July 2, 2025, Beijing, China – Renesas Electronics Corporation (TSE: 6723), a global supplier of semiconductor solutions, today announced the launch of its RA8P1 microcontroller (MCU) product family, designed for artificial intelligence (AI), machine learning (ML) applications, and real-time analysis. This series of MCUs sets a new benchmark for MCU performance by combining a 1GHz Arm Cortex-M85 and 250MHz Cortex-M33 CPU core with an Arm EthosTM-U55 neural processing unit (NPU). This combination achieves a maximum CPU performance of over 7,300 CoreMark and AI performance of 256 GOPS at 500 MHz.

Designed for edge/endpoint AI
The RA8P1 is optimized for edge AI applications, leveraging the Ethos-U55 NPU to offload computationally intensive operations in convolutional neural networks (CNNs) and recurrent neural networks (RNNs) from the CPU, achieving up to 256 MAC per cycle and 256 GOPS at 500 MHz. The new NPU supports most common neural networks, including DS-CNN, ResNet, Mobilenet, TinyYolo, and more. Depending on the neural network used, the Ethos-U55 achieves up to 35 times the inferences per second compared to a standalone Cortex-M85 processor.

Advanced Technology
The RA8P1 MCU is manufactured using TSMC's 22ULL (22nm ultra-low leakage) process, achieving ultra-high performance while maintaining extremely low power consumption. This process also enables the integration of embedded magnetic random access memory (MRAM) into the new MCU. Compared to flash memory, MRAM offers faster write speeds, higher durability, and stronger data retention capabilities.
Daryl Khoo, Vice President of Embedded Processing Marketing Division at Renesas, said, “The demand for high-performance edge AIoT applications is growing exponentially, and the RA8P1 is our MCU product designed to address this trend. It not only demonstrates our deep technical and market expertise, but also reflects the extensive collaboration ecosystem we have established with industry partners. Renesas' customers have expressed strong interest in deploying this new MCU in a variety of AI scenarios. “
Paul Williamson, Senior Vice President and General Manager, IoT Line of Business at Arm, said: “The pace of innovation in the AI era is faster than ever before, and new edge applications place higher demands on device performance and machine learning. The Renesas RA8P1 MCU leverages the advanced AI capabilities of the Arm computing platform to meet the needs of next-generation voice and vision applications, enabling the expansion of intelligent, context-aware AI experiences.”
Chien-Hsin Lee, Senior Director of Specialty Technology Business Development at TSMC, said: “We are delighted to see Renesas fully leveraging the performance and reliability of TSMC's 22ULL embedded MRAM technology to deliver exceptional results for its RA8P1. As TSMC continues to advance embedded non-volatile memory (eNVM) technology, we look forward to strengthening our long-term collaboration with Renesas to drive innovation in future breakthrough products.”

Rich peripherals, designed specifically for AI
Renesas' RA8P1 integrates dedicated peripherals, ample memory, and advanced security features to support voice and vision AI as well as real-time analytics applications. For vision AI, the device includes a 16-bit camera interface (CEU) that supports image sensors with up to 5 million pixels, enabling vision AI applications that require camera connectivity and demanding computational power. An independent MIPI CSI-2 interface provides a low-pin-count interface with two channels, each capable of up to 720 Mbps. Additionally, multiple audio interfaces (including I2S and PDM) support microphone input, meeting the needs of voice AI applications.
The RA8P1 integrates on-chip storage and expandable external storage to enable efficient, low-latency neural network processing. The MCU includes 2 MB of SRAM for storing intermediate variables or buffers. Additionally, the product features 1 MB of on-chip MRAM for storing application code, model weights, or graphics resources. For larger models, a high-speed external memory interface is available. For more demanding AI application requirements, this MCU also offers SIP options with 4 MB or 8 MB of external flash memory in a single package.

New RUHMI Framework
Launched alongside the RA8P1 MCU is Renesas RUHMI (Renesas Unified Heterogeneous Model Integration). As a comprehensive AI compiler and framework for MCUs and MPUs, RUHMI provides efficient AI tools capable of deploying various state-of-the-art neural network models. It supports model optimization, quantization, graph compilation, and conversion, generating efficient, MCU-compatible source code. RUHMI natively supports machine learning AI development frameworks such as TensorFlow Lite, Pytorch, and ONNX, and provides the tools, APIs, code generators, and runtime environments needed to deploy pre-trained neural networks, including demonstration use cases for the RA8P1. In addition, RUHMI integrates with Renesas' proprietary e2Studio IDE for seamless AI development, providing a common development platform for MCUs and MPUs.

