proposal for a High Speed Multicast Switch Fabric Design

A Proposal for a High Speed Multicast Switch Fabric Design A Proposal for a High Speed Multicast Switch Fabric Design Cheng Li, R.Venkatesan and H.M.Heys Faculty of Engineering and Applied Science Memorial University of Newfoundland St. John s, NF, Canada AB X

More information

ECE 697J Advanced Topics in Computer Networks

ECE 697J Advanced Topics in Computer Networks ECE 697J Advanced Topics in Computer Networks Switching Fabrics 10/02/03 Tilman Wolf 1 Router Data Path Last class: Single CPU is not fast enough for processing packets Multiple advanced processors in

More information

Introduction. Introduction. Router Architectures. Introduction. Recent advances in routing architecture including

Introduction. Introduction. Router Architectures. Introduction. Recent advances in routing architecture including Router Architectures By the end of this lecture, you should be able to. Explain the different generations of router architectures Describe the route lookup process Explain the operation of PATRICIA algorithm

More information

Performance of Multihop Communications Using Logical Topologies on Optical Torus Networks

Performance of Multihop Communications Using Logical Topologies on Optical Torus Networks Performance of Multihop Communications Using Logical Topologies on Optical Torus Networks X. Yuan, R. Melhem and R. Gupta Department of Computer Science University of Pittsburgh Pittsburgh, PA 156 fxyuan,

More information

Virtual Circuit Blocking Probabilities in an ATM Banyan Network with b b Switching Elements

Virtual Circuit Blocking Probabilities in an ATM Banyan Network with b b Switching Elements Proceedings of the Applied Telecommunication Symposium (part of Advanced Simulation Technologies Conference) Seattle, Washington, USA, April 22 26, 21 Virtual Circuit Blocking Probabilities in an ATM Banyan

More information

Structure and Performance Evaluation of a Replicated Banyan Network Based ATM Switch

Structure and Performance Evaluation of a Replicated Banyan Network Based ATM Switch Structure and Performance Evaluation of a Replicated Banyan Network Based ATM Switch Moustafa A. Youssef, Mohamed N. El-Derini, and Hussien H. Aly Department of Computer Science and Automatic Control,

More information

Switching Hardware. Spring 2015 CS 438 Staff, University of Illinois 1

Switching Hardware. Spring 2015 CS 438 Staff, University of Illinois 1 Switching Hardware Spring 205 CS 438 Staff, University of Illinois Where are we? Understand Different ways to move through a network (forwarding) Read signs at each switch (datagram) Follow a known path

More information

Switching CHAPTER 8. Solutions to Review Questions and Exercises. Review Questions

Switching CHAPTER 8. Solutions to Review Questions and Exercises. Review Questions CHAPTER 8 Switching Solutions to Review Questions and Exercises Review Questions 1. Switching provides a practical solution to the problem of connecting multiple devices in a network. It is more practical

More information

High-Speed Cell-Level Path Allocation in a Three-Stage ATM Switch.

High-Speed Cell-Level Path Allocation in a Three-Stage ATM Switch. High-Speed Cell-Level Path Allocation in a Three-Stage ATM Switch. Martin Collier School of Electronic Engineering, Dublin City University, Glasnevin, Dublin 9, Ireland. email address: collierm@eeng.dcu.ie

More information

A General Purpose Queue Architecture for an ATM Switch

A General Purpose Queue Architecture for an ATM Switch Mitsubishi Electric Research Laboratories Cambridge Research Center Technical Report 94-7 September 3, 994 A General Purpose Queue Architecture for an ATM Switch Hugh C. Lauer Abhijit Ghosh Chia Shen Abstract

More information

CONGESTION CONTROL BY USING A BUFFERED OMEGA NETWORK

CONGESTION CONTROL BY USING A BUFFERED OMEGA NETWORK IADIS International Conference on Applied Computing CONGESTION CONTROL BY USING A BUFFERED OMEGA NETWORK Ahmad.H. ALqerem Dept. of Comp. Science ZPU Zarka Private University Zarka Jordan ABSTRACT Omega

More information

Chapter 8 Switching 8.1

Chapter 8 Switching 8.1 Chapter 8 Switching 8.1 8.2 Figure 8.1 Switched network 8.3 Figure 8.2 Taxonomy of switched networks 8-1 CIRCUIT-SWITCHED NETWORKS 8.4 A circuit-switched network consists of a set of switches connected

More information

Basic Switch Organization

Basic Switch Organization NOC Routing 1 Basic Switch Organization 2 Basic Switch Organization Link Controller Used for coordinating the flow of messages across the physical link of two adjacent switches 3 Basic Switch Organization

More information

Design of Optical Burst Switches based on Dual Shuffle-exchange Network and Deflection Routing

