Award of $200M Supercomputer To IBM Proving Controversial 114
An anonymous reader writes "According to documents accidentally placed on a federal government Web site for a short time last week the national science foundation (NSF) will award the contract to buy a $200M supercomputer in 2011 to IBM. The machine is designed to perform scientific calculations at sustained speed of 1 petaflop. The award is already proving controversial however, with questions being raised about the correctness of the bidding procedure. Similar concerns have also been raised about the award of a smaller machine to Oak Ridge national lab, which is a Department of Energy laboratory, not a site one would expect to house an NSF machine."
Because... (Score:5, Funny)
Blue Gene/P (Score:2, Interesting)
http://www-03.ibm.com/press/us/en/pressrelease/21
Re: (Score:3, Insightful)
Might also be a second-generation Roadrunner [ibm.com].
Got a good laugh about someone calling you on astroturfing, somehow I doubt Slashdot posts affect purchasing decisions on supercomputers all that much.
Re: (Score:2)
Re: (Score:1)
BlueGene/P will go online at Argonne this year. The NSF sustained petascale machine is targeted for 2011. We can safely assume that IBM won't get away with proposing to get $200 million to use today's technology for a machine 4 years in the future. Which means it is either BlueGene/Q or something from the IBM PERCS line.
The NSF solicitation can be found here http://www.nsf.gov/pubs/2006/nsf06573/nsf06573.htm l [nsf.gov]
One controversy is that the NSF has already created supercomputer cente
Re: (Score:2)
Re:Because... (Score:4, Funny)
Re: (Score:1)
Re: (Score:1)
Is there a supercomputer powerful enough... (Score:3, Funny)
I'd prefer if HAL didn't open the pod bay doors, if Zonk were out there.
The DOE bit (Score:5, Insightful)
Re: (Score:3, Interesting)
Obviously you've never worked for a government contractor. A stage example:
1: CONTRACTOR, pacing in an untidy OFFICE filled with EQUIPMENT: "We need to order, configure and install this thing at 12/10s speed to meet deadline! Where the f*ck is the chimp from the CDW ads????"
(CRICKETS sing
2: CHIEF SCIENTIST, inside raised floor lab filled with immaculate, slab-sided computing machines
Re:The DOE bit (Score:4, Insightful)
Your little script makes no mention of Service Oriented Architecture.
If you're not buzzword-compliant, how can you be meaningful?
Re: (Score:1)
Re: (Score:2)
No, the beaurocratic blight occupies a triangle stretching from Baltimore to Fredricksburg to Dulles.
Re: (Score:2)
You are so kind it's cruel.
Now I'm going to cry a little.
Why is this interesting (Score:2)
Re: (Score:1)
That is why the GP suggested it as being a good thing that they are sharing it. And your right, it does take a long time to get onto these computers. This is because they are letting people use the extra cycles in between their need for all of them.
Re: (Score:3, Informative)
The DOE and the NSF fund various projects (with some subject area overlap) but it's still up to individual scientists to write proposals asking for supercomputer time.
Re: (Score:1)
Re: (Score:1)
Re: (Score:1)
The question is why not IBM? (Score:3, Insightful)
Re: (Score:1, Offtopic)
And if you really look at the cost, it still is cheaper then other places like Canada and england for some services. Look at the excess in taxes that they pay just to get the service they do. Now imagine the cost of that over a lifetime compared to
Re: (Score:1, Offtopic)
1)Its cheaper than private insurance. No middle man taking a cut. And before you go into the government inefficiency bullshit, private corporations of a similar size are just as inefficient, if not more so.
2)You get better service, since that middle man taking a cut doesn't have a profit motive to deny you service.
3)Everyone actually gets treated, and has access to preventative care. This likely increases the savings from 1, as preventative care is far cheaper and lo
Re: (Score:1, Offtopic)
And no, It likely isn't cheaper then private insurance. You have taxes on your gasoline, tobacco products, food, income and most other items that pay for the health car. The US and Canada both spend about 7% of their GDP on health services for citizens
And yet (Score:1, Offtopic)
Re: (Score:1, Offtopic)
My point wasn't that America spend less, Of course they spend more, we have more people. There is almost 10 times as many people then in canada. The entire damn point was that you could buy it yourself. The socialized medicine costs more then it would if you turned the 3 cable pay channels off and didn't drink $200 a month in alcohol or drugs. The money has to come from somewhere, IT will be you anyways.