Advanced security features
The RA8P1 MCU provides cutting-edge security for critical applications. The new Renesas Security IP (RSIP-E50D) integrates numerous cryptographic accelerators, including CHACHA20, Ed25519, NIST ECC curves up to 521 bits, enhanced RSA up to 4K, SHA2, and SHA3. Working in conjunction with Arm TrustZone, this IP enables comprehensive and fully integrated security functionality similar to a security element. The new MCU also features a robust hardware root of trust and secure boot functionality via the first-stage boot loader (FSBL) in immutable memory (ROM). The XSPI interface, which supports real-time decryption (DOTF), allows encrypted code programs to be stored in external flash memory and decrypted in real time during secure transmission to the MCU for execution.

Ready-to-use solutions
Renesas has developed a range of easy-to-use tools and solutions for the RA8P1 MCU, including flexible software packages (FSP), evaluation kits, and development tools supporting FreeRTOS, Azure RTOS, and Zephyr. Renesas also provides multiple software example projects and application notes to help customers accelerate time-to-market. Additionally, numerous partner solutions support RA8P1 MCU development, including driver monitoring solutions from Nota.AI and traffic/pedestrian monitoring solutions from Irida Labs. For more solutions, please refer to the RA Partner Ecosystem Solutions.

Key features of the RA8P1 MCU
Processor: 1GHz Arm Cortex-M85, 500MHz Ethos-U55, 250MHz Arm Cortex-M33 (optional)
Memory: 1MB/512KB on-chip MRAM, 4MB/8MB external flash SIP options, 2MB fully ECC-protected SRAM, 32KB I/D cache per core
Graphics Peripherals: Graphics LCD controller supporting up to WXGA (1280x800) resolution, parallel RGB and MIPI-DSI display interfaces, powerful 2D graphics engine, parallel 16-bit CEU and MIPI CSI-2 camera interfaces, 32-bit external memory bus (SDRAM and CSC) interface
Other peripherals: Gigabit Ethernet and TSN switch, XSPI (8-wire SPI) with XIP and DOTF, SPI, I2C/I3C, SDHI, USBFS/HS, CAN-FD, PDM and SSI audio interfaces, 16-bit ADC with S/H circuit, DAC, comparator, temperature sensor, timer
Security features: High-performance RSIP-E50D encryption engine, TrustZone, immutable memory, secure boot, tamper-proofing, DPA/SPA attack protection, secure debugging, secure factory programming, device lifecycle management
Package: 224BGA, 289BGA

Successful Product Combinations
Renesas combines its new RA8P1 MCU with a wide range of compatible components from its product portfolio to create a broad range of “successful product combinations,” including AI-enabled video conferencing cameras, AI-powered robotic arms, and AI surveillance cameras. These “successful product combinations” are based on mutually compatible and seamlessly interoperable products, featuring technically validated system architectures that enable optimized, low-risk designs to accelerate time-to-market. Renesas has now launched over 400 “successful product combinations” based on various products in its product lineup, enabling customers to accelerate the design process and bring products to market faster.

Renesas MCU Advantages
As a leading global supplier of MCU products, Renesas Electronics' MCUs have averaged over 3.5 billion units shipped annually in recent years, with approximately 50% used in the automotive sector and the remainder in industrial, IoT, data centers, and communication infrastructure applications. Renesas offers a broad portfolio of 8-bit, 16-bit, and 32-bit products, providing exceptional quality, efficiency, and performance. As a trusted supplier, Renesas leverages decades of MCU design experience, a dual-source production model, industry-leading MCU process technology, and a robust ecosystem of over 250 partners.

About Renesas Electronics
Renesas Electronics (TSE: 6723) is committed to making life easier through technology, striving to create a safer, smarter, and more sustainable future. As a global microcontroller supplier, Renesas Electronics integrates expertise in embedded processing, analog, power, and connectivity to provide comprehensive semiconductor solutions. Its successful product portfolio accelerates the time-to-market for automotive, industrial, infrastructure, and IoT applications, empowering billions of connected smart devices to enhance people's work and lifestyle.