Want to read Slashdot from your mobile device? Point it at m.slashdot.org and keep reading!

 


Forgot your password?
Close
typodupeerror
×
Technology Hardware

Toshiba Demonstrates Cell Microprocessor 168

Posted by Hemos from the using-the-machine dept.
Cybro writes "Toshiba has demonstrated some cool applications for the Cell Microprocessor. They also revealed that they have written their own OS for the new processor. However the article on TechOn does not reveal the license of the OS."
This discussion has been archived. No new comments can be posted.

Toshiba Demonstrates Cell Microprocessor More

Toshiba Demonstrates Cell Microprocessor

Comments Filter:

  • what does it do? (Score:1, Interesting)

    by Anonymous Coward
    does this have any application besides video?

  • ARTICLE TEXT: (Score:5, Informative)

    by Anonymous Coward on Monday May 02, 2005 @12:03PM (#12408299)
    Toshiba Demonstrates Cell Microprocessor Simultaneously Decoding 48 MPEG-2 Streams
    Apr 25, 2005 14:15

    Toshiba demonstrated that its Cell microprocessor, jointly developed with the Sony Group and IBM Corp., can simultaneously decode 48 SDTV format MPEG-2 streams. At the COOL Chips VIII event held in Yokohama from April 20 to 22, 2005, the company showed a film demonstrating the decoding process.

    In the film, 48 MPEG-2 streams stored on a HDD were read, decoded and projected onto a 1,920 x 1,080 resolution display divided into 8 x 6 cells, each of which showed a different video in each cell. The company expects the technology to be used to display thumbnails for a video list. Of the eight synergistic processor elements (SPE) used in the Cell, six are used for decoding 48 MPEG-2 streams and one is used for scaling the screen. The remaining SPE can be used for a completely different processing function.

    In the demonstration, Toshiba used an operating system environment it had developed to increase the efficiency of Cell software development. One of the environment's key features is that application software developers can program software without considering which threads will be allotted to each of the different SPEs, because the environment allows the automatically scheduling software to SPEs.

  • Not much info (Score:5, Insightful)

    by Ironsides ( 739422 ) on Monday May 02, 2005 @12:04PM (#12408314) Homepage Journal
    It doesn't say anywhere what the bitrates of the originating SD streams were. That is a biggie in terms of processing power. MPEG2 can run from 1.5Mbps (crap) to 50 Mbps (I Frame only, dam good) and higher. Give me more info and I might be impressed.

    • The interesting thing to me here (Score:5, Interesting)

      by Anonymous Coward on Monday May 02, 2005 @12:07PM (#12408363)
      Isn't even *exactly* how impressive a multitasking feat it was, but that if I'm reading the article right, the 48-stream decoding thing was done *entirely by the auxillary processor units*. That is, the "SPE"s. The main [PPE] processor in the Cell was apparently not really doing anything at the time. This seems to bode wel for the usability of the SPEs.
    • Even if you're considering that you're talking about the crap feed, that's 48 times 1.5Mbps or an aggregate of 72Mbps. Pretty damn impressive considering the floating point contortions you're having to go through to get there- a PC wouldn't be likely to handle that many 1.5Mbits streams let alone higher rates. And this is going to be at the heart of the PS3.

    • Re:Not much info (Score:5, Informative)

      by benwaggoner ( 513209 ) <ben.waggoner@mic ... t.com minus poet> on Monday May 02, 2005 @12:49PM (#12408933) Homepage
      Actually, the I-frame only is quite a bit easier to decode, since it doesn't require motion estimation, doesn't reference multiple frames, etcetera. It's almost identical to a series of JPEGs at 29.97 frames per second.

      In normal IBBP MPEG-2, a given B-frame will reference frames either direction of it, requiring two frames be buffered in memory, and a lot of moving around of data from those two frames.

