The RA8P1 microcontroller (MCU) Group was unveiled by Renesas Electronics with an eye toward real-time analytics, machine learning (ML), and artificial intelligence (AI) applications. By fusing the Arm Ethos-U55 Neural Processing Unit (NPU) with 1GHz Arm® Cortex®-M85 and 250MHz Cortex-M33 CPU cores, the new MCUs set a new benchmark for MCU performance. The maximum CPU performance of over 7300 CoreMarks and AI performance of 256 GOPS at 500 MHz are provided by this combo.
Designed for Edge/Endpoint AI
With the Ethos-U55 NPU offloading the CPU for compute-intensive tasks in Convolutional and Recurrent Neural Networks (CNNs and RNNs), the RA8P1 is suited for edge and endpoint AI applications. It can deliver up to 256 MACs per cycle, which translates to 256 GOPS performance at 500 MHz.
The most widely used networks, such as DS-CNN, ResNet, Mobilenet TinyYolo, and others, are supported by the new NPU.
The Ethos-U55 may make up to 35 times as many inferences per second as the Cortex-M85 CPU alone, depending on the neural network being used.
Advanced Technology
The 22ULL (22nm ultra-low leakage) process used by TSMC to create the RA8P1 MCUs allows for extremely high performance at very low power consumption. Additionally, this method makes it possible for the new MCUs to incorporate embedded Magnetoresistive RAM (MRAM). Compared to Flash, MRAM has higher durability and retention as well as faster write speeds.
Robust, Optimized Peripheral Set for AI
To handle voice and vision AI and real-time analytics applications, Renesas has combined specialized peripherals, lots of memory, and cutting-edge security. A 16-bit camera interface (CEU), which supports sensors up to 5 megapixels, is incorporated for vision AI, enabling camera and demanding Vision AI applications.
An independent MIPI CSI-2 interface provides two lanes with a pin count of 720 Mbps each. Additionally, microphone inputs for spoken AI applications are supported via a number of audio interfaces, including as I2S and PDM.
For effective, low latency neural network computation, the RA8P1 provides both external memory and on-chip memory choices. For storing graphics framebuffers or intermediary activations, the MCU has 2MB of SRAM.
Additionally, application code and model weights or graphics assets can be stored in 1MB of on-chip MRAM. For larger versions, high-speed external memory connectors are available. SIP options with 4 or 8 MB of external flash in a single package are also available for more demanding AI applications.
New RUHMI Framework
Renesas has unveiled RUHMI (Renesas Unified Heterogenous Model Integration), a comprehensive framework for MCUs and MPUs, in addition to the RA8P1 MCUs.
RUHMI provides framework-agnostic, effective AI deployment of the newest neural network models. It produces effective source code and makes model optimization, quantization, graph compilation, and conversion possible.
Machine-learning AI frameworks like TensorFlow Lite, Pytorch, and ONNX are natively supported by RUHMI. Additionally, it offers the code-generator, runtime, APIs, and ready-to-use application examples and RA8P1-optimized models required to deploy a pre-trained neural network.
To enable smooth AI development, RUHMI is linked with Renesas’s proprietary e2 Studio IDE. A shared platform for MCU and MPU development will be made possible by this connection.
Advanced Security Features
Advanced security is offered by the RA8P1 MCUs for crucial applications. Numerous cryptographic accelerators, such as SHA2, SHA3, NIST ECC curves up to 521 bits, improved RSA up to 4K, CHACHA20, and Ed25519, are included in the new Renesas Security IP (RSIP-E50D).
This offers a thorough and completely integrated secure element-like functionality when used in conjunction with Arm TrustZone®. Secure Boot with First Stage Bootloader (FSBL) and robust hardware Root-of-Trust are also features of the new MCUs in immutable storage.
Securely transferring encrypted code images to the MCU for execution while decrypting them in real time is made possible by XSPI interfaces with decryption-on-the-fly (DOTF).
Ready to Use Solutions
Renesas provides a wide range of easy-to-use tools and solutions for the RA8P1 MCUs, including the 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 solutions are available to support development with the RA8P1 MCUs, including a driver monitoring solution from Nota.AI and a traffic/pedestrian monitoring solution from Irida Labs.
Key Features of the RA8P1 MCUs
- Processors: 1GHz Arm Cortex-M85, 500MHz Ethos-U55, 250 MHz Arm Cortex-M33 (Optional)Memory: 1MB/512KB On-chip MRAM, 4MB/8MB External Flash SIP Options, 2MB SRAM fully ECC protected, 32KB I/D caches per core
- Graphics Peripherals: Graphics LCD controller supporting resolutions up to WXGA (1280×800), parallel RGB and MIPI-DSI display interfaces, powerful 2D Drawing engine, parallel 16bit CEU and MIPI CSI-2 camera interfaces, 32bit external memory bus (SDRAM and CSC) interface
XSPI (Octal SPI) with XIP and DOTF, SPI, I2C/I3C, SDHI, USBFS/HS, CAN-FD, PDM, and SSI audio interfaces, 16bit ADC with S/H circuits, DAC, comparators, temperature sensors, and timers are additional peripherals.
Protection against DPA/SPA attacks, tamper resistance, secure boot, advanced RSIP-E50D cryptographic engine, TrustZone, secure debug, secure factory programming, and Device Lifecycle management.
Winning Combinations
Renesas has combined the new RA8P1 MCUs with numerous compatible devices from its portfolio to offer a wide array of Winning Combinations, including Video Conferencing Camera with AI Capabilities, AI Drawing Robot Arm and AI-Enabled Surveillance Camera.
These designs are technically vetted system architectures from mutually compatible devices that work together seamlessly to bring an optimized, low-risk design for faster time to market.
Renesas offers more than 400 Winning Combinations with a wide range of products from the Renesas portfolio to enable customers to speed up the design process and bring their products to market more quickly.
They can be found at renesas.com/win.
Leadership Comments
“There is explosive growth in demand for high-performance edge AIoT applications. We are thrilled to introduce what we believe are the best MCUs to address this trend,” said Daryl Khoo, Vice President of Embedded Processing Marketing Division at Renesas. “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.”
“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,” said Paul Williamson, senior vice president and general manager, IoT Line of Business at Arm. “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.”
“It is gratifying to see Renesas harness the performance and reliability of TSMC 22ULL embedded MRAM technology to deliver outstanding results for its RA8P1 devices,” said Chien-Hsin Lee, Senior Director of Specialty Technology Business Development at TSMC. “As TSMC continues to advance our embedded non-volatile memory (eNVM) technologies, we look forward to strengthening our long-standing collaboration with Renesas to drive innovation in future groundbreaking devices.”
Availability
The RA8P1 MCUs are available now. Renesas is also shipping an RA8P1 Evaluation Kit. More information is available at renesas.com/RA8P1. Samples and kits can be ordered either on the Renesas website or through distributors.
Packages: 224BGA, 289BGA
Other solutions can be found at the Renesas RA Partner Ecosystem Solutions Page.
