Cray Wins $52 Million Supercomputer Contract 133
The Interfacer writes "Cray and the U.S. Department of Energy (DOE) Office of Science announced that Cray has won the contract to install a next-generation supercomputer at the DOE's National Energy Research Scientific Computing Center (NERSC). The systems and multi-year services contract, valued at over $52 million, includes delivery of a Cray massively parallel processor supercomputer, code-named 'Hood.'"
Just anounced (Score:5, Funny)
Re:Just anounced (Score:4, Funny)
Re:Just anounced (Score:1)
Re:Just anounced (Score:2, Funny)
Vista will come early (Score:1, Funny)
Boss1: Cray has developed a computer that actually runs Vista fast
Boss2: I see, let's remove that "optimization" box from the gantt chart then..
Boss1: But customers will compain that they can't afford to buy a supercomputer
Boss2: What? it runs AMD! how can it be expensive....those morons
Re:Vista will come early (Score:1)
Re:Vista will come early (Score:1)
Re:Just anounced (Score:1, Troll)
And why is the DHS (which failed miserably during Katrina) more prevalent/widely-known?
Re:Just anounced (Score:1, Informative)
The part of the DOE that uses supercomputers does nuclear simulations. They don't give a crap about your unwise car choice.
Re:Just anounced (Score:3, Informative)
Re:Just anounced (Score:2)
Just enough for them to limp along... (Score:2)
Re:Just enough for them to limp along... (Score:1)
Re:Just enough for them to limp along... (Score:2)
Re:Just enough for them to limp along... (Score:4, Insightful)
Re:Just enough for them to limp along... (Score:4, Interesting)
Re:Just enough for them to limp along... (Score:2)
From NSA's online museum: "Working with companies, such as Cray Research Inc., NSA has been a leader in computer development throughout its history. Some of the earliest supercomputers were designed and built for the National Security Agency."
Re:Just enough for them to limp along... (Score:2)
Yes we would (Score:2)
In fact, it was widely reported in the HPTC press that the defense department was helping to fund the development of the "Black Widow" vector supercomputer, and that they funded much of the development costs for the X1. If you search the web for a while, you'll find that the NSA is the only customer for cray's bizzare MTA3 supercomputer. Every once in a while you'll see cray press releases about sales of X1's to "undisclosed" or "government" customers.
Without Uncle sam's checkbook, cray would certaintly go under. I bet the US government accounts for 1/3 of their sales, and another big chunk from foreign governments, and military contractors like boeing. That said, it may not be a bad investment on the government's part. Keeping Cray alive means that IBM has some competition, and it keeps the innovation going at both companies, and keeps down the sticker price on the high-end IBM and HP systems. Subsidizing cray is not cheap, but it may be cheaper than not subsidizing cray.
Re:Just enough for them to limp along... (Score:1)
After all, with the massive amounts of data that the NSA has been allegedly collecting, it is obvious that they would need some serious computing juice to process it. I'm not trying to come up with some sort of conspiracy theory, but from a technical standpoint, it makes sense.
Re:Just enough for them to limp along... (Score:1)
Cash Machine (Score:0, Flamebait)
Re:Cash Machine (Score:1, Offtopic)
Cray still in business... (Score:2)
Re:Cray still in business... (Score:1)
Brainwave - (Score:2)
um - nevermind.
Let's just hope (Score:1, Funny)
Re:Let's just hope (Score:2)
I am just surprized it wasn't KBR that got the contract [lol]
Re:Let's just hope (Score:2)
DoD/Army only get to store and use the suckers.
Pinky... (Score:3, Funny)
I think so, Brain! NERSC! POIT!
Re:Pinky... (Score:4, Funny)
I think so, Brain, but how do we get that many processors into a pair of rubber pants?
Re:Pinky... (Score:1)
shamelessplug on
In fact, I actually bought a domin from one of their catchphrases. http//www.murmp.com/ [slashdot.org] I really don't know what I am going to do with it, but I think it is catchy nonetheless. It was "Web 2.0" potential.
shamelessplug off
Any ideas for what I should do with it...this ought to be fun.
