The 64-bit chip runs video, handles AI tasks like voice and image, moves data fast, and saves power in machines and devices.
Renesas has launched the RZ/G3E, a 64-bit microprocessor built for edge AI and Human Machine Interface (HMI) systems in factories, hospitals, retail setups, and smart buildings. It supports Full HD video, real-time sensing, and fast data transfers, making it fit for high-performance embedded devices.
At the core, the RZ/G3E integrates a quad-core Arm® Cortex®-A55 running at up to 1.8GHz, along with a Cortex-M33 core and a built-in Ethos-U55 Neural Processing Unit (NPU). This combination enables efficient AI tasks such as image and voice recognition, object detection, and system anomaly detection—while keeping CPU usage low.
The chip supports dual-display Full HD video at 60fps through interfaces like LVDS, MIPI-DSI, and RGB, along with a MIPI-CSI input for camera support. These features make it suitable for video-based HMIs and smart sensing.
Designed for edge computing, the RZ/G3E includes high-speed PCI Express 3.0 (2 lanes) for 8Gbps bandwidth, USB 3.2 Gen2 for 10Gbps transfer, and dual-channel Gigabit Ethernet to enable seamless connections with cloud services, external storage, and 5G modules.
Power management is another key feature. The processor supports low-power standby at just 50mW and deep standby at around 1mW. Its DDR self-refresh function helps retain memory during sleep, allowing fast Linux resume when needed.
“The RZ/G3E builds on the proven performance of the RZ/G series with the addition of an NPU to support AI processing,” said Daryl Khoo, Vice President of Embedded Processing at Renesas. “By using the same Ethos-U55 NPU as our recently announced RA8P1 microcontroller, we’re expanding our AI embedded processor portfolio and offering a scalable path forward for AI development. These advancements address the demands of next-generation HMI applications across vision, voice and real-time analytics with powerful AI capabilities.”