Power Consumption

There's a lot of uncertainty around whether or not Kepler is suitable for ultra low power operation, especially given that we've only seen it in relatively high TDP (compared to tablets/smartphones) PCs. NVIDIA hoped to put those concerns to rest with a quick GLBenchmark 2.7 demo at Siggraph. The demo pitted an iPad 4 against a Logan development platform, with Logan's Kepler GPU clocked low enough to equal the performance of the iPad 4. The low clock speed does put Kepler at an advantage as it can run at a lower voltage as well, so the comparison is definitely one you'd expect NVIDIA to win. 

Unlike Tegra 3, Logan includes a single voltage rail that feeds just the GPU. NVIDIA instrumented this voltage rail and measured power consumption while running the offscreen 1080p T-Rex HD test in GLB2.7. Isolating GPU power alone, NVIDIA measured around 900mW for Logan's Kepler implementation running at iPad 4 performance levels (potentially as little as 1/5 of Logan's peak performance). NVIDIA also attempted to find and isolate the GPU power rail going into Apple's A6X (using a similar approach to what we documented here), and came up with an average GPU power value of around 2.6W. 

I won't focus too much on the GPU power comparison as I don't know what else (if anything) Apple hangs off of its GPU power rail, but the most important takeaway here is that Kepler seems capable of scaling down to below 1W. In reality NVIDIA wouldn't ship Logan with a < 1W Kepler implementation, so we'll likely see higher performance (and power consumption) in shipping devices. If these numbers are believable, you could see roughly 2x the performance of an iPad 4 in a Logan based smartphone, and 4 - 5x the performance of an iPad 4 in a Logan tablet - in as little as 12 months from now if NVIDIA can ship this thing on time.

If NVIDIA's A6X power comparison is truly apples-to-apples, then it would be a huge testament to the power efficiency of NVIDIA's mobile Kepler architecture. Given the recent announcement of NVIDIA's willingness to license Kepler IP to any company who wants it, this demo seems very well planned. 

NVIDIA did some work to make Kepler suitable for low power, but it's my understanding that the underlying architecture isn't vastly different from what we have in notebooks and desktops today. Mobile Kepler retains all of the graphics features as its bigger counterparts, although I'm guessing things like FP64 CUDA cores are gone.

Final Words

For the past couple of years we've been talking about a point in the future when it'll be possible to start playing console class games (Xbox 360/PS3) on mobile devices. We're almost there. The move to Kepler with Logan is a big deal for NVIDIA. It finally modernizes NVIDIA's ultra mobile GPU, bringing graphics API partity to everything from smartphones to high-end desktop PCs. This is a huge step for game developers looking to target multiple platforms. It's also a big deal for mobile OS vendors and device makers looking to capitalize on gaming as a way of encouraging future smartphone and tablet upgrades. As smartphone and tablet upgrade cycles slow down, pushing high-end gaming to customers will become a more attractive option for device makers.

Logan is expected to ship in the first half of 2014. With early silicon back now, I think 10 - 12 months from now is a reasonable estimate. There is the unavoidable fact that we haven't even seen Tegra 4 devices on the market yet and NVIDIA is already talking about Logan. Everything I've heard points to Tegra 4 being on the schedule for a bunch of device wins, but delays on NVIDIA's part forced it to be designed out. Other than drumming up IP licensing business, I wonder if that's another reason why we're seeing a very public demo of Logan now - to show the health of early silicon. There's also a concern about process node. Logan will likely ship at 28nm next year, just before the transition to 20nm. If NVIDIA is late with Logan, we could have another Tegra 3 situation where NVIDIA is shipping on an older process technology.

Regardless of process tech however, Kepler's power story in ultra mobile seems great. I really didn't believe the GLBenchmark data when I first saw it. I showed it to Ryan Smith, our Senior GPU Editor, and even he didn't believe it. If NVIDIA is indeed able to get iPad 4 levels of graphics performance at less than 1W (and presumably much more performance in the 2.5 - 5W range) it looks like Kepler will do extremely well in mobile.

Whatever NVIDIA's reasons for showing off Logan now, the result is something that I'm very excited about. A mobile SoC with NVIDIA's latest GPU architecture is exactly what we've been waiting for. 

