Nvidia takes “AI to the edge” with Linux GPU engine on mini card

March 10, 2017 // By Graham Prophet
Describing it as an IoT Platform for manufacturing, industrial, and retail, Nvidia has released its Jetson TX2, a credit card-sized platform that delivers AI computing at the edge, “opening the door to powerfully intelligent factory robots, commercial drones and smart cameras for AI cities.”

Jetson TX2 offers twice the performance of its predecessor, or it can run at more than twice the power efficiency, while drawing less than 7.5W. This allows Jetson TX2 to run larger, deeper neural networks on edge devices, for higher accuracy and faster response times in tasks such as image classification, navigation and speech recognition. The card can be deployed for general-purpose tasks using GPU-based parallel computing (“GPGPU”) using the Nvidia’s CUDA programming resources.

 

The Jetson TX2 joins the Jetson TX1 and TK1 products for embedded computing. Jetson is an open platform that is accessible to anyone for developing advanced AI solutions at the edge -- from enterprise companies and startups to researchers and high school students. It is based on Nvidia’s PASCAL GPU architecture, with on-chip multicore ARM Cortex-A57 compute resources.

 

Features of Jetson TX2 include:

 

GPU: 256-core NVIDIA Pascal architecture-based GPU

CPU: Dual 64-bit NVIDIA Denver 2, Quad ARM A57

Video: 4K x 2K 60fps encode and decode

Camera: 12 CSI lanes supporting up to 6 cameras; 2.5 gigabytes/second/lane

Memory: 8GB LPDDR4; 58.3 gigabytes/second

Storage: 32GB eMMC

Connectivity: 802.11ac WLAN, Bluetooth

Networking: 1GB Ethernet

OS Support: Linux for Tegra

Size: 50mm x 87mm

 

The Jetson family is supported by an SDK for AI computing, JetPack 3.0, which aids in integrating AI into a wide variety of applications, and supports the following:

 

TensorRT 1.0, a high-performance neural network inference engine for production deployment of deep learning applications

cuDNN 5.1, a GPU-accelerated library of primitives for deep neural networks

VisionWorks 1.6, a software development package for computer vision and image processing

The latest graphics drivers and APIs, including OpenGL 4.5, OpenGL ES 3.2, EGL 1.4 and Vulkan 1.0

CUDA 8, which turns the GPU into a general-purpose massively parallel processor, giving developers access to tremendous performance and power-efficiency

 

The Nvidia Jetson TX2 Developer Kit, which includes the carrier board and Jetson TX2 module, can