Military Embedded Systems

AMD releases new Versal series targeting military radar, SIGINT applications


April 28, 2022

John McHale

Editorial Director

Military Embedded Systems

AMD releases new Versal series targeting military radar, SIGINT applications

SAN JOSE, California. Military radar and signals intelligence (SIGINT) applications require intensive signal processing to fuel artificial intelligence (AI) aimed at the never ending data these systems produce. With that in mind AMD engineers announced their Versal Premium series with AI Engines.

For radar applications the solution enables radar wireless testers, digital array radar (DAR), adaptive beamforming, space time adaptive processing (STAP), and synthetic aperture radar (SAR). For SIGINT applications it targets RF machine learning; digital RF memory (DRFM), direction finding, and digital receivers/exciters (DREX).

For radar systems this solution will add a lot more capability, huge increase in AI and faster overall responsiveness. This is low latency processing, says Manuel Uhm, Director, Versal Marketing, AMD.

“In radar beamforming applications, the heterogenous compute engines enable 67% smaller footprint and up to 43% lower power with 2X beamforming performance,” says Mike Thompson, Sr. Product Line Manager, Adaptive & Embedded Computing Group, AMD.

Many Silicon valley FPGA and processing companies do not directly target the military per se with their new product launches. Thomspon says that is not the case here as AMD focused on adapting the architecture to focus on the challenges the algorithm is designed to overcome. The new Versal series also reduces size, weight, and power (SWaP) while increasing processing power by a factor of 4, he adds.

The Versal Premium series with AI Engines is part of the company’s 7nm Versal adaptive compute acceleration platform (ACAP) portfolio including the existing Versal Premium series. This latest release delivers a 4X increase in signal processing capacity compared to the last-generation Virtex UltraScale+ VU13P FPGA. It also eliminates I/O bottlenecks with as fast as 9Tb/s serial bandwidth, and offers reduced SWaP through heterogeneous, power-optimized integration of hardened, ASIC-like cores such as 100G/600G Ethernet cores, 400G high-speed crypto engines, DDR memory controller, and integrated PCIe Gen5 blocks.

By combining AI Engines with DSP Engines, users of Versal Premium with AI Engines devices can realize major performance gains compared to prior generation 16nm Xilinx devices and competing products on the market today, company officials say.

AMD provides development tools suited for a wide range of developers for the new Versal release such as Vivado ML for hardware developers and Vitis and Vitis AI development platforms for software developers and AI and data scientists. Customers can also get access to AI Engine tutorials and demo designs to help them get up and running more quickly.

AMD officials say they expect the Versal Premium series with AI Engines is expected to begin shipping in the first half of next year, but users can start test driving the solution now by prototyping using the existing Versal Premium and Versal AI Core Evaluation Kits and devices for which documentation and tools are available now. To learn more, visit Versal Premium series product page.

Featured Companies


2485 Augustine Drive
Santa Clara, CA 95054