Open deep learning compiler stack for cpu, gpu and specialized accelerators

stdgpu: Efficient STL-like Data Structures on the GPU

Dockerfiles for the various software layers defined in the Radeon Open Compute Platform

GPU Performance API for AMD GPUs

Next generation BLAS implementation for ROCm platform

AMD OpenVX Core -- a sub-module of amdovx-modules:

Agenium Scale vectorization library for CPUs and GPUs

AMD OpenVX modules: such as, neural network inference, 360 video stitching, etc.

MIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. AMD MIVisionX also delivers a highly optimized open-source implementation of the Khronos OpenVX™ and OpenVX™ Extensions.

Distributed Communication-Optimal Matrix-Matrix Multiplication Algorithm

Kubernetes (k8s) device plugin to enable registration of AMD GPU to a container cluster

The Radeon Compute Profiler (RCP) is a performance analysis tool that gathers data from the API run-time and GPU for OpenCL™ and ROCm/HSA applications. This information can be used by developers to discover bottlenecks in the application and to find ways to optimize the application's performance.

Next generation FFT implementation for ROCm

AOMP is an open source Clang/LLVM based compiler with added support for the OpenMP® API on Radeon™ GPUs. Use this repository for releases, issues, documentation, packaging, and examples,.

ROCm Parallel Primitives

RAND library for HIP programming language

Domain specific library for electronic structure calculations

MIVisionX toolkit is a comprehensive computer vision and machine intelligence libraries, utilities and applications bundled into a single toolkit.

A Benchmark Suite for Heterogeneous System Computation

ROCm Machine Learning and HPC Stack installer

Sparse 3D FFT library with MPI, OpenMP, CUDA and ROCm support

Parallel on the ROCks

The repo is obsolete. Use at your own risk.

Install guide of ROCm and Tensorflow on Ubuntu for the RX580

C++17 N-body Barnes-Hut on heterogeneous hardware architectures

Radeon Performance Primitives (RPP) library is a comprehensive high performance computer vision library for AMD (CPU and GPU) with HIP and OpenCL back-ends.

ROCm Utilities: rocm_techsupport.sh techsupport log collection utility for troubleshooting, rocminstall.py script to install ROCm releases side-by-side,