Slashdot Mirror
The Amazing Shrinking Supercomputer
mE123 writes "It would seem that IBM is trying to change what we all think of as super computers. Their new Blue Gene family of super computers is meant to be 6 times faster, consume 1/15 of the power and be 1/10 the size of current models. The prototype is already number 73 (with 2 teraflops) on the list of the most powerful super computers and it's only "roughly the size of a 30-inch television". They are hoping to be able to make it up to 360 Teraflops using only 64 racks." We covered this a bit earlier, but without the level of details.
Should the priority be making faster supercomputers (but large) or smaller supercomputers (but the same speed)? This one seems to be a step in both directions, but I wonder if they're sacrificing speed for size (or vice-versa).
My mom wouldn't let me have one because they take up so much space!
Clif
Blogzine.net
Fortress of Insanity
clifgriffin > blog
To invite entries for a super-computer that will fit in there? thats the only way this could possibly be on-topic.
Howdy Ho guys. Seems to me like large clusters of "inexpensive" machines to make supercomputers is fast becomin' the norm rather than the exception. Hell, Im even buildin' my own cluster back at the ranch out of old junk machines. I ain't gonna crack no DNA mysteries, but I sure am goin' to have a lot of fun networkin' them up, writin' load balancin' code and doin' lots of sums. Yeah Haw!
Stick Men
So, how long will it be before these become commoditised for sme's ?
...
:-)
Something that fits into the space of a 30" TV set (how about dimensions, guys ?) is presumably about half to 1/3 a standard rack in a co-lo. 2 Teraflops of processing power ought to be able to comfortably shift the bottleneck to the bandwidth, even for database-orientated sites
I think people's cost expectations are going to be significantly impacted by the size of this - if it's small, it must be cheap, right ? (wrong, but try telling them...)
Fantastic acheivement, btw, kudos to the man in blue
Simon
Physicists get Hadrons!
Yes, this is amazing--but I predict that in ten more years computers will be twice as fast, ten thousand times larger, and so expensive that only the five richest kings in Europe will be able to aford one.
I'm awaiting a supercomputer affordable by a small business...something top 100 $30-$60k...then i'll be impressed. Otherwise, it makes no difference to me as I will never get to play with one. *sigh*
The next logical step in this direction would be the challenge of building a supercomputer with the size of a cell-phone. Go IBM!
Maybe quoting submissions "verbatim" isn't such a good idea. I nearly went into convulsions trying to parse that submission.
Letting things like that get through makes the slashdot front page look a bit less "intelligent." What kind of demographic are we catering to again?
in [insert year]. It's possible when you're with IBM. I'm thinking this is a great opportunity for IBM to take hold of an exciting new market, personal supercomputers.
-Tim Louden
The real question is when are they going to make televisions that can fit into the space of a supercomputer, replacing endless hours of number crunching with endless hours of quality entertainment?
If you read the press release, they claim that previous 2 teraflop machines fill up entire rooms, with more than a dozen racks. I'm not so sure this is the case: for instance, Apple claims 798 gigaflops to a rack with the Xserve; by my reckoning that works out to needing 2.5 racks to get 2 teraflops. And that's just with dual 1.3 GHz G4 CPUs; I'd imagine there is an upcoming Xserve rev featuring dual 2.0 GHz G5's.
Don't get me wrong, it's still an impressive achievement (especially if it uses as much less power as claimed.)
"There is no night so forlorn, no mood so bleak, that it cannot be infused with pleasure by tender meat..." - R.W. Apple
Take your standard technology curve (aka Moore's Law), take any specification/cost point, then move ahead an arbitrary point in time and wonders of wonders, it costs less and is smaller and does more.
Yes, one day supercomputers will fit into your wristwatch! What's more, they already do! If you use an ancient measure from, say, 50 years ago.
It's very disappointing to see technology always reduced to whizz-bang figures that are in fact meaningless. What about the impact on our society? What about the capability for good and for bad? What do "good" and "bad" mean, anyhow? How do I know I even exist? What does "I" even mean?
