June 25, 2009
Grids around the world, or the world as one big grid, a global community of computational science unbounded by nation states, scientists from Osaka to Oklahoma connected and communicating to solve problems, some of them really big ones that affect all of us — it’s where we’re headed, and it’s exciting to be part of the ride and helping to turn the wheels getting us there. Tuesday morning’s panel on “Global Grid Perspectives” gave a taste of the future while, at the same time, acknowledging some of the obstacles, such as the importance of standardization and the difficulties of funding.
Geographically, the panel circled the globe. It comprised leaders of grids in the European Union, Japan and the United Kingdom — Hermann Lederer of DEISA (Distributed European Infrastructure for Supercomputing Applications), Kenichi Miura of Naregi (Japan’s National Research Grid Initiative Project), and Peter Coveney of the UK’s eScience. John Towns of the TeraGrid moderated.
Presentations showed many similarities among the three grids, and highlighted a few beginning steps at interoperability among them. The Application Hosting Environment interface developed by Coveney and colleagues for eScience is also used by DEISA as part of its ambitious Virtual Physiological Human project, which Coveney highlighted in an earlier talk on Tuesday morning. NAREGI’S interface software, NAREGI v. 1.0, is a testbed project at the EU supercomputing center in Lyon, France. Interoperability is important, emphasized Miura and the other speakers, and must be kept up with, since just because it works for a particular application at a particular point in time doesn’t mean it will work in the future, as the software systems involved are constantly evolving.
Towns asked the panelists to identify next steps in advancing global grid interactions. Lederer emphasized the chicken and egg problem of funding, with national agencies being reluctant for political reasons to provide support for multi-continental projects. For this reason, said Lederer, the ball is with the cyberinfrastructure projects to find ways to reach across borders to build productive collaborations.
Agreement in standards — for authentication, allocations, auditing and other areas — Coveney pointed out, is crucial and needs to be addressed with continuous effort. To drive the point home, Lederer, asked rhetorically “Why did homo sapiens survive while Neanderthal man didn’t?” The answer: communication. The ability to collaborate on ever wider scales on problems that imperil the species is still testing the survival abilities of homo sapiens.
by Michael Schneider, Pittsburgh Supercomputing Center
Posted by by Michael Schneider, Pittsburgh Supercomputing Center - June 25, 2009 @ 11:47 AM, Pacific Daylight Time
No Recent Blog Comments
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?