Sign in with
Sign up | Sign in

Intel's Video Playback Results Compared To Ours

ARM Vs. x86: The Secret Behind Intel Atom's Efficiency
By , Chris Angelini

We then had the chance to look at power consumption during media playback.

Microsoft Surface

FPS
Platform (W)
CPU (W)
GPU (W)
Memory (W)
Panel Backlight (W)
Everything Else (W)
Local 1080p H.264 @ 20 Mb/s
30
4.21
0.35
0.51
0.58
0.88
1.90
Local 1080p H.264 @ 20 Mb/s (Split Screen)
30
4.87
0.57
0.59
0.61
1.11
2.00
Stream HTML5 Playback
30
5.37
0.69
0.78
0.89
0.90
2.10
Stream HTML5 Playback (Split Screen)
30
6.1
0.92
0.92
0.94
1.10
2.22
Acer W510

FPS
Platform (W)
CPU (W)
GPU (W)
Memory (W)
Panel Backlight (W)
Everything Else (W)
Local 1080p H.264 @ 20 Mb/s30
3.500.17
0.37
0.45
0.89
1.62
Local 1080p H.264 @ 20 Mb/s (Split Screen)30
4.03
0.37
0.33
0.45
1.19
1.69
Stream HTML5 Playback30
3.95
0.30
0.39
0.47
0.98
1.81
Stream HTML5 Playback (Split Screen)30
4.77
0.68
0.34
0.47
1.27
2.01
Local Stress Test (+McAfee)
29.8
5.93
1.39
0.42
0.56
1.19
2.37
Stream HTML5 Stress Test (+McAfee)
29.8
6.00
1.29
0.43
0.59
1.27
2.43


It's interesting to look at the impact of adding a McAfee antivirus scan to the video playback workload. Due to security flaws in older versions of Windows Media Player, the software has to scan the video file itself for malware. On our Acer tablet, we see an initial stutter while opening the video clip (while it's being scanned, resulting in dropped frames). Things smooth out after that, though.

When it comes to total platform power consumption, Acer's W510 has the edge over Microsoft's Surface. Once again, comparing processor power consumption, we know that the Tegra 3 offers superior idle results thanks to its 4-PLUS-1 architecture. But the moment a workload is applied, the Atom fares better. 

The GPU consumption column is also interesting. Intel's Atom uses less power during local and HTML5-based video playback, and when the screen is split, the difference is even greater. It's not clear whether this is related to the fixed-function hardware acceleration for H.264, or some other variable (like drivers, where Nvidia could be expected to have an advantage). 

As we noted on the previous page, there appears to be magic happening on Intel's memory controller. From best- to worst-case scenario (including a workload that wasn't even run on Tegra 3), the Atom requires a 31% increase in power; the Tegra comes close to doubling its power consumption from its best- to worst-case scenario. As the workload gets more demanding and the tablet isn't reading from memory in a purely linear fashion, Intel's two 32-bit controllers maintain lower consumption. Nvidia's single-channel controller, operating at higher data rates, isn't able to follow suit.

Verifying Intel's Numbers, In-House

Frankly, it's going to be difficult for anyone to replicate Intel's lab work, based on the equipment we saw set up in Santa Clara. But the numbers presented by Intel seem plausible. With a smaller 26.6 Wh battery in the Acer W510, plus the keyboard dock (around 53.2 Wh), 1080p video should play back for 15.2 hours based on the 3.5 W figure. My 1080p test lasted for 15 hours and 37 minutes (with the volume at 10%). So, again, the results are believable.

In contrast, Microsoft's Surface is reported as requiring 4.21 W. With its 31.5 Wh battery, that'd theoretically be up to 7.48 hours of playback. In Microsoft Surface Review, Part 2: Battery Life, Multi-Monitor, And More, Andrew measured 7 hours and 10 minutes at maximum brightness (4.4 W) and 10 hours at 200 nits with the Wi-Fi radio disabled (3.15 W). This really shows how much the display and other platform components can affect run time, and how much bit rate appears to affect the Tegra 3. What do we mean? Well, our in-house test file is a 6 Mb/s H.264-encoded file running at 720p, as opposed to Intel's 20 Mb/s test at 1080p.

We get 8.95 hours from an iPad 2 (25 Wh battery) and 7.92 hours from a third-gen iPad (42.5 Wh battery). This puts power consumption at 2.8 W and 5.37 W for each device, respectively, at maximum brightness. At 200 nits, we get 12.35 hours from the iPad 2 and 11.28 hours from the third-gen iPad, translating to 2.02 W and 3.77 W during the video workload, again, respectively. This means that the third-gen iPad appears to consume more power playing back a 6 Mb/s 720p video clip than the Atom with a 20 Mb/s 1080p file.

