×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

New Supercomputer Boosts Aussie SKA Telescope Bid

Soulskill posted more than 2 years ago | from the it's-not-the-size-of-your-cluster-it's-how-you-use-it dept.

Australia 32

angry tapir writes "Australian academic supercomputing consortium iVEC has acquired another major supercomputer, Fornax, to be based at the University of Western Australia, to further the country's ability to conduct data-intensive research. The SGI GPU-based system, also known as iVEC@UWA, is made up of 96 nodes, each containing two 6-core Intel Xeon X5650 CPUs, an NVIDIA Tesla C2050 GPU, 48 GB RAM and 7TB of storage. All up, the system has 1152 cores, 96 GPUs and an additional dedicated 500TB fabric attached storage-based global filesystem. The system is a boost to the Australian-NZ bid to host the Square Kilometer Array radio telescope."

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered

32 comments

Christmas (0)

Anonymous Coward | more than 2 years ago | (#37537014)

Well, that's my Christmas list sorted - and it's only September :-)

And still... (2)

Zaldarr (2469168) | more than 2 years ago | (#37537038)

And still it can't run Crysis...

Re:And still... (2)

Anubis350 (772791) | more than 2 years ago | (#37537096)

Not that the c2050's drivers are optimized for gaming, but it certainly has the grunt to play games, I've done it on the one in my tower right now :-p

Re:And still... (0)

Anonymous Coward | more than 2 years ago | (#37538582)

And will not be able to run Battlefield 3 as well...

So ... (1)

Mick R (932337) | more than 2 years ago | (#37537070)

should we put another GPU on the barbie for them?

Re:So ... (3, Informative)

crutchy (1949900) | more than 2 years ago | (#37537098)

c'mon... we don't "put" anything on the barbie here. stuff is always chucked on :)
i hope australia gets the ska. we have a factional space industry, but every bit extra helps

Small fry (2)

Axman6 (1562517) | more than 2 years ago | (#37537196)

This machine is tiny compared to at least one other open supercomputer in Australia, the Vayu [nci.org.au] cluster at the National Computing Infrastructure's NAtional Facility in Canberra, which has a bit less than 12,000 cores, several petabytes of storage (tape and disk), and I believe some GPU's attached (the Xe [nci.org.au] system at the NCI NF has 16 Fermi cards).

In the scheme of things, this probably won't help the bid much at all given its small size (and the truly astronomical amount of data the SKA will produce). But that said, it can't hurt. As someone who hopes to one day work on the compute infrastructure and systems show Australia get the SKA, I do hope very strongly that we do win the bid.

Re:Small fry (0)

Anonymous Coward | more than 2 years ago | (#37537344)

Heck, there is one at Murdoch now that has 9600 cores and that's just down the road. See this link [ivec.org].

Note for people in other parts of the world, 'just down the road' for the state larger than Texas is probably the entire length of your country.

Re:Small fry (1)

ciderbrew (1860166) | more than 2 years ago | (#37537478)

I've never been able to get my head around that fact. When an Aussie says "A 3-day drive". He's not using the UK understanding. Drive for a little bit, park up, sleep and set off the next day. He means a 72 hour drive add extra for sleep. The place is HUGE!

Re:Small fry (0)

Anonymous Coward | more than 2 years ago | (#37538468)

Google Maps gives the driving time from Brisbane to Geraldton (on opposite sides of the country) as 2 day 3 hour drive.

The drive time from Halifax to Vancouver, in Canada (from the east to west coast of N. America) takes about 2 1/2 days of driving.

I'd also note that in Canada, where long drives aren't unusual, we measure drive times like you do in the UK. It's the only reasonable way to do it.

Re:Small fry (1)

TrogL (709814) | more than 2 years ago | (#37540982)

I've done most of that drive. I'd place it closer to 5 days. It's 16 hours from Edmonton to Vancouver alone.

Who is building the thing? (0)

Anonymous Coward | more than 2 years ago | (#37537402)

It is funny that nobody ever talks about who is actually building the telescope parts, nevermind where it will be installed. It seems that Tellumat in South Africa is building the low noise receivers, but who is making the rest of the kit?

Re:Who is building the thing? (1)

commlinx (1068272) | more than 2 years ago | (#37538994)

but who is making the rest of the kit?

