Nvidia Tegra X1 vs Apple A10X Fusion vs Apple A10 Fusion

Nvidia Tegra X1

► remove NVIDIA X1

The NVIDIA Tegra X1 (Tegra 6, Codename Erista) is a 64-Bit high performance ARM based SoC (System on a Chip) for (mainly Android based) tablets and embedded systems (like cars). It contains four ARM Cortex A57 and four ARM Cortex A53 cores in the processor part. As a graphics card, Nvidia integrated a Maxwell based GPU with 256 CUDA cores (see for more details and benchmarks). The integrated memory controller supports LPDDR3 and LPDDR4 with a maximum bandwidth of 25.6 GB/s (2x 32 Bit LPDDR4-3200). The Tegra X1 is the successor to the exactly one year earlier announced Tegra K1 SoC.

Similar to the Symsung Exynos 5433, the Tegra X1 uses a big.LITTLE combination of four power saving and small Cortex-A53 cores and four powerful Cortex-A57 cores. Nvidia however uses an own cluster migration solution instead of the ARM Global Task Scheduling (GTS) and therefore only one of the two quad-core clusters is active at a time.

The performance of the processor cores should be in the high-end segment of ARM based SoCs. Nvidia states that the X1 offers a twice as high energy efficiency compared to the Exynos 5433 (same ARM cores at 1.9 GHz manufactured in 20nm).

Due to the big Maxwell graphics card the SoC is mainly aimed at tablets with good cooling solutions and wont be commonly seen in smartphones. The Tegra X1 is produced at TSMC in 20nm.

Apple A10X Fusion

► remove

The Apple A10X Fusion is a system on a chip (SoC) from Apple that is built into the 2017 iPad Pro models. It integrates six 64 Bit cores that are divided in two clusters. Three high performance cores are clocked at up to 2.39 GHz. The three power saving cores are used for non demanding tasks. It looks like only one of both clusters is able to run at a time (therefore the apps see only three cores). The principle is similar to the first generation of ARMs big.LITTLE concept.

The performance of the SoC is positioned in the high and and clearly faster than all previous Apple SoCs. Even compared to Android high-end SoCs like the Snapdragon 835, the A10X takes the lead (e.g. in Geekbench or Antutu).

The integrated graphics card of the SoC will most likely stem from PowerVR (again) and features 12 cores instead of 6 in the A10 SoC.

According to TechInsights, the A10X is manufactured in the brand new 10 nm FinFet process at TSMC. Altough it offers more function blocks, the A10X is with measured 96.4 mm2 significantly smaller than the previous A9X (143.9 mm2).

Apple A10 Fusion

► remove Apple A10 Fusion

The Apple A10 Fusion is a system on a chip (SoC) from Apple that is built into the iPhone 7 and iPhone 7 Plus. It integrates four 64 Bit cores that are divided in two clusters. Two high performance cores are clocked at up to 2.34 GHz and should be around 40% faster than the Apple A9 (according to Apple) and two low power cores (up to 1.1 GHz?). Up to now its unclear if all four cores can be used at once (that need only 1/5 th of the energy in some use cases). At the release of the iPhone 7 it looks like that IOS is only using two cores at a time and automatically switches between the two clusters. Therefore, apps are seeing only a dual core. The principle is similar to the first generation of ARMs big.LITTLE concept.

The integrated graphics card of the SoC will most likely stem from PowerVR (again) and perform 50% faster at 2/3 of the power consumption (according to Apple). 

All in all the chip includes 3.3 billion transistors, which is more than a current AMD Bristol Ridge (3.1) and Skylake Quad-Core (1.75)  X86 SoCs.

Sources: Apple Keynote, Ars Technica

Nvidia Tegra X1Apple A10X FusionApple A10 Fusion
NVIDIA TegraApple Apple A-SeriesApple Apple A-Series
Erista (Cortex-A57 + A53)Cyclone 4?Cyclone 4?
2000 MHz2390 MHz2340 MHz
576 KB
2.5 MB
8 / 86 / 34 / 2
20 10
4x Cortex-A57 + 4x Cortex-A53, 2x 32 Bit LPDDR4-1600 (25.6 GB/s, max. 4 GB), Maxwell-GPU (256 Shader, OpenGL ES 3.1, OpenGL 4.5, DirectX 11.2, CUDA 6.0), Dual ISP (1.3 GP/s), H.264/H.265 4K60 Encoding/Decoding, HDMI 2.0, eMMC 5.1ARMv8 Instruction SetARMv8 Instruction Set
iGPUNVIDIA Tegra X1 Maxwell GPU ( - 1000 MHz)Apple A10X Fusion GPU / PowerVRApple A10 Fusion GPU / PowerVR
: Apple A-Series Cyclone 4?
» Apple A10X Fusion2390 MHz6 / 3
Apple A10 Fusion2340 MHz4 / 2
Apple A10X Fusion2390 MHz6 / 3
» Apple A10 Fusion2340 MHz4 / 2
3300 3300