Under those same Tom’s Hardware 720p test conditions, the Tegra 3-powered Asus Transformer Prime (25 Wh battery) yields 8.33 hours at maximum brightness (3.00 W) and 10.8 hours at 200 nits (2.31 W). Compared directly against the Surface, this suggests that the Transformer Prime is thriftier with power, likely due to a combination of Android versus Windows RT and differences in both devices' screens. 

Google's Nexus 10 is advertised as doing nine hours of video playback from a 33.75 Wh battery, which calculates out to 3.75 W for a 4 MP display. We’ll be revising the Nexus 10 numbers later.

Display all 65 comments.
This thread is closed for comments
Top Comments
  • 17 Hide
    Novuake , December 24, 2012 8:06 PM
    Excellent! Was wondering about this for some time. Also made the mistake of thinking Intel was behind in the mobile space... Well done Toms.
  • 16 Hide
    tomfreak , December 24, 2012 9:47 PM
    of all the ARM types, u took one of the weakest one? I like to see the numbers vs Qualcomm krait and Apple's A6
  • 14 Hide
    AlanDang , December 24, 2012 8:59 PM
    And the Chromebook with an A15. We're looking at several other SoC's but what's empowering is how simple math can help you look at efficiency.

    But it's Christmas Eve, and sometimes there are more important things than running benchmarks and soldering wires to SoCs. ;) 
Other Comments
  • 17 Hide
    Novuake , December 24, 2012 8:06 PM
    Excellent! Was wondering about this for some time. Also made the mistake of thinking Intel was behind in the mobile space... Well done Toms.
  • 3 Hide
    tipoo , December 24, 2012 8:33 PM
    I'll be very interested to read the Cortex A15 follow up. From what I gather, if compared on the same lithography the A15 core is much larger than the A9, which likely means more power, all else being equal. It brings performance up to and sometimes over the prior generation Atom, but I wonder what power requirement sacrifices were made, if any.

    I'm thinking in the coming years, Intel vs ARM will become a more interesting battle than Intel vs AMD.
  • 3 Hide
    AlanDang , December 24, 2012 8:42 PM
    @tipoo, we're not going to hang our hat on it just yet (until we run the numbers ourselves), but A15 runs hot, which is what we hint at in our article.
  • 11 Hide
    blubbey , December 24, 2012 8:43 PM
    tipoo I'm thinking in the coming years, Intel vs ARM will become a more interesting battle than Intel vs AMD.


    I was until I saw the numbers. Intel spent $8.4 billion in 2011 ($6.6 billion in 2010 and $5.7 billion in 2009) on R&D - http://www.intc.com/intelAR2011/business/research/ - while ARM isn't worth $1b. It may take a few years but Intel are seriously massive, they'll soon be the go to guys for mobile. Plus (according to rumours) with Haswell focusing on power saving, it could be a big leap forward.
  • 5 Hide
    tipoo , December 24, 2012 8:45 PM
    AlanDang@tipoo, we're not going to hang our hat on it just yet (until we run the numbers ourselves), but A15 runs hot, which is what we hint at in our article.


    I'm guessing the same thing. So far we've only seen it in a tablet (Nexus 10), and even that with its 10 inch tablet sized battery didn't last particularly long. ARM has the distribution advantage right now, but I think once Intel gets its foot in the door it will be the 900lb gorilla in this market as well.
  • 0 Hide
    Anonymous , December 24, 2012 8:57 PM
    ARM isn't just ARM holdings, it's nVidia, Samsung, and Qualcomm just to name a few of the heavy hitters. And it should also be noted that even if your SoC is better, if the OEM integrating it is incompetent, it won't matter. I'm certain more Surface RT devices have been sold compared to the Acer W500 because it had better availability, a stronger marketing campaign, and overall is a far more solid device. Don't miss the forest for the trees.
  • 4 Hide
    tipoo , December 24, 2012 8:59 PM
    blubbeyI was until I saw the numbers. Intel spent $8.4 billion in 2011 ($6.6 billion in 2010 and $5.7 billion in 2009) on R&D - http://www.intc.com/intelAR2011/business/research/ - while ARM isn't worth $1b. It may take a few years but Intel are seriously massive, they'll soon be the go to guys for mobile. Plus (according to rumours) with Haswell focusing on power saving, it could be a big leap forward.


    Didn't Qualcomm alone overtake AMD as a chipmaker? The thing about ARM is that anyone can get a licence for the ISA and build a custom core around it, like Krait.
  • 14 Hide
    AlanDang , December 24, 2012 8:59 PM
    And the Chromebook with an A15. We're looking at several other SoC's but what's empowering is how simple math can help you look at efficiency.

