MSONoC: a non-blocking optical interconnection network for inter cluster communication

Electric router is widely used for multi-core system to interconnect each other. However, with the increasing number of processor cores, the probability of communication conflict between processor cores increases, and the data delay increases dramatically. With the advent of optical router, the traditional electrical interconnection mode has changed to optical interconnection mode. In the packet switched optical interconnection network, the data communication mechanism consists of 3 processes: link establishment, data transmission and link termination, but the circuit-switched data transmission method greatly limits the utilization of resources. The number of micro-ring resonators in the on-chip large-scale optical interconnect network is an important parameter affecting the insertion loss. The proposed λ-route, GWOR, Crossbar structure has a large overall network insertion loss due to the use of many micro-ring resonators. How to use the least micro-ring resonator to realize non-blocking communication between multiple cores has been a research hotspot. In order to improve bandwidth and reduce access latency, an optical interconnection structure called multilevel switching optical network on chip(MSONoC) is proposed in this paper. The broadband micro-ring resonators(BMRs) are employed to reduce the number of micro-ring resonators(MRs) in the network, and the structure can provide the service of non-blocking point to point communication with the wavelength division multiplexing(WDM) technology. The results show that compared to λ-route, GWOR, Crossbar and the new topology structure, the number of micro-ring resonators of MSONoC are reduced by 95.5%, 95.5%, 87.5%, and 60% respectively. The insertion loss of the minimum link of new topology, mesh and MSONoC structure is 0.73 dB, 0.725 dB and 0.38 dB.

Edge computing oriented virtual optical network mapping scheme based on fragmentation prediction

As edge computing services soar,the problem of resource fragmentation situation is greatly worsened in elastic optical networks(EON).Aimed to solve this problem,this article proposes the fragmentation prediction model that makes full use of the gate recurrent unit(GRU)algorithm.Based on the fragmentation prediction model,one virtual optical network mapping scheme is presented for edge computing driven EON.With the minimum of fragmentation degree all over the whole EON,the virtual network mapping can be successively conducted.Test results show that the proposed approach can reduce blocking rate,and the supporting ability for virtual optical network services is greatly improved.

Ferroelectric Liquid Crystal Gates and Optical Computing

The surface stabilized ferroelectric liquid crystal device configuration and ferroelectric liquid crystal gates are described.The liquid crystal electrooptical gates have numerous applications,including optical computation,optodigital circuits,and optical communication networks.

A review:Photonics devices,architectures,and algorithms for optical neural computing

The explosive growth of data and information has motivated various emerging non-von Neumann computational approaches in the More-than-Moore era.Photonics neuromorphic computing has attracted lots of attention due to the fascinating advantages such as high speed,wide bandwidth,and massive parallelism.Here,we offer a review on the optical neural computing in our research groups at the device and system levels.The photonics neuron and photonics synapse plasticity are presented.In addition,we introduce several optical neural computing architectures and algorithms including photonic spiking neural network,photonic convolutional neural network,photonic matrix computation,photonic reservoir computing,and photonic reinforcement learning.Finally,we summarize the major challenges faced by photonic neuromorphic computing,and propose promising solutions and perspectives.

Analog Optical Computing for Artificial Intelligence

The rapid development of artificial intelligence(AI)facilitates various applications from all areas but also poses great challenges in its hardware implementation in terms of speed and energy because of the explosive growth of data.Optical computing provides a distinctive perspective to address this bottleneck by harnessing the unique properties of photons including broad bandwidth,low latency,and high energy efficiency.In this review,we introduce the latest developments of optical computing for different AI models,including feedforward neural networks,reservoir computing,and spiking neural networks(SNNs).Recent progress in integrated photonic devices,combined with the rise of AI,provides a great opportunity for the renaissance of optical computing in practical applications.This effort requires multidisciplinary efforts from a broad community.This review provides an overview of the state-of-the-art accomplishments in recent years,discusses the availability of current technologies,and points out various remaining challenges in different aspects to push the frontier.We anticipate that the era of large-scale integrated photonics processors will soon arrive for practical AI applications in the form of hybrid optoelectronic frameworks.

