New microcontrollers usher in new era of smart and efficient edge processing

NXP's new MCX N microcontrollers include the industry's first instantiation of a specialised NPU to allow high performance, low power secure intelligence at the edge

The company has released the MCX N94x and MCX N54x, the first families in the N series of the new MCX microcontroller portfolio. Created to ease design for secure, intelligent edge applications, including IoT and industrial applications, it features the first instantiation of its proprietary Neural Processing Unit (NPU) and an integrated EdgeLock secure subsystem. The series' multicore design improves system performance and lowers power consumption by facilitating smart, efficient distribution of workloads to the analog and digital peripherals.

"Developers are increasingly looking to push the boundaries of what's possible at the edge as they create new devices that can better anticipate and automate in smart homes, smart factories and smart cities. This requires advanced MCUs that are more efficient, simplify edge intelligence and do all of that securely," said Rafael Sotomayor, Executive Vice President and General Manager of Edge Processing and Connectivity and Security, NXP. "As we look to the future of MCUs, the MCX N series delivers the balance between power and performance for tomorrow's IoT and industrial applications."

The series dual-core system couples a full-featured Arm Cortex-M33 core with a streamlined Cortex-M33 to handle control functions, allowing developers to run applications in parallel or decrease power consumption by turning off individual cores as required. For example, in secure IoT applications such as OTA communications, the main core achieves system security, while the streamlined core executes control functionality.

The series is based on dual high-performance Arm Cortex-M33 cores running up to 150MHz, with 2MB of Flash with optional full ECC RAM, a DSP co-processor for audio and voice processing and integrated NPU. The integrated NPU provides up to 30x faster machine learning throughput than a CPU core alone and multiple co-processors and accelerators, allowing it to spend less time awake and lowering overall power consumption. Also, the company's eIQ machine learning software development environment offers easy-to-use tools to train and support machine learning models employing the integrated NPU.