Nvidia’s new mobile GPU uses less than one-third the power of the iPad 4’s GPU, while still performing the same rendering.
Nvidia have offered a sneak peak at the nuts and bolts behind it’s new “Project Logan” mobile GPU, and boy does it look impressive. Project Logan supports the full spectrum of OpenGL – including the just-announced OpenGL 4.4 – and it also supports DirectX 11, Microsoft’s latest graphics API. For comparison, those of you that remember the good ol’ 8800 GTX series of videocards, Project Logan is a bit better than those. If you told me four years ago that a smartphone would have a be able to outperform my PC, i’d have said you were talking crazy, but here we are.
Epic Games CEO Tim Sweeney confirmed that Project Logan will be able to run Unreal Engine 4, empowering mobile devices with “the same high-end graphics hardware capabilities exposed via DirectX 11 on PC games and on next-generation consoles.”
Being a mobile GPU, power efficiency is a very important factor. There’s no point in being able to produce gorgeous graphics if your phone dies after ten minutes. The good news is that Project Logan uses less than one-third the power of GPUs in leading tablets, such as the iPad 4, while performing the same rendering. “We took Kepler’s efficient processing cores and added a new low-power inter-unit interconnect and extensive new optimizations, both specifically for mobile.”
Be sure to check out the video above, which shows a mobile device with Project Logan running that rather impressive FaceWorks render we saw being run by Nvidia’s horrendously expensive and equally powerful Titan series of graphics cards.
Project Logan achieves these feats of strength by utilizing Nvidia’s revolutionary Kepler architecture. “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,” said Nvidia’s Jonah Alben. “I am really excited to start showing it off to the world.”
The project is still in the prototyping phase, so don’t expect to see it anytime in the immediate future.
Source: Nvidia
