An all-optical long-distance multi-Gbytes/s bit-parallel WDMsingle-fiber link

An all-optical long-distance (>30 km) bit-parallel wavelength division multiplexed (WDM) single-fiber link with 12 bit-parallel channels having 1 Gbyte/s capacity has been designed. That system functionally resembles an optical fiber ribbon cable, except that all the bits pass on one fiber-optic waveguide. This single-fiber bit parallel wavelength link can be used to extend the (speed x distance) product of emerging cluster computer networks, such as, the MyriNet, SCI, Hippi-6400, ShuffleNet, etc. Here, the detailed design of this link using the commercially available Corning DS (dispersion-shifted) fiber is given. To demonstrate the viability of this link, two WDM channels at wavelengths 1530 and 1545 nm carrying 1 ns pulses on each channel were sent through a single 25.2-km long Corning DS fiber. The walkoff was 200 ps, well within the allowable setup and hold time for the standard ECL logic which is 350 ps for a bit period of 1 ns. This result implies that 30 bit-parallel beams spaced 1 nm apart between 1530-1560 nm, each carrying 1 Gbits/s signal, can be sent through a 25.2-km Corning DS fiber carrying information at a 30 Gb/s rate     

Wavelength reuse for efficient packet-switched transport in an AWG-based metro WDM network

Metro wavelength-division multiplexed (WDM) networks play an important role in the emerging Internet hierarchy; they interconnect the backbone WDM networks and the local-access networks. The current circuit-switched SONET/synchronous digital hierarchy (SDH)-over-WDM-ring metro networks are expected to become a serious bottleneck-the so-called metro gap-as they are faced with an increasing amount of bursty packet data traffic and quickly increasing bandwidths in the backbone networks and access networks. Innovative metro WDM networks that are highly efficient and able to handle variable-size packets are needed to alleviate the metro gap. In this paper, we study an arrayed-waveguide grating (AWG)-based single-hop WDM metro network. We analyze the photonic switching of variable-size packets with spatial wavelength reuse. We derive computationally efficient and accurate expressions for the network throughput and delay. Our extensive numerical investigations-based on our analytical results and simulations-reveal that spatial wavelength reuse is crucial for efficient photonic packet switching. In typical scenarios, spatial wavelength reuse increases the throughput by 60% while reducing the delay by 40%. Also, the throughput of our AWG-based network with spatial wavelength reuse is roughly 70% larger than the throughput of a comparable single-hop WDM network based on a passive star coupler (PSC).     

Advances in multichannel MultiGbytes/s bit-parallel WDM singlefiber link

For ultra-high-speed single media parallel interconnects, an all optical single fiber WDM format of transmitting parallel bits rather than a fiber ribbon format-where parallel bits are sent through corresponding parallel fibers in a ribbon format, can be the media of choice. Here, we discuss the realization of a multi-km×Gb/s bit-parallel WDM (BP-WDM) single fiber link. The distance-speed product of this single fiber link is more than several orders of magnitude higher than that of a fiber ribbon link. The design of a 12 b parallel channels WDM system operating at 1 Gb/s per channel rate through a single fiber is first presented. Experimental results for a two channel system operating at that rate are given. Further improvement of distance-speed product for the BP-WDM link can be obtained with JPL's newly developed 20 Gb/s per channel laser diode array transmitter. Also, new computer simulation results on how a large amplitude co-propagating pulse may induce pulse compression on all the co-propagating data pulses, thereby improving the shaping of these pulses for a WDM system, are presented and discussed. The existence of WDM solitons is also shown     

Long-distance parallel data link using WDM transmission withbit-skew compensation

This paper studies the advantages and disadvantages of using a parallel link based on wavelength division multiplexing (WDM) for long-distance data transmission through a single-mode fiber as an alternative to a high-speed serial link. A long-distance optical link operating near the 1.55 μm or 0.85 μm wavelength regions suffers the large group-delay dispersion of a standard fiber. On these wavelengths, the skew between bit-channels is the major problem for wordwide WDM transmission. We propose a method to compensate for bit skew greater than the bit time, and analyze its performance gain in terms of the increase in the maximum data throughput achievable. With bit-skew compensation, the wordwide parallel link achieves a maximum aggregate data rate that is greater than what a serial link can obtain for the same link length     

