Stories
Slash Boxes
Comments

News for nerds, stuff that matters

Slashdot Log In

Log In

Create Account  |  Retrieve Password

MIT Artificial Vision Researchers Assemble 16-GPU Machine

Posted by timothy on Sun Jul 27, 2008 03:01 AM
from the many-many-little-dots dept.
lindik writes "As part of their research efforts aimed at building real-time human-level artificial vision systems inspired by the brain, MIT graduate student Nicolas Pinto and principal investigators David Cox (Rowland Institute at Harvard) and James DiCarlo (McGovern Institute for Brain Research at MIT) recently assembled an impressive 16-GPU 'monster' composed of 8x9800gx2s donated by NVIDIA. The high-throughput method they promote can also use other ubiquitous technologies like IBM's Cell Broadband Engine processor (included in Sony's Playstation 3) or Amazon's Elastic Cloud Computing services. Interestingly, the team is also involved in the PetaVision project on the Roadrunner, the world's fastest supercomputer."
+ -
story

Related Stories

Submission: A 16-gpu machine ! by Anonymous Coward
This discussion has been archived. No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
 Full
 Abbreviated
 Hidden
More
Loading... please wait.
  • by im_thatoneguy (819432) on Sunday July 27 2008, @03:05AM (#24355963)

    "But can it run Crysis?"

    *Ducks*

    • Of course not.
    • The graphic cards might be able to handle it. But you'd have to run Vista in order to get maximized settings..
      Now there is a problem.
      • It'll have to be Vista 64-bit...

        Under Vista 32-bit you're left with only 640K after removing the video memory allocations.

        Us normal SLi users win with only 3.2GB left :P
        • DX10 vs DX9 (Score:5, Informative)

          by DrYak (748999) on Sunday July 27 2008, @06:03AM (#24356603) Homepage

          There are 2 main differences between DX9 and DX10 :

          I - The shaders offered by the two APIs are different (shader model 3 vs 4). None of the DX9 screen shot does self-shading. This is specially visible on the rocks (but even in action on the plancks of the fences). So there *are* available under Vista additional subtleties

          II - The driver architecture is much more complex in Vista, because it is built to enable cooperation between several separate processes all using the graphics at the same time. Even if Vista automatically disables Aero when games are running full-screen (and thus the game is the only process accessing the graphic card), the additional layers of abstraction have an impact on performance. It is specially visible at low quality settings where the software overhead is more noticeable.

    • Yeah, and imagine a beowulf cluster of those!

      I'm sorry, that was uncalled for.
          • I assume you men a PowerMac G5, because the MacPros are pretty much silent.

          • So it's about one fan per GPU? Seems annoying and inefficient. Why not build it more spread apart, or use a "Central Air" system like people use in their homes.

            Not using water cooling I understand, 'cause there'd be around 30 tubes snaking in and out of the box - something would fail/leak.

    • This is just what 3D Realms has been waiting for... it's almost powerful enough to run Duke Nukem Forever!
       

      • Re: (Score:2, Informative)

        no it isn't. Duke Nukem Forever will be released when a powerful enough computer is assembled. The game will just manifest itself in the machine one powered up. But you have to have downloaded 20TB of porn and covered the internals with a thin layer of cigar smoke first.
    • Fascinating (Score:5, Interesting)

      by AlienIntelligence (1184493) on Sunday July 27 2008, @05:17AM (#24356391)

      I think this part of the computing timeline is going to be
      one that is well remembered. I know I find it fascinating.

      This is a classic moment when tech takes the branch that
      was unexpected. GPGPU computing [gpgpu.org] will soon
      reach ubiquity but for right now it's the fledgling that is being
      grown in the wild.

      Of course I'm not earmarking this one particular project
      as the start point but this year has gotten 'GPU this' and
      'GPGPU that' start up events all over it. Some even said
      in 2007, that it would be a buzzword in 08 [theinquirer.net].

      And of course there's nothing like new tech to bring out [intel.com]
      a naysayer.

      Folding@home [stanford.edu] released their second generation [stanford.edu]
      GPU client in April 08. While retiring the GPU1 core in
      June of this year.

      I know I enjoy throwing spare GPU cycles to a distributed
      cause and whenever I catch sight of the icon for the GPU [stanford.edu]
      client it brings the back the nostalgia of distributed clients [wikipedia.org]
      of the past. [Near the bottom].

