Catch up on stories from the past week (and beyond) at the Slashdot story archive

 



Forgot your password?
typodupeerror
×
Google Graphics Intel Hardware Technology

Intel Considers Hardware Acceleration For Google's WebM Format 139

CWmike writes "Intel is considering hardware-based acceleration for Google's new WebM video file format in its Atom-based TV chips if the format gains popularity, an Intel executive said on Thursday. Announced last Wednesday at Google I/O, WebM files will include video streams compressed with the open-source VP8 video codec, which was acquired by Google when it bought On2 Technologies in February. 'Just like we did with other codecs like MPEG2, H.264 and VC1, if VP8 establishes itself in the Smart TV space, we will add it to our [hardware] decoders,' said Wilfred Martis, a general manager at Intel's Digital Home Group."
This discussion has been archived. No new comments can be posted.

Intel Considers Hardware Acceleration For Google's WebM Format

Comments Filter:
  • by hhawk ( 26580 )

    It would be nice to have hardware support.. and the support of Intel.. and guess they don't want to be accused of favoring some parties and not others.. and certainly there is a cost to adding to the hardware but still is it not also a chicken and egg problem?

    • Re: (Score:2, Insightful)

      by Anonymous Coward

      No offense, but I'd be happier to see theora support added first, since that is more or less guaranteed to be devoid of current patent litigation.

      If they added 'webm' support as well I wouldn't mind though :

      • Re:Nice (Score:5, Funny)

        by daveime ( 1253762 ) on Friday May 28, 2010 @12:38AM (#32372406)

        What about hardware support for animated GIFs, if today is "ridiculous uses for an FPGA day" ?

        • Re: (Score:3, Funny)

          by sakdoctor ( 1087155 )

          I want hardware support for Windows XP search dog. Do it intel!

        • Hardware acceleration for my coffee pot in the morning would be nice, too.

          • Hardware acceleration for my coffee pot in the morning would be nice, too.

            Why don't you just throw it out of the window?

            • by treeves ( 963993 )
              He lives in the basement? (Even if it were a daylight basement, there wouldn't much be opportunity for gravitational acceleration to come into play.)
      • Re: (Score:2, Insightful)

        by Anonymous Coward

        When the chicken is youtube the egg better hurry the hell up or the farmers will be pissed.

      • I'm not sure if you know this or not, but Theora - it sucks. Almost nobody's using it for anything serious, and this will be doubly true in the next few years.
    • Re:Nice (Score:5, Insightful)

      by fuzzyfuzzyfungus ( 1223518 ) on Thursday May 27, 2010 @10:15PM (#32371710) Journal
      There is certainly some chicken-and-egg concern(though this might be obviated by the fact that Google has a massive arsenal of web videos, and a browser, and mozilla could probably also be counted on).

      As for costs, it wouldn't surprise me if the format was designed(in part) to keep those low. Remember the analysis [multimedia.cx] linked to here a few days ago? The punchline was, in essence "very much like h.264, except in a few specific ways that are largely worse". Now, assuming that the On2 people aren't complete morons(which would also imply that their new Google overlords are complete suckers), why would they create a codec like that?

      Well, h.264 is the best supported(in terms of software, and embedded hardware decoders) of modern video formats. It is also considered to be quite good, the product of research by a large number of people and entities. However, it is patent encumbered. Therefore, you would expect a rational competitor to do the following: Copy h.264 as closely as possible in all unpatented respects, or respects where patents can be worked around. Nobody is giving you any extra credit for re-inventing the wheel, and (unless you have particular reasons to believe the contrary) trying to do so would likely result in a worse wheel. Where the spec is simply too patent encumbered, implement the least-worst replacement for that bit that isn't encumbered.

      Based on that technical analysis, it strikes me as extremely likely that this is more or less what On2 did. Do a patent search, presumably focusing on the MPEG-LA pool, and any other likely suspects. For any parts of h.264 too heavily covered to engineer around the patents, make the smallest legally tenable compromise.