Now, that kind of stuff is worth discussing.
OK, go ahead and mod me as a troll now, if you can't think of an intelligent answer.
Ceci n'est pas une signature
A true-super is when you through all your resources into computer and make something as fast as possible. These are typically space and power consumption hogs. After a new line of supers has been investigated for a while, then a slightly slower, but much resource friendly version is produced. By the time the 2-teraflop Blues ship, frontier supercomputing will be in the 100 gflop range.
We went through this process in the late 1980s with the cray-clones, crayettes, etc. You got like a fifth of a power of Cray (i.e. a two year old Cray) for like 1/20th the price. A Cray required a custom refirigeration unit, while Crayettes ran in ordinary computer rooms.
I mean, historically technology makes life easier for people. Of course, at the expense of lost and shifted jobs.
Blar.
In other news, the price of petrol increases.
"What about the impact on our society? What about the capability for good and for bad? What do "good" and "bad" mean, anyhow? How do I know I even exist? What does "I" even mean?"
Impact is good in some respects and bad in others. Both cababilities exist. Good=helps me, bad=hurts me. Pinch yourself. "I" is the capital version of the 9th letter in the alphabet, or a one letter reference to your memories and thought processes contained in your physical body assuming it exists.
I'm interested in what is contained in the IBM confidential trash box on top of the shelf:-)
By the way, why do they use a sprinkler system in a computer room??????
does this mean that someday my desktop will fit in a wristwatch???
just spectaclating
At the speeds these things operate, the time it takes for any signal to propagate is important - hence smaller is faster.
I just checked out the pictures of this machine. Since when does 5 racks equal a 30 inch TV? Or even for that matter, ONE rack?
This is a test. This is a test of the emergency sig system. This has been only a test.
Maybe they made some deal with Micro$oft so they would have the only computer that can run Longhorn...
Don't waste your vote! Vote for whoever you want, unless you live in a swing state it won't matter anyways
I tend to agree, though I think overall this will have some pretty good ramifications. It furthers the increase in user-available computing power, cost and size wise I'm sure. I think because of this we'll see "real" advances in user level computing, not like this photon-light based computer stuff or this quantum computer stuff (which may be a hoax for all I know... :-)
Anyway, I'm sure someone once questioned the purpose of "desktop" computers. Who needs those? Besides, we might need a computer just like this to run Office 2007 someday.
The snow doesn't give a soft white damn whom it touches. -- ee cummings
Supercomputers _do_ fit into a tower case. 10 years ago the power that I ship our the door on any given day was unheard of. Tomorrow you will be able to buy a system that has Terahertz in a normal beige box... And you will get a couple of hundred thousand FPS in your quake 3 benchmarks, and about 3 FPS in the newest games.
On Arrakis: early worm gets the bird. Magister mundi sum!
I'm not a big fan of super computers. I mean, it's kind of cool, but to me, it's just throwing a whole bunch of computers at the problem, more or less.
That being the case, why aren't distributed apps considered as part of the Super Computer list? I mean, SETI@Home has got to be far and away, #1 in terms of computing power. Granted, it's not in 1 integrated piece of hardware, and Berkeley doesn't own all the hardware, but I still think these things ought to be considered, at least to make it more realistic about who actually has the most computing power.
Just my little rant.
Would sales tax on these things be called a "Blue Gene Levy"? Hahahaha. Horrible, I know. ;)
"Yeah, well, Dracula called and he's coming over tonight for you and I said okay."
How many 30" TVs to the VW Beetle?
And how many Libraries of Congress of data will this hold?
was already having to figure the propagation delay of signals (traveling at near the speed of light) into their large multirack systems. I can only imagine one of things driving the desire for smaller supercomputers is to speed up the clock by reducing the delay across the physical size of the box.
--Rob
I submitted this story 10 days ago, November 14, 2003, the day IBM published their press release online, almost verbatim as i quoted the same material, and it was rejected!!