Why Cray doesnt sell (Score:5, Funny)
Because of it's power requirements, Cray's only possible customer was the Department of Energy
Cray "getting it" might let them come back. (Score:3, Interesting)
That is why Clusters are such a powerful paradigm. If your problem needs more processors/memory/bandwidth/data access, you can design a cluster to fit your problem and only buy what your need. In the past you had to buy a large supercomputer with lots of engineering you did not need. Designing clusters is an art, but the payoff is very good price-to-performance. A good article on this topic is the Cluster Urban Legends [clustermonkey.net], which explains many of these issues.
Re:Cray "getting it" might let them come back. (Score:3, Insightful)
Re:Cray "getting it" might let them come back. (Score:1)
Re:Cray "getting it" might let them come back. (Score:1)
Re:Cray "getting it" might let them come back. (Score:2)
Re:Cray "getting it" might let them come back. (Score:2, Funny)
"The system uses thousands of AMD Opteron processors running tuned, light-weight operating system kernels and interfaced to Cray's unique SeaStar network."
That's a cluster.
Re:Cray "getting it" might let them come back. (Score:2)
I thnk the distinction actually is, that with CrayLink/NumaLink, there's only one OS running, and the other chassis are all controlled by the master node- in a true cluster, each machine is independant, but takes commands/computations from the head node.
Re:Cray "getting it" might let them come back. (Score:3, Informative)
passing engine. its distributed memory and the OS
doesn't share any state (except for a library that
does filesystem indirection)
Re:Cray "getting it" might let them come back. (Score:1)
Re:Cray "getting it" might let them come back. (Score:1)
Re:Cray "getting it" might let them come back. (Score:2)
"The system uses thousands of AMD Opteron processors running tuned, light-weight operating system kernels and interfaced to Cray's unique SeaStar network. "
That's a cluster. It's also a supercomputer. Maybe you're looking for the word 'Mainframe'? Regardless, the article the parent links to is a really good discussion of clusters and their value/application.
Re:Cray "getting it" might let them come back. (Score:2)
I *have* to say it! (Score:1)
Re:Cray "getting it" might let them come back. (Score:2)
Slashdot is NOT digg.com , you can't advertise referrer URL here. I think everyone should report your type to slashdot admins and they should put an end to this trivial referrer crap URLs became fashion again.
Paste some stuff from some trivia source like wiki to post something everyone will find interesting with referrer url and get modded up. Nice plan.
XT3 not really a cluster (Score:2)
Nersc, and a number of other dod/doe labs are buying a new generation of "true" supercomputers (XT3, bluegene, P570/VIVA, altix, X1) as a response to the perception that commodity clusters have largely failed in delivering real performance. While performance on real (not-linpack) applications has been a problem for commodity clusters, the real problem has been reliability. A machine that gives you 10 teraflops of performance, but is down for maintenence half the time, is less useful than a much smaller machine that actually runs. While the fundamental architecture of a commodity cluster does not preclude reliable real-world performance, many of the clusters actually in use, have not provided very compelling real performance for the real world cost of owning the systems.
Nersc has owned commodity clusters, as well as large mpp machines from IBM and Cray, including the XT3's predecessor the T3E. They know what they're getting into.
I agree! Mod me down!! (Score:1, Offtopic)
Hood? (Score:5, Funny)
Re:Hood? (Score:3, Funny)
You only get this joke if yer from New England... (Score:5, Informative)
They had giant milk bottle ice cream stands, one stood outside the old Computer Museum on Congress St.
No slight intended concerning ethnic neighborhoods.
Re:You only get this joke if yer from New England. (Score:2)
And to be honest, a research question like that is probably even a better defined one than just looking at the protein folding problem in general, and therefore not a bad way at all to spend your research money!
Or if you're a Phish fan (Score:2)
Re:Or if you're a Phish fan (Score:2)
Re:Or if you're a Phish fan (Score:2)
Re:Hood? (Score:2)
Re:Hood? (Score:2)
Re:Hood? Hood College (Score:1)
Re:Hood? (Score:2)
SGI owns cray? (Score:1)
Even so- I doubt 52 million is enough to save SGI in the long haul- especially if anything more than a few percent goes to actual hardware/research costs (and it will).
Apparently not. (Score:4, Informative)
Even I didn't notice that happen. Apparently Tera bought Cray from SGI and changed the name back for recognition purposes.