      Since the vast majority is extremely similar to h.264, this will likely make adding hardware support cheaper, since most of the dedicated decoder logic and/or embedded DSP firmware can be shared between h.264 and WebM, with small additions to cover the differences.
      • Not the first time (Score:5, Informative)

        by Anonymous Coward on Thursday May 27, 2010 @10:18PM (#32371720)

        Its not the first time that someone has had to build and incredibly similar version yet slightly worse, just to fill a civic need. On2 is doing what Tesla did when Edison prevented him from using his lightbulb design.

        • Re: (Score:1, Funny)

          by Anonymous Coward

          Actually Tesla's version was superior to Edison's, do your research.

        • Re: (Score:1, Informative)

          by Anonymous Coward

          Except that On2 didn't create VP8 out of charity. If it wasn't for Google buying them, VP8 would have never been open sourced.

          • Never is a long time. Did you know Theora is based on VP3 [vp3.com]? Eventually they probably would have done the same thing, just not so soon.

        • by rumith ( 983060 )

          Google is doing what Tesla did when Edison prevented him from using his lightbulb design.

          There, fixed that for you

      • Re: (Score:2, Interesting)

        by westlake ( 615356 )

        However, it is patent encumbered. Therefore, you would expect a rational competitor to do the following: Copy h.264 as closely as possible in all unpatented respects, or respects where patents can be worked around. Nobody is giving you any extra credit for re-inventing the wheel

        The problem here is that H.264 licensors are industrial giants like Mitsubishi Electric.

        Philips. Samsung. LG. Fujitsu. Hitachi, NTT...

        It's easy to forget that H.264 is a broadcast standard:

        NTT Electronics has produced the world's fi

        • or is it?
          Seems to me more and more people are actually watching videos from the net, or via their provider's private net, not via DVB-T and friends.

      • Since the vast majority is extremely similar to h.264, this will likely make adding hardware support cheaper, since most of the dedicated decoder logic and/or embedded DSP firmware can be shared between h.264 and WebM, with small additions to cover the differences.

        That's overly optimistic. They'll both use completely separate code paths.

        But since they decode in similar ways, any hardware optimized for decoding H.264 will decode VP8 very well.

    • The egg came first; the first egg from which the first chicken emerged was laid by a bird that we would not fully classify as a chicken. The actual resulting chicken was the result of a genetic mutation relative to the mother.
  • by frinkster ( 149158 ) on Thursday May 27, 2010 @10:20PM (#32371726)

    How long will it take to get popular? 1 year?
    How long will it take to design the hardware implementation? 6 months?
    How long will it take to get into production? 1 year?
    How long will it take to get into a product that is on store shelves? 6 months?

    This is too long. Intel may as well have said they aren't interested. 3 years from now there are going to be how many tens of millions of devices with hardware H.264 support and no way of upgrading to VP8 support? People aren't going to toss these things in the trash just so the can buy brand new devices that give them the exact same experience.

    • by ducomputergeek ( 595742 ) on Thursday May 27, 2010 @10:25PM (#32371750)

      3 years from now? H.264 is on my computers, my blu ray player, my phone, my camera, my video camera, it's everywhere now. In order for any codec to replace H.264 it has to be technically superior, just not "free". And from what I've seen, VP8 is better than Theora, but still not H.264.

      • by frinkster ( 149158 ) on Thursday May 27, 2010 @10:35PM (#32371806)

        My point is that by the time Google and their partners could get this into widespread use, H.264 is going to be in even more widespread use than it is now.

        If Google wanted to really compete, the time to do it was a few years ago. It's too late now. The only way to stop H.264 is to come out with a codec that makes H.264 look like bloated garbage. This isn't such a codec.

        Anyway, that's my opinion. I would love to be proven wrong - I don't really want to have to start paying royalties in 2015.

