Optical Interconnection Networks Research Articles

A module design of rearrangeable nonblocking double omega optical network using binary optics elements

Omega network plays an important role in all optical communication and optical interconnection networks. In this paper, a novel technology, which binary optics element (micro-blazed grating array) can realize perfect shuffle transform including inverse perfect shuffle and left perfect shuffle, is proposed. Moreover, by a cascade of inverse perfect shuffle and left perfect shuffle, a multistage rearrangeable nonblocking omega network can be constructed. Simultaneously, the bipartition graph algorithm (BGA) is adopted to ascertain the state of node switch in each node stage (straight or crossover connection). At last, a module of the rearrangeable nonblocking omega network which is integrated with polarizing beam-splitter, half-wave plate, micro-blazed grating array, is presented. It can accomplish the functions of 8-channel signal beams’ sorting and switching without routing conflict and blocking, and has advantages of being compact in structure, easy to integrate, efficient in performance etc. Finally, both the theoretical analysis and the experimental result show that this module proposed here may be helpful in free-space optical interconnection network and optical information processing.

Implementation method for a three-dimensional Banyan network in free space

Banyan optical networks play an important role in free-spatial photonic networks and optical communications. Based on previous research on the one-dimensional (1-D) Banyan network, the characteristics and structures of three-dimensional (3-D) Banyan networks are introduced and analyzed. Simultaneously, the experimental module of a 3-D Banyan network, which is integrated with a polarizing beam-splitter, 4×4 micro blazed-grating array plane, half-silvered mirror, 4×4 spatial light modulator, and mirror, is proposed and demonstrated. The 4×4 micro blazed-grating array plane can fulfill the vertical and horizontal connections of the 3-D Banyan network, and the mirror provides the straight connections. The theoretical analysis shows that the experimental setup can accomplish some functions such as optical signal switch, multicast, broadcast, and the 4×4 matrix conversion, and has advantages of compact in structure, low crosstalk, high speed, and efficient performance. Therefore, the designed experimental module of 3-D Banyan network can be implemented in free-spatial optical interconnection networks and optical signal processing.

Optimization of a Switching Node for Optical Multistage Interconnection Networks

In this letter, we demonstrate a 2 times 2 switching node optimized for optical multistage interconnection networks. The optical packet-switched node is improved by making use of comparators with dual-threshold action to regenerate the routing header signal. The switching node is shown to correctly route packets with the presence of glitches in the header information. We employ a hybrid integrated semiconductor optical amplifier in the switching node that reduces packet guard times enabling a 67% increase in the number of stages for large-scale multistage networks.

Building Ultralow-Latency Interconnection Networks Using Photonic Integration

Ultralow-latency interconnection networks have become a necessity in modern high-performance computing systems. recent advances in photonic integration technology are paving the way for a disruptive step in the design of these networks. We present SPINet, an optical interconnection network architecture designed for implementation using photonic integration, providing an end-to-end photonic path while completely avoiding optical buffering. SPINet resolves contentions through message dropping, but facilitates message recovery using a novel physical-layer acknowledgment protocol.

Performance evaluation of the augmented data vortex switch fabric: An all-optical packet switched interconnection network

Modern high-performance computing systems require networks with high capacity, extremely high throughput and low latency in order to pass messages between thousands of processors and memory elements. Optical Interconnection Networks (OIN) offer a potentially viable solution to this requirement. An all-optical packet switched interconnection network called a Data Vortex (DV) switch has already been proposed by Yang et al. for the purpose of large scale photonic interconnections. For any interconnection network, fault tolerance and reliability are crucial issues, evaluation of which lacked attention for the case of the DV switch. In our earlier work we therefore presented the results for fault tolerance and reliability analysis of the primary DV switch. We also proposed a new Augmented Data Vortex (ADV) switch fabric, to improve the fault tolerance of the primary DV switch. The performance as regards fault tolerance of the ADV switch was computed and detailed results were obtained. In this paper, performance of ADV is investigated with reference to parameters such as latency and injection ratio (throughput) by means of numerical simulations. A uniform random traffic model has been used for the performance evaluation. The results obtained are compared with the results reported for the DV switch. The results show that the ADV switch with enhanced fault tolerance also improves the performance regarding latency. For same switch sizes (i.e. the same number of angles A , and height H ) the injection ratios (throughput) for the DV and the ADV switches are comparable. Hence it can serve as a suitable candidate for high performance computing.