Chip-Based High-Dimensional Optical Neural Network

Parallel multi-thread processing in advanced intelligent processors is the core to realize high-speed and high-capacity signal processing systems.Optical neural network(ONN)has the native advantages of high parallelization,large bandwidth,and low power consumption to meet the demand of big data.Here,we demonstrate the dual-layer ONN with Mach-Zehnder interferometer(MZI)network and nonlinear layer,while the nonlinear activation function is achieved by optical-electronic signal conversion.Two frequency components from the microcomb source carrying digit datasets are simultaneously imposed and intelligently recognized through the ONN.We successfully achieve the digit classification of different frequency components by demultiplexing the output signal and testing power distribution.Efficient parallelization feasibility with wavelength division multiplexing is demonstrated in our high-dimensional ONN.This work provides a high-performance architecture for future parallel high-capacity optical analog computing.

Simplified Echo-State-Network Based Services Awareness for High-Speed Passive Optical Network

With the challenge from services diversity grows greatly,the service-oriented supporting ability is required to current high-speed passive optical network(PON) .Aimed to enhance the quality of service(Qo S) brought by diversified-services,this paper proposes an Simplified Echo State Network(SESN) Based Services Awareness scheme in High-Speed PON(Passive Optical Network) .In this proposed scheme,the ring topology is adopted in the reservoir of SESN to reduce the complexity of original Echo State Network,and system dynamics equation is introduced to keep the accuracy of SESN.According to the network architecture of 10G-EPON,a SESN Master is running in the OLT and a number of SESN Agents work in ONUs.The SESN Master plays the main function of service-awareness from the total view of various kinds services in 10G-EPON system,by fully SESN training.Then,the reservoir information of well-trained SESN in OLT will be broadcasted to all ONUs and those SESN Agents working in ONUs are allowed to conducts independent service-awareness function.Thus,resources allocation and transport policy are both determined just only in ONUs.Simulation results show that the proposed mechanism is able to better supporting ability for multiple services.

A Novel Stateful PCE-Cloud Based Control Architecture of Optical Networks for Cloud Services

The next-generation optical network is a service oriented network,which could be delivered by utilizing the generalized multiprotocol label switching(GMPLS) based control plane to realize lots of intelligent features such as rapid provisioning,automated protection and restoration(P&R),efficient resource allocation,and support for different quality of service(QoS) requirements.In this paper,we propose a novel stateful PCE-cloud(SPC)based architecture of GMPLS optical networks for cloud services.The cloud computing technologies(e.g.virtualization and parallel computing) are applied to the construction of SPC for improving the reliability and maximizing resource utilization.The functions of SPC and GMPLS based control plane are expanded according to the features of cloud services for different QoS requirements.The architecture and detailed description of the components of SPC are provided.Different potential cooperation relationships between public stateful PCE cloud(PSPC) and region stateful PCE cloud(RSPC) are investigated.Moreover,we present the policy-enabled and constraint-based routing scheme base on the cooperation of PSPC and RSPC.Simulation results for verifying the performance of routing and control plane reliability are analyzed.

Review of the Low-Latency Optical Interconnect Technologies for Peta-Scale Computing

This paper reviews the recently developed optical interconnect technologies designed for scalable, low latency and high-throughput comunications within datacenters or high perforrmnce computers. The three typical architectures including the broadcast-and-select based Optical Shared Memory Supercomputer Interconnect System （OSMOSIS） switch, the defection routing based Data Vortex switch and the arrayed waveguide grating based Low-latency Interconnect Optical Network Switch （LIONS） switch are discussed in detail. In particular, we investigate the various Ioopback buffering technologies in LIONS and present a proof of principle testbed demonstration showing feasibility of LIONS architecture. Moreover, the performance of LIONS, Data Vortex and OSMOSIS with traditional state-of-the-art electrical switching network based on the Flattened-ButterFly （FBF） architecture in terms of throughput and latency are compared. The sinmlation based perfortmnce study shows that the latency of LIONS is almost independent of the number of input ports and does not saturate even at very high input load.

