Hierarchical optical ring interconnection (HORN): scalable interconnection network for multiprocessors and multicomputers

A new interconnection network for massively parallel computing is introduced. This network is called a hierarchal optical ring interconnection (HORN). The HORN consists of a single-hop, scalable, constant-degree, strictly nonblocking, fault-tolerant interconnection topology that uses wavelength-division multiple access to provide better utilization of the terahertz bandwidth offered by optics. The proposed optical network integrates the attractive features of hierarchical ring interconnections, e.g., a simple node interface, a constant node degree, better support for the locality of reference, and fault tolerance, with the advantages of optics. The HORN topology is presented, its architectural properties are analyzed, and an optical design methodology for it is described. Furthermore, a brief feasibility study of the HORN is conducted. The study shows that the topology is highly amenable to optical implementation with commercially available optical elements.     

SYMNET: an optical interconnection network for scalable high-performance symmetric multiprocessors

We address the primary limitation of the bandwidth to satisfy the demands for address transactions in future cache-coherent symmetric multiprocessors (SMPs). It is widely known that the bus speed and the coherence overhead limit the snoop/address bandwidth needed to broadcast address transactions to all processors. As a solution, we propose a scalable address subnetwork called symmetric multiprocessor network (SYMNET) in which address requests and snoop responses of SMPs are implemented optically. SYMNET not only has the ability to pipeline address requests, but also multiple address requests from different processors can propagate through the address subnetwork simultaneously. This is in contrast with all electrical bus-based SMPs, where only a single request is broadcast on the physical address bus at any given point in time. The simultaneous propagation of multiple address requests in SYMNET increases the available address bandwidth and lowers the latency of the network, but the preservation of cache coherence can no longer be maintained with the usual fast snooping protocols. A modified snooping cache-coherence protocol, coherence in SYMNET (COSYM) is introduced to solve the coherence problem. We evaluated SYMNET with a subset of Splash-2 benchmarks and compared it with the electrical bus-based MOESI (modified, owned, exclusive, shared, invalid) protocol. Our simulation studies have shown a 5-66% improvement in execution time for COSYM as compared with MOESI for various applications. Simulations have also shown that the average latency for a transaction to complete by use of COSYM protocol was 5-78% better than the MOESI protocol. SYMNET can scale up to hundreds of processors while still using fast snooping-based cache-coherence protocols, and additional performance gains may be attained with further improvement in optical device technology.     

Scalable optical hypercube-based interconnection network for massively parallel computing

Two important parameters of a network for massively parallel computers are scalability and modularity. Scalability has two aspects: size and time (or generation). Size scalability refers to the property that the size of the network can be increased with nominal effect on the existing configuration. Also, the increase in size is expected to result in a linear increase in performance. Time scalability implies that the communication capabilities of a network should be large enough to support the evolution of processing elements through generations. A modular network enables the construction of a large network out of many smaller ones. The lack of these two important parameters has limited the use of certain types of interconnection networks in the area of massively parallel computers. We present a new modular optical interconnection network, called an optical multimesh hypercube (OMMH), which is both size and time scalable. The OMMH combines positive features of both the hypercube (small diameter, high connectivity, symmetry, simple routing, and fault tolerance) and the torus (constant node degree and size scalability) networks. Also presented is a three-dimensional optical implementation of the OMMH network. A basic building block of the OMMH network is a hypercube module that is constructed with free-space optics to provide compact and high-density localized hypercube connections. The OMMH network is then constructed by the connection of such basic building blocks with multiwavelength optical fibers to realize torus connections. The proposed implementation methodology is intended to exploit the advantages of both space-invariant free-space and multiwavelength fiber-based optical interconnect technologies. The analysis of the proposed implementation shows that such a network is optically feasible in terms of the physical size and the optical power budget.     

Topologies for optical interconnection networks based on the optical transpose interconnection system

Many results exist in the literature describing technological and theoretical advances in optical network topologies and design. However, an essential effort has yet to be made in linking those results together. We propose a step in this direction by giving optical layouts for several graph-theoretical topologies studied in the literature, using the optical transpose interconnection system (OTIS) architecture. These topologies include the family of partitioned optical passive star (POPS) and stack-Kautz networks as well as a generalization of the Kautz and the de Bruijn digraphs.     