Re:Apparently not. (Score:2)
http://news.com.com/SGI+buys+supercomputer+vendor
SGI sells Cray in 2000..
http://www.wired.com/news/business/0,1367,34698,0
Re:Apparently not. (Score:1)
good to see... (Score:3, Interesting)
Then it was back to my PDP-11
Is this big as far as contracts go? (Score:2)
Will this thing be cooled with that cool nonconductive liquid goo stuff that it all just bathes in?
Re:Is this big as far as contracts go? (Score:2)
Brett
Re:Is this big as far as contracts go? (Score:2)
Re:Is this big as far as contracts go? (Score:3, Informative)
$52M is rather large nowadays. At least, for a 'commodity' part cluster it is. For a 'vector' supercomputer, it may be only medium sized.
You can easily break the top 50 for less than $10M. A couple thousand nodes, each with two dual-core Opteron/Xenons, InfiniBand or Myrinet (maybe 10GigE), and a compiler that optimizes better than gcc... no problem.
That being said, NERSC is a pathologically tough customer. Cray will have to work very hard to earn each and every penny they get. It may very well be a 'live or die' deal for Cray.
specmarks? (Score:1, Funny)
Re:specmarks? (Score:1)
Who else bid? (Score:1)
It would be interesting to know the other bids and their performance
Re:Who else bid? (Score:3, Interesting)
It seems like they had a lock on the last few big DoE supers (and supercomputer sales in general); now all of a sudden we see Cray getting back in there. I wonder if IBM stepped on somebody's toes and got given the boot on this one (it's small, maybe this is just a spanking), or if they've gotten behind in the research and power/dollar worlds because they were doing so well for so long? Or is this just the government trying to spread the love around, giving a small project to somebody else for a change?
Reminds me a little of the whole Thinking Machines business a few years ago; they were the real darlings of the govt.-contract world, and then Cray and IBM started to get upset that TM was eating out of their rice bowl and lobbied Congress to even things out. Given that they're not around anymore, I think we can all figure how how that went.
Re:Who else bid? (Score:2)
Re:Who else bid? (Score:2)
http://www.inc.com/magazine/19950915/2622.html [inc.com]
Basically, IBM and Cray got caught by surprise when the MPPs, of which TMC was just one, came onto the market. Eventually they got their act together and put out the SP and the T3D, which were both good products. Thinking machines got hit by the same post-cold-war lull in supercomputer buying that hit everyone else, and they just weren't big enough to ride it out. Even at their peak, they were a $100million/year (inflation adjusted) company. The corporate landscape is littered with the corpses of supercomputing companies that rose and fell, particularly those that rose in the late 80's, and disappeared in the 90's.
Re:Who else bid? (Score:3, Informative)
But....... "the Hood system installed at NERSC will be among the world's fastest general-purpose systems".
Nersc are looking for general purpose computing systems to fill the needs of 2500 users. Blue gene is blindingly fast at some things, but general purpose it aint. I've benchmarked both the XT3 and Blue Gene with a set of general Scientific Codes and the opteron delivers much better general price/performance for a representative set of tasks. Blue gene will fly if you have the time to get REALLY low level in your optimisation but most scientists don't have the time or knowledge to start dealing with that ind of thing.
Re:Who else bid? (Score:2)
The rest of the story (Score:1)
This is actually related to this story [slashdot.org] that ran on Slashdot a month ago. Turns out the Inquirer article that everyone ripped to shreds for being light on details was right all along. (I saw sanitized excerpts from e-mails regarding the incident, so I can tell you that Intel's Woodcrest chips performed abysmally in the DOE's testing compared to the Opterons.) The competitor that lost was IBM and the reason was because of problems with Woodcrest. The supercomputer in question will be running on 24,000 quad core Opterons. I will leave it up to the rest of you to draw your own conclusions from this.
Re:The rest of the story (Score:1)
anything here, it would have been either a BlueGene, or, perhaps, something like the
ASCI machines, which are conventional PowerPCs with a fast interconnect. Hard - no - impossible -
to believe that IBM would have bid an Intel processor.
