NVIDIA Reveals Tegra X1, Fastest Mobile GPU, Runs Epic’s Elemental Tech Demo In Real-Time

During this year’s CES, NVIDIA revealed Tegra X1. Tegra X1 is based on the Maxwell architecture, supports OpenGL ES 3.1, Open GL4.5, DirectX 12 and AEP, and comes with 256 stream processors. And in order to demonstrate the chip’s power, NVIDIA showcased Epic’s Elemental Tech Demo running in real-time on that new mobile GPU.

Naturally, the Elemental Tech Demo has been ‘downgraded’ in some areas, especially when it comes to its on screen particles effects. Still, it’s amazing witnessing a mobile GPU offering console-like visuals.

Linley Gwennap, founder and principal analyst of the Linley Group, said:

“Tegra K1 set a new bar for GPU compute performance, and now just a year later Tegra X1 delivers twice that. This impressive technical achievement benefits both 3D graphics, particularly on devices with high-resolution screens, as well as GPGPU software that is becoming more prevalent, particularly in automotive applications.”

NVIDIA’s Tegra X1 integrates four high-performance ARM Cortex-A57 cores with 512KB L2 cache, 48KB L1 instruction cache and 32KB L1 data cache per core as well as four low-power ARM Cortex-A53 cores with 128KB L2 cache, 32KB L1 instruction cache and 32KB L1 data cache per core.

NVIDIA’s Tegra X1’s technical specifications include:

  • 256-core Maxwell GPU
  • 8 CPU cores (4x ARM Cortex A57 + 4x ARM Cortex A53)
  • 60 fps 4K video (H.265, H.264, VP9)
  • 1.3 gigapixel of camera throughput
  • 20nm process

Enjoy (the Elemental Tech Demo starts at 6:40)!

8 thoughts on “NVIDIA Reveals Tegra X1, Fastest Mobile GPU, Runs Epic’s Elemental Tech Demo In Real-Time”

  1. Hm.. funny how technology advances. Just 5/6 years ago, this would of made me laugh, and id seriously question if its true or not. Now? Totally normal and expected..

  2. The jump from Tegra K1 to Tegra X1 was a huge leap, So no doubt next year we will see mobile devices way faster than all consoles.

    1. The biggest problem of parallel computing is an application support, AMD graphics / processor has very same problem, especially on PC. On embedded it is much better/easier.
      NVidia often comparing hypothetical to practical performance, which is not a bad thing (to know what can be done – PC could be easier in theory couple of times powerful) but it is good to know about.
      However – great achievement without the question. Wouldn’t compare it to next gen consoles though, same as I would not call it mobile chip!^^

  3. this was supposed to be out last year and now that they finally made it ITS NOT EVEN GOING TO BE OUT FOR COMMERCIAL PC TILL 2016 FU-NVIDIA (sarcasm: fun-vidia)! I have been waiting to upgrade my PC with this particular maxwell architecture GPU for the last 2 years….another year does not cut it….I WANT IT NOW!
    nvidia has been dragging fans by the noses for the past 2 years….showing great PR about the ARMS chip integrated maxwell architecture and then at the release date they go “Psyche! it was all a joke but since u retards were such good sports here is a pile of crap GPU from our failed experiment box we will sell to u for everything in ur wallet plus ur pants. enjoy it!”.

Leave a Reply

Your email address will not be published. Required fields are marked *