一种可扩展的双层光互连网络设计与分析

本文设计一种具有可扩展性的双层并行光互连网络.顶层为数字路由结点和光网络接口卡组成的星型网,底层为光网络接口卡连接而成的环形网.结点机以及数字路由结点影响网络的性能.结点机的吞吐能力限制了整个网络的吞吐率;扩展PCI总线的位数能够提高光网络接口卡的吞吐速率,采用64bit/66MHz工作模式可获得4.224 Gbps峰值传输速率.网络的实际最大吞吐速率为8.448Gbps,环网内平均延迟2195ns,环网间平均延迟4713 ns.可以采用本文设计的数字路由结点对网络进行低成本级联扩展,扩展后网络性能显著提高.     

Feasibility study of a scalable optical interconnection network for massively parallel processing systems

The theoretical modeling of a novel topology for scalable optical interconnection networks, called optical multimesh hypercube (OMMH), is developed to predict size, bit rate, bit-error rate, power budget, noise, efficiency, interconnect distance, pixel density, and misalignment sensitivity. The numerical predictions are validated with experimental data from commercially available products to assess the effects of various thermal, system, and geometric parameters on the behavior of the sample model. OMMH is a scalable network architecture that combines positive features of the hypercube (small diameter, regular, symmetric, and fault tolerant) and the mesh (constant node degree and size scalability). The OMMH is implemented by a free-space imaging system incorporated with a space-invariant hologram for the hypercube links and fiber optics to provide the mesh connectivity. The results of this work show that the free-space links can operate at 368 Mbits/s and the fiber-based links at 228 Mbits/s for a bit-error rate of 10(-17) per channel. The predicted system size for 32 nodes in the OMMH is 4.16 mm × 4.16 mm × 3.38 cm. Using 16-bit, bit-parallel transmission per node, the system can operate at a bit rate of up to 5.88 Gbits/s for a size of 1.04 cm × 1.04 cm × 3.38 cm.     

Multichip free-space global optical interconnection demonstration with integrated arrays of vertical-cavity surface-emitting lasers and photodetectors

The experimental optical interconnection module of the Free-Space Accelerator for Switching Terabit Networks (FAST-Net) project is described and characterized. Four two-dimensional (2-D) arrays of monolithically integrated vertical-cavity surface-emitting lasers (VCSEL's) and photodetectors (PD's) were designed, fabricated, and incorporated into a folded optical system that links a 10 cm x 10 cm multichip smart pixel plane to itself in a global point-to-point pattern. The optical system effects a fully connected network in which each chip is connected to all others with a multichannel bidirectional data path. VCSEL's and detectors are arranged in clusters on the chips with an interelement spacing of 140 mum. Calculations based on measurements of resolution and registration tolerances showed that the square 50-mum detector in a typical interchip link captures approximately 85% of incident light from its associated VCSEL. The measured optical transmission efficiency was 38%, with the losses primarily due to reflections at the surfaces of the multielement lenses, which were not antireflection coated for the VCSEL wavelength. The overall efficiency for this demonstration is therefore 32%. With the measured optical confinement, an optical system that is optimized for transmission at the VCSEL wavelength will achieve an overall efficiency of greater than 80%. These results suggest that, as high-density VCSEL-based smart pixel technology matures, the FAST-Net optical interconnection concept will provide a low-loss, compact, global interconnection approach for high bisection-bandwidth multiprocessor applications in switching, signal processing, and image processing.     

Experimental demonstration of an automatic alignment system for optical interferometers

An automatic alignment system, based on a differential phase-sensing technique described in a companion paper [Appl. Opt.33, 0000, (1994)], has been experimentally demonstrated on the 10-m prototype laser interferometric gravitational wave detector in Glasgow. The alignment system developed was used to control the orientations of two mirrors in a 10-m-long suspended Fabry-Perot cavity with respect to the direction defined by the input laser beam. The results of the test and a discussion of the performance of the system are given.     