Not only that this strikes me as old news, but its publication now completely baffles me.
so where is this list of the most powerful supercomputers? i'd like to see it...
technology is getting faster and better and cheaper. damn. who'da thunk it.
My problem? I was perfectly gruntled, until some numbnuts came by and dissed me.
Nevermind. Mister Editor fixed it.
...assuming it exists.
:)
Good going until this point.
If Darwin was right, we're just replicators, the concept of "I" is a trick of perspective created by our minds in order to improve our performance, and intelligence is limited by the awareness horizon that, once we cross, we realize it's all a big joke and we self-destruct. Philosophically speaking, of course.
Sigh. At least we'll be able to buy brain-sized supercomputers to replace our auto-anihilating intelligence organs.
Ceci n'est pas une signature
I work on the project.
We're packing 1024 compute nodes (each node having two CPU cores) into a rack. The nodes are small and based on the PowerPC 440, with beefed up floating point. It has to be air cooled - water is a PITA.
The finished machine will still be quite large - 64 racks with miles of cables. And that doesn't count disk drives. There isn't a single disk drive on the thing - the customer provides the filesystem, which will also be another beefy set of machines. It requires a new building.
The machine featured in the article is just half a rack. It is still respectable, coming in at #73 on top500.org. Might be quite useful for business and small scale scientific in it's current form. (This is far more than my alma matter had access too.)
That's one hell of a p0rn server. Now compile apache, and connect to a pair of DS-3s...
hmm... how many Counterstrike servers will it run at the same time...
(Note: The above is meant to be foolish and meaningless. Any other interpritation is pure coincidence. The names have been changes to protect the inocent)
Why worry? Each of us is wearing an unlicensed "nucular" accelerator on his back.
Sig changed for readability by G.W.
>It's very disappointing to see technology always reduced to whizz-bang figures that are in fact meaningless. What about the impact on our society? What about the capability for good and for bad? What do "good" and "bad" mean, anyhow? How do I know I even exist? What does "I" even mean?
Dude, since the answer to the ultimate question is "42", we need all the power we can to compute that ultimate question.
Only then will you get an answer to "What does 'I' even mean?"
I agree entirely! It can't be kewl unless it's made by Apple! All hail!
Humanity has been developing Super Computers for the last 50 years. We only hear from them when they are developing them. For the time they finish it, it's allmost obsolete. They prommise that the machine is going to make a revolution in science, but after that the computer is just sold to the army to research how to destroy small countrys in a cost-effective way, or dedicated to some obscure research that never gives out any results. And, since the price of this things is just a delirium, just a few privileged ones can have use one for their research.
I think there is a more logic, more upgradeable, more cheap and scalable solution, which is Clustering / Parallel Computing.
It's scalable, you can start with to machines, and keep adding more to fit your needs, use a few PII to run quake and john the ripper, or you can have a real environment for use on research, achieving allmost the same funcionality that with supercomputers, but with the advantage that you created it with available hardware that you can buy anywhere, allmost anyone can afford one, just different size of the network and different bandwith will make the difference, and more important, you can upgrade it easily whenever you want.
I think we should be developing and improving this kind of solution FOR EVERYONE, and not spending millions to develope something that just a few ones will have.
BTW, who wants them to be smaller? : )
WTF am I doing replying to an AC at 5 A.M on a Friday night?
You can find most of what you want to know on IBM Research or US Department of Energy (search for bluegene). I think both can survive slashdotting.
Top500.org
Is that a super computer in your pocket, or are you just really glad to see me?
This system was designed for low power consumption. I believe the clock speed was intentionally lowered to have a higher speed/power ratio per processor. The reason for this is that power usage over lifetime of the system can be more than hardware costs. This makes for a lower cost per speed-lifetime unit. They made important technical changes in design.
What this extra speed is used for is important. But it is a separate issue.
Hmmm, since we're on a serious but enjoyable tangent here, I'll take your question and double it.
The "self-destruction" is implicit in the surrender of the "I". By definition.