    But it's Christmas Eve, and sometimes there are more important things than running benchmarks and soldering wires to SoCs. ;) 
  • -5 Hide
    richarduk , December 24, 2012 9:14 PM
    Measurements taken when running Windows. Arm and Intel chips both require different coding styles to make them preform. The way windows has been coded favours the Intel Arch. Intel chips like to lean heavy on their cache, Arm chips prefer code to do as much processing on it's data as it can using all it's registers before moving on.

    Bit like comparing a 4x4 and a sports car in a muddy field.

  • -3 Hide
    darkchazz , December 24, 2012 9:23 PM
    nvidia tegra 3 is a piece of overhyped garbage.
  • 16 Hide
    tomfreak , December 24, 2012 9:47 PM
    of all the ARM types, u took one of the weakest one? I like to see the numbers vs Qualcomm krait and Apple's A6
  • -5 Hide
    jonjonjon , December 24, 2012 9:51 PM
    down with arm! if i ever do use a tablet (wont be anytime in the foreseeable future) i want to be able to run x86 programs.
  • 8 Hide
    esrever , December 24, 2012 10:32 PM
    just another article showing how much of a piece of crap tegra is.
  • 3 Hide
    fudoka711 , December 24, 2012 10:55 PM
    I agree that it will be interesting to see ARM based tablets/phones to battle with upcoming Intel Atom cpu's in tablets (and phones?). Intel's really stepping up their game and it'll just force ARM to step up theirs.

    We're already at quad-core ARM SoC's running at up to 1.7ghz. My understanding is that they won't be able to run too much faster anymore and will instead have to do more work per cycle. I think that's where Atom has the advantage in this case, which is why they can run slower but still accomplish the same amount of work with less power (but not faster).

    If only this would translate into the Desktop/Laptop sector. We haven't had huge performance gains in the longest time. I miss the old days of Athlon 64...
  • 8 Hide
    Anonymous , December 24, 2012 11:06 PM
    Once again, Intel manages to sort of tie with a middle-of-the-pack last-generation ARM CPU, well done.

    Tegra 3 is junk and everybody knows it, bring on the Samsung Chromebook or a comparable tablet running an A15, and run Linux on them. Or rather than just waiting for Tom's to do it, check out the benchmarks on Phoronix that show the A15 eating the Atom for breakfast...
  • 5 Hide
    AlanDang , December 24, 2012 11:30 PM
    @jessica. Phoronix tested the older Atom which we note has the same name but nowhere near the same performance or energy efficiency. Also keep in mind that Phoronix didn't actually try to run their benchmarks off the battery. A15 is fast, but the performance isn't free.

    The advertised battery life on a Chromebook is very telling. It gets 6.5 hours of web browsing with a 30 watt-hour battery, so it's drawing 4.62W under that workload. This Atom tablet is drawing closer to 3.11W under an average web browsing workload and the Tegra 3 is drawing about 3.9W. We're looking at Snapdragon next and then A15, but I think everyone's going to be surprised once they look at the actual numbers when you're running apps other than Phoronix's benchmarks.
  • 2 Hide
    Anonymous , December 24, 2012 11:35 PM
    Alan: But the new mobile Atom is slower than the old netbook Atom, which is why you never see them in the same benchmark. Those power savings weren't free, and yet the A15 still destroys either Atom.
  • 7 Hide
    AlanDang , December 25, 2012 12:35 AM
    Geekbench would argue differently.

    Atom Z530 (the "Z-class" Atom Phoronix tested).
    http://browser.primatelabs.com/geekbench2/search?utf8=%E2%9C%93&q=z530

    Atom D525 (the fastest netbook Atom Phoronix tested, which beats Exynos Dual in some applications)
    http://browser.primatelabs.com/geekbench2/search?utf8=%E2%9C%93&q=d525

    http://www.phoronix.com/scan.php?page=article&item=samsung_exynos5_dual&num=5

    Atom Z2760
    http://browser.primatelabs.com/geekbench2/search?utf8=%E2%9C%93&q=z2760

    The Atom D525 had a TDP of 15W in 2010. The Atom Z2760 has the same performance with a TDP of
  • 8 Hide
    AlanDang , December 25, 2012 12:37 AM
    less than 2W. The Exynos has a TDP of 4W.

    If the A15 is 2x the power consumption, is it consistently 2x as fast?
  • -4 Hide
    Anonymous , December 25, 2012 12:51 AM
    Jessica... you couldn't be more wrong. Good grief!
Display more comments