Incrementally scalable optical interconnection network with a constant degree and constant diameter for parallel computing

A new scalable interconnection topology called the spanning-bus connected hypercube (SBCH) that is suitable for massively parallel systems is proposed. The SBCH uses the hypercube topology as a basic building block and connects such building blocks by use of multidimensional spanning buses. In doing so, the SBCH combines positive features of both the hypercube (small diameter, high connectivity, symmetry, simple routing, and fault tolerance) and the spanning-bus hypercube (SBH) (constant node degree, scalability, and ease of physical implementation), while at the same time circumventing their disadvantages. The SBCH topology permits the efficient support of many communication patterns found in different classes of computation, such as bus-based, mesh-based, and tree-based problems, as well as hypercube-based problems. A very attractive feature of the SBCH network is its ability to support a large number of processors while maintaining a constant degree and a constant diameter. Other positive features include symmetry, incremental scalability, and fault tolerance. An optical implementation methodology is proposed for the SBCH. The implementation methodology combines the advantages of free-space optics with those of wavelength-division multiplexing techniques. An analysis of the feasibility of the proposed network is also presented.     

Free-space optical relay for the interconnection of multimode fibers

We present results from a system that shows that multimode fibers can be used for both the input and the output of a free-space optical system. The system consists of plastic microlenses integrated with plastic optomechanical components that are suitable for low-cost fabrication and assembly. Such a system opens up opportunities to construct large repeaters and switches for multigigabit ethernet applications by integration with two-dimensional arrays of optoelectronic devices. We demonstrate a 2.5-Gbit/s transmission rate by using commercial vertical-cavity surface-emitting lasers coupled to 62.5-mum core fibers. We consider the design constraints and the capabilities of custom optical modules suitable for mass production.     

Experimental free-space optical network for massively parallel computers

A free-space optical interconnection scheme is described for massively parallel processors based on the interconnection-cached network architecture. The optical network operates in a circuit-switching mode. Combined with a packet-switching operation among the circuit-switched optical channels, a high-bandwidth, low-latency network for massively parallel processing results. The design and assembly of a 64-channel experimental prototype is discussed, and operational results are presented.     

Implementation of a large-scale optical neural network by use of a coaxial lenslet array for interconnection

Optical implementation of a large-scale neural network with 32 x 32 neurons is reported. The experimental setup is described, error caused by limited precision of hardware is analyzed, and experimental results are presented.     

Experimental demonstration of an optical phased array antenna for laser space communications

The feasibility of an optical phased array antenna applicable for spaceborne laser communications was experimentally demonstrated. Heterodyne optical phase-locked loops provide for a defined phase relationship between the collimated output beams of three single-mode fibers. In the far field the beams interfere with a measured efficiency of 99%. The main lobe of the interference pattern can be moved by phase shifting the subaperture output beams. The setup permitted agile beam steering within an angular range of 1 mr and a response time of 0.7 ms. We propose an operational optical phased array antenna fed by seven lasers, featuring high transmit power and redundance.     

Highly efficient interconnection for use with a multistage optical switching network with orthogonally polarized data and address information

A novel optical interconnection is introduced for a multistage optical switching network that uses orthogonally polarized data and address information. The network is unique in that the data information is never regenerated and remains in optical form throughout (i.e., it is never converted into electrical information). This has two main consequences: (1) the bandwidth of the data is not restricted by electrical circuit considerations, and (2) the optical interconnections from one stage of the network to the next must be highly efficient. The interconnection meets several goals: high efficiency, preservation of cross polarization of data and address, low cross talk between polarizations, good manufacturability, resistance to misalignment caused by thermal expansion, and absence of significant aberrations. In addition, sychronization of the signals is maintained, as the optical path lengths for all routes through the system are equal.     

