ROCm is an open-source stack, composed primarily of open-source software, designed for graphics processing unit (GPU) computation. ROCm consists of a collection of drivers, development tools, and APIs that enable GPU programming from low-level kernel to end-user applications.
You can customize the ROCm software to meet your specific needs. You can develop, collaborate, test, and deploy your applications in a free, open-source, integrated, and secure software ecosystem. ROCm is particularly well-suited to GPU-accelerated high-performance computing (HPC), artificial intelligence (AI), scientific computing, and computer-aided design (CAD).
ROCm is powered by HIP, a C++ runtime API and kernel language for AMD GPUs. HIP allows developers to create portable applications by providing a programming interface that is similar to NVIDIA CUDA™.
ROCm supports programming models, such as OpenMP and OpenCL, and includes all necessary open-source software compilers, debuggers, and libraries. ROCm is fully integrated into machine learning (ML) frameworks, such as PyTorch and TensorFlow.
Important
A new open-source build platform for ROCm is under development at https://github.com/ROCm/TheRock, featuring a unified CMake build with bundled dependencies, Microsoft Windows support, and more.
- Supported hardware and operating systems
- Quick start
- Core components
- Release notes
- Licenses
- ROCm release history
- Contribute
Use the Compatibility matrix for official support across ROCm versions, operating system kernels, and GPU architectures (CDNA/Instinct™, RDNA/Radeon™, and Radeon Pro). Recent releases cover Ubuntu, RHEL, SLES, Oracle Linux, Debian, Rocky Linux, and more. GPU targets include CDNA4, CDNA3, CDNA2, RDNA4, and RDNA3.
If you’re using AMD Radeon GPUs or Ryzen APUs in a workstation setting with a display connected, see the ROCm on Radeon and Ryzen documentation for operating system/framework support and step-by-step installation instructions.
Follow these instructions to start using ROCm.
Follow the ROCm installation guide to install ROCm on your system.
Follow the PyTorch on ROCm installation guide to install PyTorch with ROCm support in a Docker environment.
The core ROCm stack consists of the following components:
- rocBLAS, hipBLAS, and hipBLASLt
- rocFFT and hipFFT
- rocRAND and hipRAND
- rocSOLVER and hipSOLVER
- rocSPARSE and hipSPARSE
- rocWMMA and hipTensor
For a complete list of ROCm components and version information, see the ROCm components.
- Latest version of ROCm - production
- ROCm 7.12.0 – preview stream
For information on older ROCm releases, see the ROCm release history.
AMD welcomes ROCm contributions using GitHub PRs or issues. See the links below for contribution guidelines.