NVIDIA Tegra X1 Maxwell GPU vs Apple A10X Fusion GPU / PowerVR
NVIDIA Tegra X1 Maxwell GPU
► remove from comparison
The NVIDIA Tegra X1 Maxwell GPU is an integrated graphics card in the NVIDIA Tegra X1 SoC for (mostly Android based) tablets. It is the successor of the Tegra K1 GPU and based on the Maxwell architecture. It offers the same features as the laptop and desktop Maxwell based products like OpenGL 4.5, CUDA 6.0, OpenGL ES 3.1 and DirectX 11.2. The GPU offers 256 shader cores (2 SMMs) and clocks at up to 1000 MHz. The memory interface offers a maximum bandwidth of 25.6 GB/s (2x 32 Bit LPDDR4-3200).
First benchmarks of the Tegra X1 graphics card using GLBench show twice as high scores as the PowerVR GXA6850 in the Apple A8X. Therefore, the X1 should be the fastest GPU for Android based devices that should not struggle with high end Android games in high resolutions.
The improved video part of the SoC is able to en- and decode 4K videos in H.265 according to Nvidia (decoding at 60fps, encoding at 30fps). Thanks to HDMI 2.0 support, the 4K60 material can be transmitted to external displays (2 displays in parallel at max). The integrated dual ISP is able to drive up to 6 cameras (max. 100 MP, 4096 focus points) at once.
The power consumption of the whole SoC should be rather big compared to other ARM based SoCs. Therefore, Tegra X1 based smartphones are unlikely. As the Tegra K1, the X1 will be most likely seen in tablets with good cooling solutions. Similar to the Apple A8X, the Tegra X1 is manufactured in 20nm.
Apple A10X Fusion GPU / PowerVR
► remove from comparison
The Apple A10X Fusion / PowerVR graphics card is integrated in the Apple A10X Fusion SoC that can be found in the Apple iPad Pro from 2017. Most likely based on PowerVR technology. According to Apple it integrates 12 cores (compared to the 6 cores of the A10 GPU) and is therefore significantly faster.
NVIDIA Tegra X1 Maxwell GPU | Apple A10X Fusion GPU / PowerVR | |
Codename | Erista | |
Architecture | Maxwell | PowerVR Rogue |
Pipelines | 256 - unified | |
Core Speed | 1000 MHz | |
Memory Speed | 3200 MHz | |
Memory Bus Width | 64 Bit | |
Shared Memory | yes | no |
API | DirectX 11.2, OpenGL 4.5 | |
technology | 20 nm | 10 nm |
Features | CUDA 6.0, OpenGL ES 3.1, AEP | |
Date of Announcement | 05.01.2015 | 07.06.2017 |
|
|
Benchmarks
GFXBench T-Rex HD Offscreen C24Z16 + NVIDIA Tegra X1 Maxwell GPU
Average Benchmarks NVIDIA Tegra X1 Maxwell GPU → 100% n=10
Average Benchmarks Apple A10X Fusion GPU / PowerVR → 135% n=10

* Smaller numbers mean a higher performance
1 This benchmark is not used for the average calculation
For more games that might be playable and a list of all games and graphics cards visit our Gaming List