Trade.Information

GridPP Collaboration Has Successfully Constructed a Distributed Computer System for Scientists Working on the World's largest Experiment, the Large Hadron Collider

UK scientists building a computing Grid for particle physics have launched the next phase of their project, in advance of the start of the world’s largest experiment. Over the last six years, the GridPP collaboration has successfully built a distributed computer system for scientists working on the world's biggest experiment, the Large Hadron Collider (LHC) at CERN near Geneva. The Science and Technology Facilities Council (STFC), has extended the project for another three years which ensures that the expertise built up in the UK will be there for the start of the LHC later this year and for the crucial first years of data taking. The data crunching and storage capabilities of the Grid are essential to the LHC’s science mission of exploring the fundamental particles and forces of nature.

The LHC is currently in the final stages of commissioning at CERN, the European particle physics laboratory in Geneva. Once switched on, expected to be in July 2008, it will collide sub-atomic particles inside cathedral-sized detectors, searching for clues to how the universe works. But to discover the next generation of physics, scientists will need to sift through the petabytes (100,000s of Gigabytes) of data that the experiment will produce.

To store and analyse this data will require a whole new approach to computing - the world’s largest scientific computing Grid, a massive co-ordination of over 50,000 CPU in 50 countries, creating a virtual supercomputer that can be expanded and adapted. GridPP is the UK’s contribution to this Grid, with 10,000 CPU and 700TB (700,000 Gigabytes) of disk storage at 17 sites in the UK. The GridPP grid has already been helping scientists run simulations to prepare for the LHC, running over 7 million computer programs in 2007.

Dave Britton, GridPP's new project leader is looking forward to the future of the project “I am excited to be leading the project as we move into the phase that will start to produce physics. The infrastructure that we have been building up will now be required to process huge amounts of information produced at CERN. With the LHC turn on just months away there is intense excitement, and a certain amount of understandable trepidation, amongst the collaboration but I am sure we will overcome the challenges that are going to be presented in the coming years. ”

GridPP has been developing the system in conjunction with international partners and has been a leading force in the development of the Grid. In the UK the Grid has been a fully functional system for a number of years helping out other sciences and has recently passed the first computing readiness challenge for the LHC and is preparing for the second. The ultimate test for the group can only come from handling real data in real time.

Tony Doyle has been Project Leader since the beginning of GridPP “It has been 7 years since we first bid to start work on the computing challenge that the LHC would present. We have come a long way since then and have achieved our goal of a large-scale production computing system for particle physicists in the UK. This next phase of the project will build upon this success as we enter the exploitation phase providing the necessary computing and data services required for LHC and other user analyses.”

GridPP's main objective is to allow British scientists to process the data they need from the LHC to ensure that the UK is at the cutting edge of this important and ground-breaking new work. To this end, GridPP works very closely with these scientists to ensure their needs are being met. Roger Jones, Chair of the International Computing Board for ATLAS, one of the biggest experiments at the LHC, is glad to see that the UK has provided continued funding. “The ATLAS collaboration in the UK is delighted that GridPP has again been funded by STFC. Without this infrastructure, LHC physics in the UK would be almost impossible. I am very confident that the project is ready to deal with the impending challenges of the next few years and that physics, and science, in the UK will benefit from their experience.”

Grid computing, which was originally conceived by scientists in the US, does not replace the Internet or the Web, but relies on both.

Note for Grid Computing
Grid computing is a phrase in distributed computing which can have several meanings:
Multiple independent computing clusters which act like a "grid" because they are composed of resource nodes not located within a single administrative domain. (formal)
Offering online computation or storage as a metered commercial service, known as utility computing, computing on demand, or cloud computing.
The creation of a "virtual supercomputer" by using spare computing resources within an organization.
The creation of a "virtual supercomputer" by using a network of geographically dispersed computers. Volunteer computing, which generally focuses on scientific, mathematical, and academic problems, is the most common application of this technology.

Functionally, one can also speak of several types of grids:
Computational grids (including CPU scavenging grids) which focuses primarily on computationally-intensive operations.
Data grids or the controlled sharing and management of large amounts of distributed data.
Equipment grids which have a primary piece of equipment e.g. a telescope, and where the surrounding Grid is used to control the equipment remotely and to analyze the data produced.

"Distributed" or "grid" computing in general is a special type of parallel computing which relies on complete computers (with onboard CPU, storage, power supply, network interface, etc.) connected to a network (private, public or the Internet) by a conventional network interface, such as Ethernet. This is in contrast to the traditional notion of a supercomputer, which has many processors connected by a local high-speed computer bus.

