Forgot your password?
typodupeerror
Upgrades Hardware

Cell Chip Coming To the PC Via a PCI Express Card 164

Posted by timothy
from the buy-one-for-every-prisoner dept.
arcticstoat writes with an excerpt from Custom PC: "After developing a brand new CPU architecture from the ground-up, you'd expect that Toshiba, Sony and IBM would have more uses for the Cell architecture than the PlayStation 3, and Toshiba has been quick to make use of the architecture's HD video transcoding abilities in its new Qosimo laptops. However, Leadtek is now taking Toshiba's efforts a step further by putting the chip onto a PCI-E card for desktop PCs. The WinFast PxVC1100 is based on Toshiba's SpursEngine SE1000 processor, which is a cut-down version of the Cell chip. The SpursEngine chip features four SPEs (synergistic processing elements) based on 128-bit RISC cores, along with H.264 and MPEG-2 codecs, but it doesn't contain its own CPU as the chip in the PS3 does. The chip is capable of encoding and decoding H.264, MPEG-2 and MPEG-4 video streams in hardware."
This discussion has been archived. No new comments can be posted.

Cell Chip Coming To the PC Via a PCI Express Card

Comments Filter:
  • Just maybe? [wikipedia.org] Had anyone other than the submitter and TFAuthor not heard of this?
    • The whole point is that this is a way to get Cell power in "Personal Computers", rather than supercomputers or games consoles.

      • by Fred_A (10934)

        So we can get "cell power" and then all we have to do is write cell empowered applications !

        This is so exciting, I can hardly wait ! Soon I'll be able to index my cactus seeds in no time ! (I've got almost 30)

        I mean, gosh !

        • by aliquis (678370)

          Yeah, I can't understand why anyone would want a crippled Cell. I really doubt they are all that superawesome powerful in the PS3 so why would I want something less powerful in my computer?
          Also the price will probably be to expensive compared to what you get for the money.

          For general computing shouldn't say an Intel Q9550 be a much better choice? Or if I'd really wanted something this specialized why not get whatever Nvidia-card and use their CUDA-stuff?

          Where is the market for this card? Sure it may be sad

          • by aliquis (678370)

            (I thought it was obvious so I never said it but also modern graphic cards already do HD-video decoding so this is useless there to, just get a decent graphics card.)

          • by cbreaker (561297)

            This card is supposed to do HD Encoding. Not just decoding.

            Show me a current application that uses your GPU to do good H.264 or MPEG2 encoding in realtime and I'll bite.

            • This card is supposed to do HD Encoding. Not just decoding

              That may be true, but that significantlty limits the potential market for this chip. I'd say just off the cuff that MUCH less than %1 of the total video market has a need to encode HD in real-time, or is encoding HD often enough to notice the improvement.

              For the less than %5 of the video market who have EVER encoded their own HD video, most of them don't do it often enough to notice an improvement. And without noticeable improvement, they cannot ju

              • by cbreaker (561297)

                First of all, not every product manufactured had to appeal to 90% of the market or sell 10 million units to be successful. Who knows what their target sell rate is, but it sure as hell won't be iPod numbers. A vendor could sell 10,000 cards and have a very successful product depending on R&D costs. For something like this, they just assembled existing parts onto a PCB and probably tied togeter some software for it.

                I would love to be able to encode HD video with some decent speed. I've re-coded BD

    • Re: (Score:3, Informative)

      by Nursie (632944)

      Yeah, and there's that whole "Roadrunner" thing, fastest supercomputer in the world. And IBM sell Cell bladeservers...

  • mythtv apps (Score:5, Interesting)

    by pak9rabid (1011935) on Thursday October 02, 2008 @07:25PM (#25240383)
    this + mythtv = interesting possibilities
    • by rtechie (244489) *

      As many have said, this isn't cost-effective for the hobbyist (assuming there is proper Linux support, which is unlikely) unless he's encoding shitloads of video i.e. he as at least 4 HD streams he's encoding. This is more for content providers making dedicated encoding boxes.

      • Wasn't part of the news that both WinDVD and PowerDVD would potentially support this? That would certainly help for lightweight Windows HTPC's especially given that the card is a half-height and only needs a PCIe x1.
    • by Ilgaz (86384)

      I hope Leadtek already got CVS commit accounts in VLC, mplayer, ffmpeg, x264 projects for their optimisations.

      That is the most practical way to gain full support to Windows, OS X and Linux. Also imagine a micro laptop which can crunch data better than a desktop PC when on demand.

