Intel’s Quick Sync Technology

In recent years video transcoding has become one of the most widespread consumers of CPU power. The popularity of YouTube alone has turned nearly everyone with a webcam into a producer, and every PC into a video editing station. The mobile revolution hasn’t slowed things down either. No smartphone can play full bitrate/resolution 1080p content from a Blu-ray disc, so if you want to carry your best quality movies and TV shows with you, you’ll have to transcode to a more compressed format. The same goes for the new wave of tablets.

At a high level, video transcoding involves taking a compressed video stream and further compressing it to better match the storage and decoding abilities of a target device. The reason this is transcoding and not encoding is because the source format is almost always already encoded in some sort of a compressed format. The most common, these days, being H.264/AVC.

Transcoding is a particularly CPU intensive task because of the three dimensional nature of the compression. Each individual frame within a video can be compressed; however, since sequential frames of video typically have many of the same elements, video compression algorithms look at data that’s repeated temporally as well as spatially.

I remember sitting in a hotel room in Times Square while Godfrey Cheng and Matthew Witheiler of ATI explained to me the challenges of decoding HD-DVD and Blu-ray content. ATI was about to unveil hardware acceleration for some of the stages of the H.264 decoding pipeline. Full hardware decode acceleration wouldn’t come for another year at that point.

The advent of fixed function video decode in modern GPUs is important because it helped enable GPU accelerated transcoding. The first step of the video transcode process is to first decode the source video. Since transcoding involves taking a video already in a compressed format and encoding it in a new format, hardware accelerated video decode is key. How fast a decode engine is has a tremendous impact on how fast a hardware accelerated video encode can run. This is true for two reasons.

First, unlike in a playback scenario where you only need to decode faster than the frame rate of the video, when transcoding the video decode engine can run as fast as possible. The faster frames can be decoded, the faster they can be fed to the transcode engine. The second and less obvious point is that some of the hardware you need to accelerate video encoding is already present in a video decode engine (e.g. iDCT/DCT hardware).

With video transcoding as a feature of Sandy Bridge’s GPU, Intel beefed up the video decode engine from what it had in Clarkdale. In the first generation Core series processors, video decode acceleration was split between fixed function decode hardware and the GPU’s EU array. With Sandy Bridge and the second generation Core CPUs, video decoding is done entirely in fixed function hardware. This is not ideal from a flexibility standpoint (e.g. newer video codecs can’t be fully hardware accelerated on existing hardware), but it is the most efficient method to build a video decoder from a power and performance standpoint. Both AMD and NVIDIA have fixed function video decode hardware in their GPUs now; neither rely on the shader cores to accelerate video decode.

The resulting hardware is both performance and power efficient. To test the performance of the decode engine I launched multiple instances of a 15Mbps 1080p high profile H.264 video running at 23.976 fps. I kept launching instances of the video until the system could no longer maintain full frame rate in all of the simultaneous streams. The graph below shows the maximum number of streams I could run in parallel:

  Intel Core i5-2500K NVIDIA GeForce GTX 460 AMD Radeon HD 6870
Number of Parallel 1080p HP Streams 5 streams 3 streams 1 stream

AMD’s Radeon HD 6000 series GPUs can only manage a single high profile, 1080p H.264 stream, which is perfectly sufficient for video playback. NVIDIA’s GeForce GTX 460 does much better; it could handle three simultaneous streams. Sandy Bridge however takes the cake as a single Core i5-2500K can decode five streams in tandem.

The Sandy Bridge decoder is likely helped by the very large (and high bandwidth) L3 cache connected to it. This is the first advantage Intel has in what it calls its Quick Sync technology: a very fast decode engine.

The decode engine is also reused during the actual encode phase. Once frames of the source video are decoded, they are actually fed to the programmable EU array to be split apart and prepared for transcoding. The data in each frame is transformed from the spatial domain (location of each pixel) to the frequency domain (how often pixels of a certain color appear); this is done by the use of a discrete cosine transform. You may remember that inverse discrete cosine transform hardware is necessary to decode video; well, that same hardware is useful in the domain transform needed when transcoding.

Motion search, the most compute intensive part of the transcode process, is done in the EU array. It's the combination of the fast decoder, the EU array, and fixed function hardware that make up Intel's Quick Sync engine.

A Near-Perfect HTPC Quick Sync: The Best Way to Transcode
POST A COMMENT

282 Comments

View All Comments

  • omelet - Tuesday, January 11, 2011 - link

    For almost any game, the resolution will not affect the stress on the CPU. It is no harder for a CPU to play the game at 2560x1600 than it is to play at 1024x768, so to ensure that the benchmark is CPU-limited, low resolutions are chosen.

    For instance, the i5 2500k gets ~65fps in the Starcraft test, which is run at 1024x768. The i5 2500k would also be capable of ~65fps at 2560x1600, but your graphics card might not be at that resolution.

    Since this is a review for a CPU, not for graphics cards, the lower resolution is used, so we know what the limitation is for just the CPU. If you want to know what resolution you can play at, look at graphics card reviews.
    Reply
  • Tom - Sunday, January 30, 2011 - link

    Which is why the tests have limited real world value. Skewing the tests to maximize the cpu differences makes new cpus look impressive, but it doesn't show the reality that the new cpu isn't needed in the real world for most games. Reply
  • Oyster - Monday, January 03, 2011 - link

    Maybe I missed this in the review, Anand, but can you please confirm that SB and SB-E will require quad-channel memory? Additionally, will it be possible to run dual-channel memory on these new motherboards? I guess I want to save money because I already have 8GB of dual-channel RAM :).

    Thanks for the great review!
    Reply
  • CharonPDX - Monday, January 03, 2011 - link

    You can confirm it from the photos of it only using two DIMMs in photo. Reply
  • JumpingJack - Monday, January 03, 2011 - link

    This has been discussed in great detail. The i7, i3, and i5 2XXX series is dual channel. The rumor mill is abound with SB-E having quad channel, but I don't recall seen anything official from Intel on this point. Reply
  • 8steve8 - Monday, January 03, 2011 - link

    the K processors have the much better IGP and a variable multiplier, but to use the improved IGP you need an H67 chipset, which doesn't support changing the multiplier? Reply
  • ViRGE - Monday, January 03, 2011 - link

    CPU Multiplier: Yes, H67 cannot change the CPU multiplier

    GPU Multiplier: No, even H67 can change the GPU multiplier
    Reply
  • mczak - Monday, January 03, 2011 - link

    I wonder why though? Is this just officially? I can't really see a good technical reason why CPU OC would work with P67 but not H67 - it is just turbo going up some more steps after all. Maybe board manufacturers can find a way around that?
    Or is this not really linked to the chipset but rather if the IGP is enabled (which after all also is linked to turbo)?
    Reply
  • Rick83 - Monday, January 03, 2011 - link

    I just checked the manual to MSI's 7676 Mainboard (high-end H67) and it lists cpu core multiplier in the bios (page 3-7 of the manual, only limitation mentioned is that of CPU support), with nothing grayed out and overclockability a feature. As this is the 1.1 Version, I think someone misunderstood something....

    Unless MSI has messed up its Manual after all and just reused the P67 Manual.... Still, the focus on over-clocking would be most ridiculous.
    Reply
  • Rick83 - Monday, January 03, 2011 - link

    also, there is this:http://www.eteknix.com/previews/foxconn-h67a-s-h67...

    Where the unlocked multiplier is specifically mentioned as a feature of the H67 board.
    So I think anandtech got it wrong here....
    Reply

Log in

Don't have an account? Sign up now