      I think I was with United Devices [wikipedia.org] the longest.
      And the Grid [grid.org].

      Now we are getting a chance to see GPU supercomputing
      installations from IBM [eurekalert.org] and this one from MIT.
      Soon those will be littering the Top 500 list [top500.org].

      I also look forward most to the peaceful endeavors the new
      processing power will be used for... weather analysis [unisys.com],
      drug creation [wikipedia.org], and disease studies [medicalnewstoday.com].

      Oh yes, I realize places like the infamous Sandia will be using
      the GPU to rev up atom splitting. But maybe if they keep their
      bombs IN the GPU it'll lessen the chances of seeing rampant
      proliferation again.

      Ok, well enough of my musings over a GPU.

      -AI

      • Huh? GPGPU was a buzzword in 2005 (at least, that's when I first saw large numbers of books about the subject appearing). Now it's pretty much expected - GPUs are the cheapest stream-vector processors on the market at the moment.
      • Re: (Score:3, Insightful)

        "I think this part of the computing timeline is going to be one that is well remembered. I know I find it fascinating."

        Well remembered? Perhaps... but I wouldn't sing their praises just yet. Advances in memory are critically necessary to keep the pace of computational speed up. The big elephants in the room are: Heat, memory bandwidth and latency. Part of the reason the GPU's this time round were not as impressive is because of increasing memory bandwidth linearly will start not have the same effects

  • I noticed they didn't have 8GB of RAM though. Very sad.
  • When gamers grow up and go to college.. blue leds and bling in the server room!

  • Alright! (Score:4, Funny)

    by religious freak (1005821) on Sunday July 27 2008, @03:48AM (#24356097)
    One more step to the last invention man ever need make... hooker bot. (mine would be a Buffy Bot, but that's just personal preference)
    • One more step to the last invention man ever need make... hooker bot. (mine would be a Buffy Bot, but that's just personal preference)

      She would have to be cooled with liquid nitrogen, running all those GPUs.

    • One more step to the last invention man ever need make... hooker bot. (mine would be a Buffy Bot, but that's just personal preference)

      Here you go: one robotic buffing cell [intec-italy.com]

    • I know this is slashdot so you have probably not spent much time around females at leat not those of our species, but let me tell you an angry one is a dangerous creature. All of them do get pissed off some of the time. You can be the greatest guy ever and sooner or later you will make a mistake. The good news if you are a good guy they will forgive you but the period between your screw up and their forgiveness can be extreemly hazardous.

      Buffy is a fun show and all but if I were ordering robo girl, I am

  • by MR.Mic (937158) on Sunday July 27 2008, @03:56AM (#24356129)

    I keep seeing all these articles about bringing more types of processing applications to the gpu, since it handles floating point math and parallel problems better. I only have a rudimentary understanding of programming compared to most people on this site, so the following may sound like a dumb question. But how do you determine what types of problems will perform well (or are even possible to be solved) through the use of GPUs, and just how "general purpose" can you get on such specialized hardware?

    Thanks in advance.

    • Its just a matter of transforming the data in to a format the GPU can handle efficiently.

      • by hansraj (458504) * on Sunday July 27 2008, @04:37AM (#24356251)

        Not really. Not every problem gains from a gpu.

        As a rule of thumb, if you problem requires solving many instances of one simple subproblem which are independent of each other then a gpu helps. A gpu is like a cpu with many many cores where each cpu is not as general purpose as your intel, rather each core is optimized for some solving small problem (without optimizing for frequent load/store/switching operations etc that a general cpu can handle quite well).

        So if you see an easy parallelization of your problem, you might think of using a gpu. There are problems that are believed to not be efficiently parallelizable (Linear Programming is one such problem). Also, even if your problem can be easily made parallel it might be tricky to benefit from a gpu as each subroutines might be too complex.

        I don't program but my guess would be that if you can see the solution to your problem consisting of a few lines of codes running on many processors and gaining anything, a gpu might be the way to go.

        Perhaps someone can explain it better.

        • Re: (Score:3, Informative)

          I think you did a good job explaining, one point thought. The sub-problems need not be independent.