Re:The rest of the story (Score:1)
I agree that it sounds crazy. I'm just passing along the information I was given. Your impression telling you that there's no way IBM would bid an Intel chip makes a lot of sense. It's not been their standard M.O. in the past. All I know is that Cray won the bid with Opterons, the e-mails I read gave unfavorable reviews of Woodcrest chips, and that Woodcrest is supposed to kick the snot out of Opteron. In any case, the fact that Cray won the bid with an Opteron-based supercomputer should be more than a little eye-opening.
In any case, based on the things I have witnessed with my own eyes, I stand by my assertion that IBM used Intel chips in their bid.
ummm.... (Score:1)
Ummm... no offense to Cray, but that's pretty f*ing lame.
This, ladies and gentlemen, is why we need to 'encourage' our kids to desire scientific jobs.
Re:ummm.... (Score:1)
A few notes to clear things up (mod me up!) (Score:5, Informative)
* Clusters can not compete with supercomputers. They aren't even in the same market space. Cray doesn't make clusters, and clusters have not taken away their business.
* Cray doesn't take off the shelf hardware and sell it as fancy clusters. Actually look into the details of these machines. While processors sometimes are off the shelf much of the surrounding hardware and software is custom.
* This 50 million contract is one of many that cray has. They also just recently in the news got a 200 million dollar contract. They also are a contender in the DARPA HPCS thing. That could be a lot more if they get it. They aren't dieing.
* They aren't owned by SGI any longer. They were bought from SGI by Tera who renamed themselves cray.
* The top500 list is nonsense. It is based off of 1 benchmark (linpack.) That benchmark doesn't stress the interconnect too much and can allow clusters to appear to compete with supercomputers if you manage to ignore all the other factors. The number of teraflops has very little to do with performance. To see a more well rounded and thought out measurement of top systems check out HPCC's website. http://icl.cs.utk.edu/hpcc/hpcc_results.cgi [utk.edu]
* Bluegene doesn't kick Cray's ass. See the above and then see how it really performs overall. In some areas it does better and in others it just gets destroyed. Depending on the real world problem a full size blue gene may not even be able to perform as well as a much smaller Cray.
If you don't know what you are talking about look it up before posting. Just because it's the common belief doesn't mean there is any truth to it!
Re:A few notes to clear things up (mod me up!) (Score:1)
Re:A few notes to clear things up (mod me up!) (Score:1)
Cray making a comeback!? Now if that don't beat all.
What's next? Borland selling a good, cheap Pascal compiler again?
Re:A few notes to clear things up (mod me up!) (Score:3, Informative)
Secondly, to say the computers that Cray sells is not "off the shelf" can be argued depending on how you look at it. Today's Crays are not the fully proprietary machines of yesteryear. They all use AMD Opteron processors and leverage the onboard memory controller and hypertransport bus to make a processor fabric simple. The main custom items in the system are the "interconnect routers" that tie all the hypertransport busses together. Even the FGPA components that facilitates handling specific custom tasks on hardware are somewhat "off the shelf" and just woven into the greater hypertransport happiness fabric.
Sure, the average person is not going to be able to build a "supercomputer" like this with stuff they bought off the frys shelf. But are we talking about "off the shelf" as in the average electronics store? Or "off the shelf" as in parts that are pre-existing and available on some shelf somewhere and have published documenation?
Benchmarks of any multiuse system are never universal. They best they can do for a large list like that is to use a benchmark that can reasonably represent a common use of such systems. Cray has been good about having systems that can be configured to perform exceptionally for very specific applications. Modern offerings like the XD1 are no different in that respect as they offer that in the FPGAs. To say they are not in the same market space as custers is like saying MySQL isn't in the same market space as PostGreSQL. They both have their strong points but there is many instances where a user has to decide which to go with.
I'm going to stop there...time for sleep.
Re:A few notes to clear things up (mod me up!) (Score:2, Informative)
The linpack benchmark used to do the top500 list is a basic, dense matvec solver algorithm. (See wikipedia : http://en.wikipedia.org/wiki/LINPACK [wikipedia.org]) This algorithm used to be the core of most scientific codes, back in the days when you would simply use the computer to solve a simple (but large) set of equations. In the last decade(s), the scientific world has moved to unstructured problems where the solvers are no longer solely matvec operations. Adaptive mesh methods, multigrid, and other similar "modern" methods in scientific computing do NOT have the same behavior as a basic dense matvec - a simple case would be considering a matvec problem where one deals with sparse matrices. Life gets even worse if you try to use linpack to reason about how a machine would perform on something highly data dependent, such as an n-body code or molecular dynamics simulation.
