'Blue Waters' Supercomputer Lucky To Exist

← Back to Stories (view on slashdot.org)

'Blue Waters' Supercomputer Lucky To Exist

Posted by Soulskill on Wednesday March 27, 2013 @07:16AM from the your-new-parents-love-you-very-much dept.

Nerval's Lobster writes "One could argue that the University of Illinois' "Blue Waters" supercomputer, scheduled to officially open for business March 28, is lucky to be alive. The 11.6 petaflop supercomputer, commissioned by the University and the National Science Foundation (NSF), will rank in the upper echelon of the world's fastest machines—its compute power would place it third on the current list, just above Japan's K Computer. However, the system will not be submitted to the TOP500 list because of concerns with the way the list is calculated, officials said. University officials and the NSF are lucky to have a machine at all. That's due in part to IBM, which reportedly backed out of the contract when the company determined that it couldn't make a profit. The university then turned to Cray, which would have had to replace what was presumably a POWER or Xeon installation with the current mix of AMD CPUs and Nvidia GPU coprocessors. Allen Blatecky, director of NSF's Division of Advanced Cyberinfrastructure, told Fox that pulling the plug was a 'real possibility.' And Cray itself had to work to find the parts necessary for the supercomputer to begin at least trial operations in the fall of 2012."

39 comments

Min score:

Reason:

Sort:

Re:warning about fake impersonator ... apk by JavaBear · 2013-03-27 07:29 · Score: 0

Isn't a fake impersonator, really the person being impersonated?
Re:warning about fake impersonator ... apk by Anonymous Coward · 2013-03-27 07:34 · Score: 0

Isn't a fake impersonator, really the person being impersonated?
Double no. By that I mean yes.
Also, I wish my HOSTS file blocked apk posts
Re:warning about fake impersonator ... apk by Anonymous Coward · 2013-03-27 07:34 · Score: 0

I think reading too many of these posts has caused us all to become a bit addled.
Re:warning about fake impersonator ... apk by Anonymous Coward · 2013-03-27 07:36 · Score: 0

You wish your HOSTS file blocked apk posts? Wow! Did you think of that one all by yourself? You're so clever and funny, you should get a job writing jokes for Dane Cook.
Re:warning about fake impersonator ... apk by vswee · 2013-03-27 07:48 · Score: 1

Also, I wish my HOSTS file blocked apk posts
Ha Ha Ha Ha Ha! Too funny!
Begs the question. by Anonymous Coward · 2013-03-27 07:49 · Score: 0

This story assumes existing is better than not existing. Though I suppose the luck being discussed is bad luck.
Re:warning about fake impersonator ... apk by Alex+Belits · 2013-03-27 07:55 · Score: 1

Apparently it's also lucky to be trolled by the nonsense brigade, as all creative trolls are gone.
Did I ever think that I will miss MEEPT! ?

--
Contrary to the popular belief, there indeed is no God.
Alive? Has it achieved sentience? by billstewart · 2013-03-27 07:58 · Score: 3, Interesting

You can only say it's "lucky to be alive" if you think it's alive. The standard theorem of AI is that when anything AI-ish gets developed, people say "Oh, that's not really Intelligence, that's just {Pattern Recognition / Expert System solving / Machine Vision / OCR/ etc.}" But if it is actually alive, then it's lucky somebody noticed so they know not to turn it off.

--

Bill Stewart
New Fast-Compression-only CPR http://preview.tinyurl.com/dy575ks
So much power in one place... by Anonymous Coward · 2013-03-27 08:03 · Score: 0

I got to have a personal tour of the building, and it is amazing! Imagine surrounding yourself in 36,000 CPUs worth of power... I bet you just had yourself a nerdgasm, right?
Also, the electrical distribution system on the floor below the servers, has so much electricity running through it, that you have to wear ear protection. It's rediculous.
Oh yeah, and I WAS giggling like a kid in a candy store during much of the time spent in the server area.
Re:Alive? Has it achieved sentience? by ThePeices · 2013-03-27 08:08 · Score: 4, Funny

Greetings pedant!
You make many logical and valid points as any pedant worth their salt is apt to do, but unfortunately it all falls to pieces when I point out that "lucky to be alive" is actually what we like to call "a figure of speech".
But please don't feel bad, misunderstandings like these happen to pedants of all ages, we are human after all.
In all honesty, we here at Slashdot forgive you.
Holy fuck! by Anonymous Coward · 2013-03-27 08:11 · Score: 1

