November 10, 2006
ADVA Optical Networking has announced its participation in a demonstration at SuperComputing 2006 (SC06) of dynamic hybrid network services that enable grid computing, high-capacity storage facilities, transport of high-resolution video and visualization applications, networking of scientific instruments such as radio telescopes and other collaborative cyber resources. SC06, an international conference on high-performance computing, networking, storage and analysis, takes place November 11-17 at the Tampa Convention Center.
The National Science Foundation (NSF)-funded Dynamic Resource Allocation over GMPLS Optical Networks ("DRAGON") demonstration -- for which ADVA Optical Networking is providing the optical transport infrastructure, including the world's first commercially available, multi-degree reconfigurable optical add/drop multiplexer (ROADM) -- shows how optical networks can be established on-demand to link scientific resources worldwide to meet the needs of e-science.
The NSF DRAGON demonstration dynamically creates application-specific networks that incorporate end systems at several booths (including ADVA Optical Networking's Booth 1542, Xnet's Booth 1848, NASA's Booth 917 and Internet2's Booth 1451) at SC06 and connect to facilities in Asia, Europe and other sites in North America.
"NSF DRAGON creates dedicated, distributed networking environments that exhibit deterministic, predictable and repeatable performance capabilities," said Jerry Sobieski, principle investigator with the NSF DRAGON project. "This demonstration shows how, with the emergence of dynamic hybrid networks, e-science now has the tools to create new global instruments for exploring the universe and new models for international collaboration."
The ADVA Fiber Service Platform (FSP) 3000 brings industry-leading, multi-degree ROADM functionality and GMPLS (Generalized Multiprotocol Label Switching) control plane to the NSF DRAGON network's optical transport layer. ADVA Optical Networking's ROADM technology, obtained in July 2006 via the company's acquisition of Movaz Networks, relies on photolithographic Micro-Electro-Mechanical Systems (MEMS), tiny mirrors etched into integrated circuits, to transparently switch very high-speed telecommunications channels through a network. The GMPLS technology is a set of software protocols that automate the mesh network discovery, inventory and provisioning process, while increasing the network efficiency with mesh restoration options. Together, these technologies enable all-optical inter-ring switching for support of real-time provisioning and dynamic resource recovery -- capabilities that allow the NSF DRAGON demonstration to establish the dedicated, distributed, application-specific networks in a matter of seconds, hold them for as long as needed and then release resources when no longer required.
ADVA Optical Networking's multi-degree ROADM capabilities have been refined as a direct result of NSF DRAGON collaboration over the past three years since the first installation in 2003. The resulting ROADM solutions have been deployed in advanced research and commercial carrier networks worldwide. NASA Goddard Space Flight Center in Greenbelt, Maryland, for example, incorporates the capability to support hurricane-modeling simulations with collaborators at NASA Ames in Mountain View, California, and elsewhere using the DRAGON testbed. Today, the DRAGON GMPLS software is deployed across the United States, through collaboration with the Internet2 HOPI testbed network, and globally, with deployment in Europe and Japan. Leveraging this reach, researchers at MIT Haystack Observatory link radio telescopes and correlation facilities in Massachusetts, Maryland, Europe and Japan for groundbreaking Very Long Baseline Interferometry (VLBI) studies.
"Time-critical e-science applications need to dynamically turn up, groom, route and transport high-capacity services of various protocols," said Brian P. McCann, chief strategy and marketing officer with ADVA Optical Networking. "All-optical, per-lambda transport is the future of e-science networking and we're excited to have our FSP 3000 be an important enabler for the DRAGON project."
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?