Latest in Data centric computing

Image credit:

IBM's new computers may change how we process big data

Shares
Share
Tweet
Share
Save

IBM HQ. INT. DAY.

An oppressive curtain of rain beats down against the window of this small meeting room in IBM's New York HQ. Two IBM scientists are engaging in excited conversation with a representative from the DEPARTMENT OF ENERGY while a third IBM employee sits at one end, removed from the action, chewing their pen and staring out of the window.

DOE REPRESENTATIVE:
What do you mean $300 million won't get me the two supercomputers I need?

SCIENTIST #1:
You're generating too much data. There isn't enough bandwidth for it all to go through.

DOE REPRESENTATIVE:
I don't understand. You're the supercomputer company, make it happen!

SCIENTIST #2:
No, it's not that. Look, each day the world generates 2.5 billion gigabytes of data. Honestly, processing it is the simple part. The hard part now is moving it to and from the chip.

DOE REPRESENTATIVE:
Can you explain it to me like I'm a child?

SCIENTIST #1:
Imagine that you run some water through a generator, like a hydroelectric dam. Building and running a dam is the easy part, it's the miles and miles of waterways each side to move the water -- that's the problem.

DOE REPRESENTATIVE:
So the issue is that there's too much water to move efficiently.

SCIENTIST #2:
Bingo.

DOE REPRESENTATIVE:
So how do we fix it?

SCIENTIST #2:
That's the problem. We can't.

DOE REPRESENTATIVE:
Then I'm just gonna have to take this $300 million somewhere else.

The DOE REPRESENTATIVE gets up to leave, just then, SCIENTIST #3 turns around in his chair to face the audience. Except it's not a scientist, but DON DRAPER from popular TV series Mad Men.

DON DRAPER:
Wait. What if you didn't have to move the water at all?

There is a STUNNED SILENCE.

DON DRAPER picks up a WHITEBOARD MARKER, gets up, and begins scribbling on the wall.

DON DRAPER:
What if we created something called "Data Centric Computing," that, rather than pumping information in and out of supercomputers, we put the processing power into the data itself.

SCIENTIST #2:
But that's impossible.

DON DRAPER:
Think about it. If we put computing power on every stage of the process, then we won't have to move the data at all. It'll be like putting a tiny hydroelectric dam on every river in the country. That's how you get the power you need.

DOE REPRESENTATIVE:
Make it happen. I want one in the Lawrence Livermore National Laboratory and one in the Oak Ridge National Laboratory by 2017.

The DOE REPRESENTATIVE hands over a check for $300 million. The SCIENTISTS sit, open mouthed in admiration. DON DRAPER goes over to the cabinet and fixes himself a large glass of Woodford Reserve, no ice.

From around the web