Linpack is really an archaic relic of the past, and it is NOT a benchmark of a multiuse system. It is a benchmark of a supercomputer from 15+ years ago. This is not news in the parallel computing world -- many efforts such as ParkBench, NAS Parallel Benchmarks, Livermore loops, etc... have been proposed as replacements for linpack to better cover the sorts of applications that a real "multiuse" systems will run. Unfortunately, the fact that most procurement folks and politicians who help fund these big govt. machines do not understand that linpack is a total waste of time have caused it to persist, contrary to the desires of people who either use the systems, or spend their careers studying performance issues in big parallel systems.
Re:A few notes to clear things up (Score:1)
However, the arena of molecular dynamics is one in which clusters and MPP in general are easily the better choice than a monolithic supercomputer. On the one hand, you can make each node an automaton to describe a single particle in a very object-orientated fashion. On the other hand, you can make each node representative of a spatial cell whereby the boundaries interact with those of its nearest-neighbour nodes. It is particularly in this second scenario where the MPP approach wins hands down (and scalably so).
So, just because the benchmark is biased (which it clearly is), do not assume that this means that it undervalues one architecture or the other for solving an entirely different problem.
Re:A few notes to clear things up (mod me up!) (Score:2)
That's not very true. Supercomputers will have a solid market into the foreseeable future, but they certainly are facing competition from improvements in clusters.
Sometimes interconnect speed can be reasonably traded-off in exchange for a significantly reduced price, or for additional CPU power, local RAM, etc. Often, problems that are generally considered single-threaded can be parallelized, with a performance hit, but still turns out cheaper because of the huge price difference between clusters and supercomputers.
Claiming there is no competition between the two is nonsense.
Re:A few notes to clear things up (mod me up!) (Score:1)
To quote a collegue of mine "The interconnect IS the machine!"
The primary difference between a supercomputer and a cluster is the degree of itegration between the computing elements. You can demand that a Supercomputer MUST have a crossbar switch or similar close coupled interconnection method but that only scales so far. For a good example have a look at the earth simulator [jamstec.go.jp], you're not telling me THAT is not a supercomputer ? The XT3 is similar in that it has a customised high bandwidth, low latency interconnect it just doesn't have the SMP elements that the earth simulator has.
As an aside Cray get a LOT of contracts that we never hear about . They are actually financially fairly healthy.
Re:A few notes to clear things up (mod me up!) (Score:2)
The other problem with it is that it only counts systems that people want you to know exist. For example, it's a safe bet that the NSA has multiple systems that would qualify but are not listed. There are probably a significant number of systems like that in the world - so calling it the 'top 500' is just silly.
Re:A few notes to clear things up (mod me up!) (Score:3, Informative)
He's right. For *ALL* computing tasks, using the right tool for the job can increase performance exponentially. Slashdotters should know this -- A 400mhz GPU can outperform a 3ghz CPU on vector and matrix operations by huge leaps and bounds
Clusters are just another tool that work very well for very specific jobs, and very poorly for others. These jobs are mainly those that can be massively parallelized (ie. brute-forcing a math equation -- Computer A should try these values, Computer B should try these values, etc...). Anything more complex than that puts a huge strain on the system being used to interconnect the machines. Once you start incorporating a fast interconnect system, the cluster begins to resemble an extremely inefficent supercomputer with multiple points of failure. At this point, it makes more sense to just use a Cray.
Over the past few years, for the first time, it's been possible to use the same chips in supercomputers as in desktops -- specifically the Opteron and the PPC970. As a result, consumers got more powerful chips, and supercomputers got a lot cheaper due to economies of scale. As an added bonus, now that the R&D is combined into one architecture, we're getting faster chips on a more regular basis.
AMD did a lot of things right with the Opteron. They made a series of consumer chips that were inexpensive, and blazing fast. They then took the same architecture, and made enterprise-grade chips that were rock solid, equally fast, energy-efficent, and still pretty cheap. HyperTransport is also an incredible technology, in that it's suitable for inexpensive machines and supercomputers alike. Itanium was none of these things.