Design of Optical Burst Switches based on Dual Shuffle-exchange Network and Deflection Routing Design of Optical Burst Switches based on Dual Shuffle-exchange Network and Deflection Routing Man-Ting Choy Department of Information Engineering, The Chinese University of Hong Kong mtchoy1@ie.cuhk.edu.hk

More information

ROUTERS serve to connect external links with various data

ROUTERS serve to connect external links with various data 304 IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, VOL. 15, NO. 4, APRIL 2004 Multistage-Based Switching Fabrics for Scalable Routers Nian-Feng Tzeng, Senior Member, IEEE Abstract Rapidly growing

More information

Space-division switch fabrics. Copyright 2003, Tim Moors

Space-division switch fabrics. Copyright 2003, Tim Moors 1 Space-division switch fabrics 2 Outline: Space-division switches Single-stage Crossbar, Knockout Staged switches: Multiple switching elements between input and output Networks of basic elements Clos

More information

Switch Architecture for Efficient Transfer of High-Volume Data in Distributed Computing Environment

Switch Architecture for Efficient Transfer of High-Volume Data in Distributed Computing Environment Switch Architecture for Efficient Transfer of High-Volume Data in Distributed Computing Environment SANJEEV KUMAR, SENIOR MEMBER, IEEE AND ALVARO MUNOZ, STUDENT MEMBER, IEEE % Networking Research Lab,

More information

Parallel Read-Out High-Speed Input Buffer ATM Switch Architectures

Parallel Read-Out High-Speed Input Buffer ATM Switch Architectures Parallel Read-Out High-Speed Input Buffer ATM Switch Architectures 95 Chugo Fujihashi and Junji Ichikawa The prototype first in first out (FIFO) input buffer asynchronous transfer mode (ATM) switch is

More information

Crossbar - example. Crossbar. Crossbar. Combination: Time-space switching. Simple space-division switch Crosspoints can be turned on or off

Crossbar - example. Crossbar. Crossbar. Combination: Time-space switching. Simple space-division switch Crosspoints can be turned on or off Crossbar Crossbar - example Simple space-division switch Crosspoints can be turned on or off i n p u t s sessions: (,) (,) (,) (,) outputs Crossbar Advantages: simple to implement simple control flexible

More information

588 IEEE/ACM TRANSACTIONS ON NETWORKING, VOL. 7, NO. 4, AUGUST 1999

588 IEEE/ACM TRANSACTIONS ON NETWORKING, VOL. 7, NO. 4, AUGUST 1999 588 IEEE/ACM TRANSACTIONS ON NETWORKING, VOL 7, NO 4, AUGUST 1999 The Deflection Self-Routing Banyan Network: A Large-Scale ATM Switch Using the Fully Adaptive Self-Routing its Performance Analyses Jae-Hyun

More information

Router Construction. Workstation-Based. Switching Hardware Design Goals throughput (depends on traffic model) scalability (a function of n) Outline

Router Construction. Workstation-Based. Switching Hardware Design Goals throughput (depends on traffic model) scalability (a function of n) Outline Router Construction Outline Switched Fabrics IP Routers Tag Switching Spring 2002 CS 461 1 Workstation-Based Aggregate bandwidth 1/2 of the I/O bus bandwidth capacity shared among all hosts connected to

More information

Switching CHAPTER 8. Figure 8.1

Switching CHAPTER 8. Figure 8.1 CHAPTER 8 Switching A network is a set of connected devices. Whenever we have multiple devices, we have the problem of how to connect them to make one-to-one communication possible. One solution is to

More information

Cell Switching (ATM) Commonly transmitted over SONET other physical layers possible. Variable vs Fixed-Length Packets

Cell Switching (ATM) Commonly transmitted over SONET other physical layers possible. Variable vs Fixed-Length Packets Cell Switching (ATM) Connection-oriented packet-switched network Used in both WAN and LAN settings Signaling (connection setup) Protocol: Q2931 Specified by ATM forum Packets are called cells 5-byte header

More information

FIRM: A Class of Distributed Scheduling Algorithms for High-speed ATM Switches with Multiple Input Queues

FIRM: A Class of Distributed Scheduling Algorithms for High-speed ATM Switches with Multiple Input Queues FIRM: A Class of Distributed Scheduling Algorithms for High-speed ATM Switches with Multiple Input Queues D.N. Serpanos and P.I. Antoniadis Department of Computer Science University of Crete Knossos Avenue

More information

Efficient Queuing Architecture for a Buffered Crossbar Switch

Efficient Queuing Architecture for a Buffered Crossbar Switch Proceedings of the 11th WSEAS International Conference on COMMUNICATIONS, Agios Nikolaos, Crete Island, Greece, July 26-28, 2007 95 Efficient Queuing Architecture for a Buffered Crossbar Switch MICHAEL