  • The chip is capable of encoding and decoding H.264, MPEG-2 and MPEG-4 video streams in hardware.

    Don't video cards do that? or does this thing just sorta add juice to your system?

    I WANT THIS TO BE AWESOME but I'm just a bit underwhelmed.

    • by batkiwi (137781) on Thursday October 02, 2008 @07:55PM (#25240649)

      -in linux, no. only mpeg2 decoding
      -in any OS, not really. There is a brand new ENCODER for h.264, but reviews show it to be crap and limited

      Windows does have full GPU decoding of h.264 with modern nvidia (not sure about ATI, but it is likely), but that's it.

    • Is the author aware that H.264 is one of two video encoding standards that fall under the umbrella of "MPEG4"? (H.264 is MPEG 4 Part 10, with the other being Part 2, and I can't honestly remember what it's called. DivX is built off of it, but it's otherwise generally considered kinda irrelevant these days.)

      • XviD and DivX are the two most popular video codecs used on the internet, both of which are MPEG-4 Part 2 encodings. i would hardly consider it irrelevant. XviD in particular is useful because it provides high-quality video compression under a GNU license and is supported on all platforms. H.264 is a patented codec, so despite there being open source implementations, it's still excluded from certain FOSS products.

        the author probably wanted to specifically mention H.264 because it's a very well-known encodin

    • Re: (Score:3, Informative)

      by doctor_no (214917)

      Its not meant for playback of a single video like the GFX cards do, or watch a DVD or Blu-ray, its designed for content creation and distribution. In an early demo, the Cell did 48 simultaneous Mpeg2 streams in real-time.

      http://gizmodo.com/gadgets/home-entertainment/playstation/cell-processor-demos-mpeg2-x-48-100853.php [gizmodo.com]

       

    • by evilviper (135110)

      Don't video cards do that?

      No. Video cards don't do any encoding.

      • I believe the confusion stems from ATI's AVIVO Video Encoder.

        Yes, it is a fast video encoder. No, it does not use the GPU; instead, it uses optimizations that sacrifice quality for performance.

        I personally find it really sad that ATI made the claim in 2005 that the converter would eventually be hardware-accelerated, and failed to deliver on that promise.

  • Two things (Score:2, Interesting)

    #1: Is there going to be a Mac Version? I would love to put this in my Apple Tower, I have 3 PCI-E x16 slots sitting around doing nothing. #2: When is this actually going to come out? I mean, I keep reading things on "fantastic pieces of tech" and they either never come out, or they come out everyone forgets about them. Anyone know what this should retail for, or if software can even take advantage of it yet?
    • Re: (Score:3, Interesting)

      by somersault (912633)

      Any PCIe card is a 'mac version' just as much as it is a 'PC version' - perhaps you mean will there be drivers or a developer API for the Mac - the good thing is that a lot of Linux geeks will be wanting this (probably good for University research projects), and if there is Linux support then basically you will already have OSX support.

      The interesting question is, what are you planning to do with it that you can't already do fast enough with a multicore CPU, GPU or physics type add in card? Or do you just w

      • Re: (Score:3, Insightful)

        by christurkel (520220)
        and if there is Linux support then basically you will already have OSX support.
        You've never tried to write a Mac OS X driver, have you? If so, you'd know you couldn't be more wrong. OS X uses a totally different different architecture; they are not even close. OS X uses I/O Kit. Not even FreeBSD is close.
        • No, I've never written drivers so I'm quite ignorant in that area. I guess I was just thinking more of a linux library which takes advantage of the abilities of the card, but you would indeed need a driver for that to be useful.

        • However, if it works under Linux, you can bet your ass that means the hardware has been "figured out" and so could be brought to other OSs.

          Open docs always works best, but what can you do? =/

      • by Trelane (16124)

        what are you planning to do with it that you can't already do fast enough with a multicore CPU, GPU or physics type add in card?

        If it's cheap enough, it's an affordable Cell processor to play^H^H^h^Hprototype with. :)

      • by aliquis (678370)

        No, because macs use EFI so they atleast require special graphics cards. So special cards for this purpose may not be as strange as it sounds.

  • Why bother? (Score:5, Insightful)

    by HateBreeder (656491) on Thursday October 02, 2008 @07:30PM (#25240453)

    This spurs engine sounds just like an extra GPU...

    Why not just go with CUDA or some other GP-GPU platform and avoid the hassle?

    I know nVidia and AMD/ATI are doing H.264 decoding in hardware using their GPUs... I'm sure you can get software for encoders too.