However, that is neither good nor bad, since these terms can't even be defined without recourse to the "self" we've just destroyed.
The temporary collection of genes that has registered under the Slashdot alias of HeironymousCoward, and which we can abbreviate as "I" for the purposes of discussion, thinks that what is left after destruction of the "self" is in fact a very harmonious situation.
With no "I" (except in Slashdot, where we can all agree that an alias "exists", representing Karma points, a journal, and many slanderous comments that will haunt the replicator in question until its disintegration), there is also no blame or responsibility beyond the genetic obligation to replicate. Further, there is no need to reflect or plan except when reflection and planning are the natural and easy thing to do.
(I would interject deliciously self-destructive the observation that "conscious decisions" are made about 0.5 seconds after most acts.)
The destruction of the self is therefore not just inevitable as we move towards a deeper understanding of how we (and this replicator uses the term loosely) function, but it is also highly desirable, because it frees us. This replicator cannot say what such freedom brings, but after about 30 minutes of experiencing it, "I" have to report that it is, on the whole, enjoyable.
Ceci n'est pas une signature
JUST imagine a beo...Ah fsckit! This isn't funny anymore. Was it ever?
It is much more difficult to use them for most applications most of us can think of. For example, VLSI CAD software (simulation/analysis/synthesis) is very compute intesive. However, these systems usually do not even take advantage of the multiple CPUs in a typical general purpose SMP system. You have to manually partition designs and sometimes loose the advantages of global optimization.
So don't run and order your new Blue Gene yet :)
Multivac, can I be the Voter?
No, I'm New Here
Did you have Greenlee?
Why do we need to have small, power-efficient supercomputers? Isn't the main goal of the supercomputer to be fast as hell? Granted, if this can be achieved while simultaneously minimizing power and size then by all means go for it. However, as stated by my parent, what sacrafices are being made?
The increase in speed is related to the reduction in size.
For a moment, let's pretend that electricity within a wire travels at the speed of light.
Now, let's pretend that we wish to carry pulses of electricity from one end of the computer to the other at a very high speed.
At some point, the distance the signal has to travel will become significant to the speed of the computer.
This is already happening in PCs. If you take a close look at the motherboard in your computer, chances are you'll see weird places where the traces just zig-zag back and forth (notice the angles on them, that's not by accident either, but I'm not going to try to explain a fourth-year university course in microwave and RF design here). These zig-zags add length to the traces so that they have the same length as other traces within the same bus, and all the signals on that bus arrive at the same time. Think of them as being "equal length headers", if you're into the throb of a big-block V8.
Length of interconnecting wires is non-trivial at this point. Stray capacitance and inductance caused by any conductor are non-trivial at this point. As a result, a terrific limiting factor to the speed of a computer is now its size.
Power consumption is also related. Modern ICs are made of millions of MOSFET transistors which behave as switches. These switches are not perfect: during the transition between a logic high and a logic low, the transistors spend time in the linear state where they are resistive. As a result, they waste energy as heat.
Stray capacitance and inductance - even within the junctions of the transistors themselves - slow their ability to switch instantaneously. As a result, they must be made as small as possible to reduce capacitance (C) and inductance (L).
This also explains why newer generations of a processor can run faster than their predecessors: smaller and smaller features on the IC mean less stray C and L, which means that the transistors can switch states faster, which means that they spend less time in the linear state and therefore heat up less. This means less energy wasted as heat.
Fire and Meat. Yummy.
If supercomputers were ubiquitous, more uses would be found. So I don't see how "need" comes into the picture. Now who can afford one? That is a good question. If they were affordable you'd see needs popping up all over.
Lasers Controlled Games!
I RTFA and I think this is really good stuff. However, doesn't it stand to reason that this is just the natural progression of things? For years we've worked towards miniaturization and it seems logical that hardware developers would continue to try pushing the envelope for new systems designs and architectures. It will be amazing to see how much power can be crammed in to a shoebox sized device within the next twenty years.
