The article on the news.com.au site featuring that eye-popping spec reported that IBM has "agreed to research and develop IT systems for the transfer, management, processing and storage of the vast amount of radio astronomical data likely to be produced by the SKA."
And if that's not enough of a head-bender, another article about the project, this one on the slashdot.org site, said IBM believes the gizmo it needs to create to handle all that data will require the processing power of a billion PCs. Yep, a billion-with-a-B PCs, as per the slashdot post:
"IBM is researching an exaflop machine with the processing power of about one billion PCs. The machine will be used to help process the Exabyte of data per day expected to flow off the Square Kilometre Array (SKA) telescope project. The company is also researching solid state storage technology called 'racetrack memory' which is much faster and denser than flash and may hold the secret to storing the data from the SKA. The story also says that the SKA is unlikely to use grid computing or a cloud-based approach to processing the telescope data due to challenge in transferring so much data (about one thousand million 1Gb memory sticks each day)."
An interesting effort for IBM to pursue: just as IBM is positioning business analytics as one of its key initiatives because of that technology's ability to help predict future developments, it is also taking up this extraordinary project to look into the opposite direction, billions of years into the past, to see not so much where we are headed but instead where we have been.
I may think of IBM in a whole new way: the Time Machine company.