Dataflow Compiler

A Complete & Scalable Software Toolchain

Product Inquiry

Hailo devices are accompanied by a comprehensive dataflow compiler that seamlessly integrates with existing deep learning development frameworks to allow smooth and easy integration in existing development ecosystems.

ML Frameworks
Machine Learning Frameworks Keras, TensorFlow, PyTorch, ONNX
Hailo Dataflow Compiler

Model Parser

Model Optimizer

Resource Allocator

Compiler

Emulator

Profiler

Hailo Device
Hailo AI Chip for Edge Devices

Full deployment flow toolchain capabilities:

  • Model Translation from industry-standard frameworks to Hailo executable format
  • Model Optimization to the internal representation, using state of the art quantization scheme
  • Automated resource allocation for meeting user requirements in FPS, latency, and power consumption
  • Compilation of models into Hailo binary by the dedicated deep learning compiler
  • Loading binary and running inference on the Hailo target device
  • Supports both standalone inference allowing direct access to the device, and Tensorflow-integrated inference for easy integration with existing environments

Analysis and debug tools:

  • Emulator providing bit exact emulation of chip behavior
  • Profiler providing chip performance estimations (e.g. FPS, power and latency)

Documents marked with a lock icon are available for registered users only. To sign up click here

Title File type Date modified
Hailo Command Line Interface HTML
Hailo Quantization-Aware Fine-Tuning HTML
Hailo Dataflow Compiler Video
01 - Hailo Parser Video
Hailo Quantization Scheme HTML
Hailo Command Line Interface Video
02 - Hailo Quantizer Video
03 - Hailo Compiler & Allocator Video
Multiple Networks Guide PDF
Hailo Dataflow Compiler User Guide PDF 31/03/2023
Breathe life into your edge products
with the Hailo-8™ AI processor

EU Research and Innovation Program

EU flag

This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No. 849921

This project has received funding from the European Union’s Horizon 2020.