More information

Shared-Memory Combined Input-Crosspoint Buffered Packet Switch for Differentiated Services

Shared-Memory Combined Input-Crosspoint Buffered Packet Switch for Differentiated Services Shared-Memory Combined -Crosspoint Buffered Packet Switch for Differentiated Services Ziqian Dong and Roberto Rojas-Cessa Department of Electrical and Computer Engineering New Jersey Institute of Technology

More information

PERFORMANCE AND IMPLEMENTATION OF 4x4 SWITCHING NODES IN AN INTERCONNECTION NETWORK FOR PASM

PERFORMANCE AND IMPLEMENTATION OF 4x4 SWITCHING NODES IN AN INTERCONNECTION NETWORK FOR PASM PERFORMANCE AND IMPLEMENTATION OF 4x4 SWITCHING NODES IN AN INTERCONNECTION NETWORK FOR PASM Robert J. McMillen, George B. Adams III, and Howard Jay Siegel School of Electrical Engineering, Purdue University

More information

Comparative Study of blocking mechanisms for Packet Switched Omega Networks

Comparative Study of blocking mechanisms for Packet Switched Omega Networks Proceedings of the 6th WSEAS Int. Conf. on Electronics, Hardware, Wireless and Optical Communications, Corfu Island, Greece, February 16-19, 2007 18 Comparative Study of blocking mechanisms for Packet

More information

Performance Characteristics of a Packet-Based Leaky-Bucket Algorithm for ATM Networks

Performance Characteristics of a Packet-Based Leaky-Bucket Algorithm for ATM Networks Performance Characteristics of a Packet-Based Leaky-Bucket Algorithm for ATM Networks Toshihisa OZAWA Department of Business Administration, Komazawa University 1-23-1 Komazawa, Setagaya-ku, Tokyo 154-8525,

More information

The Network Layer and Routers

The Network Layer and Routers The Network Layer and Routers Daniel Zappala CS 460 Computer Networking Brigham Young University 2/18 Network Layer deliver packets from sending host to receiving host must be on every host, router in

More information

Unique Journal of Engineering and Advanced Sciences Available online: Research Article

Unique Journal of Engineering and Advanced Sciences Available online:   Research Article ISSN 2348-375X Unique Journal of Engineering and Advanced Sciences Available online: www.ujconline.net Research Article A POWER EFFICIENT CAM DESIGN USING MODIFIED PARITY BIT MATCHING TECHNIQUE Karthik

More information

CS343: Data Communication Switched Communication Network

CS343: Data Communication Switched Communication Network CS343: Data Communication Switched Communication Network by Dr. Manas Khatua Assistant Professor Dept. of CSE IIT Guwahati E-mail: manaskhatua@iitg.ac.in Switched Communication Network Broader aspect interconnecting

More information

Performance Enhancement Techniques of a Banyan Network Based Interconnection Structure

Performance Enhancement Techniques of a Banyan Network Based Interconnection Structure Performance Enhancement Techniques of a Banyan Network Based Interconnection Structure Moustafa A. Youssef, Mohamed N. El-Derini, and Hussien H. Aly Department of Computer Science and Automatic Control,

More information

Scheduling. Scheduling algorithms. Scheduling. Output buffered architecture. QoS scheduling algorithms. QoS-capable router

Scheduling. Scheduling algorithms. Scheduling. Output buffered architecture. QoS scheduling algorithms. QoS-capable router Scheduling algorithms Scheduling Andrea Bianco Telecommunication Network Group firstname.lastname@polito.it http://www.telematica.polito.it/ Scheduling: choose a packet to transmit over a link among all

More information

Accurate modelling of the queueing behaviour of shared bu!er ATM switches

Accurate modelling of the queueing behaviour of shared bu!er ATM switches INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS Int. J. Commun. Syst. 12, 297}308 (1999) Accurate modelling of the queueing behaviour of shared bu!er ATM switches Mahmoud Saleh and Mohammed Atiquzzaman*

More information

IP Paging Considered Unnecessary:

IP Paging Considered Unnecessary: IP Paging Considered Unnecessary: Mobile IPv6 and IP Paging for Dormant Mode Location Update in Macrocellular and Hotspot Networks James Kempf DoCoMo USA Communications Labs 181 Metro Drive, Suite 3 San

More information

Chapter 10. Circuits Switching and Packet Switching 10-1

Chapter 10. Circuits Switching and Packet Switching 10-1 Chapter 10 Circuits Switching and Packet Switching 10-1 Content Switched communication networks Circuit switching networks Circuit-switching concepts Packet-switching principles X.25 (mentioned but not