  • WMP? (Score:3, Informative)

    by oiarbovnb ( 728906 ) on Monday May 02, 2005 @12:05PM (#12408333)
    I swear the screenshot looks like it is WMP... I can't believe that windows is going to work on the CELL. Anybody have any info on what OS will be supported (other than the Toshiba OS?)

    • Re:WMP? (Score:2, Informative)

      by Anonymous Coward
      It said "the company showed a film demonstrating the decoding process"

    • Re:WMP? (Score:5, Insightful)

      by vectorian798 ( 792613 ) on Monday May 02, 2005 @12:08PM (#12408378)
      You are right that it looks EXACTLY like WMP in full-screen mode. However, it seems unlikely that they ported it over to the weird OS they have going. Most likely they decode the streams and send raw data streams over a fast gigabit ethernet over to a comp with a media player that just chugs it through onto the screen. Or something like that anyways.

      • Re:WMP? (Score:3, Informative)

        by Jozer99 ( 693146 )
        Possilby, they did not allow cameras into the demo. They did provide a video, and the picture is simply an amerature screenshot of WMP playing said video.

    • Re:WMP? (Score:1, Informative)

      by Elenyon ( 790257 )
      From TFA you see that is a video of the computer decoding video it is not a live presentaiton but it is WMP playing a video of the prior event.
    • Some clever Linux programmers will have ported their favorite distro over to the Cell processor within a few minutes of its release.
    • Actually, I think thats a photograph of WMP10 playing a video of the decoding process. The article mentions they didn't actually see it live, but were sent a video, which was presumably played in WMP.

    • Re:WMP? (Score:3, Funny)

      by jnaujok ( 804613 )
      They say in the article that this is a "video of a wide-screen monitor". In other words, the Cell processor ran this video to a big LCD display, and someone filmed it with a camera. Then the film of that display was played back at the demo.

      This isn't that uncommon, in order to hide the fact that the ball of "wire-spaghetti" sitting on the bench below the monitor is the prototype system. It might also hide the liquid nitrogen pump they were using to cool it...

      In other words, they wanted to hide something

  • I am still (Score:5, Interesting)

    by Anonymous Coward on Monday May 02, 2005 @12:05PM (#12408334)
    totally baffled how one could write something for the cell that we would traditionally call an "OS". At least, a time sharing OS. Who gets to use the SPE/APU/SPUs, and when? The attatched memory on the SPEs is nontrivial to swap to memory, and it seems absurd to think that it would just be done offhand with a context switch. Yet, context switches must happen. So are SPEs merely given to processes, who get to keep them, so that the main processor is switching betwen processes normally in a preemptive style but the SPEs stay under the control of single processes?

    Or is the Cell OS Toshiba's using here non-multitasking or cooperative multitasking? Or what?

    • Re:I am still (Score:5, Interesting)

      by adam31 ( 817930 ) <adam31.gmail@com> on Monday May 02, 2005 @12:33PM (#12408719)
      I am also baffled. But the SPE has a memory size of only 256kb and 25 GByte/s bandwidth to main memory, so it's not like a context switch is out of the question. Also I'm pretty sure that each SPE can run 2 threads SMP (or is that just the Power chip?)

      It probably is a combination of the method you describe (where a SPE is dedicated to a thread) and traditional pre-emptive... And it probably boils down to the more processor-intensive threads get their own SPE, while a couple SPEs are dedicated to context-switching threads.

      To me, that part is not as baffling as how programs are going to be written in the first place. A thread will have to communicate all the memory accesses it will need to make to prefetch all that data. On the PS2, we use environments like this, where that memory would be double- or triple-buffered so we can simultaneously stream, process, and write-back... but that's hand-written individually for the hardest-core processing pieces, where memory accesses are predictable and sequential. How to do this in a general way to make the process easier on application developers?

      That's never really been a concern for Sony...

    • The hardware deterimes what gets broken down and how. At least that's how I understood it. There is a General PU(PowerPC core) and the other cores send their completed data back to memory when done.

      I think. I could be very wrong on it though.

