NVIDIA Jetson Embedded Computers

Introducing the NVIDIA Jetson family

The NVIDIA Jetson family, comprising the most recent Jetson AGX Orin and its predecessors, the Xavier series, the TX2 and Jetson Nano, is a series of System-on-Modules (SoM) designed to satisfy a range of applications. From basic Edge AI to fully autonomous machines, the Jetson series is a staple for industrial processes that require a powerful and compact embedded module.

The most powerful addition to the Jetson family, the AGX Orin achieves the highest TOPS at 200 trillion per second at minimum, making it an efficient option for the most intense Edge AI applications. Comparatively, the entry-level Jetson Nano offers an excellent cost-to-performance ratio for basic Edge AI applications, with the Jetson TX2 adding some extra processing grunt to allow for flexible integrations into automation control through the rich IO features. The Xavier NX packs significant AI number crunching power into a module the size of the Nano, producing a perfect platform for more advanced embedded and machine control applications. Finally, the Xavier AGX packs workstation-grade power into a small form factor, bringing with it capabilities for Robotics, AGVs and Industrial Control applications at the Edge.

The NVIDIA Jetson hardware

NVIDIA Jetson AGX Orin

The Jetson AGX Orin is the new flagship and is described by Nvidia as an "energy-efficient AI supercomputer", which they claim is 6 times more powerful than its predecessor the Jetson AGX Xavier and is intended to support large, complex AI models for natural language understanding, 3D perception, and multi-sensor fusion. The 32GB model features 1792-core NVIDIA Ampere GPU with 56 Tensor cores and an 8-core Arm Cortex-A78AE v8.2 64-bit CPU, with dual V2 NVDLA engines. There is also 32GB 256-bit LPDDR5 onboard memory and a 64GB of onboard eMMC storage included.

Bringing a remarkable 200 TOPS to the table, the Jetson AGX Orin 32GB is capable of 200 trillion operations per second (according to Nvidia), which is realistic given the more than tripling of CUDA cores over the AGX Xavier, topping out at 1792 across its 14 multiprocessors (SM). Combining this increase in performance with next-gen deep learning and vision accelerators provided by the Ampere architecture (and the new Arm Cortex-A78AE CPU), high-speed interfaces, faster memory bandwidth, and multimodal sensor support, the Orin even has the ability to run multiple AI application pipelines concurrently.

View Jetson AGX Orin Embedded PCs

NVIDIA Jetson AGX Xavier

The Jetson AGX Xavier is the largest of the Jetson modules, offering up 32 TOPS of INT8 performance. Like the Xavier NX it is built around the ARM V8.2 64-bit Carmel microarchitecture, but this time with an Octa-core processor, a 512-Core Volta GPU, 64 Tensor cores and dual NVDLA engines. There is also 32GB of 256-bit LPDDR4x onboard memory and 32GB of onboard eMMC storage included. All this extra processing power targets AGX Xavier a bit differently — providing this exceptional GPU performance in a 30W package means the AGX Xavier is capable of running autonomous mobile robots (AMRs) or being used for inference for large scale machine vision at the edge.

All of the Jetson boards have a small amount of PCIe support for the addition of a capture card or extra I/O. The AGX Xavier can support multiple expansion devices through its PCIe Gen4.0 controller, including simultaneous support for multiple PCIe devices such as an additional GPU through PCIe x8.

View Jetson AGX Xavier Embedded PCs

NVIDIA Jetson Xavier NX

The Jetson Xavier NX is the same form factor as the Jetson nano and TX2 NX, but boasts a huge bump in performance without increasing the power consumed. The Xavier NX SoM leverages NVIDIA's latest ArmV8.2 64-Bit microarchitecture (code-named Carmel), a Hexa-core processor and a 384-core Nvidia Volta GPU. Unlike the Nano and the TX2, there is some additional AI focused processing power, through 48 Tensor cores and dual NVDLA Engines. As with the other Jetson SoMs, there is 8GB LPDDR4X memory and 16GB eMMC storage onboard.

