Overview

AMD extends its heritage in space applications, extending the XQR Space-grade portfolio with AMD Versal XQR Adaptive SoCs.

Versal adaptive SoCs combine adaptable processing of the programmable logic and acceleration engines with leading-edge memory and interfacing technologies to deliver customized, powerful heterogeneous acceleration for any application.

Visit the Space Applications page to learn more about the broader space-grade offerings and solutions.

Portfolio

AMD Versal AI Edge Gen 2 XQR Series

AMD Versal AI Edge Gen 2 XQR Series

  • Increased application processing performance for next-generation space missions
  • AI Engines optimized for ML inference, delivering up to 3x TOPS/Watt vs AIE-ML1
  • Integrated security, vision, video, and programmable computing in a single adaptive platform
AMD Versal RF XQR Series

AMD Versal RF XQR Series

  • Integrated RF data converters and signal processing functions
  • Direct RF sampling supports wideband spectrum capture and analysis
  • Reduced size, weight, and power through monolithic integration
AMD Versal AI Edge XQR Series

AMD Versal AI Edge XQR Series

  • AI engines optimized for ML inferencing applications
  • Low power consumption and low latency
  • Small form factor packaging
AMD Versal AI Core XQR Series

AMD Versal AI Core XQR Series

  • Heterogeneous computing architecture featuring vector, scalar, and DSP compute resources
  • AI engines optimized for signal processing and ML inferencing applications
  • Optimized for complex matrix multiplications

Specifications

The Space-Grade (XQR) Versal Devices are a continuation of AMD ultra-high throughput, machine learning capable, and high-bandwidth Versal™ Adaptive SoCs, offering reconfigurability dedicated to satellite and space applications. The Versal XQR Series is targeted for onboard processing payload applications with a dramatic increase in system logic cells, onboard SRAM, and multi-gigabit transceiver bandwidth to enable vector-based algorithms and high-speed signal processing. Building on AMD space heritage, these devices advance the space industry by supporting multiple process nodes, setting a new standard for reconfigurable solutions in space.

Available Space-Grade Features:

  • Radiation tolerance with comprehensive single event effects characterization
  • AMD class B manufacturing, qualification, and burn-in process
  • Enhanced organic ruggedized package, extending from defense-grade
  • Full M-temp range support, -55C to +125C
  • Mask set control
  • Intended for Space environments and Space 2.0 applications
FEATURED
AMD Versal XQR Portfolio for Space Applications brief detailing space-grade adaptive SoCs, packaging, and key takeaways.

Product Brief

AMD Versal XQR Product Brief

The Space-grade Versal series delivers heterogeneous computing with full radiation tolerance, ultra-high throughput, and machine learning capabilities for satellite and space applications.

Read Brief

Developers

AMD provides a leading software development environment for designing with adaptive SoCs and FPGAs—this includes tools (compilers, simulators, etc.), IP, and solutions.

​This environment can reduce development time while allowing developers to achieve high performance per watt. AMD adaptive SoCs & FPGA design tools enable all types of developers from AI scientists, application and algorithm engineers, embedded software developers, and traditional hardware developers to use AMD adaptive computing solutions.​

Get Started

Evaluation Kits

Connect with AMD

Access the Space Secure Site or contact an AMD sales representative.

Footnotes
  1. Based on AMD internal performance and power projections for the AIE-ML v2 compute tile architecture in the Versal AI Edge Series Gen 2 using the MX6 data type, compared to performance specifications and AMD Power Design Manager power results for the AIE-ML compute tile architecture featured in the first-generation Versal AI Edge Series using the INT8 data type. Assumptions: 2 row, 8 column sub-arrays. Operating conditions: 1 GHz FMAX, 0.7V AIE operating voltage, 100C junction temperature, typical process, 60% vector load, % activations = 0 < 10%. Actual performance will vary when final products are released in market. Performance projections as of March 2024. (VER-023)