Near Geneva, on the Swiss-French border, scientists at the European Organization for Nuclear Research (still known as CERN) are readying the particle accelerator called the Large Hadron Collider (LHC), which will look for the fundamental building blocks of matter by smashing two beams of protons traveling near the speed of light in opposite directions into each other. The resulting bursts of energy and subatomic particles will be so complex and rich in detail that even the fastest computers will be unable to keep up with the torrent of data produced. In this month's feature "Old World, New Grid", authors Fabrizio Gagliardi and Francois Grey examine the alternative researchers are putting in place to store and analyze results from the LHC's experiments.
The initiative is a massive distributed grid computing system dubbed the European Union Enabling Grids for E-sciencE (EGEE). Its creators are attempting to securely federate some 100 000 computers of all kinds via the Internet and various private networks, chiefly among scientific and educational enterprises in Europe, Asia, and North America. With 20 000 CPUs already connected to the EEGE, the new grid now has a storage capacity of about 5 million GB and a global network connecting some 200 sites in places like Paris, Moscow, Taipei, and Chicago, making it the world's largest general-purpose scientific computing grid, according to the authors.
Gagliardi, a senior staff member at CERN was, until recently, the director of the EGEE project and now serves as director for technical computing in Europe, the Middle East, Africa, and Latin America for Microsoft Corp. Grey manages communications and outreach activities for the information technology department at CERN. They write that EEGE attempts to maximize high-throughput computing in order to deal with large amounts of similar but independent calculations by chopping processes into smaller pieces that can be solved in parallel.
Gagliardi and Grey believe the EEGE will be able to accomplish its mission of identifying the most exotic and mysterious fragments of the universe, but not before hurdling a few potential obstacles. "[T]he grid will catch on only if researchers—who are, in general, fussy customers—are convinced that it gives them big gains and little pain," they write. "Botched processing jobs or poor user interfaces could easily turn off such users, who would probably stay with local resources even if they were no match for the grid."
Somewhere out there an incredibly important yet infinitesimally small physical object is just waiting to make contact with us. Let's hope we'll have the sheer computing power to make sure we find it.