RINGOSTAR: an evolutionary AWG-based WDM upgrade of optical ring networks

The paper describes the study of the multichannel upgrade of IEEE Standard 802.17 Resilient Packet Ring (RPR) in particular and optical single-channel ring networks in general by making use of wavelength-division multiplexing (WDM). The paper describes and discusses a novel evolutionary multichannel upgrade approach that uses WDM on a central passive arrayed-waveguide grating (AWG)-based single-hop star network rather than on the ring. The AWG-based star subnetwork allows for a dramatically larger spatial reuse of WDM wavelength channels than conventional upgrades of optical single-channel ring networks that use WDM on the ring where all nodes need to be WDM upgraded. In the resultant hybrid optical ring-star network, termed RINGOSTAR, only a subset of the nodes are required to be WDM upgraded with a single additional tunable transceiver in order to improve the performance dramatically. The novel concept of proxy stripping is also introduced, which is used to route ring traffic on single-hop short cuts across the star subnetwork rather than the peripheral ring, resulting in a dramatically increased spatial reuse factor on the ring. By means of analysis, the performance of RINGOSTAR is investigated in terms of mean hop distance, spatial reuse, and capacity. The findings show that RINGOSTAR significantly outperforms unidirectional, bidirectional, and meshed WDM rings. Finally, the tradeoffs of RINGOSTAR are addressed.     

Achieving 100% Throughput in Reconfigurable Optical Networks

We study the maximum throughput properties of dynamically reconfigurable optical network architectures having wavelength and port constraints. Using stability as the throughput performance metric, we outline the single-hop and multi-hop stability regions of the network. Our analysis of the stability regions is a generalization of the BvN decomposition technique that has been so effective at expressing any stabilizable rate matrix for input-queued switches as a convex combination of service configurations. We consider generalized decompositions for physical topologies with wavelength and port constraints. For the case of a single wavelength per optical fiber, we link the decomposition problem to a corresponding Routing and Wavelength Assignment (RWA) problem. We characterize the stability region of the reconfigurable network, employing both single-hop and multi-hop routing, in terms of the RWA problem applied to the same physical topology. We derive expressions for two geometric properties of the stability region: maximum stabilizable uniform arrival rate and maximum scaled doubly substochastic region. These geometric properties provide a measure of the performance gap between a network having a single wavelength per optical fiber and its wavelength-unconstrained version. They also provide a measure of the performance gap between algorithms employing single-hop versus multi-hop electronic routing in coordination with WDM reconfiguration.      

Optimal all-to-all broadcast in WDM optical networks with breakdown or power-off transceivers

All-to-all broadcast is an interesting special case of the packet transmission scheduling in which every pair of nodes has exactly one packet to be transferred. This paper considers the all-to-all broadcast problem in wavelength division multiplexed (WDM) optical star network with some breakdown or power-off transceivers. For reaching high data transmission rates, we will focus the problem on the all-optical scheduling where the traffic reaches its destination in single-hop without being converted to electronic form. Each transmitter is tunable with an associated tuning delay and each receiver is fixed-tuned to one of available wavelengths. In this model, we study two kinds of all-to-all broadcast problems depending on whether each node transmits packets to all nodes including or except itself. We identify the lower bound of the scheduling length for each kind of problems and propose single-hop scheduling algorithms to find the optimal solution in both terms of arbitrary number of wavelengths and value of tuning latency.     

