Intel's Video Playback Results Compared To Ours
We then had the chance to look at power consumption during media playback.
| Microsoft Surface | |||||||
|---|---|---|---|---|---|---|---|
| Row 0 - Cell 0 | 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 | |||||||
|---|---|---|---|---|---|---|---|
| Row 0 - Cell 0 | FPS | Platform (W) | CPU (W) | GPU (W) | Memory (W) | Panel Backlight (W) | Everything Else (W) |
| Local 1080p H.264 @ 20 Mb/s | 30 | 3.50 | 0.17 | 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 Playback | 30 | 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.
