- Arm launches industry’s first microNPU for Cortex-M combined with newest Cortex-M processor to securely deliver up to a 480x uplift in ML performance
- New IP will enable AI everywhere on billions of next-generation smaller, power-constrained devices with greater on-device ML processing
- Software development flow specifically optimized for developer productivity and maximizing ML performance across all configurations of these new processors
Today, Arm announced significant additions to its artificial intelligence (AI) platform, including new machine learning (ML) IP, the Arm® Cortex®-M55 processor and Arm Ethos™-U55 NPU, the industry’s first microNPU (Neural Processing Unit) for Cortex-M, designed to deliver a combined 480x leap in ML performance to microcontrollers. The new IP and supporting unified toolchain enable AI hardware and software developers with more ways to innovate as a result of unprecedented levels of on-device ML processing for billions of small, power-constrained IoT and embedded devices.
“Enabling AI everywhere requires device makers and developers to deliver machine learning locally on billions, and ultimately trillions of devices,” said Dipti Vachani, senior vice president and general manager, Automotive and IoT Line of Business, Arm. “With these additions to our AI platform, no device is left behind as on-device ML on the tiniest devices will be the new normal, unleashing the potential of AI securely across a vast range of life-changing applications.”
As the IoT intersects with AI advancements and the rollout of 5G, more on-device intelligence means that smaller, cost-sensitive devices can be smarter and more capable while benefiting from greater privacy and reliability due to less reliance on the cloud or internet. By delivering this intelligence on microcontrollers designed securely from the ground up, Arm is reducing silicon and development costs and speeding up time to market for product manufacturers looking to efficiently enhance digital signal processing (DSP) and ML capabilities on-device.
Arm Cortex-M55: Arm’s most AI-capable Cortex-M processor
Cortex-M processors have become the computing platform of choice for developers, with Arm partners shipping more than 50 billion chips based on Cortex-M into a vast range of customer applications. With the addition of the Cortex-M55, Arm is offering its most AI-capable Cortex-M processor ever and the first based on the Armv8.1-M architecture with Arm Helium vector processing technology for significantly enhanced, energy-efficient DSP and ML performance. Cortex-M55 delivers up to a 15x uplift in ML performance and a 5x uplift in DSP performance, with greater efficiency, compared to previous Cortex-M generations.
Additionally, Arm Custom Instructions will be available to extend processor capabilities for specific workload optimization, a new feature for Cortex-M processors.
Ethos-U55: Arm’s first microNPU for Cortex-M
For even more demanding ML systems, the Cortex-M55 can be easily paired with the Ethos-U55, Arm’s first microNPU, together delivering a combined 480x increase in ML performance over existing Cortex-M processors.
The Ethos-U55 is highly configurable and specifically designed to accelerate ML inference in area-constrained embedded and IoT devices. Its advanced compression techniques save power and reduce ML model sizes significantly to enable execution of neural networks that previously only ran on larger systems.
Simplified software brings secure AI within reach of all developers
Arm understands the developer experience is fundamental to enabling the AI revolution. For this reason, Cortex-M55 and Ethos-U55 are fully supported by Arm’s industry leading Cortex-M software toolchain. This ensures a unified development flow for traditional, DSP and ML workloads – while specific integration and optimizations for leading machine learning frameworks, starting with TensorFlow Lite Micro, will ensure that developers have a seamless experience and get the best performance from any Cortex-M and Ethos-U55 configuration.
Arm believes security should never be an afterthought and is critical for IoT to scale. To ensure the most secure designs and provide a seamless route to PSA Certified products, these processors and the accompanying Corstone reference design work with Arm TrustZone to ensure security can be more easily incorporated into the complete system-on-chip.
Empowering the ecosystem
The new Cortex-M CPU and the Ethos microNPU underline Arm’s commitment to empower silicon designers and device manufacturers with the agility to innovate on the Arm architecture at even the smallest endpoints, igniting a new wave of creativity and innovation for the IoT. This technology is receiving widespread industry support from ecosystem partners, including Amazon, Alif Semiconductor, Bestechnic, Cypress, Dolby, Google, NXP, Samsung, STMicroelectronics and more.
Read more about how it will bring AI to billions more in this blog from Dipti Vachani, senior vice president and general manager, Automotive and IoT Line of Business, Arm.
More technical details on Cortex-M55 can be found here and on Ethos-U55 here.
Supporting Partner Quotes
“For distributed intelligence to be effective, each endpoint must have more processing capacity to reduce cloud traffic, perform AI inferences, enhance security, and act instantaneously. We’ve adopted the new Cortex-M55 core due to its ability to efficiently cover a wide spectrum of tasks. The new core performs brilliantly from extreme battery life to all-out processing performance.”
Reza Kazerounian, President and co-founder, Alif Semiconductor
“The latency, privacy and security benefits of moving AI workloads from the cloud to mobile and embedded IoT devices is well understood by OEMs. This trend will touch an array of markets, but key to the success of this transformation will be the compute clusters capable of supporting these workloads such as the new Cortex-M55 and Ethos-U55 processors from Arm, and production-grade ML development tools.”
Brad Scott, CEO, Au-Zone
“Barriers to AI adoption include cost, power, consumption, performance, and software support limitations. By introducing this new technology, Arm is accelerating AI innovation on Bestechnic Bluetooth audio system-on-chip for more natural voice interaction with smart devices, such as voice assistants on TWS earbuds, by enabling enhanced digital signal processing and machine learning techniques within stringent cost and power budgets.”
Liang Zhang, CEO, Bestechnic
“Cypress solutions help designers create smart, secure IoT edge devices. As the ML landscape rapidly evolves, we see a clear opportunity for real-time, flexible endpoint solutions. The new Arm Cortex-M55 processor provides the efficient compute platform necessary for ML tasks, while staying within the power and form-factor limitations that define these applications.”
Vikram Gupta, Senior Vice President, ICW Business Unit, Cypress
“Signal processing is key to rendering immersive audio experience in compact form factors such as smart speakers. The Arm Cortex-M55 processor will help Dolby further revolutionize entertainment with its higher digital signal processing performance and power efficiency, enabling chip manufacturers and OEMs to bring Dolby Atmos to more products within their portfolio.”
Mahesh Balakrishnan, Vice President, Audio Business, Dolby
“Google and Arm have been collaborating to fully optimize TensorFlow on Arm’s architecture, enabling machine learning on embedded devices for very power-constrained and cost-sensitive applications, often deployed without network connectivity. This new IP from Arm furthers our shared vision of billions of TensorFlow-enabled devices using ML at the endpoint. These devices can run neural network models on batteries for years, and deliver low-latency inference directly on the device.”
Ian Nappier, Product Manager, TensorFlow Lite for Microcontrollers, Google
“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
“Our Qeexo AutoML platform can automatically build ‘TinyML’ solutions, the lightweight machine learning that brings the benefit of intelligence to all sorts of small devices. Arm’s new Cortex-M55 and Ethos-U55 processors allow Qeexo to further innovate embedded ML solutions for endpoint devices with the combination of unprecedented high performance, low latency, and ease of developing machine learning for microcontrollers.”
Sang Won Lee, CEO, Qeexo
“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
“The new Arm Cortex-M55 technology offers the enhanced ML performance and efficiency needed for the next generation of ST microcontrollers. Its support in the STM32Cube.AI tools and ecosystem means this new technology will be simple, fast and optimized to use for all STM32 developers, improving the already wide range of AI applications accessible to them.”
Ricardo De Sa Earp, General Manager, Microcontroller Division, STMicroelectronics