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.     

Experimental demonstration of the optical multi-mesh hypercube: scaleable interconnection network for multiprocessors and multicomputers

A prototype of a novel topology for scaleable optical interconnection networks called the optical multi-mesh hypercube (OMMH) is experimentally demonstrated to as high as a 150-Mbit/s data rate (2(7) - 1 nonreturn-to-zero pseudo-random data pattern) at a bit error rate of 10(-13)/link by the use of commercially available devices. OMMH is a scaleable network [Appl. Opt. 33, 7558 (1994); J. Lightwave Technol. 12, 704 (1994)] architecture that combines the positive features of the hypercube (small diameter, connectivity, symmetry, simple routing, and fault tolerance) and the mesh (constant node degree and size scaleability). The optical implementation method is divided into two levels: high-density local connections for the hypercube modules, and high-bit-rate, low-density, long connections for the mesh links connecting the hypercube modules. Free-space imaging systems utilizing vertical-cavity surface-emitting laser (VCSEL) arrays, lenslet arrays, space-invariant holographic techniques, and photodiode arrays are demonstrated for the local connections. Optobus fiber interconnects from Motorola are used for the long-distance connections. The OMMH was optimized to operate at the data rate of Motorola's Optobus (10-bit-wide, VCSEL-based bidirectional data interconnects at 150 Mbits/s). Difficulties encountered included the varying fan-out efficiencies of the different orders of the hologram, misalignment sensitivity of the free-space links, low power (1 mW) of the individual VCSEL's, and noise.     

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.     

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.     

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.     

Testbed for a scalable terabit optical local area network

The design of a fiber-optic local area network (LAN) demonstration system is described. A complete LAN system would consist of an array of 16 personal computers (PC's), where each PC has a network interface card (NIC) with a parallel fiber-optic datalink to a centralized optoelectronic switch core. The centralized core switches the data generated by 16 NIC's, up to 128 Gbit/s of bandwidth. The demonstrator is designed to scale to terabits of bandwidth by use of an emerging optoelectronic technology, i.e., integrated complementary metal-oxide semiconductor (CMOS) substrates with vertical-cavity surface-emitting laser (VCSEL) and photodetector optical input and output. A subset of the complete system was constructed and is operational. A prototype NIC card, with Motorola Optobus VCSEL transceivers for the optical datalinks, was constructed and is described. A prototype high-speed bipolar switch core, with statically configurable electrical positive-emitter coupled-logic 16 x 16 crossbar switches, CMOS field-programmable gate arrays, and Motorola Optobus transceivers, was constructed and is described. We successfully demonstrated the transmission of high-speed packetized data from one NIC card, through 10 m of parallel fiber ribbon and the centralized switch core, and back to the NIC. We summarize our experiences on the design and testing of our first demonstration system and our development toward a terabit switch core.     

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.     

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.     

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.     

Double ring and Fabry-Perot ring resonators: application for an optical fiber laser

Two fiber-based resonators are studied. Their properties of light confinement are examined as a function of their couplers' parameters. Conditions for optimum performance of these devices as frequency filters or as laser resonators for a given pump wavelength are found.     

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.     

Single-crystalline Bi(2)S(3) nanowire network film and its optical switches

A single-crystalline bismuth sulfide (Bi(2)S(3)) nanowire network film at a centimeter scale is fabricated by the facile hydrothermal method. The Bi(2)S(3) film is easily tape-transferred onto a soft plastic substrate, and is further used to fabricate optical switches by screen-printing an Ag?electrode array on its top. Our studies demonstrate that the Bi(2)S(3) nanowire network has a pronounced increase in conductance upon exposure to visible light, and possesses a very fast response time of about 2?ms. This work provides a simple and economic method to fabricate a high performance optical switch array and could offer great potential for a low cost, mass-manufacturing process.     

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.     

Azobenzenes for photonic network applications: Third-order nonlinear optical properties

We review the third-order nonlinear performance of pseudo-stilbene type azobenzenes with an eye to application in ultrafast optical signal processing. We discuss mechanisms responsible for the nonlinear response of the azobenzenes. By aggregating experimental data and theoretical trends reported in the literature, we identify five characteristic regions of optical nonlinear response. Analyzed with respect to Stegeman figures of merit, pseudo-stilbene type azobenzenes show promise for ultrafast optical signal processing in two spectral regions, one lying between the main and two-photon absorption resonances, and the other for wavelengths longer than the two-photon absorption resonance. © 2001 Kluwer Academic Publishers     

Multilevel (Hierarchical) Modeling: What It Can and Cannot Do

Multilevel (hierarchical) modeling is a generalization of linear and generalized linear modeling in which regression coefficients are themselves given a model, whose parameters are also estimated from data. We illustrate the strengths and limitations of multilevel modeling through an example of the prediction of home radon levels in U.S. counties. The multilevel model is highly effective for predictions at both levels of the model, but could easily be misinterpreted for causal inference.     

Depletion-enhanced body-isolation (DEBI) array on SOI for highly scalable and reliable NAND flash memories

A novel array architecture [depletion-enhanced body-isolation (DEBI)] has been proposed for NAND-type flash memories, and its memory characteristics are investigated in detail by device simulations. Having the shallow junctions on the thin active area, the proposed array architecture achieves high device performances with a fully depleted silicon-on-insulator (FDSOI) structure and enables stable erase operation without any problems based on an SOI structure. In particular, during the program operation, the DEBI architecture exhibited excellent self-boost efficiency originating from the isolated body. This can reduce the program disturbance effectively and can lower the V/sub pass/ voltages.     

A co-ordinated network for radiation dosimetry (CONRAD): an overview

The European Radiation Dosimetry Group (EURADOS) carried out a co-ordinated action, supported within the 6th Framework Programme of the European Commission entitled 'A Co-ordinated Network for Radiation Dosimetry (CONRAD)'. The project, executed from January 2005 to March 2008, yielded a large number of scientific results in different areas of dosimetry. This paper describes the objectives and general aspects of the project while the results are given in several contributions in this volume. Special consideration is given to the results and implications of the feasibility study for a sustainable network in radiation dosimetry, which was also carried out within the CONRAD project.