Echo-state-network classification based multi-services awareness in high-speed optical passive networks

With the challenge of great growing of services diversity,service-oriented supporting ability is required by current high-speed passive optical network( PON). Aimed at enhancing the quality of service( Qo S) brought by diversified-services,this study proposes an echo state network( ESN)based multi-service awareness mechanism in 10-Gigabite ethernet passive optical network( 10GEPON). In the proposed approach,distributed architecture is adopted to realize this ESN based multi-service awareness. According to the network architecture of 10G-EPON,where a main ESN is running in OLT and a number of ESN agents works in ONUs. The main-ESN plays the main function of service-awareness from the total view of various kinds of services in 10G-EPON system,by full ESN training. Then,the reservoir information of well-trained ESN in OLT will be broadcasted to all ONUs and those ESN agents working in ONUs are allowed to conduct independent service-awareness function. Thus,resources allocation and transport policy are both determined only in ONUs. Simulation results show that the proposed mechanism is able to better support the ability of multiple services.

Parallel Optical Interconnect Technology: Combination of Higher Performance and Lower Energy Consumption

This paper analyzes the physical potential, computing performance benefi t and power consumption of optical interconnects. Compared with electrical interconnections, optical ones show undoubted advantages based on physical factor analysis. At the same time, since the recent developments drive us to think about whether these optical interconnect technologies with higher bandwidth but higher cost are worthy to be deployed, the computing performance comparison is performed. To meet the increasing demand of large-scale parallel or multi-processor computing tasks, an analytic method to evaluate parallel computing performance ofinterconnect systems is proposed in this paper. Both bandwidth-limit model and full-bandwidth model are under our investigation. Speedup and effi ciency are selected to represent the parallel performance of an interconnect system. Deploying the proposed models, we depict the performance gap between the optical and electrically interconnected systems. Another investigation on power consumption of commercial products showed that if the parallel interconnections are deployed, the unit power consumption will be reduced. Therefore, from the analysis of computing influence and power dissipation, we found that parallel optical interconnect is valuable combination of high performance and low energy consumption. Considering the possible data center under construction, huge power could be saved if parallel optical interconnects technologies are used.

Use Single－chip Computer to Realize Automatic Compensation for Optical Fiber Sensors

Being directed against two kinds of noise in optical fiber sensors,a simple and effective method of automatic compensation for optical fiber sensors is presented.Not only the unstability effect of light source,but also zero drift of photoelectronic devices,can be eliminated or enormously restrained with the aid of this method.In another way,by using single-chip microcomputer,the optical fiber sensor system fabricated is connected to a computer network to realize an automatic compensation.

Decision-making and control with diffractive optical networks

The ultimate goal of artificial intelligence(AI)is to mimic the human brain to perform decision-making and control directly from high-dimensional sensory input.Diffractive optical networks(DONs)provide a promising solution for implementing AI with high speed and low power-consumption.Most reported DONs focus on tasks that do not involve environmental interaction,such as object recognition and image classification.By contrast,the networks capable of decision-making and control have not been developed.Here,we propose using deep reinforcement learning to implement DONs that imitate human-level decisionmaking and control capability.Such networks,which take advantage of a residual architecture,allow finding optimal control policies through interaction with the environment and can be readily implemented with existing optical devices.The superior performance is verified using three types of classic games:tic-tac-toe,Super Mario Bros.,and Car Racing.Finally,we present an experimental demonstration of playing tic-tac-toe using the network based on a spatial light modulator.Our work represents a solid step forward in advancing DONs,which promises a fundamental shift from simple recognition or classification tasks to the high-level sensory capability of AI.It may find exciting applications in autonomous driving,intelligent robots,and intelligent manufacturing.

Multimode diffractive optical neural network

On-chip diffractive optical neural networks(DONNs)bring the advantages of parallel processing and low energy consumption.However,an accurate representation of the optical field’s evolution in the structure cannot be provided using the previous diffraction-based analysis method.Moreover,the loss caused by the open boundaries poses challenges to applications.A multimode DONN architecture based on a more precise eigenmode analysis method is proposed.We have constructed a universal library of input,output,and metaline structures utilizing this method,and realized a multimode DONN composed of the structures from the library.On the designed multimode DONNs with only one layer of the metaline,the classification task of an Iris plants dataset is verified with an accuracy of 90%on the blind test dataset,and the performance of the one-bit binary adder task is also validated.Compared to the previous architectures,the multimode DONN exhibits a more compact design and higher energy efficiency.