        • Re: (Score:2, Interesting)

          by Anonymous Coward

          There is a good chance that it is gone too far already but considering the company pushing this codec and their ties to the internet and marketing muscle in general, I wouldn't be so quick to count them out yet.

          Remember, google is starting to release their own channel along with the fact they own YouTube and a host of other services, all of which I am betting will be migrated over to this format all of which is supposed to be supported in the new HTML setup they are going for. Face man, they are like the ne

          • Let's say the Google overlords are good to the little people these days.. and successful or not that's certainly worth the try.
            In any case when going to youtube and having VP8 served through flash, VP8 will have some market share, not matter what.

        • by rtfa-troll ( 1340807 ) on Friday May 28, 2010 @03:23AM (#32372982)

          This only needs to get to be the current GIF vs PNG situation and it's enough. There are still GIFs on the internet everywhere. They will never go away. However, nobody needs to put new content in GIF format because PNG is available everywhere. GIF licensing fees are now taxes on stupidity and help to mean that IP supporting companies become ever less competitive.

          That means that the entire television industry, which is locked into H.264 will become less competitive against the internet / Google / web / open access type companies. This is the reason why the MPEG-LA is desperately spreading FUD. Hint; if you know that there's a patent which is essential to a particular existing standard there is absolutely no reason not specify exactly which patent it is out loud. If you don't do it you risk losing money for accusations of bad faith. If these people really knew which patent it was, then they wouldn't say they had it (admit they've done that analysis) without specifying exactly where the breach was. The very fact the MPEG-LA says there are patents but won't specify which shows that there actually aren't any.

          • Re: (Score:3, Informative)

            by Hal_Porter ( 817932 )

            The patents on GIF have expired. It's not just as free as PNG. Plus it supports animation. Also a lot of software - notably Photoshop - tends to produce smaller GIFs than PNGs for most images because the GIF generation code is more optimized.

            • APNG (.png) supports animation in any non-IE web browser.

              A properly optimized PNG file will often be half the size of a gif, and supports 24bit colour too...

              • Re: (Score:2, Insightful)

                by Hal_Porter ( 817932 )

                APNG (.png) supports animation in any non-IE web browser.

                APNG was also voted down as a standard - MNG is the official way to do animation but no one supports it.

                http://sourceforge.net/mailarchive/message.php?msg_name=3.0.6.32.20070420132821.012dd8e8%40mail.comcast.net [sourceforge.net]

                A properly optimized PNG file will often be half the size of a gif, and supports 24bit colour too...

                Part of the problem with PNG is that a lot of applications will generate 24bit PNGs for images that would be smaller if they used a palette.

                In both cases PNG's official feature set often works against

                • by makomk ( 752139 )

                  APNG was also voted down as a standard - MNG is the official way to do animation but no one supports it.

                  Mozilla used to support MNG, back before they ripped out support in favour of their new APNG format.

          • However, nobody needs to put new content in GIF format because PNG is available everywhere.

            MNG and APNG, the animated extensions to PNG, are not available elsewhere. The alternatives to animated GIF are SWF and HTML+PNG+JavaScript.

            The very fact the MPEG-LA says there are patents but won't specify which shows that there actually aren't any.

            There is aleady a PDF listing patents in the H.264 pool [mpegla.com]. As for the proposed WebM pool, give it time. MPEG-LA members are still reviewing their portfolios to see which patents are essential enough to go on such a list.

      • by mjwx ( 966435 ) on Friday May 28, 2010 @03:41AM (#32373068)

        3 years from now? H.264 is on my computers, my blu ray player, my phone, my camera, my video camera, it's everywhere now. In order for any codec to replace H.264 it has to be technically superior, just not "free". And from what I've seen, VP8 is better than Theora, but still not H.264.

        No, it has to be used more by providers. Why does everything have a H.264 codec, because Youtube and everyone else uses H.246. What Google needs to do is to get providers to switch to VP8 and make their intentions clear to swtich off H.264. HW manufacturers will follow the providers.

