Renesas Electronics Releases RZ/V Series Devices with Built-in Vision AI Accelerator

Renesas Electronics has introduced a new RZ/V2MA device capable of processing image data from multiple cameras, further expanding its RZ/V series microprocessor (MPU) lineup and bringing a new level of high-precision image recognition capability to vision AI applications. The new device integrates two 64-bit Arm® Cortex®-A53 cores that deliver high computational performance at a maximum operating frequency of 1 GHz, and a proprietary low-power DRP-AI (Dynamically Reconfigurable Processor) gas pedal that can process image data at 1 TOPS/W (million operations per second per watt) performance.

The RZ/V2MA device is equipped with high-speed interfaces such as Ethernet, USB and PCI Express, allowing image input from multiple external cameras. In addition to the DRP-AI gas pedal, the RZ/V2MA includes an OpenCV gas pedal to perform rule-based image processing simultaneously. These features allow machine vision products such as AI gateways, video servers, security gates, POS terminals and robotic arms to gain high-precision image recognition capabilities.

The new RZ/V2MA comes with a full suite of development tools to aid vision AI system design. In addition to the existing DRP-AI Translator, the new device adds DRP-AI TVM (Note 2) based on the open-source deep learning compiler Apache TVM technology (Note 1).The DRP AI Translator is designed to convert AI models into DRP-AI executables, while the DRP-AI TVM compiler lets the DRP-AI gas pedal work with the CPUs to work together, enabling DRP-AI to convert and generate more AI models than ever before. Renesas is targeting the first phase of industry development to provide support for ONNX and PyTorch AI models, with plans to support Tensorflow in the future.

"One of the challenges for embedded system developers who want to implement machine learning is keeping up with the latest AI models that are constantly evolving," said Shigeki Kato, vice president of the Enterprise Infrastructure Business Unit at Renesas Electronics. With the new DRP-AI TVM tool, Renesas brings designers the choice of extending AI frameworks and AI models. These frameworks and models can be converted into executable formats, enabling them to leverage new AI models to build cutting-edge Image recognition capabilities."

"The Renesas RZ/V series is ideal for embedded devices," said Chiharu Nakabayashi, president of amnimo Inc., a wholly-owned Yokogawa subsidiary and provider of IoT and AI-based services. Power consumption and heat, so there is no need for fans or heat sinks. With these devices, we are confident to develop a powerful image AI gateway that can be installed in any occasion."

Key Features of the RZ/V2MA

• Dual 64-bit Arm Cortex-A53 cores operating up to 1GHz
• AI gas pedal DRP-AI (1 TOPS/W class), reaching 52 fps (frames per second) when executing the TinyYoloV3 program
• OpenCV gas pedal for rule-based image processing
• Ethernet, USB and PCI Express interfaces for external camera image inputs
• Video codecs (H.265 and H.264)
• DRP-AI TVM tool for converting AI models based on TVM technology; ONNX and PyTorch formats are supported at this stage
• High-speed memory interfaces including LPDDR4 (3200Mbps), USB 3.1 (up to 5Gbps) and PCI Express (2 lanes)
• Available in 15mm square BGA package

If you like this article, may wish to continue to pay attention to our website Oh, later will bring more exciting content. If you have product needs, please contact us