波长重用的单跳星形WDM网络

波分复用（ｗａｖｅｌｅｎｇｔｈｄｉｖｉｓｉｏｎｍｕｌｔｉｐｌｅｘｉｎｇ，ＷＤＭ）提供了充分利用光纤通信带宽的有效途径，但是ＷＤＭ中的独立波长数目十分有限，而普通的无源星形ＷＤＭ网络中每个时刻每个波长只能有一个用户发送信息，难以支持大量用户。为此，本文提出了一种新型的ＷＤＭ网络ＷＲＳＮ（ｗａｖｅｌｅｎｇｔｈｒｅｕｓａｂｌｅｓｔａｒｎｅｔｗｏｒｋ）。在ＷＲＳＮ中每个时刻每个波长可以同时有两个用户发送信息。分析和模拟结果表明ＷＲＳＮ网络吞吐量高，分组时延小。具有很高的实用价值。     

Analysis and Design of Low-Cost Bit-Serial Architectures for Motion Estimation in H.264/AVC

Variable block-size motion estimation (VBSME) process occupies a major part of computation of an H.264 encoder, which is usually accelerated by bit-parallel hardware architectures with large I/O bit width to meet real-time constrains. However, such kind of architectures increase the area overhead and pin count, and therefore will not be suitable for area-constrained electronic consumer designs such as small portable multimedia devices. This paper addresses this problem by proposing two area efficient least significant bit (LSB) bit-serial architectures with small pin numbers. Both designs take advantage of data reusing technique in different ways for sum of absolute differences (SAD) computation and reading reference pixels, leading to a considerable reduction of memory bandwidth. The first architecture propagates the partial SAD and sum results and broadcasts the reference pixel rows whereas the second design reuse the SAD of small blocks and has a reconfigurable reference buffer leading to a better memory bandwidth when using hardware parallelism. The proposed designs benefit from several optimization techniques including an efficient serial absolute difference architecture, word length reduction by parallelism, bit truncation, mode filtering, and macroblock (MB) level subsampling, which significantly enhance their performances in terms of silicon area, throughput, latency, and power consumption. The first and second designs can support full search VBSME of 720?×?480 video with 30 frames per second (fps), two reference frames, and [?16, 15] search range at a clock frequency of 414 MHz with 29.28 k and 31.5 k gates, respectively.     

WDM coherent optical star network

The results obtained with a fiber-optical star network using densely-spaced wavelength division multiplexing (WDM) and heterodyne detection techniques are reported. The system consists of three lasers transmitting at optical frequencies around 234000 GHz, spaced at a frequency interval of 300 MHz. The lasers are frequency-shift-key (FSK) modulated at 45 Mb/s. A 4×4 optical star coupler combines the three optical signals. The WDM signals received from one of the four outputs of the star coupler are demultiplexed by a heterodyne receiver. The minimum received optical power needed to obtain a bit-error rate of 10^-9 is -61 dBm or 113 photon/bit, which is 4.5 dB from the shot noise limit. The degradation caused by co-channel interference was measured and found to be negligible when the channels, modulated at 45 Mb/s, are spaced by more than 130 MHz in the IF domain. These results indicate that a WDM coherent optical star network of this type has a potential throughput of 4500 Gb/s     

Systolic and Non-Systolic Scalable Modular Designs of Finite Field Multipliers for Reed–Solomon Codec

In this paper, we present efficient algorithms for modular reduction to derive novel systolic and non-systolic architectures for polynomial basis finite field multipliers over $GF(2^{m})$ to be used in Reed–Solomon (RS) codec. Using the proposed algorithm for unit degree reduction and optimization of implementation of the logic functions in the processing elements (PEs), we have derived an efficient bit-parallel systolic design for finite field multiplier which involves nearly two-thirds of the area-complexity of the existing design having the same time-complexity. The proposed modular reduction algorithms are also used to derive efficient non-systolic serial/parallel designs of field multipliers over $GF(2^{8})$ with different digit-sizes, where the critical path and the hardware-complexity are further reduced by optimizing the implementation of modular reduction operations and finite field accumulations. The proposed bit-serial design involves nearly 55% of the minimum of area, and half the minimum of area-time complexity of the existing bit-serial designs. Similarly, the proposed digit-serial/parallel designs involve significantly less area, and less area-time complexities compared with the existing designs of the same digit-size. By parallel modular reduction through multiple degrees followed by appropriate logic-level sub-expression sharing; a hardware-efficient regular and modular form of a balanced-tree bit-parallel non-systolic multiplier is also derived. The proposed bit-parallel non-systolic pipelined design involves less than 65% of the area and nearly two-thirds of the area-time complexity of the existing bit-parallel design for a RS codec, while the non-pipelined form offers nearly 25% saving of area with less time-complexity.      