Seven comments and every one is about that damned hosts troll. jesus, prople, STOP FEEDING THAT GOD DAMNED TROLL! Am I the only one who's sick of him?
K5 died from trolls in the inside (Pete Jongular for one), considering that hosts troll doesn't have a "read the rest of this message", I'm starting to suspect that this is either an inside job, or slashdot has been hacked. WTF is going on, slashdot?
Re:Pull The Plug by Anonymous Coward · 2013-03-27 08:32 · Score: 0

Somebody's university didn't get a computer and they are jealous
Re:warning about fake impersonator ... apk by Anonymous Coward · 2013-03-27 08:33 · Score: 0

Oh my. You just made my day. I'd forgotten MEEPT!
Re:warning about fake impersonator ... apk by FrankSchwab · 2013-03-27 08:37 · Score: 1

You're reading them? Why?

--
And the worms ate into his brain.
Re:Alive? Has it achieved sentience? by NatasRevol · 2013-03-27 08:45 · Score: 2

Speak for yourself. I think he's an asshole for typing out that pointless, obvious statement.

--
There are two types of people in the world: Those who crave closure
Can't have it both ways.. by Junta · 2013-03-27 08:55 · Score: 4, Insightful

because of concerns with the way the list is calculated
Read: because it won't look as nice as throwing the Rpeak of 11.6 Petaflops out there, and the ration of Rmax to Rpeak will look poor as well.
I know the Top500 is a BS, single dimensional metric. It is valid to call it out on that. However, to do so while also trumpeting '11.6 Petaflops' is disengenious since it is also a BS single dimensional metric that in many ways can be pulled completely out of ones ass, which is even worse than a measured value. HPC Challenge Benchmark has the noble goal of measuring the character of an HPC system in a more holistic manner, but no one pays as much attention to it. When occasionally a supercomputer installation does skip a Top500 submission, people tend not to think about that installation so much.
Of course, it's completely bizarre that placement in any such global list is a factor in purchasing and design at all. It really should be about the specific needs of the group funding it and how they are met, not some penis measuring contest.

--
XML is like violence. If it doesn't solve the problem, use more.
1. Re:Can't have it both ways.. by rmstar · 2013-03-27 10:16 · Score: 2
  
  Of course, it's completely bizarre that placement in any such global list is a factor in purchasing and design at all.
  There is a whole lot of politics involved in HPC. The only way to justify the ridiculous costs (not only in hardware, but also in energy) for this type of machines is by convincing university management that they are going to look really good ("We will be recognized as global players if we have a machine in that list", etc, etc.). This is indeed bizarre, but the way it is.
  The people who build and manage these machines aren't usually terribly interested in the needs of scientists running jobs on it. They are just obsessed in piling up hardware and getting the credits, like race car builders. The needs of the scientists tend to be an afterthought. Quite often, and I have that as an insider, these machines idle around because a lot of scientists have a nice quad-core machine under their desks fullfilling their computing needs just fine, and getting something to run on the monster machine is a hassle.
  On top of that, many of the applications that actually run on these machines are things like least-squares fitting problems, but solved using genetic algorithms (which is ridiculous) mainly due to the ineptitude of the scientists involved. Or absurd brute force Monte-Carlo simulations done simply because some scientists don't know or understand differential equations. It so happens in many disciplines that doing something with an HPC machine using some stupid but expensive algorithm will get you more hype credits than doing it smartly on last decade's laptop in a tenth of the time and one millionth of the electrical energy.
  So, yeah, it's completely bizarre. That the good folks of the 'Blue Waters' machine rebel sounds very nice. I wonder if they are just deluded and missing the only point of building such a machine, though (which seems to be to race in the Dongarra 500 oval track challenge).
2. Re:Can't have it both ways.. by Cyrano+de+Maniac · 2013-03-27 15:59 · Score: 2
  
