PR10.01

20.09.2001

 

LHC Computing Grid Project

Launches into Action with International Support 

 

'A thousand times more computing power by 2006'

 

The first phase of the LHC Computing Grid project was approved at an extraordinary meeting of the CERN[1] Council on 20 September 2001.  CERN is preparing for the unprecedented avalanche of data that will be produced by the multinational experiments at its new particle accelerator, the Large Hadron Collider (LHC), the most powerful device of its kind ever built.

 

CERN's need for a dramatic advance in computing capacity is urgent.  As from 2006, the four giant detectors observing trillions of elementary particle collisions at the LHC will accumulate over ten million Gigabytes of data, equivalent to the contents of about 20 million CD-ROMs, each year of its operation.  A thousand times more computing power will be needed than is available to CERN today.

 

The strategy CERN has adopted to analyse and store this unprecedented amount of data is the coordinated deployment of Grid technologies at hundreds of institutes which will be able to search out and analyse information from an interconnected worldwide grid of tens of thousands of computers and storage devices.

 

CERN is not delving into this monumental project alone.  Three leading Information Technology firms: Enterasys Networks, Intel and KPNQwest have joined CERN to push forward this groundbreaking project in advanced distributed computing by sponsoring a virtual community called “Openlab” that will give nearly ten thousand scientists at hundreds of universities around the world to the data from the LHC.  Each company will invest 2.5 MCHF ($1.5M) over a period of 3 years to help CERN achieve its ambitious objectives. 

 

Significant investments are also being made by other participants in the LHC programme around the world, particularly in Europe, the US and Japan.  CERN and all of its partners will coordinate their activities to form the first 'virtual organisation' to adapt Grid technologies to a giant data-intensive, worldwide, computing problem. 

 

"We are faced with the largest data-intensive computing application foreseen in this decade," says Manuel Delfino, Leader of CERN’s Information Technology Division who will head the CERN openlab.  "We are planning how to exploit and index the tidal wave of data produced by the LHC.  We will certainly have to break new ground. However, similar  challenges  to the one we are meeting now will certainly be faced by many large corporations and institutions in the near future.” And such challenges have been met before, after all, the demands of international particle physics communication were the factors that gave birth to the Web at CERN some ten years ago. 

 

The Grid will be a very different beast from the Web though.  Grid technologies will be able to search out and analyse data from an interconnected worldwide grid of tens of thousands of computers and storage devices.  This extra capability of analysis will empower researchers to exploit information that is stored world wide much more efficiently.  Particle physics is the first community to exploit the potential of the Grid but meteorologists, biologists and medical researchers amongst many others are joining Grid collaborations.  Who knows - like the Web, Grid applications may eventually be taken for granted by an enormous community of users.