Video & Movies: The Video Codec Engine, UVD3, & Steady Video 2.0

When Intel introduced the Sandy Bridge architecture one of their big additions was Quick Sync, their name for their hardware H.264 encoder. By combining a specialized fixed function encoder with some GPU-based processing Intel was able to create a small, highly efficient H.264 encoder that had quality that was as good as or better than AMD and NVIDIA’s GPU based encoders that at the same time was 2x to 4x faster and consumed a fraction of the power. Quick Sync made real-time H.264 encoding practical on even low-power devices, and made GPU encoding redundant at the time. AMD of course isn’t one to sit idle, and they have been hard at work at their own implementation of that technology: the Video Codec Engine (VCE).

The introduction of VCE brings up a very interesting point for discussing the organization of AMD. As both a CPU and a GPU company the line between the two divisions and their technologies often blurs, and Fusion has practically made this mandatory. When AMD wants to implement a feature, is it a GPU feature, a CPU feature, or perhaps it’s both? Intel implemented Quick Sync as a CPU company, but does that mean hardware H.264 encoders are a CPU feature? AMD says no. Hardware H.264 encoders are a GPU feature.

As such VCE is being added to the mix from the GPU side, meaning it shows up first here on the Southern Islands series. Fundamentally VCE is very similar to Quick Sync – it’s based on what you can accomplish with the addition of a fixed function encoder – but AMD takes the concept much further to take full advantage of what the compute side of GCN can do. In “Full Mode” VCE behaves exactly like Quick Sync, in which virtually every step of the H.264 encoding process is handled by fixed function hardware. Just like Quick Sync Full Mode is fast and energy efficient. But it doesn’t make significant use of the rest of the GPU.

Hybrid Mode is where AMD takes things a step further, by throwing the compute resources of the GPU back into the mix. In Hybrid Mode only Entropy Encode is handled by fixed function hardware (this being a highly serial process that was ill suited to a GPU) with all the other steps being handled by the flexible hardware of the GPU. The end goal of Hybrid Mode is that as these other steps are well suited to being done on a GPU, Hybrid Mode will be much faster than even the highly optimized fixed function hardware of Full Mode. Full Mode is already faster than real time – Hybrid Mode should be faster yet.

With VCE AMD is also targeting Quick Sync’s weaknesses regardless of the mode used. Quick Sync has limited tuning capabilities which impacts the quality of the resulting encode. AMD is going to offer more tuning capabilities to allow for a wider range of compression quality.  We don’t expect that it will be up to the quality standards of X264 and other pure-software encoders that can generate archival quality encodes, but if AMD is right it should be closer to archival quality than Quick Sync was.

The catch right now is that VCE is so new that we can’t test it. The hardware is there and we’re told it works, but the software support for it is lacking as none of AMD’s partners have added support for it yet. On the positive side this means we’ll be able to test it in-depth once the software is ready as opposed to quickly testing it in time for this review, however the downside is that we cannot comment on the speed or quality at this time. Though with the 7970 not launching until next year, there’s time for software support to be worked out before the first Southern Islands card ever goes on sale.

Moving on, while encoding has been significantly overhauled decoding will remain largely the same. AMD doesn’t refer to the Universal Video Decoder on Tahiti as UVD3, but the specifications match UVD3 as we’ve seen on Cayman so we believe it to be the same decoder. The quality may have been slightly improved as AMD is telling us they’ve scored 200 on HQV 2.0 – the last time we scored them they were at 197 – but HQV is a partially subjective benchmark.

Finally, with Southern Islands AMD is introducing Steady Video 2.0, thesuccessor to Steady Video that was introduced with the Llano APU last year. Steady Video 2.0 adds support for interlaced and letter/pillar boxed content, along with a general increase in the effectiveness of the steadying effect. What makes this particularly interesting is that Steady Video implements a new GCN architecture instruction, Quad Sum of Absolute Differences (QSAD), which combines regular SAD operations with alignment operations into a single instruction. As a result AMD can now execute SADs at a much higher rate so long as they can be organized into QSADs, which is one of the principle reasons that AMD was able to improve Steady Video as it’s a SAD-heavy operation. QSAD extends to more than just Steady Video (AMD noted that it’s also good for other image analysis operations), but Steady Video is going to be the premiere use for it.

Display Tech, Cont: Fast HDMI PCI Express 3.0: More Bandwidth For Compute
Comments Locked

292 Comments

View All Comments

  • Esbornia - Thursday, December 22, 2011 - link

    Fan boy much?
  • CeriseCogburn - Thursday, March 8, 2012 - link

    Finally, piroroadkill, Esbornia - the gentleman ericore merely stated what all the articles here have done as analysis while the radeonite fans repeated it ad infinitum screaming nvidia's giant core count doesn't give the percentage increase it should considering transistor increase.
    Now, when it's amd's turn, we get ericore under 3 attacks in a row...---
    So you three all take it back concerning fermi ?
  • maverickuw - Thursday, December 22, 2011 - link

    I want to know when the 7950 will come out and hopefully it'll come out at $400
  • duploxxx - Thursday, December 22, 2011 - link

    Only the fact that ATI is able to bring a new architecture on a new process and result in such a performance increase for that power consumption is a clear winner.

    looking at the past with Fermy 1st launch and even Cayman VLIW4 they had much more issues to start with.

    nice job, while probably nv680 will be more performing it will take them at least a while to release that product and it will need to be also huge in size.
  • ecuador - Thursday, December 22, 2011 - link

    Nice review, although I really think testing 1680x1050 for a $550 is a big waste of time, which could have to perhaps multi-monitor testing etc.
  • Esbornia - Thursday, December 22, 2011 - link

    Its Anand you should expect this kind of shiet.
  • Ryan Smith - Thursday, December 22, 2011 - link

    In this case the purpose of 1680 is to allow us to draw comparisons to low-end cards and older cards, which is something we consider to be important. The 8800GT and 3870 in particular do not offer meaningful performance at 1920.
  • poohbear - Thursday, December 22, 2011 - link

    Why do you bencmark @ 1920x1200 resolution? according to the Steam December survey only 8% of gamers have that resolution, whereas 24% have 1920x1080 and 18% use 1680x1050 (the 2 most popular). Also, minimum FPS would be nice to know in your benchmarks, that is really useful for us! just a heads up for next time u benchmark a video card! Otherwise nice review! lotsa good info at the beginning!:)
  • Galcobar - Thursday, December 22, 2011 - link

    Page 4, comments section.
  • Esbornia - Thursday, December 22, 2011 - link

    They dont want to show the improvements on min FPS cause they hate AMD, you should know that already.

Log in

Don't have an account? Sign up now