The RA8P1 is optimized for edge and endpoint AI applications, utilizing the Ethos-U55 NPU to offload computationally intensive operations in convolutional and recurrent neural networks (CNNs and RNNs) from the CPU, delivering up to 256 MACs per cycle and 256 GOPS at 500 MHz. The new NPU supports widely used networks such as DS-CNN, ResNet, Mobilenet TinyYolo, and many more. Depending on the neural network used, the Ethos-U55 provides up to 35 times more inferences per second than a Cortex-M85 processor alone.
The RA8P1 MCUs are manufactured using TSMC's 22ULL (22 nm ultra-low leakage) process, enabling ultra-high performance with very low power consumption. This process also allows the use of magnetoresistive RAM (MRAM) integrated into the new MCUs.
MRAM offers faster write speeds, along with greater endurance and retention compared to Flash memory. There is explosive growth in demand for high-performance AIoT applications for peripheral devices.
Renesas has integrated dedicated peripherals, ample memory, and advanced security to support voice and vision AI applications and real-time analytics. For vision AI, a 16-bit camera interface (CEU) is included, supporting sensors up to 5 megapixels, enabling the use of cameras and demanding vision AI applications. A separate MIPI CSI-2 interface provides a low-pin count interface with two lanes, each supporting up to 720 Mbps. Additionally, multiple audio interfaces, including I2S and PDM, support microphone inputs for voice AI applications.
The RA8P1 offers both integrated and external memory options for efficient, low-latency neural network processing. The MCU includes 2 MB of SRAM for storing intermediate activations or graphics frame buffers. An additional 1 MB of integrated MRAM is available for application code and storing model weights or graphics resources. High-speed external memory interfaces are available for larger models. SIP options with 4 or 8 MB of external flash memory in a single package are also available for more demanding AI applications.
Renesas has introduced RUHMI (Renesas Unified Heterogenous Model Integration), a comprehensive environment for MCUs and MPUs. RUHMI offers efficient AI implementation of the latest neural network models, independent of the environment. It enables model optimization, quantization, 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 to deploy a pre-trained neural network, including ready-to-use application examples and models optimized for RA8P1. RUHMI is integrated with the Renesas e2 studio IDE to enable seamless AI development. This integration will facilitate a common development platform for MCUs and MPUs.
The RA8P1 MCUs provide state-of-the-art security for mission-critical applications. Renesas' new Security IP (RSIP-E50D) includes numerous cryptographic accelerators, including CHACHA20, Ed25519, NIST ECC curves up to 521 bits, enhanced RSA up to 4K, SHA2, and SHA3. Combined with Arm TrustZone®, it provides comprehensive, fully integrated, secure element-like functionality. The new MCUs also provide a robust hardware root of trust and secure boot with the First Stage Boot Loader (FSBL) on immutable storage. Decrypt-on-the-fly (DOTF) XSPI interfaces allow encrypted code images to be stored in external flash memory and decrypted on the fly as they are securely transferred to the MCU for execution.
Renesas offers a wide range of user-friendly tools and solutions for RA8P1 MCUs, including the Flexible Software Package (FSP), evaluation kits, and development tools. FreeRTOS and Azure RTOS are supported, as is Zephyr. Several sample software projects and application notes from Renesas are available to accelerate time to market. In addition, numerous partner solutions are available to support development with RA8P1 MCUs, including a controller monitoring solution from Nota.AI and a traffic and pedestrian monitoring solution from Irida Labs. Further solutions can be found on the Renesas RA Partner Ecosystem Solutions page.
Main features of the RA8P1 MCU
Processors: Arm Cortex-M85 at 1 GHz, Ethos-U55 at 500 MHz, Arm Cortex-M33 at 250 MHz (Optional)
Memory: 1 MB/512 KB on-chip MRAM, 4 MB/8 MB optional external SIP flash, 2 MB SRAM with full ECC protection, 32 KB I/D cache per core
Graphics peripherals: Graphics LCD controller supporting resolutions up to WXGA (1280 x 800), RGB display and parallel MIPI-DSI interfaces, powerful 2D drawing engine, parallel 16-bit MIPI CSI-2 and CEU camera interfaces, 32-bit external memory bus interface (SDRAM and CSC)
Other peripherals: Gigabit Ethernet and TSN switch, XSPI (octal SPI) with XIP and DOTF, SPI, I2C/I3C, SDHI, USBFS/HS CAN-FD, PDM, and SSI audio interfaces, 16-bit ADC with S/H circuitry, DAC, comparators, temperature sensor, timers. Security: Advanced RSIP-E50D cryptographic engine, TrustZone, immutable storage, secure boot, tamper resistance, DPA/SPA attack protection, secure debugging, secure factory programming, device lifecycle management.
Packages: 224BGA, 289BGA
Availability: The RA8P1 MCUs are now available. Renesas also markets an RA8P1 evaluation kit.
Samples and kits can be ordered on the Renesas website or through distributors.