        • No, it has to be used more by providers. Why does everything have a H.264 codec, because Youtube and everyone else uses H.246. What Google needs to do is to get providers to switch to VP8 and make their intentions clear to swtich off H.264. HW manufacturers will follow the providers.

          I think they might just throttle it and put up a notice. They would need to let their users know that their phone is using 'outdated software' or whatever.

    • Re: (Score:3, Informative)

      by Microlith ( 54737 )

      People aren't going to toss these things in the trash just so the can buy brand new devices that give them the exact same experience.

      And chances are they won't have to. Few devices have silicon h.264 decoders, instead having a DSP and a software h.264 codec. Plenty faster than a regular software decoder, cheaper and more flexible than a fixed decoder.

      • A few of those DSPs have instruction sets that are tweaked to make it easy to implement H.264, but given the similarities between H.264 and VP8, it's likely that they'll also make it easier to implement VP8.
    • Re: (Score:3, Insightful)

      by eulernet ( 1132389 )

      My bet: the next version of Google Chrome will include the VP8 codec, and Youtube will provide VP8 encoded videos.

      Since Chrome is gaining more market share every day, VP8 could become the standard de-facto for Web streaming, especially if Youtube doesn't support H264.

      Google doesn't care about offline products.

      • Some say this has already happened. I use Chromium nightlies that include VP8 and use YouTube's HTML5 VP8. It's lovely.

        • Same with FF and Opera. And IE9 will support it as long as the codec is installed. Which means that when these versions actually role out, the vast majority of desktop browsers that support the video tag with also support WebM.
    • This is what it will take for INTEL to support hardware accelerated VP8.
      Mainly because they'll have to create a full blown VP8-core (or more likely, try to see if they can modify the existing video core and cram in the few missing parts).
      That's because their embed 3D chips aren't that brilliant and Larrabree project is heading nowhere.

      Now, for other companies, it might simply be a purely software problem, leveraging the various SIMG, DSP & GPU components.
      Theora has hardware implementation runing on the

  • by Sycraft-fu ( 314770 ) on Thursday May 27, 2010 @10:22PM (#32371736)

    According to their page AMD, ARM, nVidia, MIPS, Marvell, TI, and Freescale are all onboard. That leaves pretty much just Intel and Analog Devices as the only two major chip makers for various devices that haven't cast in. If they can get widespread hardware support, it means that devices will likely have WebM acceleration by default, simply due to the chips they use. That being the case, enabling software support for it makes good sense.

    I think it has a real shot at becoming the streaming media standard. H.264 is likely to remain the high quality standard for video because it is used on Blu-ray and a good deal of recording devices, but WebM could well take over streaming. While it isn't as high quality per bit, it is good enough (after all, VP6, its predecessor is used in a good deal of Flash video) and free is hard to say no to. If devices support it in hardware, then there you go.

    Have to see how things shake out, but I'm optimistic. There's a large base of support for it in all the right areas. Only real thing that could sink it is a successful patent lawsuit. However I believe Google when they claim they've evaluated it before and after purchasing On2 and they are confident. I think it is likely that if VP8 infringes on any patents, it infringes only on ones that they can find prior art for, and that they may also have some patents of their own they can hit back with.

    Here's hoping. Not only would a completely free format be good various uses, but its existence should force MPEG-LA to keep H.264's licensing terms reasonable.

    • and free is hard to say no to

      So that's why Theora has been such a smashing success?

      • Re: (Score:2, Insightful)

        by pseudofrog ( 570061 )
        Because it sucks and has no corporate support.

        VP8 doesn't suck and appears to be gaining corporate support.
        • Re: (Score:1, Troll)

          VP8 doesn't suck

          Then you've apparently never used it or you actually fell for that shitty comparison from their website which was nothing but misleading marketing material.