Illiud Latine dici non potest
Finally a computer exists that can easily fit in my apartment with enough power to play Doom III at 30 fps.
You've got 8% of my love - 8% of my love - 8/100's of the time you're the only girl I'm dreaming of.
I think it's hilarious that we still talk in terms of computers taking up a mere half a tennis court. Once upon a time, computers took up an entire room - and they still do.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
This set of sldes compares some of the architecture of the BlueGene/L to other ASCI machines.
Seems to me there was once a guy named Seymour, who could do the fast *and* small thing quite well. Since we're talking in terms of Televisions...
Big screen #1
40" HDTV and a A size perspective
We have DEFINITELY been down this road before folks. I don't see why it's so hard to do this, unless you're using COTS components. Hence, the point of "engineering" - not cramming a bunch of stuff in boxes/packages into bigger boxes and packages.
Detachment 3 Media
Exposed, Exploited, Exploded
798 Gflops in an imaginary application taking full advantage of SIMD in every clockcycle and never needs to flush cache or even access RAM.
entee
Opinions stated are mine and do not reflect those of the Illuminati
i agree... if you can afford xxx million dollar computer, housing and power shouldn't be an issue...
if it's really a problem... why not string 10,000 laptops together?
or how about a super cluster of Palms ?
on an Apple Jean? (think Lisa)
2130?
This one little computer is small and efficent and all the waste heat easily taken care of. Now imagine not just one of these, but a whole building of these. Our heat problem crops right back up.
IBM knows what it is doing.
That being the case, why aren't distributed apps considered as part of the Super Computer list?
Most of the tasks you pick a supercomputer for aren't things you can cut up into a thousand chunks and let every computer finish it's chunk of the problem independently. In particular, the benchmarks (LINPACK) that determine who goes where on that supercomputer list generally measure a computer's performance at big linear algebra problems (which are what takes up most of the compute time for huge classes of real problems), and for those problems every node needs to share results with many other nodes after essentially every iteration: this means you need high bandwidth and very low latency connecting the nodes.
Now, the supercomputer benchmarks may make things worse than they have to be: according to this they're measuring performance on dense matrices (where every node needs to talk to every other node), whereas many real world problems can be discretized into very sparse matrices (where each node only has to talk directly to a few of the others) instead - still, even in the sparse situation you want your computers to be separated by microseconds across your high speed interconnect rather than milliseconds across the low bandwidth internet.
Comment removed based on user account deletion
Why is it that every so-called "supercomputing" article posted to slashdot never mentions Apple. You remember, the company that has pretty much SET THE BAR for clustered supercomputers? Seems to me this IBM stuff is a poor attempt to try to match the amazing price performance of the Apple supercomputer (you know, number THREE in the top-500 list) but it lacks the usability, applications and overall value of the APPLE solution, so why would anyone bother? Honestly, I find it amazing how Apple has continually set the standard in all areas of computing and yet the so-called "techie" slashdot crowd appears to ignore them every time.
now just make one that's PDA sized :)
-illumina+us "I put on my robe and wizard hat..."
They have no hope of bucking the Earth Simulator and taking the real crown, so they're pretending the rules have changed.
I recently did a search of top500.org which has specs back to June 1993 and up to June 2003
BTW WHO THE HELL BROKE top500.org!?!? This site used to be easy to use and informative, now it is a banner add hell, that obscures the info you used to be able to get to easily, with many broken links and apologies for works in progress.
Anyway I digress, the point is that in 1993 the fastest computer was the TMC at Los Alamos with GigaFlops ratings of 59.7 Rmax 131.0 Rpeak
My Dell XPS today would rate in the top half of fastest machines in the world for 1993 if I'm reading the stats right with just over a GigaFlop of power.
Todays fastest machine is Japan's Earth Simulator rated at 35860 Rmax 40960 Rpeak
If we define a super computer as the ability to get in the top500 then 245.1 Rmax 384.0 are the numbers that indicate your machine would be a super computer by 2003 standards.
