New AI software framework eases development and enables easy migration with MPUs.
Jul. 03, 2025 –
Renesas Electronics Corporation introduced the RA8P1 microcontroller (MCU) Group designed for artificial intelligence (AI), machine learning (ML), and real-time analytics applications. The MCUs integrate a 1GHz Arm Cortex-M85 core and a 250MHz Cortex-M33 core, along with the Arm Ethos-U55 Neural Processing Unit (NPU). This configuration delivers CPU performance of over 7300 CoreMarks and AI processing capabilities of 256 GOPS at 500 MHz.
The RA8P1 microcontroller is designed for edge and endpoint AI applications. It incorporates the Ethos-U55 Neural Processing Unit (NPU), which handles compute-intensive tasks associated with Convolutional and Recurrent Neural Networks (CNNs and RNNs), enabling 256 multiply-accumulate operations per cycle, or 256 GOPS at 500 MHz. The NPU supports commonly used models such as DS-CNN, ResNet, MobileNet, and TinyYOLO. Depending on the network type, the Ethos-U55 can deliver significantly more inferences per second compared to using the Cortex-M85 processor alone.
The RA8P1 MCUs are manufactured on the 22ULL (22nm ultra-low leakage) process from TSMC, enabling ultra-high performance with very low power consumption. This process also enables the use of embedded Magnetoresistive RAM (MRAM) in the new MCUs. MRAM offers faster write speeds along with higher endurance and retention compared with Flash...