Slashdot Mirror
Software to Make Blue Gene Top 200 Teraflops
An anonymous reader writes "New Scientist has a story about the most intensive computer program ever created. It runs on IBM's big beast, Blue Gene/L, at Lawrence Livermore National Laboratory in California and carries out 207.3 teraflops (trillion cacluations per second). The program, called Qbox, performs very complex quantum calculations to simulate the behaviour of thousands of atoms in three dimensions. Wow."
It does not perform very complex quantum calculations, instead
It simulates interactions between 1000 molybdenum atoms under high pressure using equations that take the quantum behaviour of electrons into account.
Also, when its not being used to dynamically model atomic structures, the IRS uses it to calculate Bill gates's taxes.
liqbase
Yeah, but can it beat Kasparov at chess?
/whisper/ Thanks for the candy!
Does it run Linux(R)?
Too bad for Q-Box that their title will be stripped of them so soon. Vista's almost here.
Wait a minute, Vista? Nevermind...Q-box should have it for a long while.
Ride the skies
"Wow."
More importantly, at what FPS does it play WoW?
Though I wouldn't be surprised if it needs a new graphics card for Crysis...
Specs here and yes, Suse
I mean, I'm sure I could use up more than 200 teraflops with my "while (1);" program.
I don't need no instructions to know how to rock!!!!
So in essence, it takes about .2 teraflops per atom... And that was only after spending a lot of time condensing the algorithms. This makes me wonder two things. First, what do these equations look like such that it takes 200 gigaflops just to model one atom. Second, over what timeframe does this simulation take place? Are we talking real-time, calculating for 50 years, what?
Regardless, as a computer scientist, I say way to go to these guys, this is damn impressive.
Government's view of the economy: If it moves, tax it. If it keeps moving,regulate it. If it stops moving, subsidize it.
The program, called Qbox, performs very complex quantum calculations to simulate the behaviour of thousands of atoms in three dimensions.
"Molest me not with this pocket calcualtor stuff."
Weaselmancer
rediculous.
How do they know they got it right?
Slashdot.. where people join together in deliberate ignorance.
So what? My destroyer in EVE does 215tf!
Wait....I need to stop playing that game so much.....
Man is the lowest-cost, 150-pound, nonlinear, all-purpose computer system which can be mass-produced by unskilled labor.
Oblig. H2G2. "Here I am, brain the size of a planet and they ask me to take you down to the bridge. Call that job satisfaction? 'Cos I don't." - Marvin
BlueGene/L has a sister project, Cyclops64 (formerly known as BlueGene/C) due out sometime late in 2006 or early 2007. My research group is (a) helping IBM do hardware verification on it. and (b) developing the systems software for it [esp. the compiler]. Cyclops64 could very well blow BlueGene/L out of the water.
To make laws that man cannot, and will not obey, serves to bring all law into contempt.
--E.C. Stanton
42.
It doesn't take .2 teraflops to model one atom, or even two atoms, even account for effects on the quantum level.. However, when you take into acount that each atom will more or less interact with every other atom, you have a massive amount of interactions to model. Thats what takes so much processing power.
2016:
Imagine a _________ cluster of those.
Well done, you may now enter. Gaming room to the right, pron cubicles left, and crazy linux hardware center up ahead.
We hope you enjoy your stay at Geek Heaven.
http://www.hpcwire.com/hpc/699401.html
There's some additional info about BlueGene and what Livermore thinks of it here. What this interview neglects to mention is the millions of dollars being spent on IBM and internal developers to get this code (and any others) working on BlueGene. I was briefed by the hardware and software teams that built BlueGene and I can tell you, it's no easy task to bring apps to that platform. Kuznezov seems to trivialize it in the interview and I'm gonna have to go back and review the process again. Maybe it has changed since my briefing in early 2004, but somehow I doubt it.
can it run windows vista?
i thought there were more dimensions in the subatomic world o_O
Did you know that "FTW" ("for the win") is a direct translation of "Sieg Heil"?
"... The program, called Qbox, performs very complex quantum calculations to simulate the behaviour of thousands of atoms in three dimensions. ... "
Rumours say that it may actually be able to render Aero's 3D-interface as well.
I wonder what the cubes represent?
Oh, wait. Qbox. Nevermind.
m-
You catch enchiladas by picking them up behind the head and holding them underwater until they don't kick anymore -VeGas
The article is light on details but I suppose the only quantum algorithm that can handle 1000 atoms is Quantum Monte Carlo. The problem is that the algorithm is cubic with the number of particles (and has a huge prefactor). So in essence 1000 atoms is 1000^3=10^9 more time consuming than one. And I'm sure they still use dramatic simplifications, even though they have the most powerful computer. They probably do not consider all electrons, instead they use pseudopotentials. And the Quantum Monte Carlo is likely in a fixed-node variant which is approximate. How long does it take? It's hard to tell but probably a few hours or days each and they are performing several those with different conditions.
Save the bandwidth. Don't use sigs!
Only if it's in base-13.
...but all the nodes fell off.
Regards, Phil
Like finding The Answer to The Ultimate Question Of Life, the Universe and Everything
Introducing Microsoft Vacuum 1.0 The first Microsoft product that doesn't suck.
Does anyone know what these calculations are trying to determine? In essence, what's the central problem to determining the reliability of old nuclear weapons? I would have thought they're doing simulations of detonation of these aged weapons, but the article talks about using molybdenum, which isn't a fissile material.
AccountKiller
Sounds impressive, but that's only about a 10 atoms on a side.