Letter To Iran
But then I always want one.
I is a word, a metaphysical handle for a concept. That concept is your "self." Now of course, you can't actualize or understand the true nature of your "self" because all that your are, your very intelegence is imprinted with the imperfection of language. Language has, implicit to it, definitions that are both inprecise and imutable.
"I" then, is a word refering to the reflection of your "self" as seen through the lense of the world you've been conditioned to accept.
"I" must exist, however, because without someone to QUESTION if "I" exists "I" can not exist. In short, the capability of questioning the existance of "I" cements that very existance.
Ok... I'm done. Now someone else handle the good and evil part.
Killfile(TGK)
No trees were killed in the creation of this post. However, many electrons were inconvenienced.
Ask yourself: why do you need a supercomputer?
Answer: To do a very sophisticated simulation that would be too difficult or costly to conduct in real life.
But if the supercomputer is so expensive to purchase and maintain, it might be easier and cheaper to use CAD and rapid prototyping to make a few doo-dads and knock them into each other for real, as an example.
So if the supercomputers can't scale with the rest of computing or manufacturing, then no one will buy them (no one who doesn't want to get fired for being thickheaded, at least)
THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
While progress in making supercomputers more efficient in terms of power usage and space, the widespread adoption of supercomputers is still really hampered by functionality. The majority of supercomputers are used for modeling, simulations, or code breaking. This limits their usage to academic and government institutions. These break through only help those kinds of institutions afford a super computer. I would think that most businesses have little use for that kind of raw computing power. Their computing bottlenecks are more related to transactions per time as opposed to calculations per time.
Well, there's spam egg sausage and spam, that's not got much spam in it.
But who cares really what the outside looks like? Really. Couldn't the 3d artist do a cutaway or something? They have pictures of the prototype but there's no sense of scale or anything. I'm not saying it will, but form should not dictate function. And I don't really care for that slanting theme.
THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
I will provide the answers to the important and serious questions posed above; for I believe in providing light where thier is darkness...
What about the impact on our society? Nothing. It's just a computer dude!
What about the capability for good and for bad? Nothing. It's just a computer dude!
What do "good" and "bad" mean, anyhow? I just HOPE you are not expecting a computer to help you answer THAT question!
How do I know I even exist? I don't know if you exist but if I was to take a guess, you probably don't.
What does "I" even mean? "You" probably don't "need" an "answer" to this one since "you" probably don't "exist" anyway so the "answer" to "I" should not "bother" "you".
Now with this new knowledge of morality and metaphysics, go spread the answers amongst the masses.
I miss the Karma Whores.
Probably lots of people submitted that article. Slashdot editors, not being complete idiots, had the same reaction as a lot of the posters here, to paraphrase: "Shock! IBM makes smaller, faster, clusterable computer!" So they featured this in a group article on the 14th about a bunch of similar articles.
Later on after about 20 more people submitted it, they gave in and posted it directly. They generally attribute the person who causes them to post it, rather than a group.
THIS THING CAN TURN ON A DIME, MACROSSZERO STYLE ALSO FUCK BETA, ~NYORON
798 Gflops in an imaginary application taking full advantage of SIMD in every clockcycle and never needs to flush cache or even access RAM.
Yeah, just like the 2TF for a BlueGene/L node is an imaginary application that uses MADD in every operation, and never hits RAM.
That's what theoretical peaks are supposed to be.
I'm more than half-way serious, though. Just TRY to imagine a Beowuld cluster of these. (Yes, I know it's already a cluster. So are the individual cell columns within your brain.)
I do think that this is the wrong apporach from the long term, but for now...
What I see for the long term is some chip maker implementing a complete Beowulf node on a chip. And using a Beowuld bus for the connection lines...though you might design it so that it could link directly to "nearest neighbors" to the four sides (corners probably have too narrow a communication bandwidth... but perhaps allow a full-duplex single-bit channel [two wires] for sync signals). Still, the main connection would be the base link into the beowulf net. Don't concentrate on making these nodes fast. Concentrate on making them low power & heat efficient. So they can be stacked densely.
