AMD ROCm Performance Primitives (RPP) library is a comprehensive, high-performance computer vision library for AMD processors that have HIP, OpenCL, or CPU backends.

Input (nifti1 .nii medical image)	fused_multiply_add_scalar (brightened 3D image)

• Below are the list of audio functions supported
  • Non Silent Region Detection (HOST and HIP)
  • To Decibels (HOST and HIP)
  • Downmixing (HOST and HIP)
  • Preemphasis Filter (HOST and HIP)
  • Resample (HOST and HIP)
  • Mel Filter Bank (HOST and HIP)
  • Spectrogram (HOST and HIP)

Spectrogram kernel output represented as a image

• Linux

  • Ubuntu - 22.04 / 24.04
  • RedHat - 8 / 9
  • SLES - 15-SP5

• ROCm-supported hardware

• Install ROCm 6.1.0 or later with amdgpu-install: Required usecase:rocm

• CMake Version 3.5 and above

  sudo apt install cmake

• Clang Version 5.0.1 and above

  sudo apt install clang

• Half-precision floating-point library - Version 1.12.0 or higher

  sudo apt install half

The installation process uses the following steps:

• ROCm-supported hardware install verification

• Install ROCm 6.1.0 or later with amdgpu-install with --usecase=rocm

Install RPP runtime, development, and test packages.

• Runtime package - rpp only provides the rpp library librpp.so
• Development package - rpp-dev/rpp-devel provides the library, header files, and samples
• Test package - rpp-test provides CTest to verify installation

sudo apt install rpp rpp-dev rpp-test

sudo yum install rpp rpp-devel rpp-test

sudo zypper install rpp rpp-devel rpp-test

• Clone RPP git repository

  git clone https://github.com/ROCm/rpp.git

mkdir build-hip
cd build-hip
cmake ../rpp
make -j8
sudo make install

• Run tests - test option instructions

make test

mkdir build-ocl
cd build-ocl
cmake -DBACKEND=OCL ../rpp
make -j8
sudo make install

The installer will copy

• Libraries into /opt/rocm/lib
• Header files into /opt/rocm/include/rpp
• Samples, and test folder into /opt/rocm/share/rpp
• Documents folder into /opt/rocm/share/doc/rpp

Test package will install CTest module to test rpp. Follow below steps to test package install

mkdir rpp-test && cd rpp-test
cmake /opt/rocm/share/rpp/test/
ctest -VV

To test latest Image/Voxel/Audio/Miscellaneous functionalities of RPP using a python script please view AMD ROCm Performance Primitives (RPP) Test Suite

MIVisionX RPP extension vx_rpp supports RPP functionality through the OpenVX Framework.

For RPP questions and feedback, you can contact us at mivisionx.support@amd.com.

To submit feature requests and bug reports, use our GitHub issues page.

You can build our documentation locally using the following code:

• Sphinx

  cd docs
  pip3 install -r .sphinx/requirements.txt
  python3 -m sphinx -T -E -b html -d _build/doctrees -D language=en . _build/html

• Doxygen

  doxygen .Doxyfile

All notable changes for each release are added to our changelog.

• Linux distribution
  • Ubuntu - 22.04 / 24.04
  • RedHat - 8 / 9
  • SLES - 15-SP5
• ROCm: rocm-core - 6.3.0.60300
• CMake - Version 3.16.3+
• Clang - Version 5.0.1+
• half - IEEE 754-based half-precision floating-point library - Version 1.12.0 / package V1.12.0.60200
• OpenCV - 4.6.0