    • Maybe (Score:5, Informative)

      by News for nerds ( 448130 ) on Monday May 02, 2005 @12:48PM (#12408910) Homepage
      this image can explain a lot for you?
      http://pcweb.mycom.co.jp/photo/articles/2005/04/28 /coolchips1/images/016l.jpg [mycom.co.jp]
    • Dedicating individual processors to applications (there are, what, a dozen or so SPEs at least?), and then the main PPC CPU can act as a normal task-switching general-purpose CPU when the tasks get too numerous, or for doing low-utilization or one-time tasks.

      I'm sure you could architect more sophisticated schemes that allows the OS to more transparently allocate processes to SPEs.

      I would probably use the PowerPC chip for low-impact background threads and general application use that doesn't push the pro
    • I suspect it will be more like firmware that you download to the cells via device drivers. You then communicate via shared memory or bus traffic or something.

      Chris
    • Next week's tech news: "Toshiba, Sony, and IBM jointly sponsor NetBSD 3.0 development" Next month's tech news: "NetBSD enthusiasts develop CELL powered toaster"

  • Huh? (Score:5, Insightful)

    by garcia ( 6573 ) * on Monday May 02, 2005 @12:06PM (#12408350)
    Well, in this [nikkeibp.co.jp] picture I see a movie file being played (on what seems to be WMP) showing the cells on the screen.

    Now, I wasn't there, nor was the article really in depth by any means, but it would seem to me that this was nothing more than a movie demonstration and nothing live.

    I'm not quite so impressed. Maybe we should start linking to real content from the front page (i.e. in-depth accounts and not some blogger's one page summary with a blurry photo of a movie file being played on a projection screen).

    • Re: (Score:3, Insightful)

      by account_deleted ( 4530225 )
      Comment removed based on user account deletion
      • I have to agree w/ Grandparent. It's a hell of a lot easier to get something to work once and tape it than it is to demo a live system. Even streaming the video over a VTC would have sufficed. The fact that it was recorded makes me think it is not stable yet.

  • perhaps more interesting (Score:5, Informative)

    by Anonymous Coward on Monday May 02, 2005 @12:06PM (#12408355)
    Ken Kutaragi Talks about Cell

    http://techon.nikkeibp.co.jp/english/NEWS_EN/20050 407/103542/ [nikkeibp.co.jp]
    • Agreed. I found that the better article, as well. Especially interesting was this bit:

      Q: Cell has 8 embedded "SPE" CPU cores. What is the basis for this number?

      A: Because it's a power of two, that's all there is to it. It's an aesthetic. In the world of computers, the power of two is the fundamental principle - there's no other way. Actually, in the course of development, there's this one occasion when we had an all-night, intense discussion in a U.S. hotel. The IBM team proposed to make it six. But my an
    • I found it an interesting interview on several fronts, but it was slightly curious to me that he didn't mention the Inmos Transputer in his short review of the evolution of computing.

      Of course, in such a brief summary you can't expect much detail, but the point about the Transputer was that it's the only relevant precursor to the Cell that has made it to market in a substantial way (there was a whole Transputer industry very active for most of a decade). Arbitrary-sized networks of small communicating har

  • Mebbe it can power (Score:4, Funny)

    by KingBahamut ( 615285 ) on Monday May 02, 2005 @12:07PM (#12408371)
    this............
    http://www.lod.org/Projects/Other//index.htm [lod.org]

  • That Cell microprocessor is pretty good... (Score:5, Funny)

    by TripMaster Monkey ( 862126 ) * on Monday May 02, 2005 @12:13PM (#12408436)
    ...but the smart money's on the Goku miccroprocessor.


    ^_^


    • The smartest money's on the Gohan processor; Cell killed Goku.
    • and I don't really care what it's called... as long as it repairs itself after being fried, I'm happy! ^_^
    • and in other news, shortly after announcing the new cell processor, toshiba's research facility was destoyed in what appeared to be an atomic blast.. however no residual radiation was detected, witnesses reporting seeing numerous flashing lights across the sky, with thundering reports. also, in a nearby wasteland, several mountains collapsed into piles of rubble, for no apparent reason, and nearby seismological equipment reqistered several succeding level 10 earthquakes.

