Ara-1: Discrete NPU for Optimized Edge AI

  • This page contains information on a product not recommended for new designs. Specifications and information herein are subject to change without notice. For additional information, please contact NXP support or your NXP sales representative.

Roll over image to zoom in

Block Diagram

Choose a diagram:

NXP Applications Processor and Ara DNPU Connection

ARA-1-DNPU-BD-2

Integration of Ara DNPU and Applications Processors Host with Drivers

ARA-1-DNPU-BD-3

Machine learning deployment flow

ARA-1-DNPU-BD

Features

AI model frameworks supported

  • TensorFlow
  • PyTorch
  • ONNX

AI Model Architectures Supported

  • Convolutional Neural Networks (CNNs)

Performance1

  • Up to 6 eTOPS*

Operating system support (Runtime)

  • Linux

Interface

  • PCIe Gen3 x4
  • USB 3.2 Gen1 x1

Chip package

  • 15 mm x 15 mm EHS-FCBGA

Documentation

Quick reference to our documentation types

1 documents

Compact List

Design Resources

Hardware

Quick reference to our board types.

2 hardware offerings

Software

Quick reference to our software types.

2 software files

Note: For better experience, software downloads are recommended on desktop.

Support

What do you need help with?