More information

A Path Decomposition Approach for Computing Blocking Probabilities in Wavelength-Routing Networks

A Path Decomposition Approach for Computing Blocking Probabilities in Wavelength-Routing Networks IEEE/ACM TRANSACTIONS ON NETWORKING, VOL. 8, NO. 6, DECEMBER 2000 747 A Path Decomposition Approach for Computing Blocking Probabilities in Wavelength-Routing Networks Yuhong Zhu, George N. Rouskas, Member,

More information

PERFORMANCE OF A THREE-STAGE BANYAN-BASED ARCHITECTURE WITH INPUT AND OUTPUT BUFFERS FOR LARGE FAST PACKET SWITCHES

PERFORMANCE OF A THREE-STAGE BANYAN-BASED ARCHITECTURE WITH INPUT AND OUTPUT BUFFERS FOR LARGE FAST PACKET SWITCHES I PERFORMANCE OF A THREE-STAGE BANYAN-BASED ARCHITECTURE WITH INPUT AND OUTPUT BUFFERS FOR LARGE FAST PACKET SWITCHES Fabio M. Chiussi and Fouad A. Tobagi Technical Report No. CSL-TR-93-573 June 1993 This

More information

Introduction. Router Architectures. Introduction. Introduction. Recent advances in routing architecture including

Introduction. Router Architectures. Introduction. Introduction. Recent advances in routing architecture including Introduction Router Architectures Recent advances in routing architecture including specialized hardware switching fabrics efficient and faster lookup algorithms have created routers that are capable of

More information

A reliable procedure in a new power management technique for a 200-Gbps packet forwarding LSI

A reliable procedure in a new power management technique for a 200-Gbps packet forwarding LSI LETTER IEICE Electronics Express, Vol.10, No.11, 1 6 A reliable procedure in a new power management technique for a 200-Gbps packet forwarding LSI Sadayuki Yasuda a), Shoko Ohteru, Yasuyuki Itoh, Koji

More information

STATE UNIVERSITY OF NEW YORK AT STONY BROOK. CEASTECHNICAL REPe. Multiclass Information Based Deflection Strategies for the Manhattan Street Network

STATE UNIVERSITY OF NEW YORK AT STONY BROOK. CEASTECHNICAL REPe. Multiclass Information Based Deflection Strategies for the Manhattan Street Network ; STATE UNIVERSITY OF NEW YORK AT STONY BROOK CEASTECHNICAL REPe Multiclass Information Based Deflection Strategies for the Manhattan Street Network J.-W. Jeng and T.G. Robertazzi June 19, 1992 Multiclass

More information

Switching Technology S38.165

Switching Technology S38.165 Switching Technology S38.165 Pertti Raatikainen VTT Information Technology pertti.raatikainen@vtt.fi L1-1 General Lecturer: Pertti Raatikainen, research professor /VTT email: pertti.raatikainen@vtt.fi

More information

Content Addressable Memory with Efficient Power Consumption and Throughput

Content Addressable Memory with Efficient Power Consumption and Throughput International journal of Emerging Trends in Science and Technology Content Addressable Memory with Efficient Power Consumption and Throughput Authors Karthik.M 1, R.R.Jegan 2, Dr.G.K.D.Prasanna Venkatesan

More information

An Analysis of Blocking vs Non-Blocking Flow Control in On-Chip Networks

An Analysis of Blocking vs Non-Blocking Flow Control in On-Chip Networks An Analysis of Blocking vs Non-Blocking Flow Control in On-Chip Networks ABSTRACT High end System-on-Chip (SoC) architectures consist of tens of processing engines. These processing engines have varied

More information

Stop-and-Go Service Using Hierarchical Round Robin

Stop-and-Go Service Using Hierarchical Round Robin Stop-and-Go Service Using Hierarchical Round Robin S. Keshav AT&T Bell Laboratories 600 Mountain Avenue, Murray Hill, NJ 07974, USA keshav@research.att.com Abstract The Stop-and-Go service discipline allows

More information

Wavelength conversion in optical packet switching

Wavelength conversion in optical packet switching Downloaded from orbit.dtu.dk on: Aug 18, 2018 Wavelength conversion in optical packet switching Danielsen, Søren Lykke; Hansen, Peter Bukhave; Stubkjær, Kristian Published in: Journal of Lightwave Technology

More information

Int. J. Advanced Networking and Applications 1194 Volume: 03; Issue: 03; Pages: (2011)

Int. J. Advanced Networking and Applications 1194 Volume: 03; Issue: 03; Pages: (2011) Int J Advanced Networking and Applications 1194 ISA-Independent Scheduling Algorithm for Buffered Crossbar Switch Dr Kannan Balasubramanian Department of Computer Science, Mepco Schlenk Engineering College,