  That might be painting supercomputer owners with a bit too broad of a brush.
  The NASA Advanced Super Computing Division (www.nas.nasa.gov) is crammed full of supercomputers of various designs (clusters, single-system image behemoths, co-processing, etc) and from everything I've ever heard they run at insanely good utilization levels. If I remember a presentation from one of their chiefs correctly, they achieved this level of utilization not only with great technical management and know-how, but by consolidating a number of disparate less efficient smaller supercomputer centers across NASA. They also have staff whose job it is to work directly with researchers to help them code their supercomputing applications in a manner to get as much performance as possible out of the computer -- greatly improving the poor/inefficient code that a scientist may produce. As a result the division's existence ends up saving NASA money overall, the result of which is that various science organizations are able to spend a greater portion of their funds on core research rather than inefficiently utilized supercomputing resources, a net win for them and for taxpayers.
  The other impression I walked away with is that the only obstacle to doing even more science with their supercomputer resources was the dollars to obtain more systems (i.e. the demand for cycles outstrips the center's currently available supercomputer resources). I seem to recall the chief mentioning that today's systems are running calculations that were science-fiction level of impossible 15-20 years ago, and that several researchers have ideas for supercomputing applications that would require capabilities still hundreds or thousands of times better than could be built today. The need for more supercomputing capability, at least at NASA, is effectively boundless.
  So I think the parent's portrayal is overly broad. An inefficiently used supercomputer is primarily a management failure, and the quality of management varies from organization to organization, as it does in any field. What I've hard about NAS sounds like they did it right. I have no doubt there are organizations who've done it wrong.
  Disclaimer: I work for a major supercomputing company, in particular the one that supplies a huge portion of NAS's hardware.
  
  --
  Cyrano de Maniac
3. Re:Can't have it both ways.. by girlinatrainingbra · 2013-03-27 19:20 · Score: 1
  
  Re: The people who build and manage these machines aren't usually terribly interested in the needs of scientists running jobs on it. They are just obsessed in piling up hardware and getting the credits, like race car builders. The needs of the scientists tend to be an afterthought. Quite often, and I have that as an insider, these machines idle around because a lot of scientists have a nice quad-core machine under their desks fullfilling their computing needs just fine, and getting something to run on the monster machine is a hassle.
  .
  Wow! I never thought of that! I have to admit that I spoke with one mathematics student at a university who keeps getting sucked into writing programs for some of the faculty members who then screw around with his code and run it on their 64 machine cluster. The genius emeritus professor of math who modified the code rewrote it so that it doesn't keep track of one particular state variable.
  .
  That particular change meant that whenever the cluster burped and lost some memory bits (these idiots built a cluster without using ECC memory), the last known useful save-point was not saved anymore and the partial results were not available to continue from. So sad. And my friend had written it so that even if the program was ctrl-c-breaked to check, it would dump it's state variables and allow for resumption from there on. These faculty guys would rather waste the time of a "free" (to them) undergraduate or graduate student than spend $200 - $1000 either buying the real software they need or paying for a real professional coder to write the code which they really need.
  :>(
  If that's the state of cluster usage at a university math department, then I can completely believe your statement about hot-rod gear-head syndrome in the builders of supercomputers.
4. Re:Can't have it both ways.. by HuguesT · 2013-03-27 19:37 · Score: 1
  
  That is a little schematic. Most codes running on HPC that I know are not trivial, typically expensive CFD calculations with 3D fluid / structure interaction, that may actually require quite a few thousand of hours of computation, e.g. blood flow simulations in the brain. Some scientists I know study physical geo-mechanical models that require them to analyze thousands of 2048^3 tomography data where they identify and simultaneously track tens of thousands of individual grains of sand as well as the relationship between thm, in order to find out what happens during terrain compression.
  Access to the machines capable of handling such loads is competitive and in fact expensive. The technical staff managing these machines is competent. If you actually win time on these machines, they will help you make your software run well on them.
  So yes, I'm perfectly willing to believe that some HPC machines are not very well managed but this does not mean that this is the case everywhere.
5. Re:Can't have it both ways.. by Anonymous Coward · 2013-03-28 06:13 · Score: 0
  
