Optics inside future computers

Lund, Craig

doi:10.1109/mppoi.1997.609174

Cited by 6 publications

(5 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prototypical use of the data reorganization engine is to support corner turn operations on space-time adaptive processing (STAP) applications [3]. Here, the data is commonly block-decomposed matrices, and the communication required from one node to another consists of some number of fixed size blocks of data that are located a regular distance apart (with a given stride within each block).…”

Section: Network Interface/memory Interfacementioning

confidence: 99%

“…Large volumes of sensor-derived data are often processed into a smaller data set and presented to a user or automated control system. Critical communications performance bottlenecks typically occur during data transpose, or "corner turn" operations, and memory access patterns during such operations are often not sequential [3]. For the class of applications considered, a cycle consists of a computation phase followed by a communication phase.…”

Section: Applications and Application Modelsmentioning

confidence: 99%

“…The design is targeted at multicomputer systems that require frequent, massive data transfer among processors, from input sensors, and to output devices. Examples of embedded systems with these requirements include space-time adaptive processing [3], synthetic aperture radar [4], and real-time image processing applications [5].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

VLSI Photonic Ring Multicomputer Interconnect: Architecture and Signal Processing Performance

Chamberlain

Franklin

Krishnamurthy

et al. 2005

J VLSI Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

This paper presents the architectural design of a multicomputer interconnection network based on the use of optical technology. The performance of the system is evaluated on a set of signal processing applications. The interconnect uses Vertical Cavity Surface Emitting Lasers (VCSELs) and flexible fiber image guides to implement a physical ring topology that is logically configured as a multiring. Processors in the multicomputer are nodes on the ring and extremely high communication bandwidth is possible. Using the Laser Channel Allocation (LCA) algorithm and the Deficit Round Robin (DRR) media access protocol, the bandwidth available in the optical interconnect can be reconfigured to make efficient use of the interconnect resources. A discrete-event simulation model of the interconnect is used to examine performance issues such as throughput, latency, fairness, and the impact of reconfigurability.

show abstract

Section: Network Interface/memory Interfacementioning

confidence: 99%

Section: Applications and Application Modelsmentioning

confidence: 99%

See 1 more Smart Citation

VLSI Photonic Ring Multicomputer Interconnect: Architecture and Signal Processing Performance

Chamberlain

Franklin

Krishnamurthy

et al. 2005

J VLSI Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

show abstract

“…The mechanism brings mutual exclusion to let one packet at a time use dedicated hardware to recover from a potential deadlock. Finally, it can be noted that both Myricom (Myrinet) and Mercury (RACEway) are looking at optical technologies for their future products [32].…”

Section: Optical Fibers and Electronic Crossbarsmentioning

confidence: 99%

Fiber-optic interconnection networks for signal processing applications

Jönsson

1999

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In future parallel radar signal processing systems, with high bandwidth demands, new interconnection technologies are needed. The same reasoning can be made for other signal processing applications, e.g., those involving multimedia. Fiber-optic networks are a promising alternative and a lot of work have been done. In this paper, a number of fiber-optic interconnection architectures are reviewed, especially from a radar signal processing point-of-view. Two kinds of parallel algorithm mapping are discussed: (i) a chain of pipeline-stages mapped, more or less directly, one stage per computation node and (ii) SPMD (Same Program Multiple Data). Several network configurations, which are simplified due to the nature of the applications, are also proposed.

show abstract

“…Here, large volumes of sensor-derived data are processed into a smaller data set and presented to a user or automated control system. Critical communications performance bottlenecks occur during data transpose, or "corner turn" operations and memory access patterns during a transpose are often not sequential [19].…”

Section: Introductionmentioning

confidence: 99%

Gemini: an optical interconnection network for parallel processing

Chamberlain

Franklin

Baw³

2002

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

The Gemini interconnect is a dual technology (optical and electrical) interconnection network designed for use in tightlycoupled multicomputer systems. It consists of a circuit-switched optical data path in parallel with a packet-switched electrical control/ data path. The optical path is used for transmission of long data messages and the electrical path is used for switch control and transmission of short data messages. This paper describes the architecture of the interconnection network and related communications protocols. Fairness issues associated with network operation are addressed and a discrete-event simulation model of the entire system is described. Network performance characteristics derived from the simulation model are presented. The results show significant performance benefits when using virtual output queuing and quantify the tradeoffs between throughput and fairness in the system.

show abstract

Optics inside future computers

Cited by 6 publications

References 1 publication

VLSI Photonic Ring Multicomputer Interconnect: Architecture and Signal Processing Performance

VLSI Photonic Ring Multicomputer Interconnect: Architecture and Signal Processing Performance

Fiber-optic interconnection networks for signal processing applications

Gemini: an optical interconnection network for parallel processing

Contact Info

Product

Resources

About