This month has seen Advanced Micro Devices Inc. (AMD) introduce the AMD Embedded+ architecture, integrating Ryzen Embedded processors with Versal adaptive SoCs into a scalable, power-efficient board designed to speed up the development for ODM partners.
Aimed at enhancing performance for smart devices and robots by processing sensor data swiftly, AMD combines decades of innovation in computing and graphics to support applications across medical, industrial, and automotive sectors. Embedded+ is touted as the first to blend AMD x86 computing, integrated graphics, and programmable I/O for AI-inferencing and sensor-fusion tasks. It features low-latency processing, efficient AI inferencing, and Radeon graphics for superior multimedia experiences. System designers can access a variety of ODM board options based on Embedded+ to meet diverse performance and power needs. Sapphire Technology launched the first ODM system using this architecture, the Sapphire Edge+ VPR-4616-MB, offering comprehensive capabilities with minimal power consumption. This system is now available for purchase.
“In automated systems, sensor data has diminishing value with time and must operate on the freshest information possible to enable the lowest-latency, deterministic response,” stated Chetan Khona, senior director of industrial, vision, healthcare, and sciences markets at AMD, in a release.
“In industrial and medical applications, many decisions need to happen in milliseconds,” he continued. “Embedded+ maximizes the value of partner and customer data with energy efficiency and performant computing that enables them to focus in turn on addressing their customer and market needs.”
Khona also said that there is an increasing reliance on diverse sensor data across various applications. He raised a question about how to transfer sensor data from autonomous systems into a PC when it is not connected via USB or some consumer interface. He also mentioned that the market for processing closer to the sensor is expanding quickly. Furthermore, Khona explained that the use cases for embedded AI are on the rise, with projections showing the machine vision market growing to $600 million and sensor data analysis reaching $1.4 billion by 2028.
“AMD makes the path to sensor fusion, AI inferencing, industrial networking, control, and visualization simpler with this architecture and ODM partner products,” said Khona, explaining further that the single motherboard is compatible with various sensor types, enabling processing to be offloaded and situational awareness to be enhanced.
