Highest AI performance-per-watt for multiple applications

15-06-2021 | Xilinx | New Technologies

Xilinx, Inc. has introduced the Versal AI Edge series, created to allow AI innovation from the edge to the endpoint. With 4X the AI performance-per-watt versus GPUs and 10X greater compute density against previous-generation adaptive SoCs, the series is claimed to be the world’s most scalable and adaptable portfolio for next-generation distributed intelligent systems.

The series ACAPs provides intelligence to a wide range of applications, including automated driving with the greatest levels of functional safety, collaborative robotics, predictive factory and healthcare systems, and multi-mission payloads for the aerospace and defence markets. The portfolio provides AI Engine-ML to achieve 4X machine learning compute compared to the previous AI Engine architecture. It combines new accelerator RAM with an enhanced memory hierarchy for evolving AI algorithms. These architectural innovations give up to 4X AI performance-per-watt versus GPUs and lower latency providing far more capable devices at the edge.

AI-enabled automated systems need high compute density to accelerate whole applications from sensor to AI to real-time control. These devices accomplish this by giving 10X compute density versus Zynq UltraScale+ MPSoCs, allowing more intelligent autonomous systems. Furthermore, these devices support multiple safety standards across industrial (IEC 61508), avionics (DO-254/178), and automotive (ISO 26262) markets, where vendors can meet ASIL C random hardware integrity and ASIL D systematic integrity levels.

"Edge computing applications require an architecture that can evolve to address new requirements and scenarios with a blend of flexible compute processing within tight thermal and latency constraints,” said Sumit Shah, senior director, Product Management and Marketing at Xilinx. “The Versal AI Edge series delivers these key attributes for a wide range of applications requiring greater intelligence, making it a critical addition to the Versal portfolio with devices that scale from intelligent edge sensors to CPU accelerators.”

“The market opportunity at the edge is growing exponentially, and AI chipsets that serve these unique applications are expected to more than double from 2021 to 2025,” said Dan Mandell, senior analyst, IoT and Embedded Technology at VDC Research. “By creating a design for AI-specific tasks that focuses on performance acceleration while remaining scalable and with low power, Xilinx’s Versal AI Edge series is a compelling solution to address these critical markets.”

The series is the latest member of the Versal ACAP portfolio, adaptive SoCs that are fully software-programmable, with performance and flexibility far exceeding conventional CPUs, GPUs, and FPGAs. ACAPs can be altered at both the hardware and software level to dynamically adapt to the demands of an extensive range of applications and workloads from edge to cloud.

By Natasha Shek