SOM accelerates deployment of edge-based applications
Article By : Susan Nordyk
The Kria K26 adaptive system-on-module (SOM) from Xilinx is a production-ready embedded board for rapid deployment of edge-based applications.
The Kria K26 adaptive system-on-module (SOM) from Xilinx is a production-ready embedded board for rapid deployment of edge-based applications. Aimed at vision AI applications in smart cities and smart factories, the Kria K26 is based on the Zynq UltraScale+ MPSoC architecture, which leverages a quad-core Arm Cortex A53 processor, >250,000 logic cells, and an H.264/265 video codec.
With 1.4 tera-ops of AI compute power, the Kria K26 enables developers to create vision AI designs that offer more than three times the performance of GPU-based SOMs. Its lower latency and power are critical for smart-vision applications like security, traffic and city cameras, retail analytics, machine vision, and guided robotics. The 77×60×11-mm SOM packs 4 Gbytes of DDR4 memory and 245 I/Os, permitting it to adapt to virtually any sensor or interface.
A starter kit for the Kria K26 SOM lets engineers develop vision applications right out-of-the-box. The Kria KV260 kit is purpose-built to support accelerated vision applications available in the Xilinx app store. Get up and running in less than an hour with no knowledge of FPGAs or FPGA tool.
The Kria KV260 vision AI starter kit costs $199. When ready to move to deployment, customers can seamlessly transition to the Kria K26 production SOM, including commercial and industrial variants priced at $250 and $350, respectively. The starter kit is available immediately, while the commercial-grade Kria K26 SOM ships in May 2021 and the industrial-grade K26 SOM ships this summer.
Find more datasheets on products like this one at Datasheets.com, searchable by category, part #, description, manufacturer, and more.
This article was originally published on EDN.
Related articles:
- RISC-V-enabled SOM aids embedded development
- ReRAM enhances edge AI
- AI hardware acceleration needs careful requirements planning
- Embedded PC meets AI edge-network demands
