gpuarithm module fixes

modules/gpuarithm/CMakeLists.txt

@@ -4,7 +4,7 @@ endif()
 
 set(the_description "GPU-accelerated Operations on Matrices")
 
-ocv_warnings_disable(CMAKE_CXX_FLAGS -Wundef -Wmissing-declarations)
+ocv_warnings_disable(CMAKE_CXX_FLAGS /wd4127 /wd4324 /wd4512 -Wundef -Wmissing-declarations)
 
 ocv_add_module(gpuarithm opencv_core OPTIONAL opencv_gpulegacy)
 

modules/gpuarithm/doc/core.rst

+Core Operations on Matrices
+===========================
+
+.. highlight:: cpp
+
+
+
+gpu::merge
+--------------
+Makes a multi-channel matrix out of several single-channel matrices.
+
+.. ocv:function:: void gpu::merge(const GpuMat* src, size_t n, GpuMat& dst, Stream& stream = Stream::Null())
+
+.. ocv:function:: void gpu::merge(const vector<GpuMat>& src, GpuMat& dst, Stream& stream = Stream::Null())
+
+    :param src: Array/vector of source matrices.
+
+    :param n: Number of source matrices.
+
+    :param dst: Destination matrix.
+
+    :param stream: Stream for the asynchronous version.
+
+.. seealso:: :ocv:func:`merge`
+
+
+
+gpu::split
+--------------
+Copies each plane of a multi-channel matrix into an array.
+
+.. ocv:function:: void gpu::split(const GpuMat& src, GpuMat* dst, Stream& stream = Stream::Null())
+
+.. ocv:function:: void gpu::split(const GpuMat& src, vector<GpuMat>& dst, Stream& stream = Stream::Null())
+
+    :param src: Source matrix.
+
+    :param dst: Destination array/vector of single-channel matrices.
+
+    :param stream: Stream for the asynchronous version.
+
+.. seealso:: :ocv:func:`split`
+
+
+
+gpu::copyMakeBorder
+-----------------------
+Forms a border around an image.
+
+.. ocv:function:: void gpu::copyMakeBorder(const GpuMat& src, GpuMat& dst, int top, int bottom, int left, int right, int borderType, const Scalar& value = Scalar(), Stream& stream = Stream::Null())
+
+    :param src: Source image. ``CV_8UC1`` , ``CV_8UC4`` , ``CV_32SC1`` , and  ``CV_32FC1`` types are supported.
+
+    :param dst: Destination image with the same type as  ``src``. The size is  ``Size(src.cols+left+right, src.rows+top+bottom)`` .
+
+    :param top:
+
+    :param bottom:
+
+    :param left:
+
+    :param right: Number of pixels in each direction from the source image rectangle to extrapolate. For example:  ``top=1, bottom=1, left=1, right=1`` mean that 1 pixel-wide border needs to be built.
+
+    :param borderType: Border type. See  :ocv:func:`borderInterpolate` for details. ``BORDER_REFLECT101`` , ``BORDER_REPLICATE`` , ``BORDER_CONSTANT`` , ``BORDER_REFLECT`` and ``BORDER_WRAP`` are supported for now.
+
+    :param value: Border value.
+
+    :param stream: Stream for the asynchronous version.
+
+.. seealso:: :ocv:func:`copyMakeBorder`
+
+
+
+gpu::transpose
+------------------
+Transposes a matrix.
+
+.. ocv:function:: void gpu::transpose( const GpuMat& src1, GpuMat& dst, Stream& stream=Stream::Null() )
+
+    :param src1: Source matrix. 1-, 4-, 8-byte element sizes are supported for now (CV_8UC1, CV_8UC4, CV_16UC2, CV_32FC1, etc).
+
+    :param dst: Destination matrix.
+
+    :param stream: Stream for the asynchronous version.
+
+.. seealso:: :ocv:func:`transpose`
+
+
+
+gpu::flip
+-------------
+Flips a 2D matrix around vertical, horizontal, or both axes.
+
+.. ocv:function:: void gpu::flip( const GpuMat& a, GpuMat& b, int flipCode, Stream& stream=Stream::Null() )
+
+    :param a: Source matrix. Supports 1, 3 and 4 channels images with ``CV_8U``, ``CV_16U``, ``CV_32S`` or ``CV_32F`` depth.
+
+    :param b: Destination matrix.
+
+    :param flipCode: Flip mode for the source:
+
+        * ``0`` Flips around x-axis.
+
+        * ``>0`` Flips around y-axis.
+
+        * ``<0`` Flips around both axes.
+
+    :param stream: Stream for the asynchronous version.
+
+.. seealso:: :ocv:func:`flip`
+
+
+
+gpu::LUT
+------------
+Transforms the source matrix into the destination matrix using the given look-up table: ``dst(I) = lut(src(I))``
+
+.. ocv:function:: void gpu::LUT(const GpuMat& src, const Mat& lut, GpuMat& dst, Stream& stream = Stream::Null())
+
+    :param src: Source matrix.  ``CV_8UC1``  and  ``CV_8UC3``  matrices are supported for now.
+
+    :param lut: Look-up table of 256 elements. It is a continuous ``CV_8U`` matrix.
+
+    :param dst: Destination matrix with the same depth as  ``lut``  and the same number of channels as  ``src`` .
+
+    :param stream: Stream for the asynchronous version.
+
+.. seealso:: :ocv:func:`LUT`

