Optical Interconnection Network for Massively Parallel Processors Using Beam-Steering Vertical Cavit - Massively Parallel Processing Using Optical Interconnections, 1995., Proceedings of the Second Int
نویسندگان
چکیده
An ultra-dense optical interconnection network is proposed for massively parallel processors. Using twodimensional arrays of beam-steering vertical cavity surface-emitting lasers (VCSEL) as space-division switching elements, a single-chip, free-space photonic banyan network (or other multi-stage networks) can be constructed. Our scheme does not require critical optical alignment and can be easily packaged in compact chips. The optical beam steering of VCSELs are realized with an integrated beam router. Steering angles as large as IO" from surface-normal direction has been demonstrated. The VCSEL has a threshold current of 4 mA and output power of 1 m W f o r 4pmx8pm device) and a modulation bandwidth of I O GHz. Dynamic switching of optical beam angles at 2 GHz has been demonstrated.
منابع مشابه
Single Chip 8x8 Optical Interconnect Using Micromachined Free-Space Micro-Optical Bench Technology - Massively Parallel Processing Using Optical Interconnections, 1996., Proceedings of the Third Inte
A three-dimensional multi-stage optical interconnection network is proposed for mussively purullel processors. The interconnection network employs beamsteering vertical cavity surface-emitting lasers FCSEL) as space-division switching elements, and micromachined micro-Fresnel lenses as free-space optical elements. The entire switching network is integrated on a Si chip using the free-space micr...
متن کاملA Class of Highly Scalable Optical Crossbar-Connected Interconnection Networks (SOCNs) for Parallel Computing Systems
ÐA class of highly scalable interconnect topologies called the Scalable Optical Crossbar-Connected Interconnection Networks (SOCNs) is proposed. This proposed class of networks combines the use of tunable Vertical Cavity Surface Emitting Lasers (VCSEL's), Wavelength Division Multiplexing (WDM) and a scalable, hierarchical network architecture to implement large-scale optical crossbar based netw...
متن کاملMassively Parallel Processing Using Optical Interconnections
This chapter discusses why and how optical communication technology might be used in future large scale parallel processing systems. Commercial systems currently being built can interconnect thousands of processors, and future systems may be even larger. Systems with thousands of processors are often called massively parallel systems. In these systems, the ability to eeciently communicate and s...
متن کاملHierarchical Optical Ring INterconnection (HORN): A Scalable Interconnection-Network for Multiprocessors and Massively Parallel Systems
A new interconnection network for massively parallel computing is introduced. This network is called a Hierarchal Optical Ring INterconnection (HORN). HORN consists of a single-hop, scalable, constant degree, strictly non-blocking, fault-tolerant interconnection topology that utilizes Wavelength Division Multiple Access (WDMA) to provide better utilization of the terahertz (THz) bandwidth o ere...
متن کاملComputer-Aided Design of Free-Space Optoelectronic Interconnection (FSOI) Systems - Massively Parallel Processing Using Optical Interconnections, 1995., Proceedings of the Second Int
New research in optoelectronic devices, which have made it practical to use optoelectronics in computing and communications systems, as well as the need.for these systems to support higher informatr’on capacities has brought about a growing need for dtaign and analysis tools for optoelectronic systems. While there are many research groups developing new and exciting optoelectronic devices, the ...
متن کامل