We’ve been talking a lot about Android-powered gaming devices recently. Heck, we even gave them a place here on the XDA forums not too long ago. All of this is possible thanks to the increasingly powerful Systems-on-a-Chip in modern Android-powered devices. Now, Nvidia wishes to up the ante in the low-power SoC world with its Kepler-based Tegra K1 SoC.
The K1 breaks away from previous Tegra devices by merging Nvidia’s GeForce architecture with its mobile architecture. The company accomplishes this by making the K1 (previously codenamed Project Logan) the first mobile chip based on their Kepler architecture rather than the previous GeForce ULP.
For those who have been keeping up with the desktop GPU world, the Nvidia GeForce GTX 600-series marked the introduction of the Kepler architecture, which brought many key improvements over the previous Fermi SM (Streaming Multiprocessor) architecture. Fermi, which was featured in the GTX 400- and 500-series products was widely ridiculed for its power consumption and heat output. The Kepler SMX (Next Generation Streaming Multiprocessor) architecture, on the other hand, was redesigned from the ground up to provide much increased energy efficiency through the use of a unified clock.
Just like its desktop counterpart, the Kepler SMX in the Tegra K1 features 192 Cuda Cores per SMX unit. And since there is only one SMX in the K1, this equates to 192 total Cuda Cores. This is both a marked increase from the current Tegra 4 (initially featured in the Nvidia Shield), which features 72 cores, as well as the Fermi SM, which offers 32 Cuda Cores per SM unit. All of these increased parallel shader units equate to increased shader and compute power, which can be harnessed with greater gaming visuals.
Below is an Nvidia tech demo showing what these 192 cores are capable of:
And speaking of harnessing the increased power, it’s certainly not going to waste. Nvidia chose to demonstrate the power of their Tegra K1 using Unreal Engine 4 by Epic Games.
In addition to raising the bar on the mobile GPU front, the Tegra K1 brings interesting choices when it comes to its CPU component. Initially, the K1 will only be available with a quad-core ARM Cortex A15, using Nvidia’s patented 4-Plus-1 architecture that offers a low power core for light loads. Eventually, however, Nvidia will release another version of the Tegra K1 with Nvidia’s dual-core Denver CPU. This second version will be based on ARM’s 64-bit V8 instruction set.
The initial quad-core ARM Cortex A15 version is compatible with the 32-bit ARMv7 instruction set. It is a 3-way superscalar architecture, and it will run at up to 2.3 GHz and feature two banks of 32 KB L1 cache. The dual-core Denver variant is compatible with the 64-bit ARMv8 instruction set. It is based on a 7-way superscalar architecture, and it will run at up to 2.5 GHz and feature 64 KB + 128 KB of L1 cache.
Most interestingly, these two versions will be pin-compatible. This means that OEMs will be able to easily switch between the two SoCs and offer different versions of their products for different markets. Thanks to the economies of scale that this allows for, we could possibly see this translate to lower overall costs—or higher profit margins, depending on how cynical you are.
So when will all of this be available? There’s no firm release date, and when these chips make their way to actual devices is anybody’s guess, but the quad-core Cortex A15 version will be available some time in the first half of 2014. The dual-core 64-bit Denver version will make its debut in the second half of the year.
Are you excited for the future of mobile gaming made possible by the next generation of mobile SoCs like the Tegra K1? From what we can see today, it seems like the bar has clearly been raised, and it’ll be exciting to see how Qualcomm and Samsung respond with the next generations of their Snapdragon and Exynos lines.
More information on the K1 and some basic specs can be found on Nvidia’s own site and Tegra K1 press release. There, you can also learn more about UE4 on the Tegra K1, including a video that we have posted above. And if you want to look at some of Nvidia’s strange ideas for marketing, head over here and watch the video below._________