Slashdot Mirror
IBM's Blue Gene powered by Linux
bigjnsa500 writes "Linux will be the main operating system for IBM's upcoming family of 'Blue Gene' supercomputers--a major endorsement for the operating system and the open-source computing model it represents. Blue Gene/L, the first member of the family, will contain 65,000 processors and 16 trillion bytes of memory. Due in 2004 or 2005, the system will be able to perform 200 trillion calculations per second. Lawrence Livermore National Laboratory will use the system for performing nuclear weapons simulations." Blue Gene has been announced for some time, but it's cool to see how it's shaping up.
ASCI Red Storm google search
Blue Gene/L is expected to operate at about 200 teraflops which is larger than the total computing power of the top 500 supercomputers in the world today.
It should be noted that these super computers won't be for sale... IBM simply leases the cycles, you pay based on the cycles you use every month.
What is slashdot?
The referenced article is dated October 2002. Is this a mistake, or is this old news?
Anyhow, going to the Blue Gene web page, there is a document dated Nov 2002, an overview of BlueGene/L. An excerpt:
The approach we have adopted is to split the operating system functionality between compute and I/O nodes...
The compute node operating system, also called the BlueGene/L compute node kernel, is a simple, lightweight, single-user operating system that supports execution of a single dual-threaded application compute process...
I/O nodes are expected to run the Linux operating system, supporting the execution of multiple processes. Only system software executes on the I/O nodes, no application code.
I should have linked this in my other reply. My bad. Information on so-called "low-yield" nuclear weapons for the morbidly curious.
"I know not with what weapons World War III will be fought, but World War IV will be fought with sticks and stones." - Albert Einstein
(And we thought we were past all of this...)
I want peace on earth and goodwill toward man.
We are the United States Government! We don't do that sort of thing.
Historically, the modern reason for computer simulation of nukes is to put a stopper in the nuclear proliferation genie. The logic is convoluted but sensible. The idea is that first you get a test ban treaty. Second, You offer economic and power production aid to all countries that dont develop nuke engineering or let you control their plutonium bearing nuke waste.
this creates a situation where nuke weapon engineering has to be done either in secret (since there no civial reactor technology to produce plutonium) or if done overtly, they still cant test their weapons. Neither can we.
this leaves everyone in a delightful position of 1) not being perfectly certain their nukes will work when delivered. thus they are not good offensive weapons. (imagine what would happen if pakistan launched on india and it were a dud).
2) yet they still make good defensive weapons since even though its not tested it doesn;t mean it wont work.
which is sort of nice. it discourages both developement and first use. world is MAD but better off.
Unfortunately the US would never go for this if they did not have a way of testing their own weapons. So they do it in silico rather than in nevada. This allows us the political will to go through with this. a better world results. THe clock is ticking. we know the weapons will work now but they are aging.. will they work in say ten years. THis is where computer simulations come in. within ten years we should be able to model nukes and nuke aging on one of these machines at a level that gaurentees our readiness. or maybe if this test ban thing works we can just scrap them all in ten years.
that was the plan. But now with about 30 countries with potential nuke development capability this plan maybe about to break down. thus we go to plan B.
plan B is we use these big computers to design new reactors that dont produce plutonium. We sell these to the countries. now they can have nuke power without creating weapons grade plutonium. Again every body happy.
except of course N. Korea.
Some drink at the fountain of knowledge. Others just gargle.
afaik, the research isn't on weapons development, but explosions research and weapons defense.(The more you know about the explosion the easier it is to design nuclear resistant bunkers and the like)
For those of you wondering why it takes 1 pflop to do such a simulation consider how much computing power it would take to follow each gas molecule in the explosion as it expands. They won't be able to get even remotely close to that precise, obviously. (6x10^23 molecules in 22 liters at room temp, so figure about 10^25 molecules to follow around)
Also, keep in mind that 70% of academic research dollars are defense related. (whether you like that or not, sadly)
-Ryan
AUWYHSTOT (Acronyms are Useless When You Have to Spell Them Out Too)
In something like fluid dynamics, these programs are actually keeping track of particles bouncing against one another and updating the current state of the system over very tiny intervals. If you try to keep track of enough particles and make the time resolution fine enough, you're going to require incredible amounts of computing power.
An interesting anagram of "BANACH TARSKI" is "BANACH TARSKI BANACH TARSKI"
2^128 = 3.40282E+38 keys
Suppose we can test at a rate of 1,000,000,000,000 keys/s, it will take this system 3.40282E+26 s to exhaust the keyspace, or to put it another way, roughly 1.07831E+19 years. Should be long enough for anyone.
I recently started working at IBM doing iSeries Linux work, when I mentioned to someone that I had taken an MPI class in college. I found out later that he was doing BGL work and needed help, so now I work on this! IBM Research BGL Home
There are 65536 (2^16) compute nodes (CNs) on the system running a very small, from-scratch OS. There are also 1024 (2^10) I/O nodes on the system running a full Linux system (ZDnet article). The custom CN kernel is designed to look like linux, but is much smaller and written for a very singular purpose.
The system has a number of networks that link all the nodes together. The first is the 3-D Torus network, the point-to-point node connection topology. The asteroids game is a 2-D torus because the top connects to the bottom and the sides connect; a 2-D torus looks like a donut when connected together. A 3-D torus looks like a cube (3-D Mesh), but the sides are directly connected to the opposite end (it really requires 4 Euclidean dimension to draw well). This network only connects the 2^16 CNs.
The I/O nodes (running Linux) are connected by ethernet and then each linked to 64 CNs by the tree network. Unsurprisingly, it looks like a tree (for the people who actually know what a plant called a tree looks like, it is not like that).
Summary PDF
It may be that Linux is currently being used to develop nuclear weapons, but this article has nothing to do with that. As the name implies, Blue Gene will be used for genetics research. Specifically, the protien folding problem, which in turn could help Geneticists to develop new wonder drugs without the current random trial and error methods they use. Imagine if we could simply plug in the code for HIV, run it through the computer, and custom design a drug to fight it. I'd think the developers of Linux would feel pretty good about that.
Where? BuleGene uses a varient of PPC970 chips from IBM.