Diffractive Deep Neural Networks at Visible Wavelengths

Optical deep learning based on diffractive optical elements offers unique advantages for parallel processing,computational speed,and power efficiency.One landmark method is the diffractive deep neural network(D^(2) NN)based on three-dimensional printing technology operated in the terahertz spectral range.Since the terahertz bandwidth involves limited interparticle coupling and material losses,this paper extends D^(2) NN to visible wavelengths.A general theory including a revised formula is proposed to solve any contradictions between wavelength,neuron size,and fabrication limitations.A novel visible light D^(2) NN classifier is used to recognize unchanged targets(handwritten digits ranging from 0 to 9)and targets that have been changed(i.e.,targets that have been covered or altered)at a visible wavelength of 632.8 nm.The obtained experimental classification accuracy(84%)and numerical classification accuracy(91.57%)quantify the match between the theoretical design and fabricated system performance.The presented framework can be used to apply a D^(2) NN to various practical applications and design other new applications.

Pattern recognition in multi-synaptic photonic spiking neural networks based on a DFB-SA chip

Spiking neural networks(SNNs)utilize brain-like spatiotemporal spike encoding for simulating brain functions.Photonic SNN offers an ultrahigh speed and power efficiency platform for implementing high-performance neuromorphic computing.Here,we proposed a multi-synaptic photonic SNN,combining the modified remote supervised learning with delayweight co-training to achieve pattern classification.The impact of multi-synaptic connections and the robustness of the network were investigated through numerical simulations.In addition,the collaborative computing of algorithm and hardware was demonstrated based on a fabricated integrated distributed feedback laser with a saturable absorber(DFB-SA),where 10 different noisy digital patterns were successfully classified.A functional photonic SNN that far exceeds the scale limit of hardware integration was achieved based on time-division multiplexing,demonstrating the capability of hardware-algorithm co-computation.

Reinforced virtual optical network embedding algorithm in EONs for edge computing

As the core technology of optical networks virtualization, virtual optical network embedding(VONE) enables multiple virtual network requests to share substrate elastic optical network(EON) resources simultaneously and hence has been applicated in edge computing scenarios. In this paper, we propose a reinforced virtual optical network embedding(R-VONE) algorithm based on deep reinforcement learning(DRL) to optimize network embedding policies automatically. The network resource attributes are extracted as the environment state for model training, based on which DRL agent can deduce the node embedding probability. Experimental results indicate that R-VONE presents a significant advantage with lower blocking probability and higher resource utilization.

光子神经网络研究进展

在数据海量化、信息化的时代,电子计算机处理系统所面临的算力和能耗等性能要求愈发严苛,传统冯·诺依曼架构存在“内存墙”和“功耗墙”瓶颈,加之摩尔定律放缓甚至失效,使得电子芯片在计算速度和功耗方面遇到极大挑战,利用光计算替代传统电子计算将是解决当前算力与功耗问题的极具潜力的途径之一。本文系统地梳理了片上集成和自由空间的光子神经网络架构与算法方面的研究进展,详细介绍了典型的研究工作,然后讨论并对比了这两种光子神经网络的优劣势,以及光子神经网络的训练策略等。最后探讨了光子神经网络面临的挑战,并对其未来发展进行了前瞻性的展望。

云计算智能嵌入式技术下光通信网络路由的研究

由于光通信传输带宽需求以及网络规模和复杂度不断增加,数据传输路径具有较多选择性,易导致路由能耗大、效率低。云计算平台可以提供海量的计算资源和存储空间,能够处理大规模的数据集,为此,基于云计算智能嵌入式技术研究一种光通信网络路由。利用嵌入式技术设计光通信网络的信号转换、编码、解码等功能,根据数据传输与网络节点的能耗特征建立网络路由能耗模型;引入蚁群算法,基于蚂蚁觅食原理找出所有可以实现数据传递的路由;采用遗传算法,通过选择、交叉、变异计算找出这些路由中数据传输最佳的路由,即能耗损失最小的路由。实验结果表明,所提技术能够提升数据传输速度,使丢包率在3.0%以下,且通信时延仅为23 ms,降低数据传送网络节点能量消耗,证实了所提方法的路由通信性能良好。