Performance scaling comparison for free-space optical and electrical interconnection approaches

Projected performance metrics of free-space optical and electrical interconnections are estimated and compared in terms of smart-pixel input-output bandwidth density and practical geometric packaging constraints. The results suggest that three-dimensional optical interconnects based on smart pixels provide the highest volume, latency, and power-consumption benefits for applications in which globally interconnected networks are required to implement links across many integrated-circuit chips. It is further shown that interconnection approaches based on macro-optical elements achieve better scaling than those based on micro-optical elements. The scaling limits of micro-optical-based architectures stem from the need for repeaters to overcome diffraction losses in multichip architectures with high bisection bandwidth. The overall results provide guidance in determining whether and how strongly a free-space optical interconnection approach can be applied to a given multiprocessor problem.     

Locality and decomposition of regular optical interconnection patterns

Methods that a designer can use to optimize the placement of nodes in a large switching network to decrease the requirements on holographic interconnections are investigated. Localized interconnections between subdivided switches are combined with simpler global interconnections. The interconnections between subdivided switches can be implemented by use of metallic traces on smart-pixel arrays. The global interconnections would be provided by optical free-space techniques. Several advantages arise from this procedure: (1) The regular interconnection pattern is decomposed into several pipes (collection of light beams that form a complete pattern) without loss of functionality. (2) The interconnection pattern may be optimized by variation of the placement of the switches in a switching network (e.g., to obtain a minimum deflection angle). (3) The interconnection pattern may be adjusted to the need of an algorithm by an additional parameter (the dimension). The application to photonic switching networks and signal processing is discussed.     

Space-variant optical interconnection through the use of computer-generated holograms

A space-variant optical interconnection through the use of computer-generated holograms is proposed, and specific configurations to increase the number of parallel channels are analyzed. To this end, the well-known method based on a matrix composed of subholograms is applied. The field diffracted by each channel (assumed to be square apertures) is calculated through the angular-spectrum technique, and the resulting fields are suitably superimposed to obtain a hologram matrix with a reduced bandwidth. Results show that a compact transmissive planar configuration can be handled; in particular, the small interconnect distance between the array planes and the hologram yields a limited system volume.     

Generalized methodology for modeling and simulating optical interconnection networks using diffraction analysis

Research in the field of free-space optical interconnection networks has reached a point where simulators and other design tools are desirable for reducing development costs and for improving design time. Previously proposed methodologies have only been applicable to simple systems. Our goal was to develop a simulation methodology capable of evaluating the performance characteristics for a variety of different free-space networks under a range of different configurations and operating states. The proposed methodology operates by first establishing the optical signal powers at various locations in the network. These powers are developed through the simulation by diffraction analysis of the light propagation through the network. After this evaluation, characteristics such as bit-error rate, signal-to-noise ratio, and system bandwidth are calculated. Further, the simultaneous evaluation of this process for a set of component misalignments provides a measure of the alignment tolerance of a design. We discuss this simulation process in detail as well as provide models for different optical interconnection network components.     

Design and fabrication of binary slanted surface-relief gratings for a planar optical interconnection

We propose the use of binary slanted surface-relief gratings with parallel-groove walls as input and output couplers in a planar optical interconnect. Parametric optimization of cascaded output couplers is employed to design an interconnect consisting of N output couplers producing a uniform intensity distribution with a high efficiency that may be realized in one lithographic etching step. The sensitivity of a N = 4 interconnect to various fabrication errors is analyzed. We demonstrate the operation of a slanted surface-relief grating manufactured with electron-beam lithography and reactive-ion etching for an operating wavelength of lambda = 0.633 mum.     

热声制冷效应验证的实验设计

热声制冷技术是一项新的冷制技术。它具有无运动部件、运行可靠、寿命长和环保等优点。在航天、微电子、低温物理及军事等领域有着十分诱人的应用前景。热声制冷机主要由声驱动器、共振管、热声叠和换热器等部件组成。根据热声制冷原理,利用常见的材料和仪器,采用自制的玻璃管状热声叠,设计了一套结构简单的扬声器驱动热声制冷实验验证装置。实验结果表明:以空气作工质,在无冷却措施的情况下,在系统运行较短时间内,实现了13℃的降温及25℃的温跨,热声制冷效应十分明显。该装置可用于研究热声制冷效应的影响因素。