          • Re: (Score:2, Informative)

            by EricJ2190 ( 1016652 )
            I have used VP8, and I'd also say "VP8 doesn't suck." I will agree that On2's website for it is misleading. I will also agree that H.264 does a better job of compressing video than VP8. However, just because VP8 falls short of the best performing format available doesn't mean it sucks. VP8 still is a good format, and I would argue that it is the best patent-free format for web video, assuming Google is correct about its patent status.
          • The analysis on the x264 blog [multimedia.cx] concluded that VP8 most closely resembles H.264 baseline, and the comparison [s2000.ws] shows that H.264 baseline encoded with x264 lies somewhere between Theora and H.264 Main.
        • by makomk ( 752139 )

          Nope, VP8 sucks, and it's not surprising. Part of the reason Theora got such a bad reputation is that VP3 had some really dubious design decisions which took years to correct. VP8 looks like it's not quite as bad, but it's still got some decidedly dubious aspects (bad support for quantizer selection, slow bitstream coding method, generally poor encoder, etc).

    • If MPEG-LA wanted to be really nasty about it and keep it out of the courtroom, they could pressure the chip makers not to support WebM much in the same way Microsoft pressured OEMs: "You do that and I'll make you pay more licensing fees", or the more modern, "Thanks for not supporting a rival, here's a sweet licensing deal and more free (gratis) software!".

      Yes, it's probably illegal in many jurisdictions to do that, but corporate entities have discovered that it's often more cost-effective to break the law

  • by Anonymous Coward

    With how close they are to each other as a format, it shouldn't be too hard to make it decode in hardware as most of the stuff is already there. Hell, with how close they are you could probably rig up a decoder that already ran partially in hardware as is.
    It is a win for VP8 but not exactly like it would be a hard thing to do or even expensive on Intels part.

    To be honest, this actually looks like the logical thing to do on their part.
    1) Format becomes popular that is already mostly able to run on your curre

  • by tlhIngan ( 30335 ) <slashdot&worf,net> on Thursday May 27, 2010 @11:36PM (#32372162)

    Given that VP8 is really just a minor modification of h.264, and Intel already supports h.264 decoding in hardware, what exactly has to be done to support VP8? Modify the driver to reload the proper DCT constants and other minor things. The only hardware stuff I can see is if the hardware is hardwired for h.264 in which case they need to rewire it to be a little more flexible. But given they support many codecs already with the same pieces, it should be already in place (a lot of other pieces get reused decoding VC-1, for example).

    Surely all the h.264 blocks could be re-used as VP8? In which case Theora's practically dead because everything supports h.264 decoding already and can probably be trivially converted to support VP8 as well.

    Heck, you probably can do the same with an h.264 encoder to have it spit out a VP8 bitstream...

    • by Anonymous Coward

      I don't think there is actually a _single_ h.264 hardware component that could be directly reused for a vp8 decoder. Maybe if you designed your motion compensation engine with a lot of filter flexibility it could be reworked for vp8 without too much work... but really, in engineering "similar" is not the same as "the same". For the reuse of pre-existing parts "the same" is what counts.

      • Re: (Score:3, Informative)

        by mr_mischief ( 456295 )

        For the devices using a SIMD engine and a DSP to do H.264 with instructions in firmware, it's just a firmware upgrade to support other codecs that are substantially similar. That maybe not be the approach everyone's using, but it seems a likely combination for some devices. Lots of ARM-based devices tend to use this, if I'm not mistaken. Cell phones and tablets would be a good place to not have to spend an extra dollar for licensing costs, too.

      • Re: (Score:1, Informative)

        by Anonymous Coward

        Exactly, see the VP8 technical analysis by Dark Shikari [multimedia.cx]

        The very example the OP refers to (DCT) is telling:

        H.264 uses an extremely simplified “DCT” which is so un-DCT-like that it often referred to as the HCT (H.264 Cosine Transform) instead. This simplified transform [...] can be implemented entirely with adds, subtracts, and right shifts by 1.
        VP8 uses an extremely, needlessly accurate version[..]

  • Comment removed based on user account deletion

Garbage In -- Gospel Out.

Working...