Learn how to optimize neural network inference on AMD hardware using the ONNX Runtime with the DirectML execution provider and DirectX 12 in the first part of our guide.

AMD GPUOpen

A guide covering how to optimize neural network inference on AMD hardware using ONNX Runtime with the DirectML execution provider. The tutorial demonstrates leveraging DirectX 12 for improved performance when running machine learning models on AMD GPUs.

ONNX and DirectML execution provider guide

2. Setting up ONNX Runtime with DirectX 12

3. Mapping DirectX 12 resource into ONNX Runtime

4. Faster preprocessing and postprocessing