We have detected your current browser version is not the latest one. Xilinx.com uses the latest web technologies to bring you the best online experience possible. Please upgrade to a Xilinx.com supported browser:Chrome, Firefox, Internet Explorer 11, Safari. Thank you!

Adaptable Accelerator Cards for
Data Center Workloads

Breathe New Life
Into Your Data Center

Available Now >


Acceleration for Dynamic Workloads



  • Up to 90X higher performance than CPUs1 on key workloads at one-third the cost2
  • Over 4X higher inference throughput3 and 3X latency advantage over GPU-based solutions4


Any Workload

  • Machine learning inference to video processing to any workload using the same accelerator card
  • As workload algorithms evolve, use reconfigurable hardware to adapt faster than fixed-function accelerator card product cycles


Cloud ↔ On-Premises

  • Deploy solutions in the cloud or on-premises interchangeably, scalable to application requirements
  • Applications available for common workloads, or build your own with the Application Developer Tool


Acceleration Applications Available Now

We’ve developed an ecosystem of Xilinx and partner solutions for most common workloads

Xilinx Machine Learning

  • ML Suite for inference
  • 20X more throughput than CPUs

BlackLynx Database Search

  • Elasticsearch on unstructured data
  • 90X faster search

Xilinx Video Transcoding

  • Real-time adaptive bitrate video transcoding
  • High-performance HEVC & VP9 encoders

Skreens Video Processing

  • Real-time, multi-stream video

Falcon Genomics

  • Accelerated genomics pipelines
  • 10X faster genome sequencing

Maxeler Financial Computing

  • Real-time risk analysis
  • 89X faster risk calculation

Application Developer Tool

Build Your Own Accelerated Application

Tools available to build differentiated applications in the cloud or on-premises

SDAccel Development Environment

  • Complete IDE for developing, profiling, and debugging accelerated applications
  • Supports RTL, C/C++, and OpenCL languages for accelerator function development

Build and Market Your Applications with the Xilinx Accelerator Program

A quick start program enabling companies to accelerate products and services in the cloud or on-premises

Accelerator Cards

Accelerator Cards That Fit Your Performance Needs

Alveo U200

  • 18.6 Peak INT8 TOPs
  • 77GB/s DDR Memory Bandwidth
  • 31TB/s Internal SRAM Bandwidth
  • 892,000 LUTs

Alveo U250

  • 33.3 Peak INT8 TOPs
  • 77GB/s DDR Memory Bandwidth
  • 38TB/s Internal SRAM Bandwidth
  • 1,341,000 LUTs

Alveo U280

  • 24.5 Peak INT8 TOPs
  • 460GB/s HBM2 Memory Bandwidth
  • 30TB/s Internal SRAM Bandwidth
  • 1,079,000 LUTs


Where to Buy

Run In The Cloud

Buy Solutions for


1 BlackLynx Elasticsearch on Alveo versus EC2 c4.8xlarge

2 Based on CAPEX & OPEX savings for DNN inference on Alveo accelerator cards vs dual-socket Intel Xeon Platinum servers

3 Source: Accelerating DNNs with Alveo Accelerator Cards White Paper

4 Measured on CNN+BLSTM Speech-to-Text ML inference against Nvidia P4

Page Bookmarked