Optimal hypercube simulation on the partitioned optical passive stars network

Partitioned Optimal Passive Stars network, POPS(d,g), is an optical interconnection network of N processors (N=dg) with g 2 optical passive star couplers. In this network, there are g groups of d processors each and the g 2 couplers are used for connecting each group with each of the groups, including itself. In this paper, we present a technique for optimally simulating a frequently arising hypercube communication pattern on this network for all combinations of values of d and g. Specifically, we show that one-hop movements on the hypercube along the same dimension can be simulated on the POPS(d,g) network in $\lceil \frac{d}{g}\rceil$ slots for d?g and in 2 slots for d=g.

Optical implementation of (3, 3, 2) regular rectangular CC-Banyan optical network

CC-Banyan network plays an important role in the optical interconnection network. Based on previous reports of (2, 2, 3) the CC-Banyan network, another rectangular-Banyan network, i.e. (3, 3, 2) rectangular CC-Banyan network, has been discussed. First, according to its construction principle, the topological graph and the routing rule of (3, 3, 2) rectangular CC-Banyan network have been proposed. Then, the optically experimental setup of (3, 3, 2) rectangular CC-Banyan network has been designed and achieved. Each stage of node switch consists of phase spatial light modulator (PSLM) and polarizing beam-splitter (PBS), and fiber has been used to perform connection between adjacent stages. PBS features that s-component (perpendicular to the incident plane) of the incident light beam is reflected, and p-component (parallel to the incident plane) passes through it. According to switching logic, under the control of external electrical signals, PSLM functions to control routing paths of the signal beams, i.e. the polarization of each optical signal is rotated or not rotated 90° by a programmable PSLM. Finally, the discussion and analysis show that the experimental setup designed here can realize many functions such as optical signal switch and permutation. It has advantages of large number of input/output-ports, compact in structure, and low energy loss. Hence, the experimental setup can be used in optical communication and optical information processing.

Analyzing the performance of optical multistage interconnection networks with limited crosstalk

Analytical modeling techniques can be used to study the performance of optical multistage interconnection network (OMIN) effectively. MINs have assumed importance in recent times, because of their cost-effectiveness. An N?N MIN consists of a mapping from N processors to N memories, with log??2 N stages of 2?2 switches with N/2 switches per stage. The interest is on the study of the performance of unbuffered optical multistage interconnection network using the banyan network. The uniform reference model approach is assumed for the purpose of analysis. In this paper the analytical modeling approach is applied to an N?N OMIN with limited crosstalk (conflicts between messages) up to (log??2 N?1). Messages with switch conflicts satisfying the constraint of (log??2 N?1) are allowed to pass in the same group, but in case of a link conflict, the message is routed in a different group. The analysis is performed by calculating the bandwidth and throughput of the network operating under a load l and allowing random traffic and using a greedy routing strategy. A number of equations are derived using the theory of probability and the performance curves are plotted. The results obtained show that the performance of the network improves by allowing limited crosstalk in the network.

The Data Vortex, an All Optical Path Multicomputer Interconnection Network

All optical path interconnection networks employing dense wavelength division multiplexing can provide vast improvements in supercomputer performance. However, the lack of efficient optical buffering requires investigation of new topologies and routing techniques. This paper introduces and evaluates the data vortex optical switching architecture which uses cylindrical routing paths as a packet buffering alternative. In addition, the impact of the number of angles on the overall network performance is studied through simulation. Using optimal topology configurations, the data vortex is compared to two existing switching architectures-butterfly and omega networks. The three networks are compared in terms of throughput, accepted traffic ratio, and average packet latency. The data vortex is shown to exhibit comparable latency and a higher acceptance rate (2times at 50 percent load) than the butterfly and omega topologies

The augmented data vortex switch fabric: An all-optical packet switched interconnection network with enhanced fault tolerance

Optical Multistage Interconnection Networks (OMINs) are capable of transmitting terabits of bandwidth per second, and they have been considered as possible solutions to the electronic communications bottleneck in interconnection networks. A novel architecture, the Data Vortex (DV) switch, has been proposed by Yang et al., as a scalable, ultra low latency, ultra high capacity, high throughput, low cross-talk and low BER, all-optical packet switching fabric that is a suitable candidate for use as an OMIN. For any interconnection network, its fault tolerance and reliability are crucial issues, which have lacked attention up to now in the case for a DV switch. In this paper we, therefore, present results of fault tolerance and reliability analysis of the primary DV switch, and propose (1) a new Augmented Data Vortex (ADV) switch fabric, to improve the fault tolerance of the primary DV switch. (2) The labelling and a numbering scheme, with detailed interconnections of nodes for the ADV switch is given. (3) A new self-routing procedure and a priority scheme for distributed control signalling in the ADV switch have been given. (4) For the first time, conversion of the 3-dimensional switch to an equivalent chained-MIN model, has been given, which is more suitable for later analysis of fault tolerance. (5) A multiplexing scheme at input ports and output ports which further enhances the fault tolerance of the ADV switch has been given. (6) Computation has been done of the reliability and fault tolerance of the new architecture via an analytical model. (7) Finally, comparison of the ADV switch architecture with the primary architecture (DV) in view of fault tolerance and reliability has been given, and hardware complexity and cost effectiveness have been studied.