From mobile robots and drones to portable medical equipment and embedded IoT systems, the Jetson Xavier NX is suitable for autonomous systems and intelligent edge devices that require high-performance AI and complex Deep Neural Networks in a compact, low-power form factor.

View Jetson Xavier NX Embedded PCs

NVIDIA Jetson TX2

Originally named the Tegra X2, the Jetson TX2 is the oldest of the Jetson Range. It features NVIDIAs own microarchitecture (code-named Denver2) — a 64/32bit multi-core ARM v8 processor and a 256-core Nvidia Pascal GPU, up to 8GB 128-bit DDR4 onboard memory and up to 32GB onboard eMMC storage. The Jetson TX2's 15W module has been used in projects far and wide, from military drones processing high-resolution image feeds in real-time with object classification, to monitoring the health of beehives by simultaneously analysing audio, video and sensor data streams.

The Jetson TX2 currently comes in 3 main models: a 4GB or 8GB TX2, and the more recent Jetson TX2 NX which has the same specifications as the TX2 4GB but uses the 260-pin SODIMM form factor of the Jetson Nano. The Jetson TX2 NX can also be swapped into the carrier board of the Nano to scale-up performance.

View Jetson TX2 Embedded PCs

NVIDIA Jetson Nano

The Jetson Nano is, as its name would suggest, the smallest of the range, but where it lacks in footprint it excels in functionality. Featuring 128-core Maxwell GPU and a Quad-core 32-bit ARM Cortex-A57 processor, 8GB onboard LPDDR4 and 16GB eMMC, producing 472GFLOPS of performance, the Nano is capable of decoding 4x 1080p60 feeds whilst running on-board machine learning algorithms for image classification, object detection and video analytics at the edge.

Because of the Nvidia Jetpack's versatility in deployment and support, you can design and test your AI project on the Jetson Nano, confident that it will run identically when deployed on any of the other Jetson SoMs.

View Jetson Nano Embedded PCs

Jetson AGX Orin for the Next Generation of AI Systems

Set to be released in Q1 2022, this new module is described by Nvidia as an "energy-efficient AI supercomputer", which they say is six times more powerful than its predecessor and is intended to support large, complex AI models for natural language understanding, 3D perception, and multi-sensor fusion.

Need a Jetson Developer Kit?

Develop your AI project on a Jetson Developer Kit before deploying it to one of our rugged Jetson Embedded Computers.

View Jetson Dev Kits

Software - The Jetpack SDK

If you are considering the Nvidia Jetson family to power your next AI development, then you may be familiar with the Jetpack SDK. Regardless of which Jetson chip you choose the NVIDIA Jetpack SDK is the essential solution to build your AI application.

The Jetpack SDK comprises the NVIDIA L4T (the latest Linux Driver Package and OS), CUDA-X accelerated libraries and APIs for application development, samples, documentation and developer tools, along with support for SDKs such as Deepstream for Intelligent Video Analytics and Isaac for robotics.

Impulse can pre-configure your chosen Jetson solution with the latest Jetpack SDK and any higher level SDKs pertinent to your intended application.

View our services

How can we help with NVIDIA Jetson?

Jetson development kits

Many of our clients start out with NVIDIA Jetson development kits. We stock these kits and can have you up and running in days.

Jetson Embedded Computers

Once the initial proof of concept is complete the natural transition for industrial AI projects is to a rugged computing platform. We have arguably the UKs largest range of Jetson Embedded Computers available to purchase.

Software and configuration

Our technical team has the ability to install and configure the latest Jetson software stack on any of our Jetson Embedded Computers here in our UK integration facility.

Testing

The ability to install software and configure systems means we can fully test our systems prior to despatch, giving our customers piece of mind whilst saving time and money.

Call off and stock holding

For rapid deployment our extended service offering and comprehensive warehousing means we can offer extra value in hardware call off and logistics.