AMD's UVD Debacle

by Derek Wilson on June 4, 2007 12:05 AM EST

There has been a lot of talk over the past week about the fact that the Radeon HD 2900 XT lacks UVD (Universal Video Decode) hardware for HD video decode acceleration on the GPU. We've seen sites from The Tech Report to DailyTech, and even Beyond3D reporting on the situation. While there is much discussion already out there, we would like to provide our take on things.

To recap, the situation is as follows. A huge number of press and channel partners were given the impression by AMD that their R600 GPU used to build the new Radeon HD 2900 XT contained UVD hardware. AMD's press materials are incredibly vague about the issue: they never explicitly state that the HD 2900 XT does or does not physically have UVD hardware. They do list R600 as having AVIVO HD, which they explained includes GPU offload of the entire video decode pipeline in their press materials.

In other slides and presentations, AVIVO HD and UVD have been presented as synonymous. As the entire HD 2000 line is supposed to support AVIVO HD, how could we assume that UVD hardware wasn't included on the GPU?

It seems that AMD is now trying to make it clear that R600 (the 80nm GPU for the HD 2900 XT) does not include UVD, but supports the same video decode features as the X1950. Dedicated hardware makes a big difference in entropy decoding, as we've seen with our G86 testing, but neither NVIDIA nor AMD have top end parts with full spec video decode offloading. The rationale is that high-end GPUs will be paired with CPUs capable of decoding any HD video thrown at them.

With such a huge volume of information to absorb, it seems reasonable to think that some details could get lost in the mix. But, while AMD never actually said anything untrue, they did omit details which could have easily clarified the situation. Walk with us through our experience and see for yourselves how we came to our conclusions.

Our Experience with UVD and R600
Comments Locked


View All Comments

  • LTG - Monday, June 4, 2007 - link

    Please ignore the small number of posts who called the article "blame shifting" or to "get over it".

    This article was not only well done it was important to the integrity of the process because it illuminated what went on behind the scenes.

    Whether or not there was intentional deception in the best case there was inadequate information provided (no proof but if I had to bet it would be that someone at AMD didn't act in good faith at some point in time).

    This kind of honest and direct reporting is why I come to the site. Likewise whenever AT gets hard questions from readers in the comments section, the authors directly respond much more than some other sites I see.

    Keep it up please, you're right on track.
  • kalrith - Monday, June 4, 2007 - link

    I also agree. Those who are calling AT biased, anti-AMD, and pro-Intel are just idiots. AT is for the companies that are providing the best bang for the buck of the average AT reader. AT was pro-AMD for the several years only in the sense that it stated AMD processors provided a much better value than Intel. Now, the tables have turned in Intel's favor somewhat as far as performance goes and lot as far as appropriate release dates and release information goes.
  • coldpower27 - Monday, June 4, 2007 - link

    I concur with this.
  • 7oby - Monday, June 4, 2007 - link

    Both nVidia and ATI are very vage about this topic and have in the past sometimes even released false information.

    Although you hardly find any information about this on the web, the following restrictions seem to stabilize in my mind:

    . WMV-9/VC-1 Decoding deactivated on AGP Systems in recent driver releases
    . partial H.264 hardware assisted decoding only possible with SSE2 (rules out AthlonXP systems for which the assistence would be very helpful)
    . remember GeForce 6800 where the H.264, VC-1, WMV9 assisted decoding has been announced a later recalled due to hardware defects in this silicon?

    . actually worse: I can not find any information about AGP, SSE(2) requirements
    . I remember reading on their webpage: X1000 supports hardware assisted encoding (!) of content. What has survived is "The Avivo Video Converter is only supported on Radeon™ X1000 Series or new GPUs.", which leaves a very bad taste, since it has been proven that this software runs without X1000 hardware and doesn't utilize it for the tasks it offers.

    Instead: A lot of confusion and frustration on the consumer side complaining about not properly working hardware assisted decoding.
  • ViRGE - Monday, June 4, 2007 - link

    On hardware assisted encoding:

    It's actually worse than you think. Both ATI and Nvidia go back to 2004 with promises of this for the R420 and NV40 respectively. I have product overviews and press slideshows from both companies touting hardware encoding of MPEG 1, 2, and 4. Neither company has or will be delivering on this.

    I fear GPU-based physics is going to go the same way.
  • 7oby - Monday, June 4, 2007 - link">


    ATI Avivo HD video and display architecture present in HD 2900, 2600, 2400
    UVD (Unified Video Decoder) only present in HD 2600, 2400

    Thus pretty much the same as with nvidia

    Pure Video HD architecture present in G80, G84, G86
    VP2 (for full H.264 decode) only present in G84, G86
  • Chunga29 - Monday, June 4, 2007 - link

    Am I the only one that wonders when that PDF was last updated?
  • PrinceGaz - Monday, June 4, 2007 - link

    Well, given that certain review sites which checked their facts before writing their review of the HD 2900 mentioned that it specifically did not include dedicated UVD hardware (instead relying on the shaders to perform the same task because there are enough of them to do it), it would seem the information was available at least a few days before the NDA expired.
  • Chunga29 - Monday, June 4, 2007 - link

    Care to enlighten as to which "certain sites checked their facts"? I saw Firingsquad (well, skimmed it), and Tom's and a few others. I'm not sure who got it right at the start, but someone above linked at least four other places that got the UVD informations wrong. Tech Report, AnandTech, Tom's Hardware, and Firingsquad are all (well, not so much FS) pretty major sites, and they don't usually make mistakes of this sort unless someone gave them wrong info. Then there's Gigabyte and a couple other manufacturers that put UVD on 2900 boxes, I think.
  • Goty - Monday, June 4, 2007 - link">

Log in

Don't have an account? Sign up now