The primary advantage of distributed computing is that each node can be purchased as commodity hardware, which when combined can produce similar computing resources to a multiprocessor supercomputer, but at lower cost. This is due to the economies of scale of producing commodity hardware, compared to the lower efficiency of designing and constructing a small number of custom supercomputers. The primary performance disadvantage is that the various processors and local storage areas do not have high-speed connections. This arrangement is thus well-suited to applications in which multiple parallel computations can take place independently, without the need to communicate intermediate results between processors.

The high-end scalability of geographically dispersed grids is generally favorable, due to the low need for connectivity between nodes relative to the capacity of the public Internet. Conventional supercomputers also create physical challenges in supplying sufficient electricity and cooling capacity in a single location. Both supercomputers and grids can be used to run multiple parallel computations at the same time, which might be different simulations for the same project, or computations for completely different applications. The infrastructure and programming considerations needed to do this on each type of platform are different, however.

There are also some differences in programming and deployment. It can be costly and difficult to write programs so that they can be run in the environment of a supercomputer, which may have a custom operating system, or require the program to address concurrency issues. If a problem can be adequately parallelized, a "thin" layer of "grid" infrastructure can allow conventional, standalone programs to run on multiple machines (but each given a different part of the same problem). This makes it possible to write and debug programs on a single conventional machine, and eliminates complications due to multiple instances of the same program running in the same shared memory and storage space at the same time.

About Large Hadron Collider
The Large Hadron Collider (LHC) is a particle accelerator located at CERN, near Geneva, Switzerland. It lies in a tunnel under France and Switzerland.

It is currently in the final stages of construction, and commissioning, with some sections already being cooled down to their final operating temperature of ~2K. The first beams are due for injection mid June 2008 with the first collisions planned to take place 2 months later. The LHC will become the world's largest and highest-energy particle accelerator. The LHC is being funded and built in collaboration with over two thousand physicists from thirty-four countries as well as hundreds of universities and laboratories.

When activated, it is theorized that the collider will produce the elusive Higgs boson, the observation of which could confirm the predictions and "missing links" in the Standard Model of physics and could explain how other elementary particles acquire properties such as mass. The verification of the existence of the Higgs boson would be a significant step in the search for a Grand Unified Theory, which seeks to unify the three fundamental forces: electromagnetism, the strong nuclear force and the weak nuclear force. The Higgs boson may also help to explain why gravitation is so weak compared to the other three forces. In addition to the Higgs boson, other theorized novel particles that might be produced, and for which searches are planned, include strangelets, micro black holes, magnetic monopoles and supersymmetric particles.

The collider is contained in a circular tunnel with a circumference of 27 kilometres (17 mi) at a depth ranging from 50 to 175 metres underground. The tunnel, constructed between 1983 and 1988, was formerly used to house the LEP, an electron-positron collider.

The 3.8 metre diameter, concrete-lined tunnel crosses the border between Switzerland and France at four points, although the majority of its length is inside France. The collider itself is located underground, with many surface buildings holding ancillary equipment such as compressors, ventilation equipment, control electronics and refrigeration plants.

The collider tunnel contains two pipes enclosed within superconducting magnets cooled by liquid helium, each pipe containing a proton beam. The two beams travel in opposite directions around the ring. Additional magnets are used to direct the beams to four intersection points where interactions between them will take place. In total, over 1600 superconducting magnets are installed, with most weighing over 27 tonnes.

The construction of LHC was originally approved in 1995 with a budget of 2.6 billion Swiss francs, with another 210 million francs (140 M€) towards the cost of the experiments. However, cost over-runs, estimated in a major review in 2001 at around 480 million francs (300 M€) for the accelerator, and 50 million francs (30 M€) for the experiments, along with a reduction in CERN's budget, pushed the completion date from 2005 to April 2007. 180 million francs (120 M€) of the cost increase have been due to the superconducting magnets. There were also engineering difficulties encountered while building the underground cavern for the Compact Muon Solenoid. In part this was due to allegedly faulty parts lent to CERN by fellow laboratories Argonne National Laboratory (home to the world's largest particle accelerator until CERN finishes the Large Hadron Collider) or Fermilab. The total cost of the project is anticipated to be between $5 and $10 billion (US Dollars).

In figure, Various Pictures of the cluster and racks at Queen Mary, University of London