Mobile Sandy Bridge QuickSync and 3DMarks

Anand has provided plenty of coverage of transcoding quality in the desktop SNB review, using Arcsoft’s Media Encoder 7. For the mobile side of things, we’ll turn to CyberLink’s MediaEspresso 6—a similar package that’s useful for quick encodes of movies for YouTube or mobile device consumption. NVIDIA has been touting the benefits of GPU acceleration for such tasks for over a year now, with CUDA making a fairly decent showing. MediaEspresso also supports CUDA acceleration, making for a nice head-to-head, though I’m limited to hardware that I still have on hand.

For the encoding test, I’ve grabbed two other recently reviewed notebooks to show how they compare to Sandy Bridge. The first is ASUS’ mainstream N53JF notebook, sporting an i5-460M and GT 425M GPU. For the higher performance notebook offering, we’ve got ASUS’ G73Jw with i7-740QM and GTX 460M. [Ed: Sorry for the delay in shipping it back, ASUS—it will go out this week now that we’re done with Sandy Bridge testing!] I used a 720p shot with an iPod Touch and transcoded it to a 2Mb 720p YouTube compatible stream. MediaEspresso also has some video quality enhancement features available, dubbed TrueTheater AutoLight, Denoise, and HD. I ran the transcode tests with and without the enhancements enabled, with and without QuickSync/GPU acceleration. Since MediaEspresso also supports ATI GPUs, I tossed in results from my i7-920 with CrossFire HD 5850 as well.

Accelerated MediaEspresso Encoding

CPU-Based MediaEspresso Encoding

Accelerated MediaEspresso Enhanced Encoding

CPU-Based MediaEspresso Enhanced Encoding

First things first, I’d say it’s fair to state that the GPU acceleration for AMD GPUs (at least in this particular instance) isn’t as good as NVIDIA’s CUDA or Intel’s QuickSync. Perhaps future driver, hardware, and/or software updates will change the picture, but the HD 5850 cards in my desktop fail to impress. The CUDA results for GTX 460M are quite good, while the GT 425M was roughly on par with CPU encoding on a quad-core (plus Hyper-Threading) processor. Finally, Intel’s Sandy Bridge manages to easily eclipse any of the other systems—with or without QuickSync.

Using pure CPU encoding, the 2820QM finishes the transcode in 15% less time than a desktop i7-920, and 44% less time than the i7-740QM. Enabling all of the extra TrueTheater enhancements definitely has an impact on performance (and depending on the video source may or may not be worthwhile). Sandy Bridge still required 8% less time than i7-920, and 36% less time than i7-740QM, never mind the i5-460M that requires 134% longer to accomplish the same task.

Switch on all of the GPU acceleration support (including QuickSync, which isn’t technically a GPU feature) and all of the times drop, some substantially. The basic transcode on SNB finishes in a blisteringly fast 10 seconds—this is a 1:33 minute clip with 30FPS content, so the transcode happens at roughly 280FPS (wow!). GTX 260M comes in next at 17 seconds (174FPS), then CrossFire 5850 ends up needing three times longer than SNB and almost twice as long as the mobile GTX 460M, and GT 425M brings up the rear at twice the time of the HD 5850. With the TrueTheater features enabled, the CPU appears to do a lot more work and the GTX 460M and Sandy Bridge are both over an order of magnitude slower.

This is obviously a huge in for Intel, but of course it all depends on how often you happen to transcode videos—and how patient you happen to be. I do it seldom enough that even running encodes on my old quad-core Kentsfield CPU doesn’t particularly bother me; I just set up the transcodes in TMPGEnc Express and walk away, and they’re usually done when I return. If on the other hand you’re the type that lives in the social networks and Twitter feeds, being able to get your video up on YouTube five to ten times faster (without a significant loss in quality, at least based on my iPod Touch experience) is definitely useful.

Futuremark 3DMark Vantage

Futuremark 3DMark06

Futuremark 3DMark05

One final item to quickly cover is synthetic graphics performance, courtesy of 3DMark. Sandy Bridge places in the middle of the pack, and obviously desktop solutions are far out of reach for the time being, but according to 3DMark we could see performance actually surpass some of the entry-level GPUs. Maybe 3DMark just has heavy optimizations from Intel…then again, maybe they actually do have a GPU that can compete.

