With the MRZG2LS and MRZV2LS, ARIES Embedded provides their first SoMs compliant with the SMARC 2.1 (Smart Mobility Architecture) standard by SGET (Standardization Group for Embedded Technologies e. V.). This standard defines a versatile small form factor computer module targeting applications that require low power, low costs, and high performance.
The AI accelerator “DRP-AI” from Renesas is configured with DRP and AI-MAC. DRP-AI’s excellent power efficiency eliminates the need for heat dissipation measures such as heat sinks or cooling fans. AI can be implemented cost-efficiently, not only in consumer electronics and industrial equipment but also in a wide range of applications such as point-of-sale (POS) terminals for retail. Also, the DRP-AI provides both real-time AI inference and image processing functions with the capabilities essential for camera support, such as color correction and noise reduction. This enables customers to implement AI-based vision applications without requiring an external image signal processor (ISP).
The new SoMs MRZG2LS and MRZV2LS offer a manifold feature set around the single or dual Cortex-A55, up to 1 GHz, and the Cortex-M33. In addition to the optional AI accelerator (DRP-AI on MRZV2L), they have a 3D graphics engine (Arm Mali-G31) and video codec (H.264). The memory options are comprised of 512 MB – 4 GB DDR4 RAM, SPI NOR, and 4 GB – 64 GB eMMC NAND Flash. The SoMs are very flexible and versatile thanks to their broad variety of interfaces, including dual 10/100/1000MBit Ethernet with PHY, USB2.0 Host/OTG, 2x CAN, UART, I2C, SPI, ADC, as well as a MIPI-CSI camera interface and a MIPI-DSI display interface. The temperature range is 0 °C to +70 °C for commercial and -40 °C to +85 °C for industrial environments.
ARIES Embedded supports a quick and smooth start-up into the new architecture with the corresponding evaluation kits MRZG2LSEVK and MRZV2LSEVK. Thanks to their high functionalities, they support developers for quick project entry, help to develop software, and can also be used as platforms for rapid prototyping. The baseboard supports both MRZG2LS and MRZV2LS.
The MRZG2LS and MRZV2LS SoMs will be available in the fourth quarter 2023.