Demonstration of timing skew compensation for bit-parallel WDM datatransmission with picosecond precision

We demonstrate transmission of seven wavelength-division-multiplexed (WDM) bit-parallel channels with a total of 15-nm spectral span over a 2.5-km standard single-mode fiber/dispersion-compensating fiber link with less than 3-ps timing skew. The synchronized WDM channels are generated by spectrally slicing pulses from a single femtosecond fiber laser using a femtosecond pulse shaper. The small residual timing skew arises from the residual dispersion slope of the link. We measure a dispersion slope of D'=0.017 ps/km/mn², which is roughly four times less than for an equivalent length of dispersion-shifted fiber. Our work shows that the dispersion-compensating fiber technique could significantly reduce the timing skew for WDM bit-parallel transmission over a several-kilometer fiber link     

A time optimal wavelength rerouting algorithm for dynamic trafficin WDM networks

In this paper, we consider wavelength rerouting in wavelength routed wavelength division multiplexed (WDM) networks with circuit switching, wherein lightpaths between source-destination pairs are dynamically established and released in response to a random pattern of arriving connection requests and connection holding times. The wavelength continuity constraint imposed by WDM networks leads to poor blocking performance. Wavelength rerouting is a viable and cost effective mechanism that ran improve the blocking performance by rearranging certain existing lightpaths to accommodate a new request. Recently, a rerouting scheme called “parallel move-to-vacant wavelength retuning (MTV-WR)” with many attractive features such as shorter disruption period and simple switching control, and a polynomial time rerouting algorithm, for this scheme, to minimize the weighted number of rerouted lightpaths have been proposed. This paper presents a time optimal rerouting algorithm for wavelength-routed WDM networks with parallel MTV-WR rerouting scheme. The algorithm requires only O(N²W) time units to minimize the weighted number of existing lightpaths to be rerouted, where N is the number of nodes in the network and W is the number of wavelength channels available on a fiber link. Our algorithm is an improvement over the earlier algorithm proposed in that it requires O(N³W+N²W²) time units, which is not time optimal. The simulation results show that our algorithm improves the blocking performance considerably and only very few lightpaths are required to be rerouted per rerouting. It is also established through simulation that our algorithm is faster than the earlier rerouting algorithm by measuring the time required for processing connection requests for different networks     

The AWG/spl par/PSC network:a performance-enhanced single-hop WDM network with heterogeneous protection

Single-hop wavelength-division-multiplexing (WDM) networks based on a central passive star coupler (PSC) or arrayed-waveguide grating (AWG) hub have received a great deal of attention as promising solutions for the quickly increasing traffic in metropolitan and local area networks. These single-hop networks suffer from a single point of failure: if the central hub fails, then all network connectivity is lost. To address this single point of failure in an efficient manner, we propose a novel single-hop WDM network, the AWG/spl par/PSC network. The AWG/spl par/PSC network consists of an AWG in parallel with a PSC. The AWG and PSC provide heterogeneous protection for each other; the AWG/spl par/PSC network remains functional when either the AWG or the PSC fails. If both AWG and PSC are functional, the AWG/spl par/PSC network uniquely combines the respective strengths of the two devices. By means of analysis and verifying simulations we find that the throughput of the AWG/spl par/PSC network is significantly larger than the total throughput obtained by combining the throughput of a stand-alone AWG network with the throughput of a stand-alone PSC network. We also find that the AWG/spl par/PSC network gives over a wide operating range a better throughput-delay performance than a network consisting of either two load sharing PSCs in parallel or two load sharing AWGs in parallel.     