More information

Comparison of pre-backoff and post-backoff procedures for IEEE distributed coordination function

Comparison of pre-backoff and post-backoff procedures for IEEE distributed coordination function Comparison of pre-backoff and post-backoff procedures for IEEE 802.11 distributed coordination function Ping Zhong, Xuemin Hong, Xiaofang Wu, Jianghong Shi a), and Huihuang Chen School of Information Science

More information

DESIGN OF EFFICIENT ROUTING ALGORITHM FOR CONGESTION CONTROL IN NOC

DESIGN OF EFFICIENT ROUTING ALGORITHM FOR CONGESTION CONTROL IN NOC DESIGN OF EFFICIENT ROUTING ALGORITHM FOR CONGESTION CONTROL IN NOC 1 Pawar Ruchira Pradeep M. E, E&TC Signal Processing, Dr. D Y Patil School of engineering, Ambi, Pune Email: 1 ruchira4391@gmail.com

More information

Configuration of Offset Time in Optical Burst Switching Networks for Delay Sensitive Traffic

Configuration of Offset Time in Optical Burst Switching Networks for Delay Sensitive Traffic Configuration of Offset Time in Optical Burst Switching Networks for Delay Sensitive Traffic Anupam Soni and Yatindra Nath Singh anusoni@iitk.ac.in,ynsingh@iitk.ac.in. Abstract In Optical Burst Switching

More information

SAMBA-BUS: A HIGH PERFORMANCE BUS ARCHITECTURE FOR SYSTEM-ON-CHIPS Λ. Ruibing Lu and Cheng-Kok Koh

SAMBA-BUS: A HIGH PERFORMANCE BUS ARCHITECTURE FOR SYSTEM-ON-CHIPS Λ. Ruibing Lu and Cheng-Kok Koh BUS: A HIGH PERFORMANCE BUS ARCHITECTURE FOR SYSTEM-ON-CHIPS Λ Ruibing Lu and Cheng-Kok Koh School of Electrical and Computer Engineering Purdue University, West Lafayette, IN 797- flur,chengkokg@ecn.purdue.edu

More information

Long Round-Trip Time Support with Shared-Memory Crosspoint Buffered Packet Switch

Long Round-Trip Time Support with Shared-Memory Crosspoint Buffered Packet Switch Long Round-Trip Time Support with Shared-Memory Crosspoint Buffered Packet Switch Ziqian Dong and Roberto Rojas-Cessa Department of Electrical and Computer Engineering New Jersey Institute of Technology

More information

Packet Switching Queuing Architecture: A Study

Packet Switching Queuing Architecture: A Study Packet Switching Queuing Architecture: A Study Shikhar Bahl 1, Rishabh Rai 2, Peeyush Chandra 3, Akash Garg 4 M.Tech, Department of ECE, Ajay Kumar Garg Engineering College, Ghaziabad, U.P., India 1,2,3

More information

Design and Implementation of detecting the failure of sensor node based on RTT time and RTPs in WSNs

Design and Implementation of detecting the failure of sensor node based on RTT time and RTPs in WSNs Design and Implementation of detecting the failure of sensor node based on RTT time and RTPs in WSNs Girish K 1 and Mrs. Shruthi G 2 1 Department of CSE, PG Student Karnataka, India 2 Department of CSE,

More information

Lecture (03) Circuit switching

Lecture (03) Circuit switching Agenda Lecture (03) Circuit switching Switched communication network Circuit switching technology Dr. Ahmed ElShafee ١ Dr. Ahmed ElShafee, ACU Fall 2011, Networks I ٢ Dr. Ahmed ElShafee, ACU Fall 2011,

More information

Designing Efficient Benes and Banyan Based Input-Buffered ATM Switches

Designing Efficient Benes and Banyan Based Input-Buffered ATM Switches Designing Efficient Benes and Banyan Based Input-Buffered ATM Switches Rajendra V. Boppana Computer Science Division The Univ. of Texas at San Antonio San Antonio, TX 829- boppana@cs.utsa.edu C. S. Raghavendra

More information

A simple mathematical model that considers the performance of an intermediate node having wavelength conversion capability

A simple mathematical model that considers the performance of an intermediate node having wavelength conversion capability A Simple Performance Analysis of a Core Node in an Optical Burst Switched Network Mohamed H. S. Morsy, student member, Mohamad Y. S. Sowailem, student member, and Hossam M. H. Shalaby, Senior member, IEEE

More information

A Pipelined Memory Management Algorithm for Distributed Shared Memory Switches

A Pipelined Memory Management Algorithm for Distributed Shared Memory Switches A Pipelined Memory Management Algorithm for Distributed Shared Memory Switches Xike Li, Student Member, IEEE, Itamar Elhanany, Senior Member, IEEE* Abstract The distributed shared memory (DSM) packet switching

More information

A quasi-nonblocking self-routing network which routes packets in log 2 N time.

