Based on Renesas' Smart Mobility ARChitecture (SMARC), the scalable System-on-Module (SoM) consists of ten ICs with microprocessor, power and analog chips. The board solution accelerates the development of applications for IoT face/object recognition with artificial intelligence (AI), image processing and 4K video playback, surveillance cameras, test equipment, and HMI and embedded vision systems for industrial and building automation.
The scalable SoM board in the 82 mm x 80 mm form factor is based on the SMARC 2.0 industry standard. It offers a choice of three scalable versions of Renesas' 64-bit RZ/G2 MPU: RZ/G2N with dual-core Arm Cortex-A57 (1.5 GHz) for medium performance; RZ/G2M with dual-core Cortex-A57 and quad-core Cortex-A53 (1.2 GHz) for high performance; and RZ/G2H with quad-core Cortex-A57 and quad-core Cortex-A53 for ultra-high performance. All three MPUs (two cores up to eight cores) offer integrated 600 MHz PowerVR 3D graphics, as well as 4K UHD H.265 and H.264 codecs for different data processing requirements. The AI SMARC SoM Combo Solution Board was designed by Renesas and developed together with RelySys Technologies.
The SMARC 2.0 SoM board supports dual-band Wi-Fi and Bluetooth Low Energy for wireless communication as well as fast communication interfaces such as USB, SATA, LVDS, HDMI, CSI, I2S, PCIe and Gigabit Ethernet. It includes a real-time clock for calendar-based applications powered by a small 400nA battery or supercapacitor during a power interruption. A power management IC (P8330) is provided to power multiple power rails. Two programmable clocks from Renesas (VersaClock 3S) with a small form factor and integrated DCO (32.768 kHz) are powered by a button cell in the event of a power interruption. The PCIe clock is generated by the Renesas 9FGV0641, which generates six differential 100 MHz clock outputs and supports PCIe Gen 1-4.