Re: (Score:1)
We spend more per person, moron. A lot more.
'PER PERSON' you dumb-fuck! (Score:1, Offtopic)
Re: (Score:2)
Re: (Score:2)
Yes, I believe I mentions this. I even said it wasn't an accurate because those making more pay more. But one of the pages I linked to which has/had the same information I have, drew the conclusion of how much was spent on health care. It specifically compare the US and Canada.
Re: (Score:1, Offtopic)
1. First of all, the countries you're talking about -- Canada, UK, etc -- have a SINGLE PROVIDER system. That is, there is a single provider of healthcare coverage, in the form of Gov't run hospitals and clinics, and you go to them if you want free care. (Yes, in the UK there are private clinics and hospitals, but only for those that can pay cash)
Nobody has EVER suggested that the US be a SINGLE PROVIDER system. The idea has always been a SINGLE PAYER system. Tha
Re: (Score:1, Offtopic)
I know the feeling. I'm wondering why your adding to the problem though?
This is it... (Score:2)
Very simply, you are fond of basing arguments off of broad assertions and use straw-men to support them. For example:
1. ALL OF YOUR ARGUMENTS revolve around this "not being free." You say time and again that "People who think it will be free if some entity pays for it" NOBODY THINKS THAT. NOBODY ON HERE HAS SAID ANYTHING OF THE
Re: (Score:2)
Re: (Score:2)
"Everyone they insure will be making claims and there is no room to wiggle around."
Seriously... WHAT are you talking about?
These people will be making no more or less claims than any other beneficiary that the company insures. These insurance companies are not getting paid by Medicare only when
Re: (Score:2)
Your right, all I know about it is what you are saying and what you said so far amounts to a stupid program. It would amount to asking them to take over a loss directly from the government.
I'm talking about how insurance companies work and make mon
Re: (Score:2)
Re: (Score:2)
I responded to what you said and based on how you said it. You cannot fault me if you still don't understand it yourself, or at least enough to accurately portray it to someone else. How can you eve make the conclusion of it proves government is better if you don't even know it well enough to explain it to someone else.
All this shows is that you are blindly following someone else and you cannot articulate it in the way they brainwashed you.
Cinderella gets the slipper (Score:3, Insightful)
Re: (Score:2)
Teragrid and petascale computing have always been closed games, with the price of admission being to either fund yourself (have your home institution) into a position to be recognized, or, when NSF suddenly realizes they're not looking to diversify the playing field but are always funding the same
Re: (Score:1)
Re: (Score:1)
Re: (Score:2)
Are you DENSE?
petaflop? (Score:3, Funny)
Were any animal rights activists harmed in the design or manufacture of this computer?
Re:petaflop? (Score:4, Funny)
I just get so mad at them when they try to tell me not to eat animals. If god didn't want us to eat animals, why did he make them taste like meat? If he wanted us to eat only vegetables, Wouldn't he make them taste like meat too?
Vegetable substitutes for meat (Score:1, Offtopic)
If [God] wanted us to eat only vegetables, Wouldn't he make them taste like meat too?
Tofu [wikipedia.org]. Tempeh [wikipedia.org]. Veggie burgers [wikipedia.org]. God gave man the ability to invent vegetable substitutes for meat [wikipedia.org].
Re: (Score:2)
"tempeh was referred as 'Javanese meat', and sometimes it was used as a way to bully javanese." Right from your link this line about how calling it Javanese meat was meant to insult javanese people. (If this is not what this sentence was intended to mean someone needs to be shot because the full sentence is rather broken)
I will give
PETA = "People Eating Tastey Animals" (Score:2)
Re: (Score:2)
Horrible Writing (Score:3, Insightful)
Come on editors!
Re: (Score:1, Offtopic)
Duh... (Score:1)
Re: (Score:2)
Not to mention... (Score:1)
Should be "petaFLOPS" or similar. The "S" is important, otherwise the unit of measure is a mystery. Could be minutes, hours, days...
This sounds like a simple one to me... who else? (Score:5, Insightful)
If the government was interested in a machine from a company who has consistently shown it knows how to build these things, then who else would they choose?