A quasi-nonblocking self-routing network which routes packets in log 2 N time. A quasi-nonblocking self-routing network which routes packets in log 2 N time. Giuseppe A. De Biase Claudia Ferrone Annalisa Massini Dipartimento di Scienze dell Informazione, Università di Roma la Sapienza

More information

DESIGN OF MULTICAST SWITCHES FOR SANS

DESIGN OF MULTICAST SWITCHES FOR SANS DESIGN OF MULTICAST SWITCHES FOR SANS APPROVED BY SUPERVISING COMMITTEE: Dr. Rajendra V. Boppana, Supervising Professor Dr. Turgay Korkmaz Dr. Weining Zhang Accepted: Dean of Graduate Studies DESIGN OF

More information

ATM Switches. Switching Technology S ATM switches

ATM Switches. Switching Technology S ATM switches ATM Switches Switching Technology S38.65 http://www.netlab.hut.fi/opetus/s3865 9 - ATM switches General of ATM switching Structure of an ATM switch Example switch implementations Knockout switch Abacus

More information

PAPER Adaptive Thresholds of Buffer to Solve the Beat-Down Problem of Rate Control in ATM Networks

PAPER Adaptive Thresholds of Buffer to Solve the Beat-Down Problem of Rate Control in ATM Networks 362 PAPER Adaptive Thresholds of Buffer to Solve the Beat-Down Problem of Rate Control in ATM Networks Harry PRIHANTO, Student Member and Kenji NAKAGAWA, Member SUMMARY ABR service is currently standardized

More information

A Novel Pseudo 4 Phase Dual Rail Asynchronous Protocol with Self Reset Logic & Multiple Reset

A Novel Pseudo 4 Phase Dual Rail Asynchronous Protocol with Self Reset Logic & Multiple Reset A Novel Pseudo 4 Phase Dual Rail Asynchronous Protocol with Self Reset Logic & Multiple Reset M.Santhi, Arun Kumar S, G S Praveen Kalish, Siddharth Sarangan, G Lakshminarayanan Dept of ECE, National Institute

More information

A 12-STEP SORTING NETWORK FOR 22 ELEMENTS

A 12-STEP SORTING NETWORK FOR 22 ELEMENTS A 12-STEP SORTING NETWORK FOR 22 ELEMENTS SHERENAZ W. AL-HAJ BADDAR Department of Computer Science, Kent State University Kent, Ohio 44240, USA KENNETH E. BATCHER Department of Computer Science, Kent State

More information

CHAPTER 3 ATM SWITCHING PRINCIPLES AND DESIGN ISSUES

CHAPTER 3 ATM SWITCHING PRINCIPLES AND DESIGN ISSUES 22 CHAPTER 3 ATM SWITCHING PRINCIPLES AND DESIGN ISSUES With the phenomenal growth in the speeds of optical transmission systems, there is severe pressure on switch designers to develop switches that match

More information

A Hybrid Approach to CAM-Based Longest Prefix Matching for IP Route Lookup

A Hybrid Approach to CAM-Based Longest Prefix Matching for IP Route Lookup A Hybrid Approach to CAM-Based Longest Prefix Matching for IP Route Lookup Yan Sun and Min Sik Kim School of Electrical Engineering and Computer Science Washington State University Pullman, Washington

More information

Introduction to Communications Part One: Physical Layer Switching

Introduction to Communications Part One: Physical Layer Switching Introduction to Communications Part One: Physical Layer Switching Kuang Chiu Huang TCM NCKU Spring/2008 Goals of This Lecture Through the lecture and in-class discussion, students are enabled to compare

More information

Replica Distribution Scheme for Location-Dependent Data in Vehicular Ad Hoc Networks using a Small Number of Fixed Nodes

Replica Distribution Scheme for Location-Dependent Data in Vehicular Ad Hoc Networks using a Small Number of Fixed Nodes Replica Distribution Scheme for Location-Dependent Data in Vehicular d Hoc Networks using a Small Number of Fixed Nodes Junichiro Okamoto and Susumu Ishihara Graduate School of Engineering, Shizuoka University,

More information

COMPUTER NETWORK Model Test Paper

COMPUTER NETWORK Model Test Paper Model Test Paper Question no. 1 is compulsory. Attempt all parts. Q1. Each question carries equal marks. (5*5 marks) A) Difference between Transmission Control Protocol (TCP) and User Datagram Protocol.

