SKA Telescope To Provide a Billion PCs Worth of Processing

Sharky2009 writes "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)."

Comments

thousand million?

[Lord Ender]

(about one thousand million 1Gb memory sticks each day)

Could we get that in LoC's? Also, could we stick to the standard "one million thousands" unit, please?

Re:thousand million?

[rubycodez]

could we please stick to serious measures of information within the field of IT instead of silly printer paper units, how many station wagons full of 9 track tape is that?

Re:thousand million?

[rm999]

A thousand million is probably the most correct term for international understanding.

There is no world standard term for one thousand million. In the US and most of the UK we call it a "billion", but in several countries a billion means a million million. In these countries, a thousand million is usually called "a thousand million" or a "milliard", but I've never seen "a million thousand".

Re:thousand million?

[afidel]

The long rule is stupid, if you are going to use units as big as a million million just use scientific notation.

Re:thousand million?

[Lord Ender]

Here's the way it works:

In the US and the UK, the number is officially called "billion." In India, it's called "100 Crore." Australia officially has no idea how they do their numbers, and Canada doesn't even know what language it speaks. There are no other English-speaking countries of consequence.

Therefore, "billion" is the most acceptable term for international English-language writing.

Re:thousand million?

[idontgno]

Maximum diameter of 10.5". Tape width was 1/2". The protective ring around the tape reel would add about another 1/4" to the diameter, and the thickness of the reel sides and retaining ring would add about another 1/4" to the thickness.

We're not going for a rigorous space-filling solution; we'll stack the tapes in a square array (rather than, say, a hexagonal one). So the tapes effectively become 10.75"^2 x .75" rectangular prisms. That's 0.0501573351 cubic feet per tape.

According to this scan of the 1972 Mercury station wagon brochure, the 1972 Montego MX had 91.6 cu ft of cargo space. That's 1826 tapes. (Assuming dimensions of tapes and station wagon are compatible and don't leave some wasted modulus.) So 1,000 tapes is in the right order of magnitude, but a smidge low. Good guess. But your "number of cars" division was off by a factor of ten. Using the correct version of your numbers, 58,820,000 tapes transported 1000 tapes at a time is 58,820 loads. Using the 1,826 tapes per load number, it works out to 32,213 loads.

I calculate that the capacity of a station wagon full of 9-track tapes works out to 310 GB. (170 MB per late-era IBM 3400-series tape reel at maximum length, 32K blocking, and 6250BPI. At least that's what Wikipedia says.)

Hmm... I wonder if the various IP performance calculations would work out for a MTU of 310GB and a ping time of minutes to hours (depending on trip length and freeway speeds)....

What?

[Anonymous Coward]

SKA telescope? Madness!

since when did slashdot provide BS units?

[Fulcrum of Evil]

Seriously, how is a PC a unit of processing ability? And one thousand million GB sticks is an Exabyte (hence the name). Perhaps you can just say 10^18 bytes. This is slashdot, not msnbc.

Re:since when did slashdot provide BS units?

[clem.dickey]

Original article also compares a Peta of floating ops per *second* to an Exa of byte "processing and storing" per *day.* Journalism profs should save that article for class discussion.

Re:since when did slashdot provide BS units?

[NoYob]

Seriously, how is a PC a unit of processing ability? And one thousand million GB sticks is an Exabyte (hence the name). Perhaps you can just say 10^18 bytes. This is slashdot, not msnbc.

Some of us went and got an MBA; upon which, it knocked tens of points off of our IQ.

Now, 10 carrots 18? 18 what? Rabbits?

It should read 10 carrots and 18 rabbits!

And people say I'm stewped!

Re:since when did slashdot provide BS units?

[T Murphy]

He's just giving you a good comparison so you can picture an equivalent system using everyday objects. Kind of like how instead of just saying "Bob is tall", you should use strong imagery like "Bob is as tall as a 6-foot-4-inch tall tree"

Re:Ska?

[colmore]

Hey, IBM, you dropped your telescope.

Someone should pick it up, pick it up, pick it up, pick it up.

That was a lame way of putting the data numbers

[MartinSchou]

about one thousand million 1Gb memory sticks each day

First of all, no one would be using manual storage to transfer the data.

Just throw up some numbers that makes sense to us. Like 99,420.5393 gigabit/second.

Most large ISPs use OC-192 as the backbones of their infrastructure. You'd need more than 10,200 of those to handle that data load, and that's ignoring the overhead.

Or to put it into numbers that the RIAA can understand: 1.5707309 * 10^9 music CDs every single day.

At 15 pieces of music per CD and $80,000/song that's $1.88 * 10^15 dollars/day flowing through that network. That's 632 times larger than the US federal budget for 2008.

No wonder the music industry is in trouble!

Imagine a...

[jedigeek]

Imagine a beowulf of those

omglol!

Re:Hard disks "somewhat unreliable"?

[kalirion]

And I have an uncle who smoked a pack a day for 40 years and never got lung cancer.

Re:Where are they going to store it all?

[Pretzalzz]

Maybe they could construct a really fast computer to process the data in real time so they wouldn't have to store it all. They might even release a press release about it.

From the FAQ...

[sker]

From the FAQ:

How far can this telescope see?

A: ONE STEP BEYOND!

Interferometry generates lots of data

[The_Duck271]

Some people might be interested in knowing where all this data comes from. There's a rule of thumb in astronomy that the angular resolution of your images is the wavelength of the radiation you're receive divided by the diameter of your telescope. Radio wavelengths are pretty long (up to tens of meters), so you need really big telescopes, which you get by scattering lots of little telescopes all over the place and then looking at the how the phase of the incoming radiation shifts based on location. So what you do is you sample the voltage of each antenna with 1 or 2 bits of resolution at the Nyquist frequency. So for 100Mhz radio waves you sample at 200MHz. That's 50MB/s for a single antenna. The SKA will likely have tens of thousands of little antennas scattered all over the place. So say 50MB/s times 20,000 antennas = 1TB/s = 100 petabytes/day, which is about what the summary says.

Now, it's not quite as bad as it looks. You don't have to pipe all this data to a central point to analyze it. You can take a small group of antennas and just look at the correlations between those, combine the data from that group and send the combined data to a second level of correlators, which takes data from a set of small groups, and so on, in a hierarchical fashion. You lose some information this way, but you get most of it, and the only wa to get all the information out of the data would be to bring it all to a central processing location so that data from all antennas could be compared to that of all other antennas, which is O(N^2) in the number of antennas and obviously infeasible for a telescope like the SKA. Even as it is, the system of hierarchical data collection is really pushing Moore's law, as the article shows.