      Also, the entire japanese defense

  • Business Idea (Score:4, Insightful)

    by 3770 ( 560838 ) on Monday May 02, 2005 @12:13PM (#12408445) Homepage
    Here is a business idea for some small to mid size hardware company.

    The CELL processor is cool and the geeks love it and it is based on the POWER architecture. Surely, it'll run Linux.

    Build a machine with the CELL. Don't follow any standards (well, use PCI and PCI express Serial ATA and USB 2.0 and stuff like that). But just make sure that you are first out the door with a box.

    And make it cheap. It must be possible to make it cheap since it will be sold in the PS3.

    I bet that there'll be a lot of enthusiasts that will buy it and be early adopters which will help you work out the bugs.

    And then, a year after your first release you'll have a computer that is very fast for its price and a system which is source code compatible with the largest source code library in the world.

    Well, I know I'd consider buying one.

    • Re:Business Idea (Score:4, Insightful)

      by LWATCDR ( 28044 ) on Monday May 02, 2005 @12:36PM (#12408767) Homepage Journal
      "and make it cheap. It must be possible to make it cheap since it will be sold in the PS3."

      Nope you will have to develop a chipset for it and that is not cheap. It is unlikely that Sony will hand over the supporting chipset for the PS3 to anyone. Cheap comes from big numbers and there is no such thing as a lot of enthusiast. At least when we are talking about the number it would take to make this cheap.
      The only two I can see doing this are IBM and Apple.
      A Cell based Mac mini as the ultimate gaming platform would be interesting. I could see this as part of IBMs plan of world domination. They dump the Intel line on china and then push for the Power/CELL to replace it. A Cell based workstation running Linux or even Windows talking to a Cell/Power based server. All with IBMs blessing. IBM goes back to being the master of it's own destiny with no real need to make nice with Microsoft or Intel.
      • That is almost exactly what I have been thinking. Though I had Levono dropping intel chips entrely, and moving the whole line-up over to Cell.

        Man could you imagine Micheal Dell's face when his competition is produce 10times the computer for the same price.

        Damn that would be funny.
        • Actually I was thinking that IBM was dropping Intel entirely. Let Levono have them. IBM would keep the Power/Cell line of workstations and rewrite PC history again.

      • they should offer a memory expansion and a linux kit for the ps3. that would accomplish the same thing. it would be a legacy-free computer. the only problem is that we need access to the entire development system.
        • "they should offer a memory expansion and a linux kit for the ps3. that would accomplish the same thing. it would be a legacy-free computer."

          Why should "they" Sony do that? Gaming consols do not make money. It is the games that make money so Sony will want to control the development market. They will not want just anyone writing games and software for the PS3. Look at the Linux kit for the PS2. You could only run the programs you developed on it on other PS2s running the Linux kit.
          One of the smart things a
          • They already control the distribution of the games.

            encouraging more people to develop games right up to the point they have to be approved for distribution is entirely in their interest.
        • Except that it wouldn't be cheap, in the past sony has not opened up the entire platform. AND, it would never be taken seriously.
          • it would eventually be cheap. the issue of opening the entire platform is a real one, of course. and, it's not going to be taken seriously anyway. The Cell is not necessarily suited to high-performance general-purpose processing. It's there to shovel numbers rapidly. Really useful for multimedia, gaming, that sort of thing, and probably not so useful for anything else.
  • That's really quite impressive. I wish I could see it in motion, though ;_;
    • That's really quite impressive. I wish I could see it in motion, though ;_;

      What are you expecting? It's a processor, not a car... you're not really going to see it "move" while it's working...

      I kid because I love...

