Japanese electronics giant Renesas has introduced a microcontroller (MCU) targeted at AI and machine-learning (ML) applications, as well as real-time analytics.

The RA8P1 MCU combines 1GHz Arm Cortex-M85 and 250MHz Cortex-M33 CPU cores with the Arm Ethos-U55 neural processing unit (NPU). This delivers a CPU performance of over 7300 CoreMarks and AI performance of 256GOPS at 500MHz.

Optimised for edge and endpoint AI applications, it uses the Ethos-U55 NPU to offload the CPU for compute intensive operations in convolutional and recurrent neural networks (CNNs and RNNs) to deliver up to 256MACs per cycle that yield 256GOPS performance at 500MHz. The NPU supports most commonly used networks, including DS-CNN, ResNet and Mobilenet TinyYolo. Depending on the neural network used, the Ethos-U55 provides up to 35 times more inferences per second than the Cortex-M85 processor on its own.

The MCUs are manufactured on the 22ULL (22nm ultra-low leakage) process from TSMC, enabling high performance with low power consumption. This process also enables the use of embedded magnetoresistive RAM (MRAM) in the MCUs. MRAM offers faster write speeds along with higher endurance and retention than flash.

“There is explosive growth in demand for high-performance edge AIoT applications,” said Daryl Khoo, vice president at Renesas (www.renesas.com). “We are thrilled to introduce what we believe are the best MCUs to address this trend. The RA8P1 devices showcase our technology and market expertise and highlight the strong partnerships we have built across the industry. Customers are eager to employ these new MCUs in multiple AI applications.”

Paul Williamson, senior vice president at Arm (www.arm.com), added: “The pace of innovation in the age of AI is faster than ever, and new edge use cases demand ever-improving performance and machine learning on-device. By building on the advanced AI capabilities of the Arm compute platform, Renesas’ RA8P1 MCUs meet the demands of next-generation voice and vision applications, helping to scale intelligent, context-aware AI experiences.”

Renesas has integrated dedicated peripherals, memory and security to address voice and vision AI and real-time analytics applications. For vision AI, a 16bit camera interface (CEU) is included that supports sensors up to 5Mpixels, enabling camera and demanding vision AI applications. A separate MIPI CSI-2 interface offers a low pin-count interface with two lanes, each up to 720Mbit/s. In addition, multiple audio interfaces including I²S and PDM support microphone inputs for voice AI applications.

The RA8P1 (www.renesas.com/en/products/ra8p1) offers on-chip and external memory options for efficient, low latency neural network processing. The MCU includes 2Mbyte SRAM for storing intermediate activations or graphics framebuffers. And 1Mbyte of on-chip MRAM is available for application code and storage of model weights or graphics assets. High-speed external memory interfaces are available for larger models. SIP options with 4 or 8Mbyte of external flash in a single package are also available for more demanding AI applications.

Renesas has also introduced RUHMI (Renesas Unified Heterogenous Model Integration), a framework for MCUs and MPUs. RUHMI offers efficient AI deployment of the latest neural network models in a framework agnostic manner. It enables model optimisation, quantisation, graph compilation and conversion, and generates efficient source code.

RUHMI provides native support for machine-learning AI frameworks such as TensorFlow Lite, Pytorch and ONNX. It also provides the necessary tools, APIs, code-generator and runtime needed to deploy a pre-trained neural network, including ready-to-use application examples and models optimised for the RA8P1. RUHMI is integrated with Renesas’ e² Studio IDE to allow seamless AI development. This integration will facilitate a common development platform for MCUs and MPUs.

The MCUs provide security for critical applications. The Renesas Security IP (RSIP-E50D) includes numerous cryptographic accelerators, including CHACHA20, Ed25519, NIST ECC curves up to 521bit, enhanced RSA up to 4K, SHA2 and SHA3. In concert with Arm TrustZone, this provides comprehensive and integrated secure element-like functionality.

The MCUs also provides hardware root-of-trust and secure boot with first-stage bootloader (FSBL) in immutable storage. XSPI interfaces with decryption-on-the-fly (DOTF) allow encrypted code images to be stored in external flash and decrypted on the fly as they are securely transferred to the MCU for execution.

Tools for the MCUs including a flexible software package (FSP), evaluation kits and development tools. FreeRTOS and Azure RTOS are supported, as is Zephyr. Several Renesas software example projects and application notes are available to enable faster time to market. In addition, numerous partner products support development with the RA8P1, including a driver monitoring option from Nota.AI and a traffic and pedestrian monitoring product from Irida Labs. Other options can be found at www.renesas.com/en/products/microcontrollers-microprocessors/ra-cortex-m-mcus/ra-partners.