Slashdot Mirror

← Back to Stories (view on slashdot.org)

IBM's Blue Gene Runs Continuously At 1 Petaflop

Posted by Zonk on from the all-i-can-think-is-the-games-you-could-play dept.

An anonymous reader writes "ZDNet is reporting on IBM's claim that the Blue Gene/P will continuously operate at more than 1 petaflop. It is actually capable of 3 quadrillion operations a second, or 3 petaflops. IBM claims that at 1 petaflop, Blue Gene/P is performing more operations than a 1.5-mile-high stack of laptops! 'Like the vast majority of other modern supercomputers, Blue Gene/P is composed of several racks of servers lashed together in clusters for large computing tasks, such as running programs that can graphically simulate worldwide weather patterns. Technologies designed for these computers trickle down into the mainstream while conventional technologies and components are used to cut the costs of building these systems. The chip inside Blue Gene/P consists of four PowerPC 450 cores running at 850MHz each. A 2x2 foot circuit board containing 32 of the Blue Gene/P chips can churn out 435 billion operations a second. Thirty two of these boards can be stuffed into a 6-foot-high rack.'"

6 of 231 comments (clear)

  1. Re:Obligatory.... by Dr.+Smoove · · Score: 2, Insightful

    What do you mean? A beowulf cluster is commodity hardware running free software like Linux as OS and Open MPI or whatever the free message passing interface is (/me forgets). This isn't commodity hardware, and it's already a cluster. -1 for durrr factor.

    --
    "If you plant ice, you're gonna harvest wind."
  2. Re:Depends on what you mean by real world. by timeOday · · Score: 2, Insightful

    How many of these are "real world"? Well, medical and CFD applications are significant, but hardly what you'd call mainstream, and the raytracing may have been used in Titanic on a smaller scale, but IMAX is under no threat at this time.
    Quit thinking so hard! People everywhere are setting up data centers that do nothing but serve huge numbers of clients over the Internet simultaneously. Now IBM can fit 4096 cores into a single 6 foot rack. I'd think any garden variety server farm could save a bundle. IBM big iron isn't cheap, but compared to an entire warehouse and the power for it, and all the manpower to rig up a couple thousand PC's, the IBM solution starts to sound pretty good.

    In fact, I wonder if google is still using warehouses full of normal PC hardware?

  3. Re:How far behind are desktops from super-computer by afidel · · Score: 2, Insightful

    A Cray from 12 years ago would be a T90. The top of the line was the T932 with 32 vector CPU's. It was capable of 57.6 gigaflops and had a total internode I/O bandwidth of 330GB/s. It maxed out at 8GB of main memory. Compare that to an ATI Radeon x1950xtx gpu running folding@home at ~90Gflops with a half gig of ram and ram I/O of 64GB/s, which is significantly faster than a desktop CPU. So, it really depends on what your problems throughput limitation is, CPU/GPU raw power or I/O bandwidth as to whether a current desktop is more or less powerful than a Cray from 12 years ago.

    --
    There are 4 boxes to use in the defense of liberty: soap, ballot, jury, ammo. Use in that order. Starting now.
  4. Re:Weather prediction? by 1729 · · Score: 2, Insightful

    Because its contributions will need to be simulated to be taken into account, resulting in the need for a meta-simulator. If you enjoy pondering things like this, I strongly recommend Gödel, Escher, Bach by Douglas Hofstadter. I loved that book, and although I might not be applying its concepts entirely correctly here, what I took out of the book that's relevant to this was the following: The simulation is not system. No matter how accurate math is, it does not represent the real world, and should not be mistaken for that. You can not objectively analyse an entire system if you're part of that system. e.g. You can not prove to yourself that you are sane.
    I haven't read Hofstadter's book, so I may very well be missing the connection, but that doesn't seem to follow from Gödel's Theorem. It sounds more like a philosophical analogue of Gödel's Theorem. In any case, I'll give Gödel, Escher, Bach a try.
  5. Re:Depends on what you mean by real world. by Anonymous Coward · · Score: 1, Insightful

    Actually FFTs don't scale particularly well to parallel systems as by definition they are significantly non-local.

  6. Re:The Dawn of Petaflop Computing! by flaming-opus · · Score: 2, Insightful

    well, Perhaps it's more accurate to say that IBM is not selling BG to everyone and their mother, because a limited number of applications port well to the machine. If you happen to have a big need to run one of those applications, they'll sell one to you. But, if you don't run one of those apps, they'll probably try to sell you P570's instead. It must be nice to be in those IBM salespeople's shoes, and have so many options to sell you.