3DMark - Ice Storm Standard Physics 1280x720
0 Points (0%)
3DMark - Ice Storm Extreme Physics 1920x1080
0 Points (0%)
3DMark - Ice Storm Unlimited Physics 1280x720 offscreen
100%
X1 +
min: 22527     avg: 23316     median: 23071 (27%)     max: 24349 Points
min: 19534     avg: 19551     median: 19550.5 (23%)     max: 19567 Points
min: 9189     avg: 14249     median: 15479 (18%)     max: 15626 Points
3DMark - Sling Shot Extreme (ES 3.1) Unlimited Physics 2560x1440
min: 2036     avg: 2323     median: 2323 (29%)     max: 2610 Points
min: 1252     avg: 1437     median: 1434.5 (18%)     max: 1627 Points
3DMark - Sling Shot OpenGL ES 3.0 Unlimited Physics 2560x1440
min: 2145     avg: 2370     median: 2369.5 (46%)     max: 2594 Points
min: 1408     avg: 1525     median: 1518 (30%)     max: 1690 Points
Geekbench 3 - 64 Bit Multi-Core Score
100%
X1 +
min: 4208     avg: 4318     median: 4216 (7%)     max: 4530 Points
Geekbench 3 - 64 Bit Single-Core Score
100%
X1 +
min: 1410     avg: 1460     median: 1411 (29%)     max: 1558 Points
Geekbench 4.0 - 64 Bit Multi-Core Score
min: 5585     avg: 5608     median: 5607.5 (16%)     max: 5630 Points
Geekbench 4.0 - 64 Bit Single-Core Score
min: 3476     avg: 3483     median: 3483 (55%)     max: 3490 Points
Geekbench 4.4 - 64 Bit Single-Core Score
100%
X1 +
1510 Points (24%)
min: 3924     avg: 3929     median: 3928.5 (62%)     max: 3933 Points
min: 2672     avg: 3233     median: 3499 (55%)     max: 3527 Points
Geekbench 4.4 - 64 Bit Multi-Core Score
100%
X1 +
4264 Points (7%)
min: 9293     avg: 9326     median: 9325.5 (16%)     max: 9358 Points
min: 4508     avg: 5461     median: 5922 (10%)     max: 5952 Points
Geekbench 5 - 64 Bit Single-Core Score
min: 767     avg: 771     median: 771 (57%)     max: 775 Points
Geekbench 5 - 64 Bit Multi-Core Score
min: 1426     avg: 1429     median: 1429 (9%)     max: 1432 Points
Linpack Android / IOS - Single Thread
0 MFLOPS (0%)
Mozilla Kraken 1.1 - Total Score *
100%
X1 +
min: 3844     avg: 4689     median: 4688.6 (8%)     max: 5533.1 ms
min: 968.8     avg: 971     median: 970.8 (2%)     max: 972.7 ms
min: 1025.5     avg: 1178     median: 1113.4 (2%)     max: 1531 ms
Sunspider - 1.0 Total Score *
100%
X1 +
min: 597     avg: 715     median: 715 (8%)     max: 833 ms
Octane V2 - Total Score
100%
X1 +
min: 7563     avg: 8032     median: 8031.5 (15%)     max: 8500 Points
min: 30333     avg: 30761     median: 30760.5 (59%)     max: 31188 Points
min: 19783     avg: 25316     median: 26053 (50%)     max: 27967 Points
Vellamo 3.x - Metal
100%
X1 +
2276 Points (61%)
Vellamo 3.x - Multicore Beta
100%
X1 +
2535 Points (56%)
Vellamo 3.x - Browser
100%
X1 +
6271 Points (83%)
Quadrant Standard Edition 2.0
100%
X1 +
20655 points (48%)
AnTuTu v5 - Total Score
100%
X1 +
min: 59811     avg: 63053     median: 63052.5 (64%)     max: 66294 Points
AnTuTu v6 - Total Score
100%
X1 +
min: 90568     avg: 112682     median: 112682 (38%)     max: 134796 Points
min: 217439     avg: 222713     median: 222713 (76%)     max: 227987 Points
min: 142532     avg: 153966     median: 153966 (52%)     max: 165399 Points
AndEBench - Java
100%
X1 +
2699 Iter./s (83%)
AndEBench - Native
100%
X1 +
15220 Iter./s (50%)
PassMark PerformanceTest Mobile V1 - CPU Tests
100%
X1 +
129085 Points (17%)
min: 82816     avg: 82838     median: 82837.5 (11%)     max: 82859 Points
min: 49294     avg: 49329     median: 49329 (6%)     max: 49364 Points
PCMark for Android - Work performance score
100%
X1 +
min: 6858     avg: 7492     median: 7491.5 (38%)     max: 8125 Points

Average Benchmarks Nvidia Tegra X1 → 100%

Average Benchmarks Apple A10X Fusion → 168%

Average Benchmarks Apple A10 Fusion → 121%

-
-
* Smaller numbers mean a higher performance
1 This benchmark is not used for the average calculation

v1.9
Please share our article, every link counts!
> Notebook / Laptop Reviews and News > Benchmarks / Tech > Processor Comparison - Head 2 Head
Redaktion, 2017-09- 8 (Update: 2017-09-11)