Qualcomm® AI Engine Direct
v2.39.0
  • Introduction
  • Overview
  • Setup
  • Backend
  • Op Packages
  • Tools
  • Converters
  • Quantization
  • QAIRT Quantization Specification
  • Tutorials
  • Benchmarking
  • Operations
  • API
  • Glossary
  • QNN TFLite Delegate
  • Revision History
Qualcomm® AI Engine Direct
  • »
  • Performance and Energy Guidelines

Performance and Energy Guidelines¶

  • Avoid Low Depth Activations
  • Avoid Low Depth Activations (more examples)
  • Use Space-to-depth Transformation where possible
  • Reducing TCM Requirements for Performance and Functionality
  • Choice of Activation Functions
  • Number of Channels
  • Quantized 16 bit activations (A16) vs FP16: Performance and power differences
  • INT4 encodings for weights
  • Other Performance and Energy Guidelines

© Copyright 2020-2025, Qualcomm Technologies, Inc..

Built with Sphinx using a theme provided by Read the Docs.