NVIDIA's Project Logan will be using Keplar architecture on a mobile SoC. With the rather underwhelming Tegra 4, this might give them the edge they need to take lead in the mobile market. While some mobile GPUs are just gaining OpenGL ES 3.0 support, this offers OpenGL ES 3.0, OpenGL 4.4 and DirectX 11 support.Â
NVIDIA Brings Kepler, Worlds Most Advanced Graphics Architecture, to Mobile Devices
This week at SIGGRAPH, were giving a sneak peek at the GPU inside Project Logan, our next-generation, CUDA-capable mobile processor. From a graphics perspective, this is as big a milestone for mobile as the first GPU, GeForce 256, was for the PC when it was introduced 14 years ago. I am really excited to start showing it off to the world.
GeForce 256 revolutionized PC graphics and created the GPU category, with its full workstation-class feature set and industry-leading performance. Kepler delivers the same promise to mobile. It brings a huge jump in performance. It offers extraordinary power efficiency. And it provides full support for the modern GPU feature set found in the latest PC GPUs and upcoming consoles, instead of the incomplete, outdated capabilities of current mobile GPUs.
Single Architecture Across Product Line
Project Logans GPU is based on our revolutionary Kepler architecture, which forms the foundation for products that a year ago began rolling out across our notebook, desktop, workstation and supercomputer lines.
Our mission with Project Logan was to scale this technology down to the mobile power envelope  creating new configurations that we could both deploy in the Logan mobile SOC and license to others, as announced last month.
We took Keplers efficient processing cores and added a new low-power inter-unit interconnect and extensive new optimizations, both specifically for mobile. With this design, mobile Kepler uses less than one-third the power of GPUs in leading tablets, such as the iPad 4, while performing the same rendering. And it gives us enormous performance and clocking headroom to scale up.
We achieved this efficiency without compromising graphics capability. Kepler supports the full spectrum of OpenGL including the just-announced OpenGL 4.4 full-featured graphics specification and the OpenGL ES 3.0 embedded standard. It also supports DirectX 11, Microsofts latest graphics API.
New Rendering, Simulation Techniques
These advanced APIs will allow developers to use more efficient, visually compelling rendering approaches than were previously possible in mobile. They will bring amazing images to life through a variety of advanced rendering and simulation techniques, such as:
- Tessellation which creates geometry dynamically and efficiently on the GPU from high-level descriptions, sizing triangles optimally based on the users viewpoint. By comparison, fine detail in a traditional pre-generated approach is inefficient, requiring excess geometry to deal with all possible viewpoints.
- Compute-based deferred rendering which calculates the effect of all lights in a scene in a single deferred rendering pass. This OpenGL 4 capability greatly improves deferred rendering efficiency and scalability compared to current OpenGL ES-based implementations, which require an extra pass for each light source in the scene. The scalability of the compute-based approach also paves the way to even more advanced lighting models, such as using virtual points of lights to approximate global illumination effects.
- Advanced anti-aliasing and post-processing algorithms which deliver better image quality, particularly in areas of very sharp color contrast, by making multi-sampling more programmable and allowing applications to implement their own anti-aliasing filters. These also enable more efficient film-quality post-processing effects, such as motion blur and depth of field.
- Physics and simulations which simulate the physical behavior of rendered objects, such as calculating rigid-body dynamics or animating particles of smoke. This enables gamers to enjoy more detailed, fully interactive virtual worlds not previously possible on mobile devices.
Leveraging Keplers heritage as the industry-leading architecture for general purpose GPU computing, we will also bring groundbreaking compute capability and power efficiency to new mobile applications outside of graphics. Among these are computational imaging, computer vision, augmented reality and speech recognition.
You can get a sense of Keplers capabilities in this video of our demo of Ira, a startlingly realistic digital model of a human head generated in real time. Our CEO, Jen-Hsun Huang, introduced Ira earlier this year on the stage of our GPU Technology Conference. At the time, it was running on a desktop PC equipped with an NVIDIA GeForce GTX Titan GPU, the most powerful single-GPU gaming processor on the market. In this demo, its running on the Kepler GPU inside Logan.
Logan has only been back in our labs for a few weeks and it has been amazing to see new applications coming up every day that have never been seen before in mobile. But this is only the beginning. Simply put, Logan will advance the capability of mobile graphics by over seven years, delivering a fully state-of-the-art feature set combined with awesome performance and power efficiency.
I cant wait to see what the industry can do with this technology now that it has been revealed. Stay tuned!
Below, a video showing Logan running our Island demo.Â
Head and skin data in Ira video courtesy of the Institute for Creative Technologies at USC.
NVIDIA
Anandtech on the impressive power consumption
NVIDIA Demonstrates Logan SoC: < 1W Kepler, Shipping in 1H 2014, More Energy Efficient than A6X?
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.Â
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.Â
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.Â
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.Â
Anandtech
Log in to comment