Polarization-Dependent Gain in SOA-Based Optical Multistage Interconnection Networks

The small polarization dependence (< 1 dB) of optical components becomes significant in optical multistage interconnection networks. The cumulative effect can ultimately limit physical layer scalability by changing the maximum number of internal nodes that optical packets can traverse error free. It is shown that for nodes based on commercial semiconductor optical amplifier (SOA) switches with polarization-dependent gains of less than 0.35 dB, the maximum number of cascaded nodes changes by as much as 20 nodes, depending on both the packet wavelength and its state of polarization. This deviation in the number of nodes could correspond to a 100-fold decrease in the number of interconnected ports of an optical interconnection network such as the data vortex. This dramatic effect is explained in terms of optical signal-to-noise ratio degradation due to accumulated amplified spontaneous emission noise originating from the SOA device in the node

Impact of number of angles on the performance of the data vortex optical interconnection network

Reducing communication latency in multiprocessor interconnection networks can increase system performance on a broad range of applications. The data vortex photonic network reduces message latency by utilizing all-optical end-to-end transparent links and deflection routing. Cylinders replace node storage for buffering messages. The cylinder circumference (measured as number of angles) has a significant impact on the message acceptance rate and average message latency. A new symmetric mode of usage for the data vortex is discussed in which a fraction of the angles is used for input/output (I/O), and the remainder is used for "virtual buffering" of messages. For single-angle injection, six total angles provide the best performance. Likewise, the same ratio of 5 : 1 purely routing nodes versus I/O nodes is shown to produce greater than 99% acceptance, under normal loading conditions for all other network sizes studied. It is shown that for a given network I/O size, a shorter height and wider circumference data vortex organization provides acceptable latency with fewer total nodes than a taller but narrower data vortex. The performance versus system cost is discussed and evaluated, and the 5 : 1 noninjection-to-injection angle ratio is shown to be cost effective when constructing a system in current optical technology.

Bit-parallel message exchange and data recovery in optical packet switched interconnection networks

Multiwavelength optical messages encoded in a bit-parallel fashion are successfully routed through five switching nodes of a 12-port optical packet switching interconnection network. The data payloads are entirely recovered and processed at the destination node using an embedded clock signal with a measured clock-to-data skew tolerance window of 150 ps.

A Novel Multistage Network Architecture with Multicast and Broadcast Capability

In this paper, a new class of optical multistage interconnection network (MIN) architecture is presented, which is constructed utilizing a modularization approach rather than the traditional recursive or fixed exchange pattern methods. The modified architecture consists of an input module, an output module, two point-to-point (PTP) modules, and one modified multicast/broadcast (M/B) module(s). We also implement the multicast/broadcast module with WDM technique, which reduces the hardware cost required for multicast and the re-computation cost for a new connection. We show that it has the best application flexibility and provides multicast function without imposing significant negative impacts on the whole network. A new multicast connection pattern is also proposed in this paper, which makes it practical and economical to apply amplification in space-division networks. Compared with existing multicast architectures, this new architecture with Dilated Benes PTP modules has better performance in terms of system SNR, the number of switch elements, and system attenuation in point-to-point connections. Moreover, the multicast/broadcast module adopts wavelength division multiplexing (WDM) technique to increase its multicast/broadcast assignment. As a result, given m available distinguished wavelengths, one M/B module can support at most m M/B requests at the same time. The new proposed M/B module with WDM is more practical and economical to apply amplification in space-division networks.

