feature article
Subscribe Now

Feast Your Orbs on NVIDIA’s Jetson Nano 2GB Dev Kit

It’s a funny old world and no mistake. Just a few days ago as I pen these words, I was on a video chat with my chum Adam Taylor, who hangs his hat in the UK. If you are desperately bored and/or need something to do, please feel free to watch this video and let me know what you think.

Adam and I were both born and bred in Sheffield, Yorkshire, England, and we both attended Sheffield Hallam University, although Adam graduated 20 years after yours truly. I’d like to claim this time gap was due to Adam being a slow learner but, in fact, he’s 20 years younger (I prefer to think “less experienced”) than your humble narrator.

A Fellow of the Institute of Engineering and Technology (IET), Adam is the founder of Adiuvo Engineering and Training in the UK. In his spare time (wry smile), Adam is a Visiting Professor of Embedded Systems at the University of Lincoln, England.

Adam and I are working on a series of blogs under the umbrella name of “How to Get an Engineering Job and Keep It” (we’ve already posted Part 1 and we’d love to receive your feedback), but that’s not what I wanted to talk to you about.

The reason I’m waffling on about this here is that, as part of the aforementioned interview, I remarked to Adam that when I was a student in the late 1970s, I saw an advert for a single board computer (SBC) in Practical Electronics magazine. I no longer remember the name of this SBC, but I do recall its being a bare board carrying an 8-bit microprocessor with a clock speed of 1 MHz, 1 KB of ROM, 1 KB of RAM, a hexadecimal keypad, and a few 7-segment displays that were used to display the address and data.

I cannot tell you how much I yearned to call this little beauty “my precious” (I still do, in fact), but it was substantially outside my budget at that time. I also remember thinking that I doubted I would ever be able to afford a computer of my own. This causes an ironic smile to flit across my face today as I consider the myriad computer systems scattered around my home and office.

I also have to keep pinching myself when I consider the specifications of today’s systems and compare them with those early machines of yesteryear. For example, the Apollo Guidance Computer (AGC), which almost crashed-or-landed Apollo 11 on the moon before Neil Armstrong took over, boasted a 0.043 MHz clock and only 4 KB of RAM, which wouldn’t have been enough memory to hold the characters comprising this column. By comparison — currently sitting on my desk, I have a “scorching hot off the production line” Jetson Nano 2GB Developer Kit from NVIDIA.

It’s amazing to think that NVIDIA’s original Jetson, the TK1, was introduced in 2014, which is six years ago as I pen these words. This was followed by the Jetson TX1, Jetson TX2, Jetson AGX Xavier, Jetson Nano, Jetson Xavier NX, and — now — the Jetson Nano 2GB. The various Jetson platforms are widely used in diverse fields such as robotics, intelligent video analytics, machine vision, and the AIoT (see also What the FAQ are the IoT, IIoT, IoHT, and AIoT?).

The official publicity photo for the Jetson Nano 2G kit is shown below, as is the real-word kit on my desk. Can you tell which image is which?

NVIDIA’s Jetson Nano 2GB Development Kit.

This bodacious beauty boasts a 128-core NVIDIA Maxwell graphics processing unit (GPU), a quad-core 64-bit ARM Cortex-A57 central processing unit (CPU), and 2 GB of 64-bit LPDDR4 25.6 GB/s memory. Additional storage is provided via a microSD card (I have a 64 GB card, but you can go much higher — for example, you can get microSD cards up to 1 TB, the thought of which which makes my eyes water).

Targeting artificial intelligence (AI) at the edge, this “entry-level” (their words, not mine) development kit costs only $59, which I think is an amazingly good deal.

The Jetson Nano 2G Development Kit has been designed from the ground up to facilitate the learning and teaching of AI. In order to support all of this, NVIDIA has announced the availability of free online training and AI-certification programs. In turn, these programs will serve to supplement the numerous open-source projects, how-tos, and videos contributed by thousands of developers. Speaking of which, the chaps and chapesses at NVIDIA tell me that there are currently 700,000 active developers in the vibrant Jetson community.

As is the case for all of the Jetson platforms, the Jetson Nano 2G is supported by the NVIDIA JetPack SDK (software development kit), which comes with NVIDIA container runtime and a full Linux software development environment. This allows developers to package their applications for Jetson with all its dependencies into a single container that is designed to work in any deployment.

The JetPack SDK includes the latest Linux Driver Package (L4T) with the Linux operating system and CUDA-X accelerated libraries and application programming interfaces (APIs) for Deep Learning, Computer Vision, Accelerated Computing, and Multimedia. It also includes samples, documentation, and developer tools for both host computer and developer kit, and it supports higher-level SDKs such as DeepStream for streaming video analytics and Isaac for robotics.

