Dilated Banyan Networks Research Articles

Performance enhancement of 8$$\times$$8 dilated banyan network using crosstalk suppressed GMZI crossbar photonic switches

Performance enhancement of 8$$\times$$8 dilated banyan network using crosstalk suppressed GMZI crossbar photonic switches

Diagnosing crosstalk faults in a class of dilated blocking optical multistage interconnection networks

Optical Multistage Interconnection Networks (OMINs), which are constructed by photonic switches, have been studied extensively as an important interconnecting scheme for communication and parallel computing systems. A basic element of photonic switching network is a 2×2 directional coupler with two inputs and two outputs. A crosstalk occurs, when two signal channels interact with each other, caused by the improper control of voltage, temperature and polarization along with the aging of the material. In this paper, we will focus on a specific architecture called the Dilated Blocking Networks. The characteristic of dilated blocking networks, such as Dilated Omega Network (DON), is that only one possible path can be established between any input-output pair. The two-level diagnosis algorithm is proposed to satisfy the need of this architecture. The first-order crosstalk will be detected and located in the first level. In addition, the number of unused photonic switches grows in Θ( N 2) as the size of network increases in N× N during the diagnosing crosstalk algorithm. By this property, we speed up the test by paralleling two first-order crosstalk faults at the first-level algorithm (we call it as disjoint faults). The second-level algorithm will diagnose the second- or higher-order crosstalk as well as all crosstalks will be diagnosed. Finally, we apply the diagnosing algorithm to other dilated photonic isomorphic topologies, say, Dilated Baseline Network and Dilated Banyan Network.

TDM Hypercube and TWDM Mesh Optical Interconnections

We propose the time division multiplexed hypercube (TDM-cube) and the time/wavelength division multiplexed mesh (TWDM-mesh). The TDM-cube is an extension of the earlier work by Thompson on the dilated slipped banyan network, DSB. While the DSB(N) provides the complete connection among N users in O(N) time via the time division multiplexing, the TDM-cube(N) implements the binary hypercube interconnection among N users in O(log2N) time. The TWDM-mesh(n2) uses a DSB(n), and combines the TDM and WDM. Like the Bus-Mesh, it requires at most 2 hops to send a packet from one node to any other node. The TWDM-mesh has a much higher network throughput than the Bus-Mesh. Both the TDM-cube and TWDM-mesh require only one fixed-wavelength transmitter/receiver per node, and they have a simple column control and dilated operation. The performance in terms of scalability, delay, and throughput is considered.

Evaluation of pipelined dilated banyan switch architectures for ATM networks

In the pipeline banyan (PB), the reservation cycle in the control plane is made several times faster than payload transmission in data plane. This enables pipelining multiple banyans. It is observed that the ratio of throughput to switching delay (service rate) is relatively low in the PB due to the banyan. For this, we present a scalable pipelined asynchronous transfer mode (ATM) switch architecture employing a family of dilated banyan (DB) networks together with their complexity analysis and performance. A DB can be engineered between two extremes: (1) a low-cost banyan with internal and external conflicts, or (2) a high-cost conflict-free fully connected network with multiple outlets. Between the two extremes lies a family of DBs having different switching delays and throughputs. Increasing the dilation degree reduces path conflicts, which produces noticeable increase in service rate due to increase in throughput and decrease in path delay. Compared to PB, the pipelined dilated banyan (PDB) requires smaller number of data planes for the same throughput, or provides higher throughput for a given number of data planes. Simulation of PDB is carded out under uniform traffic and simulated ATM traffic. We study the switch performance while varying the load, buffer size, and number of data planes. To analyze the robustness of the switch, we show that performance is not degradable under ATM traffic with temporal and spatial burstiness generated using the on-off model. The PDB is scalable with respect to service rate and can be engineered with respect to: (1) cell loss rate; (2) hardware resources; (3) size of buffers; (4) switching delays; and (5) delay incurred to higher priority traffic. The PDB can deliver up to 3.5 times the service rate of the PB with only linear increase in hardware cost.

