查看“视觉平台JetsonTX2”的源代码

[[ru:Nvidia#Jetson]]
'''Nvidia Jetson''' is a series of embedded computing boards from [[Nvidia]]. The Jetson TK1, TX1 and TX2 models all carry a [[Tegra]] processor (or SoC) from Nvidia that integrates an [[ARM architecture]] [[central processing unit]] (CPU). Jetson is a low-power system and is designed for accelerating machine learning applications.<ref>"[https://www.researchgate.net/publication/329802520_A_Survey_on_Evaluating_and_Optimizing_Neural_Network_Applications_on_NVIDIA's_Jetson_Platform A Survey on Evaluating and Optimizing Neural Network Applications on NVIDIA's Jetson Platform]", 2018</ref>

==Hardware==

The Jetson family includes the following boards:

* In late April 2014, Nvidia shipped the Nvidia Jetson '''TK1''' development board containing a Tegra K1 SoC in the T124 variant and running [[Ubuntu (operating system)|Ubuntu Linux]].<ref>{{cite web | url=https://www.phoronix.com/scan.php?page=news_item&px=MTY3NjA | title=NVIDIA's Tegra TK1 Jetson Board Is Now Shipping | date=29 April 2014 | author=Michael Larabel | publisher=[[Phoronix]]}}</ref>
* The Nvidia Jetson '''TX1''' development board bears a Tegra X1 of model T210.<ref>{{cite web|url=http://www.nvidia.com/object/embedded-systems.html |title=Embedded Systems Development Solutions from NVIDIA Jetson |publisher=NVIDIA |date=2015-03-18 |accessdate=2016-07-10}}</ref>
* The Nvidia Jetson '''TX2''' board bears a Tegra X2 of microarchitecture GP10B<ref>[http://www.phoronix.com/scan.php?page=news_item&px=Tegra-X2-Nouveau-Support NVIDIA Rolls Out Tegra X2 GPU Support In Nouveau] by Michael Larabel at phoronix.com on March 29, 2017</ref> (SoC type T186 or very similar). This board and the associated development platform was announced in March 2017 as a compact card design for low power scenarios, e.g. for the use in smaller camera drones. A matrix describing a set of performance modes was provided by the media along with that.<ref>[http://www.anandtech.com/show/11185/nvidia-announces-jetson-tx2-parker NVIDIA Announces Jetson TX2: Parker Comes To NVIDIA’s Embedded System Kit], March 7, 2017</ref> Further a TX2i variant, said to be rugged and suiteable for industrial use cases, is mentioned.<ref>[https://devtalk.nvidia.com/default/topic/1030837/jetson-tx2/nvidia-jetson-tx2i-module-for-industrial-environments/ NVIDIA Jetson TX2i Module for Industrial Environments]</ref>
* The Nvidia Jetson '''[[Tegra#Xavier|Xavier]]''' got announced as a development kit in end of August 2018 with a fulfillment promise of "early September".<ref>[https://developer.nvidia.com/embedded/buy/jetson-xavier-devkit NVIDIA Jetson Xavier Developer Kit]</ref> With the announce came a product image and some technical specifications. Indications were given that a 20x acceleration for certain application cases compared to predecessor devices should be expected, and that the application power efficiency is 10x improved.
* The Nvidia '''Nano''' was announced as a development system in mid-March 2019, with the a Development Kit available for pre-order at announcement and promise of wide availability in "June 2019".<ref>[https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-nano The Power of Modern AI to Millions of Devices | NVIDIA Jetson Nano]</ref>. The focus of the discussion around this product was for hobbyist robotics due to the low price point.<ref>{{cite web |title=NVIDIA Announces $99 Jetson Nano: Affordable CUDA |url=https://www.eteknix.com/nvidia-jetson-nano-99-of-cuda-x-awesomeness/}}</ref><ref>[https://hackaday.com/2019/03/18/hands-on-new-nvidia-jetson-nano-is-more-power-in-a-smaller-form-factor Hands-On: New Nvidia Jetson Nano is More Power In A Smaller Form Factor | Hackaday]</ref> The final specs expose the board beeing sort of a power optimized, stripped down version of what a full [[Tegra#Tegra X1|Tegra X1]] system would mean. Comparing in more detail only half of the CPU (only 4x A57 @ 1.43 GHz) and GPU (128 cores of Maxwell generation @ 921 MHz) cores are present and only half of the maximum possible RAM is attached (4 GB LPDDR4 @ 64 bit + 1.6 GHz = 25.6 GB/s) whilst the available or usable interfacing is determined by the baseboard design and is further subject of implementation decisions and specifics in an end user specific design for an application case.<ref>[https://www.cnx-software.com/2019/03/19/nvidia-jetson-nano-developer-kit/ NVIDIA Introduces $99 Jetson Nano Developer Kit] by Jean-Luc Aufranc on March 19, 2019 on CNXSoft</ref>

The published performance modes of the Nvidia Jetson TX2 are:
{| class="wikitable" 
|-
! Mode
! Max Clocks (Denver2 + A57)
! Max-P (Denver2 + A57)
! Max-P (only Denver2)
! Max-P (only A57)
! Max-Q (only A57)
|-
| GPU Clock / MHz
| 1302
| colspan = "3" | 1122
| 854
|-
| Denver2 Clock / MHz
| 2000
| 1400
| 2000
| stopped
| stopped
|-
| Cortex-A57 / MHz
| 2000+
| 1400
| stopped
| 2000
| 1200
|-
| TDP / W
| might vary
| 15
| 15
| 15
| 7.5
|}

The published operation modes of the Nvidia Jetson Nano are:
{| class="wikitable" 
|-
! Mode
! 0
! 1
|-
| GPU Clock / MHz
| 921
| 640
|-
| Cortex-A57 / MHz
| 4x 1428
| 2x 918<br>2x stopped
|-
| TDP / W
| 10
| 5
|}

==Software==
Various operating systems and software might be able to run on the Jetson board series.

===Linux===
JetPack is a [[Software Development Kit]] (SDK) from Nvidia for their Jetson board series. The official Nvidia download page bears an entry for JetPack 3.2 (uploaded there on 2018-03-08) that states:
:''JetPack 3.2 adds support for the [[Linux for Tegra]] r28.2 image for the Jetson OS. It is packaged with newer versions of Tegra System Profiler, [[TensorRT]], and [[cuDNN]] from the last release.''<ref>https://developer.nvidia.com/embedded/downloads</ref>

===QNX===
Even if [[QNX]] is not widely announced for the Jetson platform still there are success reports of installing and running specific QNX packages on certain Nvidia Jetson board variants. Namely the package ''qnx-V3Q-23.16.01'' that is seemingly in parts based on Nvidia's [[Vibrante]] Linux distribution is reported to run on the Jetson TK1 Pro board.<ref>https://devtalk.nvidia.com/default/topic/940116/running-qnx-onto-jetson-tk1-pro-1860-/</ref>

===See also===
* [[Raspberry Pi]]
* [https://en.wikipedia.org/wiki/Movidius#Neural_Compute_Stick Movidius neural compute stick]

==References==

{{reflist}}


{{Linux devices}}
{{Nvidia}}
{{Single-board computer}}
[[Category:ARM architecture]]
[[Category:Linux-based devices]]
[[Category:Nvidia products]]
[[Category:Single-board computers]]

{{computer-stub}}