  • The Perfect OS for the Cell Processor (Score:5, Interesting)

    by MOBE2001 ( 263700 ) on Monday May 02, 2005 @12:18PM (#12408506) Homepage Journal
    I got the perfect OS for the Cell Processor. I just need funding. :-D

    The COSA Operatin System [adelphia.net]

    See also the link below.
    • How about writing a virtual machine/emulator for this overwhelmingly complex chip archetecture. Once you have it all realized in software, transporting it to hardware is a non-step, but from the look of the complexity of the system you're describing, it could readily take a few billion gates.

  • RTFA please: (to those talking about Windows, WMP) (Score:4, Informative)

    by llamalicious ( 448215 ) on Monday May 02, 2005 @12:20PM (#12408526) Journal
    "... the company showed a film demonstrating the decoding process.

    In the film, 48 MPEG-2 streams stored on a HDD were read, decoded and projected onto a 1,920 x 1,080 resolution display divided into 8 x 6 cells, each of which showed a different video in each cell. The company expects the technology ..."

    If you bothered to read the article contents, you'll see that they simply showed a video of the process actually working.

    This is a far cry from a live tech demo, but if they can really pull it off, definitely shows the power of a Cell.
  • Wouldn't it be nice to combine this article and the previous one and have a Cell to make your 720p TV display 1080i content properly? :)
    • Far from factious. Cell would be enormously good at video processing kinds of applications, and if it's cheap enough could cetainly compete with the ASIC, DSP, and (increasingly) FPGA systems that are used in the field today.

      I'm sure a set top box vendor loves the idea of a chip that can decode compressed video, process it, and run a Java applet in the same piece of silicon.
  • From TA:
    In the demonstration, Toshiba used an operating system environment it had developed to increase the efficiency of Cell software development. One of the environment's key features is that application software developers can program software without considering which threads will be allotted to each of the different SPEs, because the environment allows the automatically scheduling software to SPEs.


    Now *THIS* is the interesting part on their OS. Because the SPEs have different kinds. When I looked at the cell architecture, I thought: "Programming for this thing is going to be a MAJOR MESS!"

    Thumbs up for Toshiba on figuring this out AND doing something about it.

  • OS for Cell and Cell Application (Score:5, Informative)

    by vectorian798 ( 792613 ) on Monday May 02, 2005 @12:27PM (#12408627)
    For all those talking about what kind of OS Cell will run:
    ZDNet Article on Cell [zdnet.com]

    The article is dated in some ways (like when it says 16 cores...I believe it is half that right?) but it does point out some interesting things, for example, like the fact that there will be a Cell SDK and a end-user OS aimed at embedded devices and the like.

    If you google around for 'cell forums' you will come across interesting discussions where they point out that linux will be ported very quickly to cell and that IBM has hinted at possible uses for Cell as a workstation. Also, Cell is OS NEUTRAL meaning that it does not have any particular hardware functionality that makes one OS run any faster.

    Overall, I would say that since market penetration is needed, you can't just say "Here is our OS and our SDK, use it from now on". The trick will be of course, to assuage the existing target audience who use today's OS's.

    Also, note that the Cell is not a processor bred entirely for the PS3 or anything like that - it will be embedded in devices such as PVR's, TV's, music players, and in all likelyhood, it will even find its way to the desktop - with its potential it is likely to also find some niche in supercomputing since it will be cheap (if 4 whole cells can be thrown into a game console why not?)
    • Don't forget the XBox 360, also based on CELL technology.

      But what's more important, from what I gather, is that the cell architecture is very scalable. That means you could take your PVR, music player, toaster or whatever, connect it to your PS3 and gain more power.

      A new game needs more power? Sony/Microsoft sell a Cell extension pack. Profit!! But also not needing to buy a completely new system for more power.
    • I can't wait for 1000+ Cells in a mainframe. Do you know what the heat output is? It's based on Power4 (?) and the clock speeds are relatively low (?) so it shouldn't be too high.

