Source-level patches for AMD ROCm to fix critical memory coherency issues on RDNA1/2 consumer GPUs
A comprehensive collection of GPU kernel examples demonstrating essential parallel computing techniques for modern GPU programming. This project supports both NVIDIA CUDA and AMD ROCm platforms, focusing on the most in-demand GPU programming skills required in industry today.
A high-performance C++ application for generating 3D point clouds from stereo camera images using GPU acceleration (CUDA for NVIDIA or HIP for AMD GPUs).
A comprehensive testing suite for validating ROCm (Radeon Open Compute) functionality with Python machine learning frameworks and libraries.
Add a description, image, and links to the gpu-rocm topic page so that developers can more easily learn about it.
To associate your repository with the gpu-rocm topic, visit your repo's landing page and select "manage topics."