The simulations help scientists at the US government's Department of Energy determine the reliability of the country's ageing stockpile of nuclear weapons without actually detonating the weapons.
Oh, my. High technology in the purpose of supporting American terrorism. Throw all those stuff away ! Let the biggest computation in the world measure the amount of happiness of the amoeba population in the year 3000.
so can it help me with my math homework?
The program, called Qbox, performs very complex quantum calculations to simulate the behaviour of thousands of atoms in three dimensions. Wow
If it come to a choice between complex calculations and playing WoW on it i know what i would pick..
God Be Gone
Imagine, if you will, taking this super-computing ability out a few years. Can the U.S. justify the invasion of a country X because X successfully simulated an attack on the U.S? Or maybe they just had the computing power to simulate it.
To the UN: We'd like you to look at these satellite images that clearly show a super computer simulating the destruction of the U.S. We have to take out these terrorists and we're willing to go it alone.
Afterward: Well it turns out that they didn't have the computing power at all, the images we had were of a mobile home park.
Bzzt Whir Click
Not *that* infinite loop. The "infinite" loop that Linux and any other OS can finish in 5 seconds (if the CPU speed is right) is:
int n;
for (n = 1; n > 0; n++) ;
This loop will actually finish because n will overflow and become negative after it reaches the largest value that can be represented as an integer in the machine it's running.
And the atomic number of molybdenum is... 42
Yeah 200 teraflops is nice, but how many Frames Per Second can it get in Half Life 2? :)
"Gentlemen, You cannot fight in here, this is the War Room...." - Dr Strangelove
That's what they want you to think...
42
So I presume that "HotBabe" winds up in the all-together when this is run?
If you're sort of on the inside, let IBM know you'd like to see Cyclops 64 or it's successors optimized for AI. By some estimates Blue Gene was the first computer to exceed the computational power of the human brain. But of course it's not intelligent because it's not optimized for that. A wee bit of software still needs to be developed also. That's kind of big news when you think about it. A computer's power may now be more than the human brain. The singularity is near indeed.
Other news: 1001 (molybdenum) atom quantum computer beats Blue/Gene.
It actually:
- calculated in nanoseconds what blue Gene took days to do
- Fits here: "."
"Fix it"
Yeah but I heard they just put Vista beta 2 on it and it gave it a performance rating of 1 :)
I think an algorithm that results in a very complicated operation like this should definitely not be the best way to solve the problem. I mean ; you can calculate the exact node voltages in a 6th order system by numerically solving the integro-differential equations using an IBM average computer. But an average school kid can also solve that system ( if the numbers are not too cumbersome ) by transforming everything into s-domain rather impressively ! Mathematical models are what we invent for theoretical solutions; but I do not think those electrons need to evaluate terabits of information to move. OF course; observing a physical system consumes entropy, i.e we have to pay to observe or simulate an electron, but the mathematical models should , among infinitely many solutions, and/or can be made simpler. If physicists tell these computer virtuosos to solve 1000th order integro-differential equations containing transcendental functions; they should be replied : Go find a simpler model for your freaky system ! =)
There's plenty of room at the bottom! Richard P. Feynmann
Parent is right, it is complex interaction of particles in a complex/coupled condensed matter system that adds complexity to the system (Usuallly solved with the time varying schrodinger equation, some pseudopotentials etc). Interactions with the nuclei are often ignored (Born approximation). Simple calculations for small clusters with good symmetry can now be relatively easily done on your PC or simple Beowulf clusters nowadays using popular programs such as Gaussian. Scaling it up to 100 atoms requores some serious horsepower like this. A good open source/GPL program for condensed matter physics related calculations can be found at www.abinit.org (ABINIT short for ab-inito caluclations)
Thousands of atoms. Shrodingers/Bohrs equations for all of them.
This has interesting consequences for the study of plastics, DNA, virii and other complex molecules.
Perhaps the program can run in a loop trying every possible atomic combination to produce the best of certain attributes, as in give me the hardest material or give me an easy to manufacture room temp superconductor. It bypasses the whole invention/discovery step.
"Give orange me give eat orange me eat orange give me eat orange give me you." -Nim Chimpsky
I thought this was about the Towbin Dodge "Sexy Blue Genie" character.
Mighty disappointing to find it's about some computer or somethin.
Chop Chop it.
Qbox. It all makes sense, world fastest basic box!
-m10
It can calculate an infinate loop in under 5 seconds!
The "Big Blue Marble" we call earth has been running at magnitudes of 'flops' for ages. Perhaps if they didn't install that evolution software, the aliens would not have stopped avoiding that planet that kept blue screening.
I suggest that even 1+1=2 is wrong at 207.3 teraflops for more than a few seconds.
E Proelio Veritas.
I think BG/L only has something like 256MB ram per node... And with no hard disk and no video card!
But could it run Linux? Yep, it does!
The problem I see with projects like BG/L is one of two things a happen:
1) Software is implemented by CS majors who have little understanding of the math and physics involved. They probably implement highly computationally intensive (inefficent) algorithms well (i.e. no bubblesort).
2) Software is implemented by Physics majors who although knowing the syntax of C/fortran, don't understand how to write good programs. Their implementations are numerically correct, but highly inefficient [e.g. they use non-scalable algorithms on huge systems]. They seem to have no clue of Amdahl's law....
So even if they proudly exclaim that they wrote a program that uses 100 Terraflops, I suppose the same result could have been found using several orders magnitude fewer operations (with better written software).
But hey, what is their competition?