Diego Dorta

Variscite and MemryX Inc. have established a collaboration to enhance AI/ML edge computing by combining scalable AI acceleration with proven System on Module solutions. This integration addresses the needs of industries requiring real-time processing, including industrial systems, healthcare devices, and vision applications.
MemryX’s integrated hardware and complementary software allow developers to build edge AI applications with enhanced performance characteristics like low latency processing and efficient power consumption while accelerating development cycles and time to market.
The collaboration launched with a plug-and-play integration of the MemryX platform with Variscite’s i.MX 8M Plus SoMs, leveraging their advanced vision and multimedia features, such as dual camera interfaces, integrated Image Signal Processor (ISP), and H.265/H.264 video encoding and 1080p60 decoding. This provides an ideal combined solution for developing vision-based applications like real-time object detection and video analytics. The collaboration will also extend across Variscite’s extensive SoM portfolio, including modules based on the i.MX 9 and i.MX 8 series.

This article provides step by step instructions on how to start developing your own Machine Learning (ML) applications using Variscite’s System on Modules. It shows how to build an image using the Yocto Linux BSP with a collection of development tools, utilities, and libraries for building ML applications from the NXP eIQ™ ML Software Development Environment, how to run the default examples built with the image, and finally, how to write a simple ML example from scratch.
1.1. eIQ™ Machine Learning Software Development Environment Overview
eIQ™ allows users to easily develop a complete system-level application to solve ML problems related to vision, audio, time-series data and so on. Common examples are face recognition, pose estimation, gesture recognition, speech accents interpretation, etc.

This article demonstrates how to customize the images and logos displayed during the boot process: The U-Boot splash image, the Linux kernel logo, the Yocto PSplash image, the Linux Pre-login message and the Wayland wallpaper. This is typically used by customers to display their own company or product logo.
1.1. Software Requirements
First, setup your host environment and get the source code of the Yocto release you want to use: Go to dev.variscite.com, click on the SOM you are using and on “Developers Guide” under the Yocto version you want to use, and then click on “Build Yocto from source code”, and follow the instructions there.

1. iMX8 overview
Variscite’s i.MX8 family of System on Modules (SoMs) provides pin-to-pin scalability between the iMX8, iMX 8X, and i.MX 8M families of NXP SoCs. Each SoM features a GPU that enables hardware acceleration of both graphical and computational applications. This article aims to introduce Variscite customers to the GPU and provide practical steps on how to select the correct SoM, as follows:
 

1. Overview
This article introduces Variscite’s Python pyvar package and demonstrates how to get started using pyvar’s Machine Learning (ML) API. This API is designed to help beginners to explore the ML field and to develop their own applications by using cameras, displays and user interfaces, targeting the System on Modules (SoMs) powered by the i.MX8 family.
 

1.1. Overview
This article demonstrates how to create a Yocto BSP layer for a custom carrier board designed for a Variscite System on Module / Computer on Module. You will learn how to create a meta layer that compiles and installs a ‘Hello, World!’ application. Then, you will modify it to be a BSP layer by adding a machine configuration file.