A Class of Benes-Based Optical Multistage Interconnection Networks for Crosstalk-Free Realization of Permutations

Vertical stacking is a novel technique for creating nonblocking (crosstalk-free) optical multistage interconnection networks (MINs). In this paper, we propose a new class of optical MINs, the vertically stacked Benes (VSB) networks, for crosstalk-free realization of permutations in a single pass. An N x N VSB network requires at most O(N log N) switching elements, which is the same as the Benes network, and much lower overall hardware cost than that of the existing optical MINs built on the combination of horizontal expansion and vertical stacking of banyan networks, to provide the same crosstalk-free permutation capability. Furthermore, the structure of VSB networks provides a more flexible way for constructing optical MINs because they give more choices in terms of the number of stages used in an optical MIN. We also present efficient algorithms to realize crosstalk-free permutations in an N x N VSB network in time O(N log N), which matches the same bound as required by the reported schemes.

Physical Layer scalability of WDM optical packet interconnection networks

The physical layer scalability of a packet-switched optical interconnection network utilizing semiconductor optical amplifier (SOA) switch elements is investigated experimentally and with numerical modeling. Optical packets containing payloads of multiple wavelength-division-multiplexing (WDM) channels are propagated through cascaded SOA-based switching nodes in a recirculating test-bed environment. Experiments show that bit-error rates (BERs) below 10/sup -9/ can be maintained through 58 switching nodes for the entire eight-channel 10-Gb/s-per-channel payload distributed over 24.2 nm of the C-band. When the packet payload consists of a single 10-Gb/s channel, 98 node hops can be traversed before a BER of 10/sup -9/ is exceeded. In conjunction with the experiments, a novel phenomenological modeling technique is developed in order to forecast the scalability of SOA-based WDM packet interconnection networks. This technique is shown to yield results that correlate well with the experimental data. These investigations are presented as predictors of the physical limitations of large-scale WDM packet-switched networks.

On cascades of resonators for high-bandwidth integrated optical interconnection networks

The power penalty characteristics of high-speed optical signals transmitted through a variety of filters based on multiple microring resonator devices are analyzed by numerical simulation. The technique used here has been verified with single-ring experimental measurements. Butterworth and Chebyshev filters are investigated, as are serial cascades of resonant devices. Although the power penalty is generally not prohibitive, it is a parameter which cannot be ignored for the design of complex high-bandwidth photonic interconnect systems that utilize microring resonators as filters and switches.

Optimization of multiple-stage optical interconnection networks

An analysis of the cost and complexity of multiple-stage optical interconnection networks is presented. Because of the high cost of photonic switching elements from which these networks are composed, the radix (degree of the switching nodes) of a simple banyan network is important in determining total network cost. For most switching node cost models, it is shown that 3 /spl times/ 3 switching nodes can actually be more efficient than 2 /spl times/ 2 ones.

Design of Optical Rearrangeable Nonblocking MINs Under Various Crosstalk Constraints

Optical interconnection networks suffer from the intrinsic crosstalk problem that should be overcome to make them work properly. Vertical stacking of optical banyan networks is a novel scheme for constructing nonblocking optical multistage interconnection networks (MINs). Rearrangeable nonblocking optical MINs are feasible since they have lower complexity than their strictly nonblocking counterparts. In this paper, we determine the sufficient condition for these MINs to be rearrangeable nonblocking under various crosstalk constraints. We show how the crosstalk constraint affects the design of rearrangeable nonblocking MINs and demonstrate that these networks can tolerate a stricter crosstalk constraint without increasing their hardware complexity significantly. The results in the paper will be useful in designing optical MINs with reasonable hardware cost and crosstalk level.

ROUTING IN OPTICAL MULTISTAGE NETWORKS WITH LIMITED CROSSTALK USING ANT COLONY OPTIMIZATION

Ant Colony Optimization (ACO) techniques can be successfully implemented to solve many combinatorial optimization problems. After the traveling salesman problem was successfully solved using the ACO technique, other researchers have concentrated on solving other problems like the quadratic assignment and the job-shop scheduling problems using the same technique. In this paper we use the ACO technique to route messages through an N × N Optical Multistage Interconnection Network (OMIN) allowing upto ' C ' limited crosstalk's (conflicts between messages within a switch) where ' C ' is a technology driven parameter and is always less than log 2 N . Messages with switch conflicts satisfying the crosstalk constraint are allowed to pass in the same group, but if there is any link conflict, then messages have to be routed in a different group. The focus is to minimize the number of passes required for routing allowing upto ' C ' limited crosstalks in an N × N optical network. This routing problem is an NP-hard problem. In this paper we show how the ACO technique can be applied to the routing problem and compare the performance of the ACO technique to that of the degree-descending algorithm using simulation techniques. Finally the lower bound estimate on the minimum number of passes required is calculated and compared to the results obtained using the two algorithms discussed. The results obtained show that the ACO technique performs better than the degree-descending algorithm and is quite close to optimal algorithms to the problem.