More information

Introduction to Real-Time Communications. Real-Time and Embedded Systems (M) Lecture 15

Introduction to Real-Time Communications. Real-Time and Embedded Systems (M) Lecture 15 Introduction to Real-Time Communications Real-Time and Embedded Systems (M) Lecture 15 Lecture Outline Modelling real-time communications Traffic and network models Properties of networks Throughput, delay

More information

WAN technology which are to be discussed:

WAN technology which are to be discussed: WAN Technology Operates at 3 layer OSI model as below: 1. PHY 2. Data Link 3. Network Most of WAN technology are packetswitched network categorized as Switched Virtual circuit Network ( 3-phase, connection

More information

Analytic Performance Models for Bounded Queueing Systems

Analytic Performance Models for Bounded Queueing Systems Analytic Performance Models for Bounded Queueing Systems Praveen Krishnamurthy Roger D. Chamberlain Praveen Krishnamurthy and Roger D. Chamberlain, Analytic Performance Models for Bounded Queueing Systems,

More information

Fractional Lambda Switching: Principles of Operation and Performance Issues

Fractional Lambda Switching: Principles of Operation and Performance Issues Fractional Lambda Switching: Principles of Operation and Performance Issues This paper introduces fractional lambda (λ) switching (FλS) and studies its blocking issues. FλS is a completely novel and extremely

More information

Switching CHAPTER 8. Figure 8.1

Switching CHAPTER 8. Figure 8.1 CHAPTER 8 Switching A network is a set of connected devices. Whenever we have multiple devices, we have the problem of how to connect them to make one-to-one communication possible. One solution is to

More information

ATM Traffic Control Based on Cell Loss Priority and Performance Analysis

ATM Traffic Control Based on Cell Loss Priority and Performance Analysis ENSC 833-3 : NETWORK PROTOCOLS AND PERFORMANCE FINAL PROJECT PRESENTATION Spring 2001 ATM Traffic Control Based on Cell Loss Priority and Performance Analysis Shim, Heung-Sub Shim_hs@hanmail.net Contents

More information

MINSimulate A MULTISTAGE INTERCONNECTION NETWORK SIMULATOR

MINSimulate A MULTISTAGE INTERCONNECTION NETWORK SIMULATOR MINSimulate A MULTISTAGE INTERNNECTION NETWORK SIMULATOR DIETMAR TUTSCH and MARCUS BRENNER Technische Universität Berlin Real Time Systems and Robotics D 18 Berlin, Germany {dietmart,mbrenner}@cs.tu-berlin.de

More information

Circuit Switching and Packet Switching

Circuit Switching and Packet Switching Chapter 10: Circuit Switching and Packet Switching CS420/520 Axel Krings Page 1 Switching Networks Long distance transmission is typically done over a network of switched nodes Nodes not concerned with

More information

FDDI-M: A SCHEME TO DOUBLE FDDI S ABILITY OF SUPPORTING SYNCHRONOUS TRAFFIC

FDDI-M: A SCHEME TO DOUBLE FDDI S ABILITY OF SUPPORTING SYNCHRONOUS TRAFFIC FDDI-M: A SCHEME TO DOUBLE FDDI S ABILITY OF SUPPORTING SYNCHRONOUS TRAFFIC Kang G. Shin Real-time Computing Laboratory EECS Department The University of Michigan Ann Arbor, Michigan 48109 &in Zheng Mitsubishi

More information

InfiniBand SDR, DDR, and QDR Technology Guide

InfiniBand SDR, DDR, and QDR Technology Guide White Paper InfiniBand SDR, DDR, and QDR Technology Guide The InfiniBand standard supports single, double, and quadruple data rate that enables an InfiniBand link to transmit more data. This paper discusses

More information

Multiprocessors Interconnection Networks

Multiprocessors Interconnection Networks Babylon University College of Information Technology Software Department Multiprocessors Interconnection Networks By Interconnection Networks Taxonomy An interconnection network could be either static

More information

Performance of a Switched Ethernet: A Case Study

Performance of a Switched Ethernet: A Case Study Performance of a Switched Ethernet: A Case Study M. Aboelaze A Elnaggar Dept. of Computer Science Dept of Electrical Engineering York University Sultan Qaboos University Toronto Ontario Alkhod 123 Canada

More information

A High Performance ATM Switch Architecture

A High Performance ATM Switch Architecture A High Performance ATM Switch Architecture Hong Xu Chen A thesis submitted for the degree of Doctor of Philosophy at The Swinburne University of Technology Faculty of Information and Communication Technology

More information

Integrating Euro-ISDN with ATM Technology : Interworking Mechanisms and Services Support

Integrating Euro-ISDN with ATM Technology : Interworking Mechanisms and Services Support Integrating Euro-ISDN with ATM Technology : Interworking Mechanisms and Services Support L. Mandalos [1], K. Leonidou [2], C. Andreopoulos [3], J. Drakos [4], S. Koubias [5], G. Papadopoulos [6] [1] Research

