Just over 50 years ago, on February 20, US astronaut John Glenn blasted into space in his tiny Friendship 7 capsule. His three quick trips around the Earth made him the first American to orbit the planet.
A team of more than 70 IBMers headed by Arthur Cohen as manager of the IBM Space Computing Center in Washington, D.C., had developed the computing systems to manage the launch, orbit and reentry for NASA’s Mercury program. IBM systems manager Saul Gass watched the launch from a grandstand at Cape Canaveral . “Think about the time, 1962. This had never been done before” says Gass, who is professor emeritus at the University of Maryland. ” There was a man in the loop whose life depended on our calculations. It was a demonstration of real-time computing.”
Beginning in the mid-1940s and continuing after the Glenn flight, IBM’s scientists and engineers have contributed substantially to astronomy and manned space exploration, but, today, they’re entering an exciting new phase of discovery. IBM scientists in Zurich, Switzerland, and the Netherlands are working with the Netherlands Institute for Radio Astronomy (ASTRON) to develop a massively powerful computing system for harvesting a huge quantity of data gathered by the international Square Kilometre Array (SKA) radio telescope.
The project demonstrates once again the belief that major advances in human achievement and knowledge come through a combination of big bets and bold scientific inquiry.
The telescope, targeted for completion in 2024, will map more than one billion galaxies, with the ultimate goal of exploring the origins of the universe. “These events are the latest in a very long chain of efforts by mankind over hundreds of years to get a better understanding of the universe,” says Martin Schmatz, IBM’s technical lead on the project. “We’re venturing beyond the ability of people to travel in space.”
When President John F. Kennedy in 1961 announced America’s goal of sending a man to the moon within a decade, the technology did not exist to get the job done. But Kennedy trusted that if America’s scientists were given adequate resources and a compelling goal, they could deliver the moon shot. The same is true of the consortium of 20 nations, including European countries and the United States, which are behind the SKA project. They plan on inventing their way to the edge of the visible universe.
The team from IBM and ASTRON is determined to produce advances in chip and computer systems design that will make it possible to handle immense amounts of information–an exabyte of data every day–in real time. (That’s 1,073,741,824 gigabytes!) Their project, called DOME, will investigate emerging technologies that might ultimately be used in the SKA computing systems. They’ll discover how to transport the data from a giant cluster of radio antennae to a central location, how to filter and store the data, and how to do all of the processing in an energy efficient way. In addition, they’ll develop a system for making all the components work together most efficiently and effectively.
One of their biggest challenges is devising a suitable microprocessor architecture. Right now, according to Schmatz, the scientists are exploring the idea of packing thousands of low-frequency (and low-power-consuming) processors in a small space and using liquid cooling micro channels to carry away the heat.
While the joint project is focused on SKA, the partners see tremendous potential to use their advances to solve a wide range of so-called Big Data problems. The domains include health care, traffic and natural resources discovery–all of which call for analyzing a tremendous amount of data in real time. The two organizations are setting up the ASTRON & IBM Center for Exascale Technology, based in Drenthe, the Netherlands. Their goal: to boldly explore the far reaches not just of space but of data.