(In the next generation all the "nearest neighbors" could be included within the same chip.)
You would quickly (say two CPU generations) have more CPU power than you can imagine... but control would be a real nightmare.
So the real need that these new supercomputers are presenting us with is to learn how to control them...so that when the next generation comes around, they can in their turn be controlled usefully. Etc.
Even a standard architecture doesn't make that an easy job, not unless you want most processors to spend most of their time waiting. Most traditional problems scale atrociously with increased parallelism, and using the algorithms that we know. Even when we know that an algorithm is maily parallel, our languages don't let us specify that. (Consider even just partitioning a vector into the even and odd elements. Now try to express that in C as a parallel algorithm. Now try it in Java, Python, Ruby, Ada, Objective-C,....) I understand why C, C++, and Ada have this problem. I have more difficulty understanding the same problem from Java, Python, and Ruby. Ruby even has an ".each" method built into many language specific classes (arrays, hashes, etc.), but it is explicitly defined as being a sequential operator rather than a potentially parallel one.
Now I'll grant you that with today's heavy processor switching costs the implementations *should* be sequential. But the language designs should ALLOW the implementation to decide to be parallel if that made sense.
I think we've pushed this "anyone can grow up to be president" thing too far.
The three or four times /. has covered the Blue Gene, the articles haven't had any useful pictures in them. Its pretty frustrating to read "about the size of a 30-inch tv" and not being able to see what the hell it looks like. If you go to IBM's website, they've got this artists' rendition of a cluster of the things, but my TV-supercomputer is nowhere to be found.
What does "I" even mean?
italics?
Im dreaming ofa big bndwdth, That can resist the
Those of us who can think of an intelligent answer are going to mod you down as a troll anyway.
Ya, except I took it the semester after he retired...
Comment removed based on user account deletion
Network is the biggest bottle neck for any home PC.
If I had a choice between a supercomputer crunching teraflops in my house or a fibre connection to the web.... I'll pick fibre connection any day.
They should have been doing this years ago. This is the same thing as taking a massive cluster and shrinking it into a relatively small, optimal, package. IBM finally gets it that massive parallel process is the way of the future. They figured out how much more sence it makes to leverage standard microprocessors.
in green please.
The supercomputer thing is cool and useful and everything, but what I really waiting for is someone to bring true 'intelligence' to computers. Despite all progress that has been made in the last 50 (?) years of computing, our present-day machines can only be described as truely gifted idiot savants. They can blaze through a list of instructions faster than ever before, but are helpless in assigning any meaning to those instructions, or learning from them.
For example say you have 2 graphics packages installed on your PC, A and B. Package A is able to export to a certain picture format, say JPEG2000, but package B isn't. Why? The instructions for writing out a JPEG2000 pic exists on the hard drive, the computer is able to follow them (as evidenced by package A). Why can't the computer simply follow the JPEG2000 instructions in package A when package B wants to write out a pic? On a larger scale, imagine a Google that understands context, subjects and objects, not just words. It could distinguish and understand the difference between searching for chinese dishes served at a restaurant and a china dish sitting on a cupoard.
IBM (and others) are doing great work in making computers bigger, better and faster, but I'm still waiting for some true computer intelligence. If it takes bigger, better and faster computers to make it happen, I'm all for it. I think true, usable, accessible machine intelligence would be a huge leap forward, and would change our world more than the Internet did.
OK - you can start with the Skynet comments now.
Somebody needs to ask, and it may as well be me. I leave the obligatory Wolfpack question for others (Im not greedy, after all).
Manipulate the moderator system! Mod someone as "overrated" today.
The pictures are right there in the article. It's the half-rack system they're standing next to. Here are more.
The Earth Simulator is 40 teraflops. Blue Gene/L is expectected to operate at 360 teraflops (in 2005), easily winning the #1 spot unless someone's been developing something in secret that no one knows about.