System-on-Modules (SOMs): How and Why to Use Them

What is a System-on-Module (SOM)?

A System-on-Module (SOM) provides the core components of an embedded processing system — including processor cores, communication interfaces, and memory blocks — on a single production-ready printed circuit board (PCB). This modular approach makes a SOM ideal for embedding into end systems, from robots to security cameras.

System-on-module SOM showing image size in comparison to a credit card being used in a smart security camera

The concept of System-on-Modules grew out of blade servers. These thin servers were created with the goal of saving storage space and minimizing power consumption. The lean design mentality behind blade servers carries over to the architecture of SOMs. They include only the components required for their intended function in as small a package as possible, and they’re flexible enough to accommodate a wide range of applications.

System-on-module SOM on carrier card showing connected starter kit components with SD card and camera

SOMs are distinct from a system-on-a-chip (SoC). An SoC, as its name implies, is a collection of key computer components placed on a single chip. While SOMs may include an SOC, they are board-based, and as such have the space to include additional components.

Smart Security camera features and facial recognition using SOMs
People walking through crosswalk showing AI security monitoring using SOMs
Defect Detection on fruit mold on farms using SOMs
Why Use a System-on-Module?

SOMs make the impossible possible for developers, reducing time-to-market and keeping costs down. Creating an embedded system is typically a lengthy process, requiring custom board design and manufacture. A SOM streamlines the steps needed to bring a design to fruition. Simply choose a SOM that fits your needs, integrate it into your end system, and you’re ready for deployment. Beyond enabling high volume deployment, module-based designs simplify product life cycle management and reduce bill of material (BOM) expenses.

Whether your focus is software, hardware, or even AI development, SOMs are worth a close look:

  • Software developers can unlock the potential of edge computing, processing data locally without latency. SOMs remove the need for deep hardware experience, providing a comfortable, intuitive design environment. And software developers working with vision applications will love the flexible, easily configurable sensors a SOM can provide. The best SOMs even offer built-in drivers and other software that saves design time.
  • Hardware developers need to complete production as quickly as possible and focus their limited resources on the highest impact tasks. With a SOM, they can get field programmable gate array (FPGA) performance and flexibility without the difficulty that comes with PCB design and integration. This enables them to complete projects ahead of time and under budget.
  • AI developers need a system that offers high, efficient performance without requiring them to become hardware experts. Thankfully, they can choose a SOM that provides the required compute power while maintaining the flexibility to easily swap out AI models, thanks to the pre-built applications the best system on module providers offer.

SOMs are being used worldwide. Here’s a look at just a few of their applications.

Smart Camera in train station for security monitoring
Security Cameras

Cutting edge security camera systems take advantage of video analytics, and SOMs make it happen. Video analytics-powered security cameras use machine learning to categorize and understand what they see, providing a stream of accurate data in real time. This wouldn’t be possible without edge computing and the ability for cameras and other devices to analyze information on site.

Machine Vision example with defect detection overlay with smart vision cameras
Machine Vision

The modern economy relies on machine vision for everything from inventory inspection to signature recognition to defect detection. Machine vision requires embedded systems that can analyze data on the spot and offer configurable sensor capabilities. SOMs enable developers to take advantage of machine vision at scale while keeping costs low.

Smart City visual graphic of light beams ascending through city skyline at sunset
Smart Cities

Smart cities employ ubiquitous sensors to gather data and provide the insights decision-makers need to keep their communities functioning and vibrant. SOMs power these sensors and help city officials stay on top of everything from utilities to traffic without missing a beat.

Smart City visual graphic of light beams ascending through city skyline at sunset
Motor Control

Electric motors are everywhere, from public transportation, wind turbine and other power generation systems, robotics for factory automation and logistics, medical equipment, aerial systems for agriculture and logistics, and much more. SOMs help accelerate development of these applications and offer adaptability to connect with new peripherals as standards continue to evolve. Users can fine tune their end system to meet the desired power and performance.

Adaptive Computing in Electric Drives
Powering Electric Drive Control & Sustainability with Adaptive Computing

Kria™ adaptive System-on-Module (SOM) devices from AMD play an important role in electric drive control. They can optimize performance, help a motor run more efficiently, reduce power consumption, mitigate noise, cut vibration, and detect potential failures before they happen. Download our new motor control eBook to learn more!

Accelerate Your AI-Enabled Edge Solution with Adaptive Computing
Accelerate Your AI-Enabled Edge Solution with Adaptive Computing

Learn all about adaptive SOMs, including examples of why and how they can be deployed in next-generation edge applications, and how smart vision providers benefit from the performance, flexibility, and rapid development that can only be achieved by an adaptive SOM.

Adaptive Computing in Robotics
Adaptive Computing in Robotics

Demand for robotics is accelerating rapidly. Building a robot that is designed to be safe and secure and can operate alongside humans is difficult enough. But getting these technologies working together can be even more challenging. Complicating matters is the addition of machine learning and artificial intelligence, which is making it more difficult to keep up with computational demands.

Roboticists are turning toward adaptive computing platforms, which offer lower latency and deterministic, multi-axis control with built-in safety and security features on an integrated, adaptable platform that is expandable for the future. Read the eBook to learn more.

starter kits

Kria Starter Kit KV260 System-on-Module SOM Starter Kit

Kria KV260 Vision AI Starter Kit 

The KV260 Vision AI Starter Kit is an out-of-the-box ready development platform for AI and embedded SW & HW developers. Designed for vision AI applications, the KV260 is the fastest way to develop unique vision solutions for production volume deployment with the K26 SOM.

Kria Starter Kit KV260 System-on-Module SOM Starter Kit

Kria KR260 Robotics Starter Kit

The KR260 Robotics Starter Kit integrates high-performance industrial interfaces and features native ROS 2 support. Designed for robotics and industrial applications, the KR260 is the fastest way to develop intelligent factory solutions for production volume deployment with the K26 SOM.

Kria Starter Kit KV260 System-on-Module SOM Starter Kit

Kria KD240 Drives Starter Kit

The KD240 Drives Starter Kit is an out-of-the-box ready development platform for motor control and DSP applications. Embedded SW developers without FPGA expertise can easily get started by running accelerated applications and leverage multiple development flows, including Python, the MATLAB® Simulink® environment, and more.

production soms

Kria Starter Kit KV260 System-on-Module SOM Starter Kit

Kria K24 SOM

Cost-optimized SOM for lower power, smaller form-factor and cost sensitive industrial applications. Targeted for power-efficient DSP applications. Available in commercial and industrial temperature ranges.

Kria Starter Kit KV260 System-on-Module SOM Starter Kit

Kria K26 SOM

Mid-range SOM for vision AI and robotics applications requiring higher performance per watt  and lower latency. Offers adaptability to connect various sensors and flexibility to customize both in HW & SW. Available in commercial and industrial temperature ranges.