      Hopefully, they'll (IBM probably) develop some compilers for it (C, Fortran at least) so the scientific community can take advantage of the Cells.
  • There is talk among the Mac community that the Cell processor might be what is needed to get fast HD video decoding capability into their systems... If you check the current system recommendations [apple.com] for decoding HD in Quicktime, it requires a pretty fast system already. Perhaps Cell would fix that.

  • Probably not an "OS" in the common sense (Score:4, Interesting)

    by Lemming Mark ( 849014 ) on Monday May 02, 2005 @12:34PM (#12408738) Homepage
    [ disclaimer: this is speculation but it's informed speculation - hopefully useful ]

    It's worth bearing in mind this is unlikely to be an OS in the common sense. I'd rate it very unlikely that this OS supports such niceties as filesystems, network IO stacks, protected processes, etc - or that it ever will.

    Rather, it's likely to be a shim (albeit a clever one) for insulating the developers of embedded-style applications from the real hardware. I wouldn't be surprised if this Toshiba OS is actually a "library operating system" which is linked into the application itself.

    Don't think of it as an OS in the Linux sense, more as a toolkit / library for Cell programmers. Exactly how a "conventional" OS will run on the Cell is not clear to me but it seems certain that it can support a Linux-style OS well - otherwise it'd scupper Cell's World Domination plans ;-)
    • I think IBM will certainly start a Linux portage to the Cell micropossesor once it takes off, they have the source code there and I think It should not be difficult to begin it relasing it in open source, sincerely I would like it to happen, I think it could really give a push the Linux OSS movement and neither anyone of the 3 companies (Toshiba, IBM, Sony) are for the OS buissness.

  • License Doesn't Matter . . . (Score:1, Interesting)

    by Anonymous Coward
    . . . as long as Toshiba's OS can be deleted and Linux can be installed on the hardware.

    Seriously, Cell Processors provide a great platform for Linux to compete head-to-head with Microsoft, and to introduce people to the world of the GPL and open-source software.

    Microsoft is inevitably going to release a version of Windows for the Cell Processors--they'd be stupid not to do so. However, Microsoft has its main marketing focus on Longhorn right now. The public has no idea what these Cell Processors are, a
    • Microsoft is inevitably going to release a version of Windows for the Cell Processors--they'd be stupid not to do so.
      I think they'd have to release such a thing as a multithreaded OS first
      • Bill:
        Shit... now we will have to make Longhorn Cell compatible... ok lets postpone the release date again... 2008 sounds good??

        Remember, we will postpone release date in order to make the system more secure!
    • "Microsoft is inevitably going to release a version of Windows for the Cell Processors"

      Regardless of the fact that the NT kernel runs on PowerPC (XBox360), this is a long way from releasing an OS for the Cell. Given the endless delays in Longhorn and WinFS, I doubt they can do it in time to be competitive.

    • Microsoft is inevitably going to release a version of Windows for the Cell Processors--they'd be stupid not to do so. No, that would piss Intel off. Why do you think Windows only runs on x86? Because right now, Intel does a lot of Microsoft's development for them, then gives it to them for free. Microsoft has very strong economic incentives to not support anything other than Intel (and by extension AMD) processors. Why do you think they dropped support for Alpha?

  • License is FCL (Score:1)

    by Anonymous Coward
    > However the article on TechOn does not reveal the license of the OS.

    It uses the FCL.

    The Fight Club License.

    First Rule of the FCL: ...

  • Related links on the Cool Chips VIII (Score:3, Informative)

    by News for nerds ( 448130 ) on Monday May 02, 2005 @12:41PM (#12408808) Homepage
    Cool Chips website with the program
    http://www.coolchips.org/ [coolchips.org]

    Another report for the conference (in Japanese, with pics)
    http://pcweb.mycom.co.jp/articles/2005/04/28/coolc hips1/ [mycom.co.jp]
    http://pcweb.mycom.co.jp/articles/2005/04/28/coolc hips1/001.html [mycom.co.jp]
  • Obviously there is some power here. What I'm curious about is :

    1. Will Video Games be able to take advantage of this (PS3)
    2. I know multithreading opens a huge bag of worms in programming (Race Conditions, concurrency, deadlock, etc.). So, How hard will it be to develop i.e. will the SDK's be any good.