Rolf Harris is making a modified versions of his wobble board [wikipedia.org] modified for resonance at RF frequencies. If you go to his official website listed under references the FAQ describes how to construct your own.

SA's bid (0)

garatheus (993376) | more than 2 years ago | (#37537466)

As a South African, I really hope that we're able to have the SKA Telescope here. The problem is, that the bandwidth issue is still a major issue, and providing the infrastructure to it in a remote area seems like a bit of a problem, especially considering that in the last report I read on it, that Telkom (the monopoly that keeps us constrained from really getting any decent level of Internet technologies at a reasonable price).

Of course, this is where a third party should step up to provide the infrastructure (since there's going to be a lot of GB's of data coming from there on a daily basis) and will obviously provide some much wanted media attention to said company... And of course yet again show how much Telkom is really ripping off the people that helped create the company that it is (since part of the infrastructure was paid for by our taxes, way back when - and since its a multi-billion Rand profit operation, I'm sure they could really afford to lower the prices to something reasonable instead of just simply ripping us off).

I guess it would also help if we stopped investing in building our own, failing satellites (and paying large sums of money to get them into space, again thanks largely to the tax payer) and invested in things that really matter (housing, electricity [which keeps going up and up, even though its Eskom's fault / government for failing to predict the usage requirements and not meeting adequate demand], water, and job creation) instead of wasting money on things that aren't really that important to us in the end.

But the SKA will at least be an impressive scientific feat that helps the global community (rather than just our nation), so I'm all for it!

Re:SA's bid (1)

garatheus (993376) | more than 2 years ago | (#37537484)

As a South African, I really hope that we're able to have the SKA Telescope here. The problem is, that the bandwidth issue is still a major issue, and providing the infrastructure to it in a remote area seems like a bit of a problem, especially considering that in the last report I read on it, that Telkom (the monopoly that keeps us constrained from really getting any decent level of Internet technologies at a reasonable price).

has tripled the expected cost of providing the infrastructure to the SKA site.

Re:SA's bid (-1)

Anonymous Coward | more than 2 years ago | (#37537498)

As a South African, I really hope that we're able to have the SKA Telescope here. The problem is, that the bandwidth issue is still a major issue, and providing the infrastructure to it in a remote area seems like a bit of a problem, especially considering that in the last report I read on it, that Telkom (the monopoly that keeps us constrained from really getting any decent level of Internet technologies at a reasonable price). Of course, this is where a third party should step up to provide the infrastructure (since there's going to be a lot of GB's of data coming from there on a daily basis) and will obviously provide some much wanted media attention to said company... And of course yet again show how much Telkom is really ripping off the people that helped create the company that it is (since part of the infrastructure was paid for by our taxes, way back when - and since its a multi-billion Rand profit operation, I'm sure they could really afford to lower the prices to something reasonable instead of just simply ripping us off). I guess it would also help if we stopped investing in building our own, failing satellites (and paying large sums of money to get them into space, again thanks largely to the tax payer) and invested in things that really matter (housing, electricity [which keeps going up and up, even though its Eskom's fault / government for failing to predict the usage requirements and not meeting adequate demand], water, and job creation) instead of wasting money on things that aren't really that important to us in the end. But the SKA will at least be an impressive scientific feat that helps the global community (rather than just our nation), so I'm all for it!

Leave science to the white-boys and get back in your tree

Re:SA's bid (0)

Anonymous Coward | more than 2 years ago | (#37538774)

Who says he's not? Ignorant fool.

Re:SA's bid (1)

Chrisq (894406) | more than 2 years ago | (#37539406)

Leave science to the white-boys and get back in your tree

Who says he's not? Ignorant fool.

Who says he's not what? In a tree?

