Slashdot Mirror
Time For A Cray Comeback?
Boone^ writes "The New York Times has an article (free reg. req.) talking about Cray Inc.'s recent resurgence in the realm of supercomputing. It discusses a bit of Cray's decline when the Cold War ended, "the occupation" under SGI, and the rebirth of the company after the Tera (now Cray Inc.) purchase. Recently Cray Inc. has been shipping their vector-based Cray X1 machine, designing ASCI Red Storm, and recently was one of 3 (also Sun, IBM) to win a large DARPA contract (PDF link) to design and develop a PetaFlops machine by 2010. Could Cray Inc. be poised for a comeback? Wall Street seems to think so."
SCO vs. Cray
There are other uses too. Consider: the weather guys that are working on the global warming and other climate modeling want a 500 petaflop sustained speed, massive memory machine to get the granularity that they want.
BTW, what's the 15 YO machine? I can't think of any...certainly not ones that are still in the Top 500. Hell, the ones I worked on 10 years ago, you can nearly buy the floppage on the desktop now...
As an interesting aside, the DARPA contract is out in part because they think the traditional drivers in computing speed are going to peter out around 2010...the implications of that are definitely interesting, no?
Do you know why the road less traveled by is littered with the bones of the unwary?
Nuclear simulations are used to see if the warheads are still effective after not being used for long times, not to see if they'll wipe out a city right after they are produced.
ato
Hahahaha. Have you ever actually run a supercomputer? They tend to have much higher failure rates then normal servers. Couple of reasons: first, they push the envelope of a given technology. The sweet spot for stability is not the leading edge. Second, they're not nearly as well tested as mainstream hardware. On a platform with thousands of installations you're much less likely to run into a problem nobody has seen before than you are on a platform with only dozens of installations.
Don't get me wrong I'm all about nuclear testing being done in 1's and 0's instead of in the ocean or in the desert, but how big of a bomb do you really need when it's estimated theres enough nukes to blast the entire land surface of the earth 3 times over.
:D
Well, the earth is over 2/3rds covered with water, and now we have the technology to reach the moon, mars, venus and beyond. Remember the spectical when a comet hit Jupiter? Just imagine a Beowulf of those, but really big nukes instead
On a more serious and less morbid note, I bet some other uses exist in physics, medicine and even cosmology. I even hear where they compare 'potential' cures for diseases using computer modeling to design drugs that we don't yet know how to make, good old biotech. You are correct that yes, this IS a very very limited market, but when you sell them for a billion bucks each, you don't need to match Dell's volume to make a profit. I wouldn't be suprised if the technology leads to some advancements in our pitiful micro world as well.
Tequila: It's not just for breakfast anymore!
...isn't 'Cray' today about as 'Cray' as the company that now owns 'Atari'? What's left besides the name of the original company?
Does it hurt to hear them lying? Was this the only world you had?
Well, almost. Let's say I have a plane that can accomodate 100 people and does NY->London in 6 hours.
My problem is that I have to move 1000 people from NY to London
Now I can either:
1. I can buy a plane that is 20 time faster, 20 times more expensive. That's the supercomputer
2. I can buy 9 other planes (same as mine) and accomodate the same results as in 1 for less than half the price (I'll let you do the math). That's the cluster.
3. I can buy a plane that has a capacity of 1000 people. That's the parallel supercomputer. But if that one can do the deal for my specific problem, it proves to be not that flexible if my problem changes (ie: 500 people NY->London and 500 people from NY->LA).
That's the power of the bewolf cluster!!!
Write boring code, not shiny code!
Our T3E was having problems well past the point where it was getting long in the tooth. Cray started adding functionality to make it more supportable a few years back, but when it was actually a cutting edge system it was pretty unstable. They probably couldn't widely sell a system today that had the problems of the earlier T3E's (one hardware problem and you need to reboot the whole thing) but that just increases the development costs and time to market in a market where delay means that the peasents will be nipping at your heels. Remember, by the time a super hits maturity, it's obsolete.
Supercomputing per se died because Intel, DEC, IBM/Motorola had a lot more money to throw at speeding things up than the supercomputing community.
In the 70's up until the early 90's it was possible to build a custom CPU out of discrete logic that ran significantly faster than the available microprocessors. Cray was able to push their clock cycle down into the nanosecond range through clever design. However, a 1ns clock rate == 1GHz. You can go buy that multi-million dollar CPU for a couple of hundred bucks in today's market.
