Table Of Contents

Previous topic

OpenGL interoperability

Next topic

Optimization Algorithms

Intel® IPP Asynchronous C/C++ Converters

General Information

This section describes conversion between OpenCV and Intel® IPP Asynchronous C/C++ library. Getting Started Guide help you to install the library, configure header and library build paths.

hpp::getHpp

Create hppiMatrix from Mat.

C++: hppiMatrix* hpp::getHpp(const Mat& src, hppAccel accel)
Parameters:
  • src – input matrix.
  • accel

    accelerator instance. Supports type:

    • HPP_ACCEL_TYPE_CPU - accelerated by optimized CPU instructions.
    • HPP_ACCEL_TYPE_GPU - accelerated by GPU programmable units or fixed-function accelerators.
    • HPP_ACCEL_TYPE_ANY - any acceleration or no acceleration available.

This function allocates and initializes the hppiMatrix that has the same size and type as input matrix, returns the hppiMatrix*.

If you want to use zero-copy for GPU you should to have 4KB aligned matrix data. See details hppiCreateSharedMatrix.

Supports CV_8U, CV_16U, CV_16S, CV_32S, CV_32F, CV_64F.

Note

The hppiMatrix pointer to the image buffer in system memory refers to the src.data. Control the lifetime of the matrix and don’t change its data, if there is no special need.

hpp::getMat

Create Mat from hppiMatrix.

C++: Mat hpp::getMat(hppiMatrix* src, hppAccel accel, int cn)
Parameters:
  • src – input hppiMatrix.
  • accel – accelerator instance (see hpp::getHpp() for the list of acceleration framework types).
  • cn – number of channels.

This function allocates and initializes the Mat that has the same size and type as input matrix. Supports CV_8U, CV_16U, CV_16S, CV_32S, CV_32F, CV_64F.

hpp::copyHppToMat

Convert hppiMatrix to Mat.

C++: void hpp::copyHppToMat(hppiMatrix* src, Mat& dst, hppAccel accel, int cn)
Parameters:
  • src – input hppiMatrix.
  • dst – output matrix.
  • accel – accelerator instance (see hpp::getHpp() for the list of acceleration framework types).
  • cn – number of channels.

This function allocates and initializes new matrix (if needed) that has the same size and type as input matrix. Supports CV_8U, CV_16U, CV_16S, CV_32S, CV_32F, CV_64F.