By Topic

# Proceedings of Massively Parallel Processing Using Optical Interconnections

## Filter Results

Displaying Results 1 - 25 of 47
• ### Proceedings of Massively Parallel Processing Using Optical Interconnections

Publication Year: 1996
| PDF (331 KB)
• ### Intra-System Optical Interconnects: Performance, Cost, Functionality - Pick any Two

Publication Year: 1996, Page(s):102 - 104
| | PDF (357 KB)

First Page of the Article
View full abstract»

• ### Panel Discussion The Roles of University and Industry in Developing Optical Interconnect Systems

Publication Year: 1996, Page(s):216 - 223
| PDF (650 KB)
• ### Author index

Publication Year: 1996, Page(s):367 - 369
Cited by:  Papers (1)
| PDF (127 KB)
• ### Optically interconnected electronics-challenges and choices

Publication Year: 1996, Page(s):138 - 145
Cited by:  Papers (5)  |  Patents (1)
| | PDF (732 KB)

The challenges facing the use of optical interconnects to provide high capacity links is reviewed. The power consumption of optical and electrical links are compared. The performance of fiber ribbon optical data links is described. It is argued that free-space digital optics may be used to provide higher capacity. The required and achieved performance of transceivers and the optics and mechanics u... View full abstract»

• ### The AMOEBA chip: an optoelectronic switch for multiprocessor networking using dense-WDM

Publication Year: 1996, Page(s):94 - 100
Cited by:  Papers (8)  |  Patents (2)
| | PDF (1016 KB)

We present AMOEBA: a single-chip asynchronous multiprocessor optoelectronic bit-sliced arrayed crossbar switch intended to provide switched interconnection between multiple processors in a distributed computing environment. AMOEBA relies on optoelectronic-VLSI integration, free-space optical interconnects, and wavelength-and-space-division multiplexed networking on single-mode fiber. We report the... View full abstract»

• ### Improved embeddings in POPS networks through stack-graph models

Publication Year: 1996, Page(s):130 - 136
Cited by:  Papers (9)
| | PDF (556 KB)

In 1996 MPPOI, Gravenstreter and Melhem presented optimal embeddings of ring and torus communications on the POPS architecture, for the case where the number of nodes (n) and the optical passive star (OPS) coupler degree (d) are powers of two. In the same conference, Bourdin, Ferreira and Marcus; see massively parallel multiprocessing using optical interconnections, San Antonio, USA, Oct, 1995, IE... View full abstract»

• ### Reconfigurable computing with optical backplanes an economic argument for optical interconnects

Publication Year: 1996, Page(s):321 - 328
Cited by:  Papers (1)
| | PDF (992 KB)

A reconfigurable computing architecture which exploits the terabit bandwidth of a free-space optical backplane is proposed. The computing system consists of many printed circuit boards (PCBs), each containing a modest number of relatively inexpensive field programmable gate arrays (FPGAs). The PCBs are optically interconnected with an intelligent optical backplane using multiple smart pixel arrays... View full abstract»

• ### Network of PCs as high-performance servers: requirements for a communication mechanism

Publication Year: 1996, Page(s):225 - 230
| | PDF (636 KB)

Networks of commodity PCs have the potential to provide extremely cost-effective computing and information services. However, they will fulfil their promise only if their system performance is truly competitive with commercial multicomputers or multiprocessors. To achieve this goal, the requirements for the communication mechanism used in such a system must not only consider end-to-end communicati... View full abstract»

• ### Scalable parallel systems: past, present and future (from an IBM perspective)

Publication Year: 1996, Page(s):33 - 35
| | PDF (268 KB)

We survey in this paper the evolution of scalable parallel computers, from the perspective of the IBM SP product line. To achieve success in the marketplace, the SP had to be more than a bunch of rack-mounted workstations, connected with a LAN. A high-performance interconnect is key to parallel performance. The current, second generation SP switch, supports a bandwidth of 150 MB/s in each directio... View full abstract»

• ### Hybrid optoelectronic backplane bus for multiprocessor-based computing systems

Publication Year: 1996, Page(s):313 - 320
Cited by:  Papers (2)  |  Patents (1)
| | PDF (964 KB)

The architecture of a hybrid electrical and optical backplane with multiple bus lines for high performance bus is proposed and bus systems with 2-bus lines at a wavelength of 850 nm are experimentally demonstrated, with a size of collimation lens (here we used graded index (GRIN) lenses) and level of collimation-limited separation of 1.5 mm between the two bus lines. For the new bus system contain... View full abstract»

• ### Performance modeling of optical interconnection technologies for massively parallel processing systems

Publication Year: 1996, Page(s):264 - 275
Cited by:  Papers (1)
| | PDF (1516 KB)

Optical interconnection technologies (OITs) are expected to play an important role in alleviating the technologically induced architectural and algorithmic compromises that have to be made in the design of high-performance, massively parallel processors (MPPs) and their target applications. The vast diversity and relative immaturity of the OITs that have been put forth, however, point to the need ... View full abstract»

• ### Flexible optical backplane interconnections

Publication Year: 1996, Page(s):178 - 185
Cited by:  Papers (5)  |  Patents (6)
| | PDF (2304 KB)

The increasing demand for bandwidth and interconnection density to provide wide bandwidth services at reasonably low cost are rapidly exhausting capabilities of interconnection techniques currently employed in conventional wide bandwidth telecommunication switching equipment. In particular, a bottleneck occurs at the intra-system (that is, board-, shelf- and cabinet-level) backplane interconnectio... View full abstract»

• ### SIMPil: an OE integrated SIMD architecture for focal plane processing applications

Publication Year: 1996, Page(s):44 - 52
Cited by:  Papers (20)  |  Patents (1)
| | PDF (1768 KB)

