Xilinx has released the first product in a new portfolio called Kria K26 SOM (system on module), which targets vision artificial intelligence (AI) applications in smart cities.
The company describes the new Kria portfolio of adaptive SOMs as embedded boards that enable rapid deployment in edge-based applications.
Kirk Saban, vice president, product and platform marketing at Xilinx, says: “The Kria SOM portfolio expands our market reach into more edge applications and will make the power of adaptable hardware accessible to millions of software and AI developers.”
Xilinx says Kria SOMs enable rapid deployment by providing an end to end board-level solution with a pre-built software stack.
Kria SOMs can reduce time to deployment by up to nine months by allowing developers to start at a “more evolved point” in the design cycle compared to chip-down design, the company adds.
The SOM also features 4GB of DDR4 memory and 245 IOs, which Xilinx insists allows it to adapt to virtually any sensor or interface.
The company claims the Kria K26 SOM comes with 1.4 tera-ops of AI compute, enabling developers to create vision applications offering more than three times higher performance at lower latency and power compared to graphics processing unit-based SOMs, critical for traffic cameras.
Additionally, Xilinx is collaborating with computer software company Canonical to provide Ubuntu Linux support, a Linux distribution used by AI developers.
According to Xilinx, this offers “widespread familiarity” with AI developers and interoperability with existing applications.
Thibaut Rouffineau, vice president of marketing at Canonical/Ubuntu, says: "For smart vision applications, developers and innovators want the Ubuntu experience they're used to from cloud to desktop. Together with Xilinx, we’re excited to provide Kria SOM customers with out-of-the-box productivity, frictionless transition from development to production, and guaranteed stability and security in the field."
The Kria KV260 Vision AI Starter Kit provides a development platform for designing vision applications. It supports accelerated vision applications available in the Xilinx App Store.