In order for superocmputing to be viable you have to be able to provide quantum leap performance above the commodity hardware AND keep your cost/performance ratio in line as well.
The CRAY-1 came out with a clock speed of about 80 MHz and vector processing and high memory bandwidth at a time when mainstream systems like the PDP 11/70 were running at about 7MHz with a 1MB/s memory bus. Microprocessors weren't even't a joke compared with the Cray.
The new Japanese NEC supercomputer came with a price tag of about $160 million if I remember correctly (some estimates say that it took $1G in research funding) and hits 35 TFlops (sustained). #3 on the Top 500 supercomputers list is a Beowulf cluster with 2304 processors coming in at 7.6 TFlops (sustained). Even figuring $2000/processor + interconnect, that puts the Beowulf cluster at around $5 million or 1/32 of the cost for 1/5th of the performance (roughly speaking).
There are other factors, of course, but the key is that for the supercomputer to stay ahead of the microprocessor a boatload of funding is needed for the supercomputer and the payoff just isn't really there. If it was a lot more supercomputer companies would still be in business.
Hmm... I'm not entirely convinced by your arguments. However, I do agree with you that "during the heyday of cray, you got a damn fine box and nothing else."
;-) Furthermore, I also suspect that if Cray Inc. built a zettaflop or yottaflop abacus and provided instructions on how to simulate the weather, people around the world would abandon their computers and begin taking abacus lessons... Remember, it's all about the hardware and algorithms in supercomputing...
My thinking, however, is that the same is true today and for all of the top 100 supercomputers in the world. That is to say, each one of those machines is a custom hardware installation, and my educated guess is that software still isn't the driving force in the supercomputing market. Rather, algorithms are the driving force. The supercomputer market is geared towards people who want to very specific tasks, very acurately, and very fast. Example applications might be calculating fourier transforms (spectroscopic analysis), mendelbrot sets (weather simulations), prime numbers (cryptography), and statistical derivatives (markets). Any of these types of applications could feasibly require only a few thousand lines of code... At the same time, however, any of these applications are fully capable of utilizing as much hardware resources as you have available...
The problem is the magnitude at which these few lines of code need to be repeated. Furthermore, each of these types of algorithms can give qualitatively different and more robust results at each order of magnitude increase in speed... thereby creating a driving market force for upgrades.... We have a computer that can predict the weather 48 hours from now? Well, give us a computer that's 10 times as powerful, and we'll predict it 56 hours from now... Give us one 100 times more powerfull, and we'll predict the weather 62 hours from now, and so on, and so on... The point I'm trying to make is that the software isn't the driving force behind these supercomputers... the algorithms are... and the optimized hardware is what the organizations are paying hard cash for, in order to calculate those algorithms fastest.
Remember, we're talking about supercomputers here... we're certainly not talking about super-electronic-typewriters, super-spreadsheet-applications, super-databases, super-webservers, super-videoeditors, etc. etc. Nor are we necessarily talking about super-von-neuman machines, super-turring-machines, or super-mainframes. We're talking about supercomputing and the Cray corporation... the company historically responsible for building the machines which simluated the weather and nuclear explosions for many years... I suspect that there are not many end users of such machines and that user interface software is kept at a minimum...
But, I'm not a physics or computer science major, so what do I know... That, and I'm beginning to ramble... just my $0.02 worth...
I remember a story from a NSA contract worker.
In the early days of Cray, he and many others were wondering how they could keep things running, considering that their official budgets only showed ten or so sales per year.
Until he got the tour of the NSA computer plant, where they had a hall the size of two football fields, filled with Crays.
How small a thought it takes to fill a whole life
SRC Computers is his legacy, not Cray Computer Corp.
He co-founded this company (with several other
ex-Cray employees) and died while still an employee/owner.
Interestingly, SRC is still around without any evidence on their website
of shipping a product. My guess is that their customers and/or investors
prefer to stay out of the limelight.
John Markoff, the same jerkoff that wrote the less then factual articles and book about kevin mitnick, and happens to belong to one of the less reputable media outles (aka the plagarized and false stories coming from the ny times).
Lawyers, MBA's, RIAA? A jedi fears not these things!