LHC is scheduled for start up in May 2008. It is estimated that it will produce approximately 15 petabytes of data per year. A petabyte corresponds to 1,540,000 ordinary 650 MB CDs.
Analyzing the data generated by LHC will require the efficiency equivalent to that produced by about 100,000 modern processors. Researchers will have access to this massive data through the grid technology, where data is distributed through the data network to several computing centers.
Distribution of data over different computing centers
The Tier “zero” (Tier0) center of CERN stores the raw data produced by the LHC (Large Hadron Collider) experiment. A part of the data is distributed to Tier1 centers, i.e., to regional supercomputer centers in, for example, Italy, France, Germany, and the USA. The Tier1 centers then forward the data to other national supercomputer centers called Tier2 centers. The Tier2 centers distribute the data to academic computing centers (Tier3) and finally, they distribute the data to scientists' workstations (Tier4).
LHC is being built in a circular tunnel 27 km in circumference. The tunnel is buried about 50 to 175 m underground. The LHC causes protons to collide with 14 TeV energy. TeV is a unit of energy used in particle physics. One TeV (teraelectron volt) is roughly equal to the kinetic energy of a flying mosquito. The LHC concentrates the energy into a space that is millions of times smaller than a mosquito.
Read more:
| Lehtovuori Pekka | Pekka.Lehtovuori at csc.fi |
