AI is impacting everything. From the data center to the 5G network edge to every connected device, AI use cases are driving massive compute requirements. Billions of smartphones already make daily use of machine learning (ML) for voice recognition, image processing, and other applications, but many forecasts show the growth of IoT creating billions more devices—using AI to unlock even greater possibilities.
The majority of these IoT devices will be small, power and cost-constrained microcontroller-based systems. Network bandwidth and consumer expectations around data privacy and user experience continue to demand more on-device processing, while the ability to deploy AI to the smallest devices opens up new use cases for innovative developers.
Arm offers new compute technologies coupled with an industry-leading ecosystem of software and tools to help companies realize the full potential of AI for IoT, and to help streamline the design, development, and support for AI-based IoT applications. Combined, the Cortex-M55, Arm's most AI-capable Cortex-M processor, and the Ethos-U55, the industry's first microNPU for Cortex-M, deliver up to a 480x leap in ML performance, bringing endpoint AI to billions more devices.
Up to an unprecedented 480x uplift in on-device ML performance, enhancing capabilities for the smallest, power-constrained IoT devices.
DSP and ML programs are integrated with classical embedded applications in a single unified software workflow for increased efficiency and reduced time to market.
Built-in support for common ML frameworks, such as TensorFlow Lite Micro, so ML workloads on Arm processors automatically have access to world-class tools.
As AI mainstream popularity grows, so does the range of applications businesses seek to develop. These fundamental use cases are inspiring companies of all sizes to innovate for new possibilities and disrupt existing markets.
Vibration and Sensor Fusion
Wearable health tracker, industrial sensors, motor control, industrial anomaly detection.
Voice and Sound
Voice-activated home devices, such as smart speakers, and lightbulbs, headsets and earbuds.
Vision and Image
Video doorbell, gesture-controlled machines, smart door unlock, quality assurance.
The combination of leading hardware IP, easy-to-use tools, open source software and leading ecosystem are enabling AI for IoT to scale.
Additionally, Arm’s comprehensive, full-stack suite of integrated software and tools make it easier and quicker to design, develop, and maintain AI-based IoT applications. Read the Blog
Cortex-M55 Processor
Arm’s most AI-capable Cortex-M processor delivers enhanced, power-efficient digital signal processing and machine learning performance.
Ethos-U55 microNPU
The industry’s first microNPU for Cortex-M, specifically designed to accelerate machine learning inference.
Corstone-300 Reference Design
The fastest way to incorporate the Cortex-M55 and Ethos-U55 processors into a system-on-chip design.
"The ‘Empowered Edge’ is becoming a new mega trend, driven by new AI paradigms, as well as the challenges of cloud-based processing like cost, latency, reliability and privacy. Arm’s new endpoint ML technologies will help NXP’s broad base of microcontroller developers accelerate edge inference in devices limited by size and power."
Geoff Lees, Senior Vice President of Edge Processing, NXP
"The flexibility, uplift in performance and ease of development that the Arm Cortex-M55 and Ethos-U55 processors bring will enable Shoreline IoT to deliver solutions with a much longer battery life and more complex, faster and advanced ML algorithms right at the endpoint."
Kishore Manghnani, Co-founder and CEO, Shoreline IoT
Find out how Arm’s new processors are enhancing on-device machine learning capabilities to help drive innovation and open up new business opportunities.
Unlock the Potential of AI
A world made better by AI has been one of humanity’s longest held technological visions, and in 2020 that vision is undoubtedly being realized. AI is making a real difference to how we experience the world around us. This Northstar report provides insight into how AI is used today and how consumers expect to use AI tomorrow.