One problem with software guys and gals is that they tend to assume everyone knows what they are talking about. The diagram above, for example, shows the term CUDA, and their literature says that the Jetson SDK is “powered by the same NVIDIA CUDA-X accelerated computing stack used to create breakthrough AI products in such fields as self-driving cars, industrial IoT, healthcare, smart cities, and more.

This is obviously exciting, but just what is CUDA when it’s at home? Thank goodness for the internet, Google, and Wikipedia, is all I can say, because a quick Google reveals the following:

CUDA (Compute Unified Device Architecture) is a parallel computing platform and application programming interface (API) model created by Nvidia. It allows software developers and software engineers to use a CUDA-enabled graphics processing unit (GPU) for general-purpose processing – an approach termed GPGPU (General-Purpose computing on Graphics Processing Units). The CUDA platform is a software layer that gives direct access to the GPU’s virtual instruction set and parallel computational elements, for the execution of compute kernels.

The CUDA platform is designed to work with programming languages such as C, C++, and Fortran. This accessibility makes it easier for specialists in parallel programming to use GPU resources, in contrast to prior APIs like Direct3D and OpenGL, which required advanced skills in graphics programming. CUDA-powered GPUs also support programming frameworks such as OpenACC and OpenCL; and HIP by compiling such code to CUDA. When CUDA was first introduced by Nvidia, the name was an acronym for Compute Unified Device Architecture, but Nvidia subsequently dropped the common use of the acronym.

I’d like to say that reading this makes me feel a lot better. What the heck, let’s go for it: “Reading this makes me feel a lot better.” Furthermore, I just ran across this handy-dandy video featuring NVIDIA’s Autonomous Machines Program Manager, Phil Lawrence, who seems to be a jolly nice person.

Quite apart from anything else, Phil’s dulcet tones are very relaxing, making me feel that even I — a humble hardware design engineer — might be able to get my Jetson Nano 2G up and running without having a nervous breakdown in the process. So, without waffling on further, I feel the urge to follow Phil’s instructions, power up my Jetson Nano 2G, and take a deep dive into the AIoT waters. What about you? Do you have any thoughts you’d care to share on anything you’ve read here?

One thought on “Feast Your Orbs on NVIDIA’s Jetson Nano 2GB Dev Kit”

Leave a Reply

featured blogs
Oct 30, 2020
[From the last episode: We saw that converters are needed around an analog memory to convert between digital and analog parts of the circuit.] We'€™ve seen that we can modify a digital memory a number of ways to make it do math for us. Those modifications include: Using the...
Oct 30, 2020
I like to do the (London) Times crossword most days. For more information on how cryptic crosswords even work, see my offtopic post Aren't All Crosswords Cryptic? There's also a blog where... [[ Click on the title to access the full blog on the Cadence Community si...
Oct 29, 2020
Autumn is shaping up to be a popular time for digital trade shows this year, and OCP Tech Week will be occurring November 9 – 13, 2020. OCP Tech Week 2020 will provide Engineering Workshops, live lectures, and interactive collaboration sessions. During this digital trad...
Oct 28, 2020
You rarely get to hear people of this caliber talk in this '€œfireside chat'€ manner, so I would advise younger engineers to take the time to listen to these industry luminaries....

featured video

Demo: Inuitive NU4000 SoC with ARC EV Processor Running SLAM and CNN

Sponsored by Synopsys

Autonomous vehicles, robotics, augmented and virtual reality all require simultaneous localization and mapping (SLAM) to build a map of the surroundings. Combining SLAM with a neural network engine adds intelligence, allowing the system to identify objects and make decisions. In this demo, Synopsys ARC EV processor’s vision engine (VPU) accelerates KudanSLAM algorithms by up to 40% while running object detection on its CNN engine.

Click here for more information about DesignWare ARC EV Processors for Embedded Vision

featured paper

Overcoming PPA and Productivity Challenges of New Age ICs with Mixed Placement Innovation

Sponsored by Cadence Design Systems

With the increase in the number of on-chip storage elements, it has become extremely time consuming to come up with an optimized floorplan using manual methods, directly impacting tapeout schedules and power, performance, and area (PPA). In this white paper, learn how a breakthrough technology addresses design productivity along with design quality improvements for macro-dominated designs. Download white paper.

Click here to download the whitepaper

Featured Chalk Talk

General Port Protection

Sponsored by Mouser Electronics and Littelfuse

In today’s complex designs, port protection can be a challenge. High-speed data, low-speed data, and power ports need protection from ESD, power faults, and more. In this episode of Chalk Talk, Amelia Dalton chats with Todd Phillips from Littelfuse about port protection for your next system design.

Click here for more information about port protection from Littelfuse.