Skip to content

A reference book on M-Profile Vector Extensions (MVE) for Arm Cortex-M Processors

License

Notifications You must be signed in to change notification settings

arm-university/Arm-Helium-Technology

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 

Repository files navigation

Arm-Helium-Technology

M-Profile Vector Extension (MVE) for Arm Cortex-M Processors

A Reference Book by Jon Marsh

This reference book is the ideal gateway into Arm’s Helium technology, the M-Profile Vector Extension for the Arm Cortex-M processor series.

About this Book

Helium brings exciting new capabilities to microcontrollers, allowing sophisticated digital signal processing or machine learning applications to be run on inexpensive, low-power devices. In the early chapters, the book introduces fundamental concepts at a very basic and accessible level, including Single Instruction Multiple Data (SIMD), vector processing, floating and fixed-point data representations, and saturation. After an overview of the MVE architecture, the instruction set is broken down into clear groups for discussion, covering subjects like pipeline structure, predication and branch handling, data processing and memory access.

The most practical sections of the book deal with the mechanics of coding for a Helium-capable core such as the Cortex-M55, including compilation, debug and optimization. Finally, the book concludes with chapters on how to implement DSP and ML workloads.

The book is intended to be useful to engineers and students who want to learn more about these new features. Knowledge of Cortex-M processors and basic DSP theory is assumed, and some prior knowledge of C and Arm assembly language is a prerequisite.

Table of Contents:

  1. Introduction

  2. SIMD/Vector Processor Overview

  3. Helium Architecture

  4. Data Processing Instructions

  5. Memory Access Instructions

  6. Helium Branch, Scalar and Other Instructions

  7. Helium Programming

  8. Performance and Optimization

  9. DSP Fundamentals

  10. DSP Filtering

  11. Application Examples

  12. Neural Networks and Machine Learning

License

You are free to fork, clone or download this book in PDF format for personal, non-commercial use only. You may reprint or republish portions of the text for non-commercial, educational or research purposes but only if there is an attribution to Arm Education. This book and the individual contributions contained in it are protected under copyright by the Publisher (other than as may be noted herein). Nothing in this license grants you any right to modify the whole, or portions of, this book.

Inclusive Language Commitment

Arm is committed to making the language we use inclusive, meaningful, and respectful. Our goal is to remove and replace non-inclusive language from our vocabulary to reflect our values and represent our global ecosystem.

Arm is working actively with our partners, standards bodies, and the wider ecosystem to adopt a consistent approach to the use of inclusive language and to eradicate and replace offensive terms. We recognise that this will take time. This book may contain references to non-inclusive language; it will be updated with newer terms at the next edition and as those terms are agreed and ratified with the wider community.

Contact us at edumedia@arm.com with questions or comments about this course. You can also report non-inclusive and offensive terminology usage in Arm content at terms@arm.com.