    This could be the most powerful system on earth, but if the game devlopers cant code against it, then whats the point?

  • PS3 SDK? (Score:3, Informative)

    by dioscaido ( 541037 ) on Monday May 02, 2005 @01:02PM (#12409098)
    Has there been any info leaked about the PS3 SDK? Programming a game on a massively parallel platform like the CELL can't be easy, especially for a console industry used to a fairly traditional hardware environment.

    In many respects, the Saturn failed because the SDK was just too hard to work with, as did the N64 (although that also had the cartridge limitation to further pull it down).

    Given that it seems like the PS3 will surely trounce the Xbox360 in HW capabilities, I wonder whether ease of development will have the final say on who has the better gaming platform.

  • BeOS did this years ago (Score:1)

    by Anonymous Coward
    wasnt BeOS's original demo 50 copies of the star wars trailer playing simultaniously
  • by releasing a new picture of the Xbox 360. Bill Gates was heard to remark, 'Quick, buy out Toshiba before they ruin everything!'

  • There is no license. (Score:3, Insightful)

    by node 3 ( 115640 ) on Monday May 02, 2005 @01:47PM (#12409742)
    You don't need a license to use your own software. A license comes into play when you distribute your software.

  • So when can we start buying them? (Score:3, Insightful)

    by nurb432 ( 527695 ) on Monday May 02, 2005 @02:44PM (#12410447) Homepage Journal
    All this stuff is nice, but until i can actually get one and mess with it on my bench its still just 'ooh, thats cool'.

    Lets see some silicon!
  • Synergistic Processor Elements? They aren't seriously going to start calling it that... please lord no.

    I refuse to use some old buzzword from the 90s' megacorporations to describe my computer hardware. Forget about it.

  • Embarrassingly parallel tasks? (Score:3, Insightful)

    by CTho9305 ( 264265 ) on Monday May 02, 2005 @04:35PM (#12412119) Homepage
    Simultaneous MPEG2 decoding, as shown here, is what computer architects call an embarrassingly-parallel problem. The easiest way to speed it up is just add more processors - with 8 processing units, the Cell is a great fit.

    However, the really interesting problems are the ones that don't scale linearly in performance with the number of processors - these are the tasks for which the Cell processor will probably be running with 7 idle units and 1 active. These are also the tasks where we need actually new architectures; supercomputers like BlueGene will tear their way through extremely parallel problems.

    One very cool approach to handling less parallel workloads (or even "sequential" workloads - like the majority of programs people usually run on PCs) is speculative threading - taking a sequential program, breaking it up into chunks, and running those chunks in parallel. Of course, when you do this, you have to make sure that the later work doesn't depend on the earlier operations, and check for violations of "sequential execution semantics" (programs expecting sequential execution semantics are ones that expect their instructions to execute in order - basically any program you'd write today). The Stanford Hydra [stanford.edu] project is an example that uses this technique; Wisconsin Multiscalar Group [wisc.edu] takes an approach that requires modified binaries to do something similar.

    One thing people fail to mention when they talk about the supposedly-amazing performance of the Cell processor is its floating point precision: first, it only attains it's >200GFLOPS with single precision numbers (not accurate enough for many scientific applications), and second, it doesn't follow IEEE754 rounding requirements. The rounding policy in IEEE754 floats is specifically designed so that as you perform more and more calculations, the error doesn't grow rapidly. Cutting corners lets you calculate faster but even less accurate numbers. Basically, to get the high FLOPS ratings, Cell sacrifices precision in both the number of bits used, and the accuracy of the data in those bits.

Slashdot Top Deals

Thus spake the master programmer: "Time for you to leave." -- Geoffrey James, "The Tao of Programming"

Close