I for one, am glad to see supercomputing coming back into fashion. The DOE's working on a lot of good science that will be essential for our survival in the long run, and the government seems to be providing them ample funding. Sure, NASA may do some cool science, but it's the DOE that's working on more meaningful things that can be put to use here on earth for the betterment of mankind. Perhaps the only positive thing to come out of the political mess right now is that the world is quickly realizing how desparately we need to move away from an oil-based society.
Re:A few notes to clear things up (mod me up!) (Score:3, Informative)
I agree completely.
This is not exactly a wrong statement, but it is incredibly broad. First off, Cray does make clusters. At a fundamental level, the basic separate-box clusters connected by Ethernet are the exact same thing as a big massively parallel system. They are on different ends of the spectrum, certainly. The sort of interconnects used by Cray certainly make their systems much more suited to certain workloads than more basic clusters. In practice, even Single System Image vs. separate boxes isn't that big a distinction. And, basic clusters certainly do compete with and take business from Cray. If basic clusters weren't an effective means of computing, then there would be a much larger market for the supers. If I refer to "clusters" in this post, I am probably referring to separate-box basic clusters -- like the parent poster seems to be. As unclear as this terminology can be, it is the way the term is usually used.
This point I fully agree with. The high end interconnects and whatnot that you see in supers are on a very different level from what you see in the more basic clusters. For the workloads where the supers kill the basic clusters, it's usually related to comms latency between the nodes, which is all about the crazy interconnects.
I'll take your word for it. I haven't specifically kept up with Cray's contracts, though it wouldn't surprise me if they are doing pretty well.
Yup, no argument there. (See, I may be a jerk, but at least I'm not arguing with everything! ;) )
I wouldn't go so far as to call top500 "nonsense." It is a very specific benchmark. People do tend to look at a very narrow, specific piece of information, and generalise it completely. *That* is nonsense. You have to be aware of what you are reading when you see stuff like benchmark numbers. Benchmarking can be very complex.
That said, there are some real world workloads that work quite a lot like linpack. Consequently, there are a lot of very real world tasks where a cluster is an appropriate tool. My personal interest in HPC tends to focus on 3D rendering performance. This tends to need a lot of FLOPS, and relatively little bandwidth. For the guys who are doing really bandwidth/latency intensive stuff, the basic clusters are useless. (I'm told that stuff like weather sim falls into this category, but I can't comment on the details.) Without specifying a workload, saying th
Possible Use (Score:1, Funny)
The Ultimate Gaming Machine!!!
Just think (Score:1, Troll)
Cray who? (Score:2)
Hood? (Score:2, Funny)
I will blow it out of the water (Score:1)
White collar welfare. (Score:2, Insightful)
America would be better served if we sink the money in creating interoperability standards and creates ways to increase competition in the computational industries. Every company from Microsoft, to Apple to Parametric Techologies to SDRC to Oracle to ANSYS to itsy-bitsy-prof-and-grad-student-garage startups work to build vendor lock-in into every one of their products. The market creates rich rewards for locking in the user to one software product and preventing the user from migrating to a more efficient competitor.
Promote interop and competition. Super computers will become dime a dozen.
Re:White collar welfare. (Score:2)
Furthermore, programming a modern cray is not very much like programming a YMP. The code is structured very much the same on a XT3 as it is on Blue Gene, or on a cluster. There really is a lot of interoperability in the HPC space.
The real flaw in your logic is that there will be a lot of competition. The supercomputing marketplace is really tiny. It's about a 4billion dollar worldwide industry. That sounds like a lot, but it's really tiny compared to the greater computer hardware industry. Why compete for supercomputer dollars, when there are so many corporate customers with more money, and simpler demands. IBM and HP already own most of the HPC market by selling clusters of their business-class servers, so there's really only a tiny slice left over for the real innovators. If your particular need is not met by a cluster of IBM unix servers, you are in the tricky situation of forking over a bundle for a cray/nec/sgi box.
Niche markets have always been expensive. JP-7 fuel costs $30/liter. Modern day fighter jets cost $100million each. The government buys expensive stuff. Not really news.