Mobile Sandy Bridge Application Performance Mobile Sandy Bridge Gaming Performance
POST A COMMENT

66 Comments

View All Comments

  • tipoo - Monday, January 03, 2011 - link

    Sorry if I missed this somewhere in the review, but does the graphics component support OpenCL? Reply
  • RyuDeshi - Monday, January 03, 2011 - link

    Second to last paragraph on the "Extended compatibility and performance results:"

    "Ultimately, Sandy Bridge’s IGP is far more capable than many would have expected. Sure, it doesn’t even try to support DX11 or OpenCL, but at least for gaming DX11 is typically too much for even midrange GPUs."
    Reply
  • CharonPDX - Monday, January 03, 2011 - link

    An Intel rep has said that Sandy Bridge will support OpenCL. (http://news.cnet.com/8301-13924_3-20024079-64.html ) The trick is that it may be a combo CPU+GPU to do it. So it may not be what you are thinking by OpenCL being solely GPU, but OpenCL code should be able to run.

    And in the end, what does it matter, really, as long as it runs? As the desktop Sandy Bridge review points out, video encoding is just as fast using solely the x86 codepaths as using nVidia's CUDA or ATI's Stream.
    Reply
  • Voldenuit - Monday, January 03, 2011 - link

    OpenCL was designed from the outset to run on heterogenous resources, including CPU.

    So intel claiming that they "support" OpenCL is nothing special - they just needed the right drivers/API.

    However, don't expect OpenCL code running solely on the CPU (my guess as to how SB will handle it) to be any faster than the x86 codepath running on the same CPU.

    Checkbox feature.
    Reply
  • jameskatt - Monday, January 03, 2011 - link

    What Intel wants to do is to have the CPU run OpenCL code.

    This totally defeats the purpose of OpenCL.

    OpenCL is suppose to allow both the GPU and the CPU to run code simultaneously. This is to allow significant acceleration in running OpenCL code compared to using just the CPU.

    Sure. OpenCL code will run. But it will run MORE SLOWLY than with a discrete GPU. And the 16 GPUs in Sandy Bridge will be wasted.

    Intel's Sandy Bridge has non-programmable GPUs. This is a serious limitation and deal killer when it comes to running OpenCL code.

    I expect Apple to continue use nVidia's or AMD's discrete GPUs with the MacBooks and Mac Book Pros.

    This is very disappointing. It shows that Intel still doesn't have the talent to produce decent GPUs.
    Reply
  • PlasmaBomb - Monday, January 03, 2011 - link

    And the 16 GPUs in Sandy Bridge will be wasted.


    *cough* I think you mean 12 EU *cough*
    Reply
  • Guspaz - Monday, January 03, 2011 - link

    <i>What Intel wants to do is to have the CPU run OpenCL code.

    This totally defeats the purpose of OpenCL.

    OpenCL is suppose to allow both the GPU and the CPU to run code simultaneously. This is to allow significant acceleration in running OpenCL code compared to using just the CPU.</i>

    No, this is the *primary* purpose of OpenCL. The goal of OpenCL is not to "allow the GPU and CPU to run code simultaneously", but to provide a single unified code path that can be used with any hardware, be it CPU or GPU. There are/were already code paths specific to each vendor/type (CUDA for nVIDIA GPUs, Stream for AMD/ATI GPUs, x86 for Intel/AMD CPUs). The problem is that fully supporting all three platforms requires three separate code paths.

    OpenCL unifies this, and allows a single codepath to be used regardless of the GPU's type or existence. You've completely misunderstood the purpose of OpenCL.
    Reply
  • Wiggy McShades - Tuesday, January 04, 2011 - link

    You need to ask what applications on a desktop actually use OpenCL in a meaningful way? Intel added hardware for media transcoding, which makes transcoding on something besides the cpu useless and that was roughly all openCL can be used for on the desktop, laptop, or cellphone.
    OpenCL is for vector calculations, AVX is for vector calculations. All four cores running AVX instructions would just be a faster choice than OpenCL on a low end gpu. Intel most likely could get sandybridge's gpu running OpenCL, but it would be pointless. OpenCL just is not a desktop feature.
    Reply
  • strikeback03 - Wednesday, January 05, 2011 - link

    Given how much money they have, I doubt Intel is lacking the "talent" to do anything they want. OpenCL execution on the GPU portion of the SNB chips was probably just not that big a deal to them, and given the number of other things (such as speed and battery life) SNB brings to the table they probably won't have trouble selling lots of these to the average consumer. Reply
  • 8steve8 - Monday, January 03, 2011 - link

    which mobile cpus on pg1 support TXT or VT-d or AES-NI or VT-x or Quick Sync? Reply

Log in

Don't have an account? Sign up now