          Many problems such as weather prediction use finite element analysis with a "clock tick" to syncronise the results of the sub-problems. The sub-problems themselves are cubes representing X cubic kilometers of the atmosphere/surface, each sub-problem depends on the state of it's immediate neighbours. The accuracy of the results depends on the resolution of the clock tick, the volume represented by the sub-pr
      • Re: (Score:3, Informative)

        You also need to make sure the I/O to/fro the GPU is good enough.

        No point being able to do calculations really fast but not be able to get the results or keep feeding the GPU with data.

        I think not too long ago graphics cards were fast, but after you added the problem of getting calculation results back, it wasn't really worth it.
        • That was due to the asymmetric design of AGP.
          PCI-Express is symmetric, so it doesn't have this limitation.

    • I have been using my own GPU to do this very same thing by automatically converting images to vertex format and use the GPU to scale, shade, etc and in this way I can have a shape recognition by simply measuring the closest match on the frame buffer. There are more complex ways to use the GPU to do pseudo computation in parallel, I still think that a commonly available CAM or near CAM would increase neural like computations by being essentially a completely parallel process. It would be better to allow more people to experiment with the methods because the greatest gain and cost is the software itself and specialized hardware for a single purpose allows better profit but limits innovation.
    • The GPU architecture has been progressively moving to a more "general" system with every generation. Originally the processing elements in the GPU could only write to one memory location, now the hardware supports scattered writes, for example.

      As such I think the GPGPU method of casting algorithms into the GPU APIs (CUDA et. al) are going to die a quick death once Larabee comes out and people can simply run their threaded codes on these finely-grained co-processors.

  • I'm still eager to see PhysX running on my dual 8800M GTX laptop. I've run all the drivers from 177.35 up and I'm running the 8.06.12 PhysX drivers as required.
    Apparently it's just the mobile versions :(
    • Thats an easy problem to solve! Just wait for the technology to mature before purchas...Oh.

  • by MoFoQ (584566) on Sunday July 27 2008, @05:40AM (#24356489)

    is it me or do I see two separate mobos...which means it's two machines, 8 per machine in one box....not 16?

    now...if it was 16 in one...now that would be amazing....otherwise...it's not...'cuz there was that other group that did 8 in 1 [slashdot.org] (aka...16/2 => 8/1)

    • Re: (Score:2, Informative)

      That's one machine for simulating one eye. That's why they need 2 * 8 for simulating human-level vision, or else you won't get the 3D vision.

      • Maybe so, but why not build just two machines? The only reason I can think of is that this sounds cooler. Maybe they save a bit of money on having a single cooling solution/power supply, but I don't see it. Strange enough, the machine doesn't seem to be symmetric. They've probably put one motherboard upside down, otherwise you would have to split the case. Let's hope the magic doesn't leak out.

  • a system with 16 x 4870x2s. they will draw less energy too.
  • by Anonymous Coward

    God, they stuck so many fans into that box that I bet it takes off the ground when it boots.

    • Re: (Score:2, Interesting)

      AMD/ATI have released the specs for their hardware. Why haven't the proprietary NVIDIA engineers done the same? What do they have to hide?

      In terms of actually being totally non-proprietary, Nvidia has to worry about ATI stealing their drivers (which they would or at least "borrow" alot from them), since Nvidia generally has that as their trump card over ATI no matter who has the better hardware. On the other hand, Nvidia has no interest in "borrowing" from ATI's drivers. ATI knows that, and that's why their

      • by TheRaven64 (641858) on Sunday July 27 2008, @05:54AM (#24356561) Homepage Journal
        A video card driver typically has three major components:
        • The parts specific to the windowing system (including context switching / multiplexing).
        • The parts specific to the 3D API.
        • The parts specific to the hardware.

        ATi could conceivably steal parts from the first two from nVidia, but it's doubtful that they could steal anything from the last part since their hardware designs are sufficiently different to make this hard.

        The problem nVidia are going to have is that the new Gallium architecture means that the first two parts are abstracted away and reusable, as is the fall-back path (which emulates functionality any specific GPU might be missing). This means that Intel and AMD both get to benefit from the other company (and random hippyware developers and other GPU manufacturers / users) improving the generic components, while nVidia are stuck developing their own entire alternative to DRI, DRM, Gallium, and Mesa. The upshot is that Intel and AMD can spend a tiny fraction of the time (and, thus, money) developing drivers that nVidia do. In the long run, this means either smaller profits or more expensive cards for nVidia, more bugs in nVidia drivers (since they don't have the same real-world coverage testing).

