ICs & Semiconductors

Renesas has expanded its RZ/V Series of microprocessors (MPUs) with a new device that targets the high-volume vision AI market. Similar to its high-end device, the RZ/V2H, the new RZ/V2N MPU comes with Renesas’ proprietary AI accelerator, DRP (Dynamically Reconfigurable Processor)-AI3, boasting 10 TOPS/W (Tera Operations Per Second Per Watt) power efficiency and an AI inference performance of up to 15 TOPS through its advanced pruning (Note 1) technology. With the latest addition of the RZ/V2N, the RZ/V series has now expanded to cover a full range of markets, from the low-end RZ/V2L (0.5TOPS) to the high-end RZ/V2H (up to 80 TOPS).

The new MPU is significantly smaller than the RZ/V2H, with its package area measuring only 15 mm square, reducing the area required for mounting by 38%. Inheriting the advanced features of the RZ/V series, the RZ/V2N combines high AI performance with low power consumption. These optimised features suppress heat generation, eliminating the need for additional cooling fans and reducing the size and cost of embedded systems. Developers can easily implement vision AI in a wide range of applications, from AI cameras for traffic and congestion analysis in commercial facilities, industrial cameras for visual inspection on production lines, to driver monitoring systems for behaviour analysis.

Double-angle image processing with two cameras
Similar to the RZ/V2H, the new RZ/V2N is equipped with four best-in-class Arm Cortex-A55 CPU cores and a single Cortex-M33 core, coupled with a high-quality image signal processor (ISP), Arm Mali-C55. The RZ/V2N also has two channels of MIPI camera interfaces, which allow two cameras to be connected to capture double-angle images. The two-camera system significantly improves spatial recognition performance compared to a single camera system and enables more precise human motion line analysis and fall detection. Furthermore, the dual-camera system captures images from different locations, allowing a single chip to count cars in a parking lot and recognise license plates efficiently.

“Since launching the RZ/V2H last year to target next-generation robotics requiring vision AI and real-time control, we have received tremendous interest in using the Renesas DRP-AI accelerator,” said Daryl Khoo, VP of Embedded Processing at Renesas. “With the addition of the RZ/V2N, sharing the same lineage as the RZ/V2H, we are extending our reach to address mid-range applications, particularly endpoint vision AI that does not need to be realised with power hungry designs. I am excited that our customers will be able to select the best AI MPU from Renesas that meets their system and budget requirements.”

“Vision AI applications across markets including smart city, enterprise and industrial are broad and varied, but all demand sustained performance and efficient processing,” said Paul Williamson, senior vice president and general manager, IoT Line of Business at Arm. “Renesas’ new RZ/V2N MPU leverages the leading-edge capabilities of the Arm compute platform to deliver against the performance and efficiency needs of next generation vision AI use cases.”

The RZ/V2N will be available with the Renesas evaluation board kit and a software development environment, along with various AI applications covering more than 50 use cases that are provided in the AI Applications and AI SDK (GitHub). The SDK assists users without in-depth AI knowledge to quickly evaluate and develop AI applications, shortening time to market. Additionally, partner companies will provide a SOM (system-on-module) board, SBC (single board computers), camera modules, and other products that incorporate the Renesas RZ/V2N. This reduces hardware design work, allowing developers to focus on AI application development and bring their products to market rapidly.

Renesas has developed the AI Camera Solution, which targets a variety of applications, including factories, public facilities, and commercial facilities. This solution consists of the RZ/V2N, power management IC, and real-time clock IC, and can be used as a reference for AI camera systems.

https://www.renesas.com/rzv2n