DIRSMIN: a fault-tolerant switch for B-ISDN applications using dilated reduced-stage MIN

We have developed and analyzed a dilated high-performance fault-tolerant fast packet multistage interconnection network (MIN). This new switch, (d,d')-DIRSMIN, uses dilation to improve performance and fault-tolerance of a network. The links at the input and output stages of the dilated banyan-based MIN are rearranged to create multiple routes for each source-destination pair in the network, after removing the first stage in the network. These multiple paths are link- and node-disjoint. This new MIN can provide low packet-loss probability and high reliability with very little hardware overhead, compared to d-dilated banyan networks (BN). Fault tolerance at low latency is achieved by transmitting multiple copies of each input-packet simultaneously using different routes. A multiple-priority scheme allows alternate paths to be explored simultaneously, which results in higher throughput and reliability under both fault-free and faulty conditions. This guarantees that high throughput is maintained even in the presence of a fault. Throughput is analyzed using analytic and simulation methods; this new design has considerably higher performance in the presence of a permanent faulty switching-element (SE) or link, in comparison to dilated networks. Under non-faulty conditions, both analytic and simulation results show that a (d,d)-DIRSMIN performs better than the original dilated BN with the same SE complexity. We analyze the network reliability and show that the new design has superior reliability compared to competing proposals. In particular, this new design is considerably better than the SEN+, the best known thus far.

A universal analytic model for photonic Banyan networks

One of the important considerations in designing waveguide-based photonic switching networks is to avoid crosstalk. Two approaches have been proposed which dilate a network in the space and time domains, respectively, to establish crosstalk-free connections. The space-domain dilation uses more hardware, representing cost in space, while the time-domain dilation uses more rounds (or time slots), representing cost in time. In order to evaluate the space-time tradeoffs involved in these two approaches, an analytical model is developed. We describe a recursive procedure which calculates the probability that a new connection can be established without crosstalk in a Banyan (or dilated Banyan) network by taking into consideration the dependency between traffic distributions at different stages. A Markov process based on such probabilities is then used to determine the average number of rounds needed for a set of one-to-one random connections. The model is applicable to both Banyan and dilated Banyan networks, with either stage or individual control. Simulation results are also obtained and compared to the analytic results. We show that the time-domain approach can achieve better space-time tradeoffs than the space-domain approach. One of the practical implications of this result is that a multiplane Banyan network may be more cost-effective than a dilated Banyan in avoiding crosstalk.

Performance of dilated banyan network with back-pressure mechanism

A dilated banyan network is one solution that can overcome the internal blocking problem in a banyan network. However, tremendous routing capacity is wasted in the dilated banyan network because d − 1 links of each input port in the first stage are unused. In this paper, we propose a dilated banyan network with back-pressure mechanism to fully utilize the wasted routing capacity. The proposed switch has input and output queues, and employs a priority scheme to prevent out-of-sequence. We also design a non-blocking element in order to reduce the hardware complexity of the dilated banyan network. The performance of the proposed switch is analyzed under uniform traffic assumption. Numerical and simulation results show that the proposed switch yields a significant improvement of the maximum throughput as compared to that of the pure dilated banyan network. Moreover, with dilation degree of d = 3, the maximum throughput of about 1 is achieved.

Comparison of two recycle dilated banyan network with output buffers

Two dilated banyan networks with recirculation and deflection routing algorithm are proposed. Without input buffers, the proposed switching fabrics can fully reuse the routing capacity wasted in a pure dilated banyan network. An analytical model of two switching fabrics and a study of packet loss probability are presented.

Performance of dilated banyan network with recirculation

A dilated banyan network with recirculation and a deflection routing algorithm is proposed. In the proposed switch architecture, the routing capacity wasted in a pure dilated banyan network can be fully used. An analytical model of the switch and a study of its throughput and packet loss probability are also presented.