Introducing the Gizmag Store

IBM looks to new technologies for unprecedented data processing challenge

By

April 2, 2012

IBM and ASTRON (the Netherlands Institute for Radio Astronomy) are working to develop tech...

IBM and ASTRON (the Netherlands Institute for Radio Astronomy) are working to develop technologies for processing the raw data that will be generated by the Square Kilometre Array radio telescope

Image Gallery (3 images)

When completed in 2024, the Square Kilometre Array (SKA) will be the largest, most sensitive radio telescope ever created. It will consist of 3,000 individual ground-based dish antennas, linked to act as one big telescope – an arrangement known as an interferometer. While their combined total surface area will be about one square kilometer (0.39 sq mile), they will be spread out across a geographical area approximately 3,000 kilometers (1,864 miles) in width. They will be gathering about one exabyte of astronomical data per day, which is twice the amount of data that is handled by the World Wide Web on a daily basis. Today, IBM announced that it has partnered with ASTRON (the Netherlands Institute for Radio Astronomy), in an effort to develop computer systems that will be able read, analyze and store all of that data, and do so in an energy-efficient manner.

The five-year €32.9 million (US$43.8 million) project, known as DOME, will be based out of the new ASTRON & IBM Center for Exascale Technology, located in the Netherlands. SKA, on the other hand, is a collaborative effort involving 67 organizations located in 20 countries. The research goals for the radio telescope include the study of evolving galaxies, dark matter, and even the origins of the universe. That telescope will be located in either Australia or South Africa. Meeting its computing requirements will certainly be no easy task.

Putting it simply, the technology required for such an application just doesn’t exist yet ... or at least, not in a practical sense. According to the researchers, several million of today’s most powerful computers would be necessary in order to handle all that data. Instead, the team is looking towards emerging technologies that show promise. These include 3D stacked chips for maximizing energy efficiency, optical interconnect technologies and nanophotonics for optimizing large data transfers, and phase-change memory systems for data storage.

An artist's depiction of the Square Kilometre Array radio telescope

An artist's depiction of the Square Kilometre Array radio telescope

Existing radio telescopes, however, will play a part in the project. The data-processing optimization system used by the ASTRON-designed LOFAR (LOw-Frequency ARray) will be analyzed, and used as a starting point for the SKA.

Needless to say, the technologies developed should have applications not only for astronomy, but for information processing in general.

“Large research infrastructures like the SKA require extremely powerful computer systems to process all the data,”said Marco de Vos, Managing Director of ASTRON. “The only acceptable way to build and operate these systems is to dramatically reduce their power consumption. DOME gives us unique opportunities to try out new approaches in Green Supercomputing. This will be beneficial for society at large as well.”

More information is available in the video below.

Source: IBM, SKA

About the Author
Ben Coxworth An experienced freelance writer, videographer and television producer, Ben's interest in all forms of innovation is particularly fanatical when it comes to human-powered transportation, film-making gear, environmentally-friendly technologies and anything that's designed to go underwater. He lives in Edmonton, Alberta, where he spends a lot of time going over the handlebars of his mountain bike, hanging out in off-leash parks, and wishing the Pacific Ocean wasn't so far away.   All articles by Ben Coxworth
7 Comments

Can we build it in Africa? They don't get enough love.

Joel Detrow
2nd April, 2012 @ 02:08 pm PDT

Instead of building square kilometer aray in Africa, use the money more wisely and scrap the project.

Gift the money to Africa, so it can actually do something of lasting value.

There are many existing projects running but which are lacking ongoing financial resourses.

One such project, is providing water wells to the many villages which still do not have that most basic of requirements.

2640-3690
2nd April, 2012 @ 07:47 pm PDT

Im, in Australia, I would ADORE it here as it would be in Western Australia and the East gets all the sporting events ... and this MAY just shake us out of the "Sporting Nation" philospophy ... And we have more political stability and greater infrastructure here to support the communities and appeal of others moving to OZ to work on it . BUT Africa does need more love. Its not wrong to grant it to Africa.

Andrew Kubicki
2nd April, 2012 @ 08:21 pm PDT

ME: "one exabyte per day?, that doesn't sound soo bad"

WolframAlpha: 1EB/day = 92.59 Tb/s (11.57 TB/s)

ME: "never mind..."

Ingo
3rd April, 2012 @ 01:27 am PDT

@ 2640-3690: I live in South Africa and have a number of friends working on the SKA project. We do not have a lot of villages without wells in South Africa, we have cities and towns with sophisticated water treatment plants. Granted, some of those are a bit run down but that's due to municipal corruption and mismanagement. Giving money is not going to change that; it will in fact make it worse. Let them sort their own problems out. SKA is doing significantly more through long term advancement of skills and capability as well as instilling a MUCH needed interest in maths and science under school children.

@Andrew: It's a pity there can only be one. Thanks for the comment. We can really do with the boost in science and technology interest among the general population. Best of luck and may the best team win.

Francois Retief
3rd April, 2012 @ 08:51 am PDT

While the push for more efficient chips is great especially for laptop users, just put a good waste heat recovery system on the data center and build a Nuclear power plant that provides at least an order of magnitude more electricity than the data center needs.

Slowburn
3rd April, 2012 @ 05:11 pm PDT

Might as well end the project where it started, and use the money to improve existing arrays such as ALMA (http://www.gizmag.com/alma-telescope-first-image/20050/).

Tinkerfan
11th April, 2012 @ 02:40 pm PDT
Post a Comment

Login with your gizmag account:

Or Login with Facebook:


Related Articles

Just enter your friends and your email address into the form below

For multiple addresses, separate each with a comma




Privacy is safe with us because we have a strict privacy policy.

Looking for something? Search our 26,490 articles