Focal plane processing applications present a growing computing need for portable telecomputing and videoputing systems. This paper demonstrates the integration of digital processing, analog interface circuitry, and thin film OE devices into a compact computing package. The SIMPil architecture provides a programmable, silicon efficient SIMD processor for effective execution of early image processi... View full abstract»

Publication Year: 1996, Page(s):282 - 289
Cited by:  Papers (3)  |  Patents (10)
| | PDF (1176 KB)

This paper describes a VCSEL-Si smart pixel array technology, developed at the University of Colorado, and reports on an optoelectronic processor that is based on these hybrid SPAs. This effort is unique in the processing complexity of the pixels, in the bidirectionary of the optical interconnects, and in the thermosonic bonding of the VCSEL and silicon chips View full abstract»

• ### Time-deterministic WDM star network for massively parallel computing in radar systems

Publication Year: 1996, Page(s):85 - 93
Cited by:  Papers (7)  |  Patents (1)
| | PDF (884 KB)

In massively parallel computer systems for embedded real-time applications there are normally very high bandwidth demands on the interconnection network. Other important properties are time-deterministic latency and services to guarantee that deadlines are met. In this paper we analyze how these properties vary with the design parameters for a passive optical star network, specifically when used i... View full abstract»

• ### Planar diffraction grating for board-level WDM applications

Publication Year: 1996, Page(s):77 - 84
Cited by:  Papers (1)  |  Patents (2)
| | PDF (716 KB)

Optical interconnects in massively parallel processing (MPP) systems will require a variety of optical components regardless of the specific implementation of the optics in such systems. These components span a range of complexity from conceptually simple structures such as connectors to quite complex structures such as VCSELs. While numerous optical components have been developed for fiber-based ... View full abstract»

• ### A comparative study of cost effective multiplexing approaches in optical networks

Publication Year: 1996, Page(s):24 - 31
Cited by:  Papers (3)
| | PDF (784 KB)

In this paper, we describe a framework for exploring various multiplexing approaches in optical networks and evaluating their cost-effectiveness. A comprehensive comparative study of two representative approaches, known as path multiplexing (PM) and link multiplexing (LM), is conducted with respect to on-line permutation scheduling. It is found that in many networks, PM is nearly as effective as L... View full abstract»

• ### Optical, optomechanical, and optoelectronic design and operational testing of a multi-stage optical backplane demonstration system

Publication Year: 1996, Page(s):306 - 312
Cited by:  Papers (5)
| | PDF (816 KB)

In this paper, we describe the optical, optomechanical, and optoelectronic design of a multistage optical backplane demonstration system. In addition, operational testing and performance is discussed View full abstract»

• ### OPTOBUSTM I: performance of a 4 Gb/s optical interconnect

Publication Year: 1996, Page(s):256 - 263
Cited by:  Papers (12)
| | PDF (856 KB)

The OptobusTM optical link is a ten channel parallel fiber bidirectional optical interconnect. The design goal was to produce a transparent' parallel data link that can be directly substituted for parallel copper regardless of the characteristics of the data stream. Transparency requires certain tradeoffs in the ultimate performance of the link. In the case of Optobus I, these trade-of... View full abstract»

• ### High-performance parallel processors based on star-coupled WDM optical interconnects

Publication Year: 1996, Page(s):62 - 69
Cited by:  Papers (4)
| | PDF (904 KB)

As the performance of individual elements within parallel processing systems increases, increased communication capability between distributed processor and memory elements is required. There is great interest in using fiber optics to improve interconnect communication beyond that attainable using electronic technology. Several groups have considered WDM, star-coupled optical interconnects. In thi... View full abstract»

• ### Towards an optimal foundation architecture for optoelectronic computing

Publication Year: 1996, Page(s):8 - 15
Cited by:  Papers (1)  |  Patents (1)
| | PDF (828 KB)

By systematically examining the tree of possibilities for optoelectronic computing architectures and offering arguments that allow us to prune suboptimal branches of this tree, we come to the conclusion that electronic circuit planes interconnected optically according to regular connection patterns, represents an alternative which is reasonably close to the best possible as defined by physical lim... View full abstract»

• ### Two-dimensional parallel optical data link: experiment

Publication Year: 1996, Page(s):206 - 214
Cited by:  Papers (1)  |  Patents (10)
| | PDF (960 KB)

Two-dimensional (2-D) parallel optical data link based upon optical space-CDMA is implemented and experimentally demonstrated for the first time to the authors' knowledge. In the experiment, the encoded bit-planes are spatially multiplexed, and it is transmitted through a 16 m-long image fiber having 3×104 pixels. Each input 4×4 bit-plane is optically encoded by an 8×8... View full abstract»

• ### High throughput optical algorithms for the FFT and sorting via data packing

Publication Year: 1996, Page(s):168 - 176
| | PDF (892 KB)

This paper demonstrates that the potential for very high speed computation provided by optical technology can be achieved for important computational problems including the fast Fourier transform and sorting. First a programming model that captures the time-of-flight' characteristics of optical fibers and switching elements is presented. Then it is shown that the FFT and the radix sort algorithms... View full abstract»

• ### 1-GHz clock signal distribution for multi-processor super computers

Publication Year: 1996, Page(s):186 - 191
Cited by:  Papers (1)
| | PDF (1272 KB)

In this paper, we present our efforts to construct an optoelectronic interconnection layer for high-speed optical clock signal distribution in a Gray T-90 supercomputer board. The optoelectronic interconnection layer under investigation employs optical channel waveguides and cascaded 3 dB 1-to-2 waveguide splitters in conjunction with surface-normal waveguide grating couplers. The planarization re... View full abstract»