Nordic Semiconductor, a provider of low power wireless connectivity solutions, has released its nRF54L Series SoC with NPU and Nordic Edge AI Lab, enabling greater ease for developers when running AI directly on devices, and providing greater power efficiency.
nRF54LM20B, the company’s latest system-on-chip designed for IoT and embedded devices, offers ultra-low-power and large-memory wireless SoC with Axon NPU. Nordic Semiconductor has also integrated an Axon neural processing unit, helping run AI workloads efficiently and directly on devices. Its Nordic Edge AI Lab is a new development tool, simplifying and boosting edge AI development.
Vegard Wollan, CEO at Nordic Semiconductor, commented on the importance of Edge AI. “Edge AI is […] the only way to deliver safety, privacy, and sustainability at scale. Nordic’s edge AI solution enables millisecond decisions without round-trip latency to the cloud, ensures compliance through local processing, and delivers radically improved battery life for billions of connected devices.”
Axon AI technology enables scalable, battery-friendly AI at the Edge
With the release of the nRF54LM20B SoC, Nordic’s introduces its first large-memory member of the NRF54L Series, also including Axon technology, like the Axon Neural Processing Unit, following Nordic’s purchase of Atlazo in 2023. The unit acts as an “ultra-efficient AI hardware accelerator,” running demanding AI tasks and workloads more efficiently than standard CPUs, the company says.
Axon can reportedly deliver performances up to seven times faster than competing solutions, as well as being eight times as efficient for tasks including keyword spotting and classification.
The nRF54LM20B is compatible with the Axon NPU with 2 MB NVM, 512 KB RAM, high-speed USB, a 128 MHz Arm Cortex-M33 plus RISC-V coprocessor, reaching 66 GPIOs, and Nordic Semiconductor’s fourth-generation ultra-low-power 2.4 GHz radio that supports modern wireless standards like Bluetooth LE, Bluetooth Channel Sounding, and more.
Big intelligence & tiny models with Neuton Edge AI
Neuton’s CPU-run edge AI models are truly minuscule, generally under 5 KB, but are as much as ten times faster and more efficient than competing CPU-powered models. Through Nordic Edge AI Lab, developers can produce new Neuton models for detecting anomalies, monitoring biometrics, and recognising activities. In turn, this protects user privacy and uses very little power and memory, proving to be highly practical, even for smaller, battery-powered devices.
According to Oyvind Strom, EVP Short-Range BU at Nordic Semiconductor, Nordic’s latest offerings makes “advanced on-device AI practical for every embedded developer.”
With devices increasingly moving to the edge, manufacturers will need to find new OTA management methods. Although intelligence continues to move to the edge, cloud-based services remain key for managing and monitoring devices, as well as location services.
By collecting and analysing real-time data from deployed devices, manufacturers can then enhance features and improve performance without interrupting the user experience. The, essentially, allows connected products to evolve further, both securely and efficiently. Nordic’s hardware, models, and software ecosystem is set to be at the forefront of this, enabling developers to bring intelligent, low-power, edge AI to billions of IoT devices.
(Image source: “Stockholm – Centralbron (Central Bridge)” by Olof S is licensed under CC BY 2.0.)
Want to learn more about IoT from industry leaders? Check out IoT Tech Expo taking place in Amsterdam, California, and London. The comprehensive event is part of TechEx and co-located with other leading technology events. Click here for more information.
IoT News is powered by TechForge Media. Explore other upcoming enterprise technology events and webinars here.
