Edge AI acceleration with Raspberry Pi
Machine Learning Workshop – Raspberry Pi AI Kit

© Lead Image © robsnowstock, 123RF.com
Raspberry Pi enters the artificial intelligence accelerator fray with a low-cost solution.
Public clouds are doubtlessly the most convenient and cost-effective tool for individuals to use to access the latest neural processing unit (NPU) artificial intelligence (AI) accelerating hardware. Due to its high cost and lack of availability, it is hard for a freelance developer to justify acquiring one of the now famous (and infamous) NVIDIA A100 [1] Ampere cards with tensor processing units, with costs running into the tens of thousands of dollars and the cards destined for inevitable obsolescence as the newer Hopper (NVIDIA H100) [2] units arrive (as I am writing, I can see A100s advertised for $1.29/hour by a cloud vendor). The economic choice is easy: Develop the code offline and only then provision a souped-up cloud instance for the actual training or inference task.
Low-cost development strategies comprise Google's Colab [3], a hosted Jupyter Notebook environment providing free access to GPU and TPU (Google's own AI chip) resources for research and learning, or purchasing older accelerators being sold secondhand at heavily discounted prices (with varying degrees of residual usefulness). At the Dragon Propulsion Laboratory, we are partial to another strategy: edge AI accelerators. Designed to enhance devices at the edge of the network, this class of chips is both low in power demands and affordable cost-wise, as well as worth understanding in its own right (Figure 1).
First Look
The Raspberry Pi AI Kit just became available, giving me the opportunity to present a first look at what promises to be a very interesting new entry in the edge accelerator class. The AI Kit consists of the standard Raspberry Pi M.2 HAT+ daughterboard and a Hailo-8L AI accelerator. Connections to the host Pi 5 board run through the GPIO pins and a dedicated ribbon connector, resulting in a single-lane PCIe 3.0 connection with 8GBbps of bandwidth (Figure 2). Rated at 13 Tera Operations per Second (TOPS) of inference performance, the accelerator should offload the Pi's CPU entirely of neural network execution, leaving it free to respond to its results, as hinted by object recognition, segmentation, and tracking demos showcased in the launch announcement [4].
[...]
Buy this article as PDF
(incl. VAT)
Buy Linux Magazine
Subscribe to our Linux Newsletters
Find Linux and Open Source Jobs
Subscribe to our ADMIN Newsletters
Support Our Work
Linux Magazine content is made possible with support from readers like you. Please consider contributing when you’ve found an article to be beneficial.

News
-
Linux Kernel 6.17 Drops bcachefs
After a clash over some late fixes and disagreements between bcachefs's lead developer and Linus Torvalds, bachefs is out.
-
ONLYOFFICE v9 Embraces AI
Like nearly all office suites on the market (except LibreOffice), ONLYOFFICE has decided to go the AI route.
-
Two Local Privilege Escalation Flaws Discovered in Linux
Qualys researchers have discovered two local privilege escalation vulnerabilities that allow hackers to gain root privileges on major Linux distributions.
-
New TUXEDO InfinityBook Pro Powered by AMD Ryzen AI 300
The TUXEDO InfinityBook Pro 14 Gen10 offers serious power that is ready for your business, development, or entertainment needs.
-
Danish Ministry of Digital Affairs Transitions to Linux
Another major organization has decided to kick Microsoft Windows and Office to the curb in favor of Linux.
-
Linux Mint 20 Reaches EOL
With Linux Mint 20 at its end of life, the time has arrived to upgrade to Linux Mint 22.
-
TuxCare Announces Support for AlmaLinux 9.2
Thanks to TuxCare, AlmaLinux 9.2 (and soon version 9.6) now enjoys years of ongoing patching and compliance.
-
Go-Based Botnet Attacking IoT Devices
Using an SSH credential brute-force attack, the Go-based PumaBot is exploiting IoT devices everywhere.
-
Plasma 6.5 Promises Better Memory Optimization
With the stable Plasma 6.4 on the horizon, KDE has a few new tricks up its sleeve for Plasma 6.5.
-
KaOS 2025.05 Officially Qt5 Free
If you're a fan of independent Linux distributions, the team behind KaOS is proud to announce the latest iteration that includes kernel 6.14 and KDE's Plasma 6.3.5.