More information

A distributed memory management for high speed switch fabrics

A distributed memory management for high speed switch fabrics A distributed memory management for high speed switch fabrics MEYSAM ROODI +,ALI MOHAMMAD ZAREH BIDOKI +, NASSER YAZDANI +, HOSSAIN KALANTARI +,HADI KHANI ++ and ASGHAR TAJODDIN + + Router Lab, ECE Department,

More information

PPP. Point-to-Point Protocol

PPP. Point-to-Point Protocol PPP Point-to-Point Protocol 1 Introduction One of the most common types of WAN connection is the point-to-point connection. Point-to-point connections are used to connect LANs to service provider WANs,

More information

Scalable crossbar network: a non-blocking interconnection network for large-scale systems

Scalable crossbar network: a non-blocking interconnection network for large-scale systems J Supercomput DOI 10.1007/s11227-014-1319-2 Scalable crossbar network: a non-blocking interconnection network for large-scale systems Fathollah Bistouni Mohsen Jahanshahi Springer Science+Business Media

More information

Design of Synchronous NoC Router for System-on-Chip Communication and Implement in FPGA using VHDL

Design of Synchronous NoC Router for System-on-Chip Communication and Implement in FPGA using VHDL Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320 088X IJCSMC, Vol. 2, Issue.

More information

Performance Evaluation of FDDI, ATM, and Gigabit Ethernet as Backbone Technologies Using Simulation

Performance Evaluation of FDDI, ATM, and Gigabit Ethernet as Backbone Technologies Using Simulation Performance Evaluation of FDDI, ATM, and Gigabit Ethernet as Backbone Technologies Using Simulation Sanjay P. Ahuja, Kyle Hegeman, Cheryl Daucher Department of Computer and Information Sciences University

More information

TECHNOLOGY BRIEF. Compaq 8-Way Multiprocessing Architecture EXECUTIVE OVERVIEW CONTENTS

TECHNOLOGY BRIEF. Compaq 8-Way Multiprocessing Architecture EXECUTIVE OVERVIEW CONTENTS TECHNOLOGY BRIEF March 1999 Compaq Computer Corporation ISSD Technology Communications CONTENTS Executive Overview1 Notice2 Introduction 3 8-Way Architecture Overview 3 Processor and I/O Bus Design 4 Processor

More information

NEW TRANSFER METHODS FOR CLIENT-SERVER TRAFFIC IN ATM NETWORKS

NEW TRANSFER METHODS FOR CLIENT-SERVER TRAFFIC IN ATM NETWORKS NEW TRANSFER METHODS FOR CLIENT-SERVER TRAFFIC IN ATM NETWORKS David Lecumberri Kai-Yeung Siu* Paolo Narv6ez Massachusetts Institute of Technology Masayoshi Nabeshima Naoaki Yamanaka NlT Network Service

More information

Designing High-Speed ATM Switch Fabrics by Using Actel FPGAs

Designing High-Speed ATM Switch Fabrics by Using Actel FPGAs pplication Note C105 esigning High-Speed TM Switch Fabrics by Using ctel FPGs The recent upsurge of interest in synchronous Transfer Mode (TM) is based on the recognition that it represents a new level

More information

Literature Survey of nonblocking network topologies

Literature Survey of nonblocking network topologies Literature Survey of nonblocking network topologies S.UMARANI 1, S.PAVAI MADHESWARI 2, N.NAGARAJAN 3 Department of Computer Applications 1 Department of Computer Science and Engineering 2,3 Sakthi Mariamman

More information

INTERCONNECTION NETWORKS LECTURE 4

INTERCONNECTION NETWORKS LECTURE 4 INTERCONNECTION NETWORKS LECTURE 4 DR. SAMMAN H. AMEEN 1 Topology Specifies way switches are wired Affects routing, reliability, throughput, latency, building ease Routing How does a message get from source

More information

Prepared by Agha Mohammad Haidari Network Manager ICT Directorate Ministry of Communication & IT

Prepared by Agha Mohammad Haidari Network Manager ICT Directorate Ministry of Communication & IT Network Basics Prepared by Agha Mohammad Haidari Network Manager ICT Directorate Ministry of Communication & IT E-mail :Agha.m@mcit.gov.af Cell:0700148122 After this lesson,you will be able to : Define

More information

A New Approach to Execution Time Estimations in a Hardware/Software Codesign Environment

A New Approach to Execution Time Estimations in a Hardware/Software Codesign Environment A New Approach to Execution Time Estimations in a Hardware/Software Codesign Environment JAVIER RESANO, ELENA PEREZ, DANIEL MOZOS, HORTENSIA MECHA, JULIO SEPTIÉN Departamento de Arquitectura de Computadores

More information