Efficient sequencing techniques for variable-length messages in WDMnetworks

Message sequencing and channel assignment are two important issues that need to be addressed when scheduling variable-length messages in a wavelength division multiplexing (WDM) network. Channel assignment addresses the problem of choosing an appropriate data channel via which a message is transmitted to a node. This problem has been addressed extensively in the literature. On the other hand, message sequencing which addresses the order in which messages are sent, has rarely been addressed. In this paper, we propose a set of scheduling techniques for single-hop WDM passive star networks, which address both the sequencing aspect and the assignment aspect of the problem. In particular, we develop two priority schemes for sequencing messages in a WDM network in order to increase the overall performance of the network. We evaluate the proposed algorithms, using analytical modeling and extensive discrete event simulations, by comparing their performance with state-of-the-art scheduling algorithms that only address the assignment problem. We find that significant improvement in performance can be achieved using our scheduling algorithms where message sequencing and channel assignment are simultaneously taken into consideration. This suggests that, when scheduling messages in WDM networks, one has to consider message sequencing, as well as channel assignment. As a result, we anticipate that this research will open new directions into the problem of on-line scheduling in WDM networks     

Dynamic scheduling protocol for variable-sized messages in aWDM-based local network

In a single-hop star network based on wavelength division multiplexing (WDM), a protocol is needed for the transmitter and receiver to coordinate message transmission. This paper proposes a dynamic scheduling protocol which can efficiently support variable-sized messages, where a control channel is used to coordinate transmissions on data channels. The protocol does not require any global information. Therefore, it can operate independently of the change of the number of nodes, and any new node can join the network at any time without requiring network initialization. Moreover, with the protocol, one can avoid data channel and destination conflicts. The protocol is analyzed with a finite population model and the throughput-delay characteristics are investigated as performance measures     

High-speed data transmission on an optical fiber using a byte-wideWDM system

The advantages and problems of using wavelength division multiplexing (WDM) to transmit byte-wide data in parallel through a single-mode optical fiber are studied. The principle problem which is particular to byte-wide transmission is shown to be bit skew caused by group delays of the different transmission wavelengths. The aggregate bit rate of the byte-wide link is shown to be equal to the aggregate bit rate of the serial link for all byte sizes     

Efficient VLSI digital logarithmic codecs

N bit digital words can be logarithmically encoded and compressed to a word length of (log/sub 2/n+m-1) bit maintaining a relative accuracy of m bit over (n-m) octaves of signal level. A bit-serial VLSI coder is reported, which requires little more than a log/sub 2/n counter and an output register and it has a latency of one wordlength. The bit-parallel coder can be built with less than n/sup 2/ transistors and has less than n/4 gate delays. The decoder has similar properties and it expands the logarithm to an antilogarithm with n bit of dynamic range. Using these codecs, digital multiplication, division, powers and roots are reduced to additions, subtractions and shifts, respectively.<>     

波分复用OCDMA系统的性能分析

分析了波分复用(WDM)光码分多址(OCDMA)系统的归一吞吐量性能。当同时用户数均匀分配到不同的波长时,得到了WDM OCDMA系统归一化吞吐量性能的上界;当同时用户数尽量分配到同一个波长时,得到了WDM OCDMA系统归一化吞吐量性能的下界。在所有用户均匀分配到不同波长信道的条件下,比较了WDM OCDMA与多波长(MW)OCDMA系统的归一化吞吐量性能。结果表明,当负载较小时,两者的性能基本相当;当负载较大时,WDM 0CDMA的性能优于MW OCDMA系统。同时,WDM OCDMA的归一化吞吐量峰值高于MW OCDMA系统的归一化吞吐量峰值。     

An adaptive congestion-aware routing algorithm based on network load for wireless routers in wireless network-on-chip

Wireless Network-on-Chip (WiNoC) is regarded as one of the promising alternative approaches for sorting out the issues of latency and power consumption in the conventional Network-on-Chip (NoC). Despite the additional bandwidth of wireless channels on a chip, wireless routers (WRs) are prone to congestion in WiNoC due to the limited number of wireless channels on a chip and the shared use of these channels among all the cores. In this paper, an adaptive congestion-aware routing algorithm consistent with traffic load is proposed for solving the congestion problem of WRs. The proposed algorithm selects source-destination pairs with the longest wired hop distance for using wireless channels. The number of selected packets is determined based on the wireless channel bandwidth and the network traffic load. Simulation results show up to 65% latency improvement, 16% wired/wireless link utilization improvement and a saturation throughput increase of approximately 11%.