Re:SA's bid (1)

fezzzz (1774514) | more than 2 years ago | (#37537526)

Technology in South Africa is being developed at a rapid pace as their bid for SKA is gaining ground. With the completion of the first 7 antennas on the KAT-7 [ska.ac.za] project, the first use of composite materials for dish reflectors. With Namibia, Botswana, Mozambique, Zambia, Mauritius, Madagascar, Kenya and Ghana partnering with South Africa [africagoodnews.com] in the bid, Africa seems to have overcome all the major obstacles associated with the project. Nokia is willing to supply the 15 petabyte per second infrastructure and EMSS Antennas [mybroadband.co.za] have already built the first seven cryogenic low noise amplifiers. 64 dishes for the MeerKAT [wikipedia.org] project has just been approved and after completion it will be one of the largest, most sensitive radio telescopes in the world."
Link to Original Source [iol.co.za]

Km2? Not a lot for radio astronomy anymore. (2)

niktemadur (793971) | more than 2 years ago | (#37537656)

Considering that the distance between 2 or more synchronized antennae becomes part of the radio telescope itself, the RadioAstron [newscientist.com] gives me chills just thinking about it, some astonishing science should come out of this bad boy.

Re:Km2? Not a lot for radio astronomy anymore. (1)

RogerWilco (99615) | more than 2 years ago | (#37547756)

While space based VLBI is certainly cool, and some of the components in RadioAstron were developed at my company, it doesn't compare to the SKA.

The RadioAstron has a 10 m antenna, so about 75 m2 collecting area. The SKA will have a of about 1000000 m2. (square kilometer). The baselines will be up to 6-7000 km long in some possible variants, compared to the 189000km of the Radioastron.

So the spacial resolution might be a bit smaller (7000/189000 = 0.037), but the sensitivity is much lower (75/1000000=0.000075)

And that doesn't take into account that you can have a much larger data connection to a groundbased system, increasing the resolution in time and/or frequency, and the bandwidth you can observe.

Re:Km2? Not a lot for radio astronomy anymore. (0)

Anonymous Coward | more than 2 years ago | (#37551416)

it's a cumulative square kilometre of dish, not a square kilometre of dishes

Wow... (1)

mjpaci (33725) | more than 2 years ago | (#37540566)

This is totally one step beyond! It's madness!

Re:Wow... (0)

Anonymous Coward | more than 2 years ago | (#37540932)

Given his interest in astronomy, I'm sure William Shatner [wikipedia.org] would approve.

Some of the images it produces will certainly be Specials [wikipedia.org], but will they be 2 tone [wikipedia.org]?

Still too small... (1)

DerekLyons (302214) | more than 2 years ago | (#37541196)

In other words, their new "supercomputer" still brings less to the table than all but the smallest of BOINC projects.

Re:Still too small... (1)

neonsignal (890658) | more than 2 years ago | (#37547338)

apart from decent working memory for each node, low inter-node latencies, and a filesystem

Re:Still too small... (1)

RogerWilco (99615) | more than 2 years ago | (#37548210)

The main thing actually is bandwidth.

Radioastronomy needs a lot of CPU power, but compared to other things like the stuff that uses BOINC, it needs a lot of bandwidth.

For example our current LOFAR system handles 200 Gb/s with a 12.000 core BlueGene and a ~3200 core, 200 machine cluster and about 6 PB of storage.

At full resolution we would write 2 PB per 24 hours.

With 2 million BOINC users, it would require an average stream of about 1 Mb/s per user, if each of them is online for 2.4 hours a day.

In other words, it's about the same bandwidth as all torrents in the USA combined (20% of ~1 Tb/s average USA bandwidth)

Yes. We're basically processing the same bandwidth as of all the torrents in the USA. Now we don't have the biggest BlueGene in the world. Much bigger versions have been purchased by customers not disclosed by IBM, but probably in the NSA/CIA/FBI/DHS corner, making at least a few capable of processing the internet in real time.

LOFAR (1)

RogerWilco (99615) | more than 2 years ago | (#37547900)

The BlueGene Stella at LOFAR central processing currently does 37 TFLops, which is about the same as this new Fornax system the article mentions (40 TFlops).

The Stella was a big computer in 2005 in http://science.slashdot.org/story/05/05/01/2316248/When-Lofar-Meets-Stella [slashdot.org]

Not so impressive in 2011.

It's the difference between being #6 on the supercomputer top 500, or not even making it.

And while LOFAR is running several other clusters besides the Stella, and manages to handle 200 GB/s, SKA is supposed to handle 15 TB/s or more.

In other words, this is a nice computer, but a toy compared to what SKA will need.

Check for New Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Sign up for Slashdot Newsletters
Create a Slashdot Account

Loading...