IBM has consistently dominated the fastest supercomputer list:
http://www.top500.org/
And as for it's location... why would the government want to keep putting all their eggs in the same basket? Also, it's not like you need a keyboard and mouse and operator directly attached to this machine... so housing it elsewhere in a facility that can house it makes sense.
Sounds more like a bunch of people grumbling that they arent going to have access to what they thought would be their newest toy. In addition, it indicates possible collaboration between the DOE and NSA which should only be a good thing.
Re:This sounds like a simple one to me... who else (Score:2)
This might be what saves the world. LOL
Re: (Score:2)
Re: (Score:2)
The DOE is probably more science oriented the the NSF in some ways. When you put the NASA elements into consideration anyway. There are many faces to the Department of energy. Just like the military which wil get it's hands into everything, so does the DOE.
Re: (Score:2)
DoD: 400 bil. US$ (not including the Iraq war costs, read another 90 bil.)
DoE: 25 bil.
NASA: 15 bil.
EPA: 8 bil.
NSF: 6 bil.
I say screw them, let them buy their own damn computer.
Re: (Score:2)
The DoE has $4 billion p.a. for such tasks; not counting money from military budgets.
Re:This sounds like a simple one to me... who else (Score:3, Insightful)
Re:This sounds like a simple one to me... who else (Score:1)
Re: (Score:2)
Umm... yeah, that was a typo, and I would be really scared over what the NSA would do with that many FLOPS. :-)
Re:This sounds like a simple one to me... who else (Score:1)
Re: (Score:2)
Or hopefully this means that the DOE is (using this machine for) concentrating on things that are applicable to the private sector such as Global Warming, the environment, climate, etc, for which a collaboration with the NSF would make sense.
hmmm (Score:2, Funny)
NSF? (Score:1)
Re: (Score:1)
From the Article... (Score:1)
Re: (Score:2, Funny)
at least it'll run linux (Score:3, Funny)
IBM and Linux (Score:1)
Re: (Score:1)
Unnecessary (Score:5, Funny)
So, what are the concerns? (Score:5, Insightful)
sour grapes are inevitable, probably (Score:3, Insightful)
That NCSA might win the contract with a proposal that IBM build the machine is about as uncontroversial and "safe" a r
Re: (Score:2)
While I'm not questioning the excellence of the existing facilities, there's certainly faculty outside of those who might be able to be more cost-effective with their money. A $2M grant falls into the "small fish" category in some places, while a $2M grant might be huge at smaller schools. Further, I personally believe the cost of getting a grant off the ground is less expensive in the M
Re: (Score:2)
It's a bit weird for Livermore to be competing for NSF dollars. Usually their funding is DOE/DoD, since they've been a closed weapons shop for decades. Oak Ridge and Los Alamos made the transition to a lot more civilian research long ago, so they have plenty of NSF money. But I think it's a bit new for Livermore to be competing so strongly for it. Again, I think
Re: (Score:2)
NSF does do seed money (i.e., smaller grants to get infrastructure started). However, they need to find a way to do sustainable funding in a better manner. Nothing's worse to see a seed grant help a site get started, only to have it dry up 2 years later (or, forcing the poor PI to become a full-time grant writer).
I'm not saying we need to send $50 million to Nowhereville, Arkansas. However, it'd be nice to see a little more invested in infrastructure out there...
Re: (Score:2)
Anyway, it's not my problem, since I've long since moved to private industry and I don't need to make pitches to t
what kind of machine? (Score:2, Informative)
Other competitors would have been Sun (linux or solaris), SGI (Altix), Cray, etc. Apparently the USGov won't consider Japanese machines so Hitachi/NEC are out.
PS Japan is building a 10x faster machine in the same timeframe.
PPS The top500 is heavily biased toward clustery machines; certain types of science codes do not run well on such systems. Not saying it's a wrong met
Re: (Score:2)
Nothing to see here.... (Score:1)
Confusing headline (Score:2)
New obligation for all /. supercomputer summaries. (Score:1)
http://en.wikipedia.org/wiki/FLOPS [wikipedia.org]
DoE and NSF (Score:2)
Really? Seems to me that the NSF and the DOE Office of Science tend to work together a lot, and sharing facilities, cross-detailing personnel, etc., are pretty common between those two organizations.