modules/gpuarithm/doc/per_element_operations.rst → modules/gpuarithm/doc/element_operations.rst

 Per-element Operations
-=======================
+======================
 
 .. highlight:: cpp
 
@@ -112,6 +112,7 @@ This function, in contrast to :ocv:func:`divide`, uses a round-down rounding mod
 .. seealso:: :ocv:func:`divide`
 
 
+
 gpu::addWeighted
 ----------------
 Computes the weighted sum of two arrays.
@@ -465,3 +466,109 @@ Applies a fixed-level threshold to each array element.
     :param stream: Stream for the asynchronous version.
 
 .. seealso:: :ocv:func:`threshold`
+
+
+
+gpu::magnitude
+------------------
+Computes magnitudes of complex matrix elements.
+
+.. ocv:function:: void gpu::magnitude( const GpuMat& xy, GpuMat& magnitude, Stream& stream=Stream::Null() )
+
+.. ocv:function:: void gpu::magnitude(const GpuMat& x, const GpuMat& y, GpuMat& magnitude, Stream& stream = Stream::Null())
+
+    :param xy: Source complex matrix in the interleaved format ( ``CV_32FC2`` ).
+
+    :param x: Source matrix containing real components ( ``CV_32FC1`` ).
+
+    :param y: Source matrix containing imaginary components ( ``CV_32FC1`` ).
+
+    :param magnitude: Destination matrix of float magnitudes ( ``CV_32FC1`` ).
+
+    :param stream: Stream for the asynchronous version.
+
+.. seealso:: :ocv:func:`magnitude`
+
+
+
+gpu::magnitudeSqr
+---------------------
+Computes squared magnitudes of complex matrix elements.
+
+.. ocv:function:: void gpu::magnitudeSqr( const GpuMat& xy, GpuMat& magnitude, Stream& stream=Stream::Null() )
+
+.. ocv:function:: void gpu::magnitudeSqr(const GpuMat& x, const GpuMat& y, GpuMat& magnitude, Stream& stream = Stream::Null())
+
+    :param xy: Source complex matrix in the interleaved format ( ``CV_32FC2`` ).
+
+    :param x: Source matrix containing real components ( ``CV_32FC1`` ).
+
+    :param y: Source matrix containing imaginary components ( ``CV_32FC1`` ).
+
+    :param magnitude: Destination matrix of float magnitude squares ( ``CV_32FC1`` ).
+
+    :param stream: Stream for the asynchronous version.
+
+
+
+gpu::phase
+--------------
+Computes polar angles of complex matrix elements.
+
+.. ocv:function:: void gpu::phase(const GpuMat& x, const GpuMat& y, GpuMat& angle, bool angleInDegrees=false, Stream& stream = Stream::Null())
+
+    :param x: Source matrix containing real components ( ``CV_32FC1`` ).
+
+    :param y: Source matrix containing imaginary components ( ``CV_32FC1`` ).
+
+    :param angle: Destination matrix of angles ( ``CV_32FC1`` ).
+
+    :param angleInDegrees: Flag for angles that must be evaluated in degrees.
+
+    :param stream: Stream for the asynchronous version.
+
+.. seealso:: :ocv:func:`phase`
+
+
+
+gpu::cartToPolar
+--------------------
+Converts Cartesian coordinates into polar.
+
+.. ocv:function:: void gpu::cartToPolar(const GpuMat& x, const GpuMat& y, GpuMat& magnitude, GpuMat& angle, bool angleInDegrees=false, Stream& stream = Stream::Null())
+
+    :param x: Source matrix containing real components ( ``CV_32FC1`` ).
+
+    :param y: Source matrix containing imaginary components ( ``CV_32FC1`` ).
+
+    :param magnitude: Destination matrix of float magnitudes ( ``CV_32FC1`` ).
+
+    :param angle: Destination matrix of angles ( ``CV_32FC1`` ).
+
+    :param angleInDegrees: Flag for angles that must be evaluated in degrees.
+
+    :param stream: Stream for the asynchronous version.
+
+.. seealso:: :ocv:func:`cartToPolar`
+
+
+
+gpu::polarToCart
+--------------------
+Converts polar coordinates into Cartesian.
+
+.. ocv:function:: void gpu::polarToCart(const GpuMat& magnitude, const GpuMat& angle, GpuMat& x, GpuMat& y, bool angleInDegrees=false, Stream& stream = Stream::Null())
+
+    :param magnitude: Source matrix containing magnitudes ( ``CV_32FC1`` ).
+
+    :param angle: Source matrix containing angles ( ``CV_32FC1`` ).
+
+    :param x: Destination matrix of real components ( ``CV_32FC1`` ).
+
+    :param y: Destination matrix of imaginary components ( ``CV_32FC1`` ).
+
+    :param angleInDegrees: Flag that indicates angles in degrees.
+
+    :param stream: Stream for the asynchronous version.
+
+.. seealso:: :ocv:func:`polarToCart`

