There is a growing awareness among industry players of reaping the benefits of mobile-cloud convergence by extending today's unmodified cloud to a decentralized two-level cloud-cloudlet architecture based on emerg...There is a growing awareness among industry players of reaping the benefits of mobile-cloud convergence by extending today's unmodified cloud to a decentralized two-level cloud-cloudlet architecture based on emerging mobile-edge computing(MEC) capabilities. In light of future 5G mobile networks moving toward decentralization based on cloudlets, intelligent base stations, and MEC, the inherent distributed processing and storage capabilities of radio-and-fiber(R&F) networks may be exploited for new applications, e.g., cognitive assistance, augmented reality, or cloud robotics. In this paper, we first revisit fiber-wireless(Fi Wi) networks in the context of conventional clouds and emerging cloudlets, thereby highlighting the limitations of conventional radio-overfiber(Ro F) networks such as China Mobile's centralized cloud radio access network(C-RAN) to meet the aforementioned trends. Furthermore, we pay close attention to the specific design challenges of data center networks and revisit our switchless arrayedwaveguide grating(AWG) based network with efficient support of east-west flows and enhanced scalability.展开更多
This paper reviews the recently developed optical interconnect technologies designed for scalable, low latency and high-throughput comunications within datacenters or high perforrmnce computers. The three typical arch...This paper reviews the recently developed optical interconnect technologies designed for scalable, low latency and high-throughput comunications within datacenters or high perforrmnce computers. The three typical architectures including the broadcast-and-select based Optical Shared Memory Supercomputer Interconnect System （OSMOSIS） switch, the defection routing based Data Vortex switch and the arrayed waveguide grating based Low-latency Interconnect Optical Network Switch （LIONS） switch are discussed in detail. In particular, we investigate the various Ioopback buffering technologies in LIONS and present a proof of principle testbed demonstration showing feasibility of LIONS architecture. Moreover, the performance of LIONS, Data Vortex and OSMOSIS with traditional state-of-the-art electrical switching network based on the Flattened-ButterFly （FBF） architecture in terms of throughput and latency are compared. The sinmlation based perfortmnce study shows that the latency of LIONS is almost independent of the number of input ports and does not saturate even at very high input load.展开更多
文摘There is a growing awareness among industry players of reaping the benefits of mobile-cloud convergence by extending today's unmodified cloud to a decentralized two-level cloud-cloudlet architecture based on emerging mobile-edge computing(MEC) capabilities. In light of future 5G mobile networks moving toward decentralization based on cloudlets, intelligent base stations, and MEC, the inherent distributed processing and storage capabilities of radio-and-fiber(R&F) networks may be exploited for new applications, e.g., cognitive assistance, augmented reality, or cloud robotics. In this paper, we first revisit fiber-wireless(Fi Wi) networks in the context of conventional clouds and emerging cloudlets, thereby highlighting the limitations of conventional radio-overfiber(Ro F) networks such as China Mobile's centralized cloud radio access network(C-RAN) to meet the aforementioned trends. Furthermore, we pay close attention to the specific design challenges of data center networks and revisit our switchless arrayedwaveguide grating(AWG) based network with efficient support of east-west flows and enhanced scalability.
基金the Department of Defense under Contract No.#H88230-08-C-0202the Google Research Awards
文摘This paper reviews the recently developed optical interconnect technologies designed for scalable, low latency and high-throughput comunications within datacenters or high perforrmnce computers. The three typical architectures including the broadcast-and-select based Optical Shared Memory Supercomputer Interconnect System （OSMOSIS） switch, the defection routing based Data Vortex switch and the arrayed waveguide grating based Low-latency Interconnect Optical Network Switch （LIONS） switch are discussed in detail. In particular, we investigate the various Ioopback buffering technologies in LIONS and present a proof of principle testbed demonstration showing feasibility of LIONS architecture. Moreover, the performance of LIONS, Data Vortex and OSMOSIS with traditional state-of-the-art electrical switching network based on the Flattened-ButterFly （FBF） architecture in terms of throughput and latency are compared. The sinmlation based perfortmnce study shows that the latency of LIONS is almost independent of the number of input ports and does not saturate even at very high input load.
