Xilinx targets Versal FPGAs at edge AI

Xilinx has released a version of its Versal FPGA for end AI applications with special AI accelerators.

The Versal AI Edge family builds on a 7nm process and increases the performance of AI computing technologies by 10 times compared to Zynq Ultrscale’s previous FPGAs by adding special AI accelerators along with FPGA fabric.

A new memory architecture with hierarchy supports new AI frameworks and provides up to 4X AI wattage per GPU, as well as lower latency for end applications.

The Versal Adaptive Computing Acceleration Platform (ACAP) was launched in 2018 to provide application-specific FPGAs with AI for specific markets, starting with data centers and telecommunications.

The end parts of artificial intelligence focus on automated driving with the highest levels of functional safety, collaborative robotics, predictable factory and health systems, and payloads with many missions for the space and defense markets that support vision, radar, LiDAR, and software-defined radio. The devices support multiple safety standards in the industrial (IEC 61508), avionics (DO-254/178) and automotive (ISO 26262) markets, where suppliers can perform ASIL C arbitrary hardware integrity and ASIL D systematic integrity levels.

“Applied computing applications require an architecture that can be developed to meet new requirements and scenarios with a combination of flexible computational processing within stringent thermal and latent constraints,” said Sumit Shah, Senior Director, Product Management and Marketing in Xilinx. “The Versal AI Edge series provides these key attributes for a wide range of applications requiring greater intelligence, making it a critical addition to Versal’s portfolio of devices that scale from intelligent edge sensors to CPU accelerators. ”

“Edge market opportunities are growing exponentially, and the AI ​​chipsets that serve these unique applications are expected to double by 2021 to 2025,” said Dan Mandel, senior analyst, IoT and embedded technology at VDC Research. “By creating an AI-specific design that focuses on accelerating performance while remaining scalable and low-power, Xilinx’s Versal AI Edge series is a compelling solution to tackle these critical markets.”

The architecture combines the algorithm with a number of computing engines in the chip, with Scalar Engines for embedded computing, Adaptable Engines for sensor synthesis and hardware adaptation, and Intelligent Engines for AI output. These AI engines scale up to 479 TOPS for 4-bit whole operations, although most performance criteria are aimed at 8-bit operations.

The connection units range from LPDDR-4266, 32Gb / s transceivers to meet all required protocols in end applications, 40G multirate Ethernet, PCIe Gen4 with CCIX and built-in MIPI support for visual sensors with a resolution of up to eight megapixels.

Edge AI development tools have been a key area of ​​focus for Xilinx, and developers can use Vivado’s HDL hardware design tools, Vitis unified software platform for software, Vitis AI for data science, and domain-specific operating systems. frameworks and accelerator libraries for the platform’s target applications.

Versal AI Edge serial design and maintenance documentation is available to customers with early access, with shipments expected in the first half of 2022 and will include a roadmap for automotive and defense devices.


Related articles about FPGA

Other articles about eeNews Europe