Ctrl+K
This page contains proposed changes for a future release of ROCm. Read the latest Linux release of ROCm documentation for your production environments.

Install HIP

Install HIP#

HIP can be installed on AMD (ROCm with HIP-Clang) and NVIDIA (CUDA with NVCC) platforms.

Note: The version definition for the HIP runtime is different from CUDA. On an AMD platform, the hipRuntimeGerVersion function returns the HIP runtime version; on an NVIDIA platform, this function returns the CUDA runtime version.

Prerequisites#

Refer to the Prerequisites section in the ROCm install guides:

Check the system requirements in the NVIDIA CUDA Installation Guide.

Installation#

HIP is automatically installed during the ROCm installation. If you haven’t yet installed ROCm, you can find installation instructions here:

By default, HIP is installed into /opt/rocm/hip.

Note

There is no autodetection for the HIP installation. If you choose to install it somewhere other than the default location, you must set the HIP_PATH environment variable as explained in Build HIP from source.

  1. Install the NVIDIA driver.

    sudo apt-get install ubuntu-drivers-common && sudo ubuntu-drivers autoinstall
sudo reboot

    Alternatively, you can download the latest CUDA Toolkit.

  2. Install the hip-runtime-nvidia and hip-dev packages. This installs the CUDA SDK and HIP porting layer.

    apt-get install hip-runtime-nvidia hip-dev
    The default paths are:

    • CUDA SDK: /usr/local/cuda

    • HIP: /opt/rocm/hip

    You can optionally add /opt/rocm/bin to your path, which can make it easier to use the tools.

Verify your installation#

Run hipconfig in your installation path.

/opt/rocm/bin/hipconfig --full
Contents