Comments Locked


View All Comments

  • ltcommanderdata - Wednesday, July 24, 2013 - link

    Even with Keplar's advanced features support, we'll have to see how much effort developers put into optimizing games for Keplar. Most mobile games are developed first for iOS and then ported over to other platforms.


    EA just announced that the iOS App Store is EA's biggest retail distribution channel, bigger than other mobile app stores, their own Origin and other PC and console channels. So games being designed for and optimized for iOS/PowerVR GPUs are a given, because that's where the market is. nVidia will have to actively convince mobile developers to support their additional features.

    What's more, I don't believe any mobile OS officially supports any version of desktop OpenGL much less OpenGL 4.4. Android 4.3 just announced incorporation of OpenGL ES 3.0. Rather than OpenGL 4.4, the most common implementations will likely have Keplar additional features exposed as a bunch of OpenGL ES 3.0 extensions, which may also limit adoption.
  • lmcd - Wednesday, July 24, 2013 - link

    It isn't like EA is popular with hardcore gamers, so no one truly uses Origin. Their console games mostly suck, their PC games mostly suck.

    Who is surprised?
  • Scannall - Thursday, July 25, 2013 - link

    I'd just point out that hard core gamers are really a niche market. World wide sales of the Xbox 360 and the PS4 over 8 years is about 70 million each. Not exactly huge.
  • Refuge - Thursday, July 25, 2013 - link

    Thank you... Someone who understands!

    To you good sir... I agree. :)
  • Kill16by9TN - Friday, July 26, 2013 - link

    Johnny's name is KeplEer, not KeplAr!
  • prophet001 - Monday, July 29, 2013 - link

    Kepleer hunh.
  • eanazag - Wednesday, July 24, 2013 - link

    I am in agreement. Features are just as much a part of the conversation as power and performance. The software side should also be good as Nvidia has done a good job with this. Software/drivers being my biggest gripe for Intel.

    This is definitely drumming up business for their IP licensing. Squarely aimed at Apple. Intel should take note also because Atom's graphics have always sucked.

    So this is big and good news for customers. Thinking smartphone only is too small.

    My question is does this do well power-wise for video. We will have to wait and see. I'm glad to see Nvidia hanging around when the idea of a GPU only company hanging around this long was pretty pessimistic. They have been good at redefining themselves, which is very tough for companies. (cough, cough Kodak and HP with Palm)
  • Refuge - Thursday, July 25, 2013 - link

    Their support may be great, but nobody is going to program for Keplar features if they don't hold a solid market share, and I mean VERY solid, mirroring Apple iPhones. I use them as an example because while Androids hold most of the market, they are a mixed back of fragmentation.

    Also, the new Atoms coming out have almost nothing in common with the old Atoms. People keep making references to the old ones, which I agree were worthless even for a netbook, but the new ones I actually have some high hopes for.
  • michael2k - Wednesday, July 24, 2013 - link

    Correct, I don't think Kepler is all that special. Nvidia has lost a lot of credibility in the mobile space by being unable to take the crown for three years straight. In any case, if you're going to be quoting Kepler PR, this is PowerVR's list of accomplishments for the 6 series GPU:

    Delivering the best performance in both GFLOPS/mm2 and GFLOPS/mW, PowerVR Series6 GPUs can deliver 20x or more of the performance of current generation GPU cores targeting comparable markets. This is enabled by an architecture that is around 5x more efficient than previous generations. => At the same power level expect 5x the perf, approximately 350GF

    All members of the Series6 family support all features of the latest graphics APIs including OpenGL ES 'Halti'*, OpenGL 3.x/4.x, OpenCL 1.x and DirectX10 with certain family members extending their capabilities to full WHQL-compliant DirectX11.1 functionality. => Just like Logan

    PowerVR Series6 GPU cores are available for licensing now. => Posted last January! Expect then to see this in SoC this year, not years from now.
  • lmcd - Wednesday, July 24, 2013 - link

    Whaddya mean? Kepler doesn't scale to those either. It only clockspeed scales and is probably close to headroom, while adding another core will make the die WAY too big.

    No, you're wrong. Also, ES 3.0 is pretty damn close to 4.2 compliance. So don't act like it's a huge jump.

    Finally, don't forget AMD's GCN is competing in this space and has proven itself very relevant.

Log in

Don't have an account? Sign up now