    • Re:Why bother? (Score:5, Informative)

      by stonecypher (118140) <stonecypher@gmai l . com> on Thursday October 02, 2008 @07:38PM (#25240509) Homepage Journal

      CUDA is a matrix processor. This is a serial processor. CUDA isn't really applicable to general purpose tasks. This is. CUDA gets its power by running the same function over an array of inputs to generate an array of outputs.

      Different beasts.

      • What does it have over a normal multi-core processor, like say a Core 2 Quad?

        The problem I've been seeing with the Cell both in terms of how it performs in the PS3 and the researchers tinkering with it at work (I work for a university) is that it doesn't really seem to have something that it is great at. A lot of the tasks people tout for it are highly parallel tasks, like Folding@Home. Ok, wonderful, except a GeForce crushes it. A GTX 280 using the CUDA client is much faster than a Cell. Ok so, not for tas

    • Re: (Score:2, Interesting)

      by tonytnnt (1335443)
      Hardware encoding acceleration h.264 isn't easy to do on GPUs as I recall. Your source video file isn't really meant to be worked in parallel, so a serial approach (like this) should work better. At least from what I've been reading/told, which is mostly related to transcoding rather than pure encoding. Someone else might be able to enlighten us more (hopefully a dev from x264 maybe?)
    • AMD has something called the Avivo video encoder which supposedly makes encoding videos really fast and uses very little CPU. Unfortunately, I have an AMD card that is just the wrong type and doesn't have the UVD chip so I can't test it out myself, but the Radeon HD 2600 and all 3x00 and 4x00 GPUs have it. Not sure why they left it out on the 2900s, ugh. I guess the 2900s already generate more heat than almost anything else, so one more chip might be too much.
  • Yes, but... (Score:2, Informative)

    by lowlymarine (1172723)

    ...can it play Crysis?

    Because if not, seeing as modern graphics cards [wikipedia.org] all feature hardware MPEG, I'm kind of underwhelmed by this announcement.

  • Does it run ... ? (Score:4, Interesting)

    by sergstesh (929586) on Thursday October 02, 2008 @07:48PM (#25240597)
    The mandatory "does it run Linux ?" boils down to "do they provide enough documentation to write drivers for it ?".

    I RTFA, but I didn't find an answer in it.
    • by Anonymous Coward
      Probably. We already have enough information about the CELL processor on its own to make use of it under Linux; this card is just taking a cut-down CELL and tacking a PCIe bus on it.

      Unless they purposefully fucked the register table to prevent it, it's probably just a matter of finding the correct PCIe offsets to access known registers/segments on the CELL. While it's possible they could "sabotage" it to prevent the first-day-out-of-the-box Linux driver, chips modified this way usually have to go under m
  • by ProppaT (557551) on Thursday October 02, 2008 @07:50PM (#25240621) Homepage

    ::checks case::
    Ooh, awesome! I have one more PCI-E slot left, right next to my PhysX accelerator! Where do I pre-order?

  • by snicho99 (984884) on Thursday October 02, 2008 @08:00PM (#25240705) Homepage
    Decoding .264 isn't really such a big deal. The ability to do low-cost multi-pass 1080 h.264 encoding at greater than real-time is something that would be EXTREMELY welcome for my company. We're a video post production house and we burn *LOTS* of CPU cycles encoding video for delivery to clients. A sub $500 card that greatly streamlined that process would be VERY welcome. Especially if it's something you could do as a background process that effectively didn't interfere with the operation of the edit suite.
    • Re: (Score:3, Interesting)

      Just hope that they expose the card's power in a nice way. Documentation and/or SDK so that your in-house geek and/or the next version of $EDIT_SUITE can silently harness the power of the coprocessor? Instant win.

      Attempting to integrate Leadtek l33tripZ SE (Now with the crushing power of the "buggy, ill-defined, good enough for consumers" h.246 profile in hardware! Totally Vista compatible(32 bit systems only, when run as administrator during waxing moon)) into a professional workflow? World of pain.

      So
  • 50/50. (Score:5, Interesting)

    by fuzzyfuzzyfungus (1223518) on Thursday October 02, 2008 @08:09PM (#25240793) Journal
    The fate of this device hinges pretty much exclusively on the quality of its software and documentation. If all you get is some gaudy half-broken-and-all-ugly fixed purpose video encode decode app(in the fine tradition of graphics card shovelware, remember the bad old days when the card vendor was responsible for the driver?) then this thing is dead in the water. A few will sell to Netflix pirates looking to rip and encode 3 times as much video as they could ever watch, instead of just twice as much; but that'll be about it.