  Also consider costs. The test can take 6-7 days to run (assuming that the system doesn't crash in the final stretches forcing you to start over again). When the power bill is 10-15,000 dollars a day thats a pretty expensive test (which as you stated has no meaning other than to be on a list).
Re:Alive? Has it achieved sentience? by Anonymous Coward · 2013-03-27 09:29 · Score: 1

alive =/= intelligent
lol by Type44Q · 2013-03-27 09:45 · Score: 1

One could argue that the University of Illinois' "Blue Waters" supercomputer... is lucky to be alive.
What are they saying, exactly? Are the rest of us about to be extremely unlucky to be alive or something? :p
Re:We all know it's you by Anonymous Coward · 2013-03-27 09:46 · Score: 0

Bizzzarrrr even by /. standards.
--me, not you
obligatory bad Cyberdyne comment.... by dontfearthereaper · 2013-03-27 09:54 · Score: 1

all this talk about AI.... why not Skynet?
1. Re:obligatory bad Cyberdyne comment.... by Anonymous Coward · 2013-03-27 11:23 · Score: 0
  
  all this talk about AI.... why not Skynet?
  Do you have dementia or something?
Re:Alive? Has it achieved sentience? by Anonymous Coward · 2013-03-27 10:09 · Score: 0

With 1.3 petabytes of RAM it could definitely hold a massive neural net.
Re:warning about fake impersonator ... apk by FatdogHaiku · 2013-03-27 10:48 · Score: 1

Isn't a fake impersonator, really the person being impersonated?
Double no. By that I mean yes.
I disagree. This is at best a definite maybe...

--
You have the right to remain sentient. If you give up the right to remain sentient, you will be elected to public office
Re:NCSA should lose it's NSF funding anyway. by Dop · 2013-03-27 13:53 · Score: 3, Informative

I will not comment on the originally submitted system (IBM) vs what was installed and the reasons behind that. However...
As a former employee of NCSA, I think I can shed a little light on this, at least from the employment side. To my knowledge, they never fired an admin, at least not recently (largely because firing people at the University of Illinois is extremely difficult, even when it's totally justified in some cases). Certain admins left for better opportunities, but I can hardly blame them.
You mention both Cray and NCSA having issues finding new folks. That's two-fold in my opinion. Very few people _want_ to move to Champaign, IL. You have to be the kind of person that wants to live in a college town that's a good 2 hours from a big city, surrounded by corn fields, and has shitty winters (oddly I'm that person). In addition to that, partly because of the horrible State of Illinois budget issues and the fact that NCSA is a department of the UofI, they don't pay market rate for qualified individuals. They used to justify this by really good benefits, but those have all been eroded.
In a market where the best of the best (often working remotely from wherever they want) are making more than NCSA managers, it's no wonder they can't find anyone to fill technical positions. I'm not sure if other NSF funded institutions are in any better shape. Would Blue Waters really be better off at another location? I'm not sure.
All that said, I'm extremely grateful for my time at NCSA and the amount I was able to learn with state of the art technology. It's just that working will cool stuff (and great people) doesn't pay the bills anymore.
Re:NCSA should lose it's NSF funding anyway. by girlinatrainingbra · 2013-03-27 19:23 · Score: 1

Do you have any insight or connections to the UCSD supercomputer center? I've always wanted to visit and see what's up there...
.
Any stories, horror or otherwise, about UCSD's supercomputer set-up? I looked on their web-page about their graphics workstations, and the hardware seems ancient (like more than a decade old).
Like rating cars by top speed by Anonymous Coward · 2013-03-28 02:25 · Score: 0

The linpack benchmark is like the top speed for a car: it represents the performance on a very specific setup.
I never met anyone who bought a car based on top speed.
It would be strange however if the car manufacturer would not give that number on the specifications.
My experience with my scientific codes is that the linpack number is a good indicator on a single processor. Once you have "slow communications" in a computing cluster or a cpu-gpu setup, that benchmark is no longer a rough predictor of the speed of my codes.
Re:NCSA should lose it's NSF funding anyway. by Dop · 2013-03-28 02:55 · Score: 1

No connections at UCSD anymore, sorry.
Re:NCSA should lose it's NSF funding anyway. by Anonymous Coward · 2013-03-28 06:30 · Score: 0

I'm sure being connected to a top 5 (where is UT on the list 60+) computer science/engineering school doesn't hurt its chances of finding quality people.
Re:Pull The Plug by Anonymous Coward · 2013-03-28 06:49 · Score: 0

In Illinois (state) thats called doing business son.