        Now, if you're talking just about specs, then you're just plain trolling. Intel doesn't lose anything to AMD by releasing the specs for the Core 2 in a 3000 page PDF, because the specs just give you the input-output semantics, they don't give you any implementation details. Anyone with a little bit of VLSI experience could make an x86 chip, but making one that gives good performance and good performance-per-Watt is a lot harder. Similarly, the specs for an nVidia card would let anyone make a clone, but they'd have to spend a lot of time and effort optimising their design to get anywhere close to the performance that nVidia get.

      • AMD/ATI have released the specs for their hardware. Why haven't the proprietary NVIDIA engineers done the same?

        Nvidia has to worry about ATI stealing their drivers {...} ATI knows that, and that's why their drivers are open.

        We are not speaking about releasing source code of current drivers. In fact ATI/AMD's fglrx *IS NOT* open. At all. What is open are 2 *separate* drivers projects, which are done using the *technical data* released by AMD.

        You're confusing the situation with Intel. (They paid Thungsten Graphics to write an open source drivers for i8xx/i9xx to begin with. There's no such thing as a proprietary intel drive on linux. Only an opensource driver written by TG)

        What we want is not nVidia releasing the source of their

        • by ya really (1257084) on Sunday July 27 2008, @04:18AM (#24356201)

          Tom's Hardware [tomshardware.com] did a pretty good job detailing the ups and downs of ATI and Nvidia with many of the major games of last year (BioShock, World in Conflict, etc). Overall, both companies faired well, but they reported quite a few crashes due to the ATI drivers. I've had an ATI card before, the 9800xt when Nvidia was producing their horrible 5xxx series back in 2003-04 that was totally worthless. The 9800xt was a good card for everything (gaming, graphical aps, etc). Sorry, I should have cited sources. Wasn't trolling on purpose, though I know that writing anything positive about Nvidia on slashdot is borderline blasphemy.

          • You are claiming ATI will outright steal from Nvidia, whether one driver is better than the other doesn't matter, I want you to back up your claim that they would do something like that.

            • You are claiming ATI will outright steal from Nvidia, whether one driver is better than the other doesn't matter, I want you to back up your claim that they would do something like that.

              Would you like me to call up ATI and ask them?

              ATI Customer Service: What can I help you with today.
              Me: If Nvidia made their drivers OSS, would you borrow from them?
              ATI Customer Service: I'm sorry sir, we cannot answer that at this time. Is there anything else I can help you with?
              Me: Nope, thanks.

              If someone makes a better

              • Also, isnt the concept of opensource to share information to better the overall technology? If nvidia feels that giving out their driver code will give ATI better video cards than their own, it would be insane for Nvidia to release them (which implies that ATI cards are more or less hardware equivilant to Nvidia). It may improve the overall tech, but only in favor of ATI (assuming ATI's own drivers do not improve from their own advancements not related to what they could potentionally gain from nvidia's). H
              • So I was right, you are trolling, too bad the mods can't see that.

    • I want to support ATI and AMD, but nVidia just works.
      Their drivers are very nice.

      Until that changes I'm a nVidia guy.
      A third party open source driver should fix the problems.

      • Maybe they work for you: I find NVidia drivers quite painful, especially for non-Windows operating sytems. And a 'third party open source driver'can't get the details of the NVidia API to work from, which means a huge amount of reverse engineering, especially of their propriatary OpenGL libraries, which are at the core of their enhanced features in non-Windows operating systems.

        • Erm are you using the open source drivers?
          No 3d acceleration.

          Use the nVidia drivers which are nearly identical to the Windows ones.

    • Maybe the don't want people writing crappy drivers [blogspot.com] for NVIDIA cards?
      • Re: (Score:2, Funny)

        by Anonymous Coward

        Jesus doesn't approve of you doing that.

    • Do you know the human brain has about 100 billion neurons? Each neuron can be represented as a weighted average of its inputs, a typical human neuron has some 1000 inputs and does around a hundred operations per second.

      So, yes, *maybe* there could be some very smart algorithm that mimics human reasoning, but that's not how it's done in the human brain. It's raw computing power all the way.