    If it has good general purpose support(I'd really prefer that this mean "good documentation" and properlinux support; but I suspect a proprietary sdk would do alright as well) then it could be a killer in certain lower end computing scenarios. Since the cell is produced in nontrivial bulk, and this thing is only about 1/2 the complexity of a full cell(does that mean that this card is "spursengine on the half-cell?) it should be cheap, cheap, cheap compared to FPGA boards or custom ASICs for such purposes as the cell architecture is useful.

    I hope the do the right thing, and get rewarded(and I hope so, surely somebody looking to sell computational hardware would see the virtues of making it as useful as possible for as many customers as possible?); but if they don't, I suspect that they'd be lucky to do as well as physX, and will probably do worse.
  • Shit man... (Score:3, Funny)

    by alexborges (313924) on Thursday October 02, 2008 @08:24PM (#25240921)

    I want to be a synergistic procesing element!

    Doesnt everyone?

  • by Joe The Dragon (967727) on Thursday October 02, 2008 @08:28PM (#25240955)

    Only pci-e x1 and 128meg of ram? ati, nv cards have more ram at a lower cost with a pci-e x16 link.

    The x1 link will slow this down. HTX is even better then pci-e for a add in cpu.

  • Mercury Computers has had a card with a cell on it for quite some time. It is, I believe, very expensive (~$10k?).
    Link to the card. [mc.com]
    • Re: (Score:2, Interesting)

      by Lance Cooper (977401)
      After looking briefly at this, it is an entirely different beast. It is a full Cell processor, with 8 SPE's and a PPE and 5GB of RAM, as well as Flash memory that allows it to boot Cell Linux. It's really a system on a PCI-E board, rather then an accelerator board.
  • The Cell is a perfect example of how not to design and build a multicore processor. It's a powerful processor but it's a pain in the ass to program. The worst thing that a multicore designer can do is build a processor before the programming model is designed and tested and all the chinks ironed out. But Sony and IBM are not alone. Intel is making the same mistake with Larrabee. AMD is soon to follow suit with its Fusion hybrid. It's enough to make a grown man cry. The truth should be clear to everyone by n

    • Re: (Score:2, Interesting)

      by 91degrees (207121)
      I wouldn't be so sure. Dedicated hardware is typically a lot cheaper than a general purpose CPU unless the tasks you want to do are extremely general. GPUs work very well with a simpler SIMD approach, and this can be extended to raytracing. It's an approach that works well for a lot of big number crunching tasks.

      For more general purpose work, MIMD is useful. I have to wonder why Cell didn't take more cues from the Transputer. From what I've read, The Cell seems to be based on the idea of running mu
    • But Sony and IBM are not alone. Intel is making the same mistake with Larrabee. AMD is soon to follow suit with its Fusion hybrid. It's enough to make a grown man cry.

      Hmm. Interesting argument, but did you consider the possibility that Sony, IBM, Intel and AMD are right, and you're not?

  • IIRC, the PS3 offers 7 SPEs, so they can increase their yield by letting those with one blown/bad SPE still ship, reserving the full 8-working SPE units to more expensive applications. So the chips in these cards are so bad that they have up to 4 dead SPEs and a dead PPE as well?

    I wouldn't think that there'd be enough of a market segment to create a separate, more limited version of this chip just for applications like this. This have got to be their mitigation strategy for incredibly low yield.

  • How is this new? (Score:4, Informative)

    by rockypg (787998) on Friday October 03, 2008 @12:13AM (#25242237) Homepage

    Mercury had a PCI-e cell expansion card [mc.com] for over a year now.

    Unlike the leadtek one, the mercury version has the full version of the cell processor, with 8SPEs. Dont think it comes with any prebuilt codecs though.

    • by owlstead (636356)

      It also has a price tag of 8K for a complete version including 2x gigabit & 4 GB of RAM. This is serious stuff, not something you would want to put into, say, a media streaming PC of under 10K.

      Personally the thing that is really new is the price point and the preinstalled codecs (if any). This would be pretty usefull for e.g. surveillance, where you might want to put a lot of security camera's onto one PC.

  • I remember when Creative and a few other companies had media decoder/encoader boards packaged with DVDROMS when they first came out, seems like a step back IMHO.

  • by Ant P. (974313)

    Whatever.

    If it can encode _Dirac_ at faster-than-realtime, then that'd be something to shout about.

A sheet of paper is an ink-lined plane. -- Willard Espy, "An Almanac of Words at Play"

Working...