modules/gpuarithm/doc/gpuarithm.rst

-*******************************************
-gpu. GPU-accelerated Operations on Matrices
-*******************************************
+*************************************************
+gpuarithm. GPU-accelerated Operations on Matrices
+*************************************************
 
 .. toctree::
     :maxdepth: 1
 
-    operations_on_matrices
-    per_element_operations
-    matrix_reductions
+    core
+    element_operations
+    reductions
+    arithm

modules/gpuarithm/doc/matrix_reductions.rst → modules/gpuarithm/doc/reductions.rst

@@ -5,25 +5,6 @@ Matrix Reductions
 
 
 
-gpu::meanStdDev
--------------------
-Computes a mean value and a standard deviation of matrix elements.
-
-.. ocv:function:: void gpu::meanStdDev(const GpuMat& mtx, Scalar& mean, Scalar& stddev)
-.. ocv:function:: void gpu::meanStdDev(const GpuMat& mtx, Scalar& mean, Scalar& stddev, GpuMat& buf)
-
-    :param mtx: Source matrix.  ``CV_8UC1``  matrices are supported for now.
-
-    :param mean: Mean value.
-
-    :param stddev: Standard deviation value.
-
-    :param buf: Optional buffer to avoid extra memory allocations. It is resized automatically.
-
-.. seealso:: :ocv:func:`meanStdDev`
-
-
-
 gpu::norm
 -------------
 Returns the norm of a matrix (or difference of two matrices).
@@ -205,3 +186,70 @@ Reduces a matrix to a vector.
 The function ``reduce`` reduces the matrix to a vector by treating the matrix rows/columns as a set of 1D vectors and performing the specified operation on the vectors until a single row/column is obtained. For example, the function can be used to compute horizontal and vertical projections of a raster image. In case of ``CV_REDUCE_SUM`` and ``CV_REDUCE_AVG`` , the output may have a larger element bit-depth to preserve accuracy. And multi-channel arrays are also supported in these two reduction modes.
 
 .. seealso:: :ocv:func:`reduce`
+
+
+
+gpu::normalize
+--------------
+Normalizes the norm or value range of an array.
+
+.. ocv:function:: void gpu::normalize(const GpuMat& src, GpuMat& dst, double alpha = 1, double beta = 0, int norm_type = NORM_L2, int dtype = -1, const GpuMat& mask = GpuMat())
+
+.. ocv:function:: void gpu::normalize(const GpuMat& src, GpuMat& dst, double a, double b, int norm_type, int dtype, const GpuMat& mask, GpuMat& norm_buf, GpuMat& cvt_buf)
+
+    :param src: input array.
+
+    :param dst: output array of the same size as  ``src`` .
+
+    :param alpha: norm value to normalize to or the lower range boundary in case of the range normalization.
+
+    :param beta: upper range boundary in case of the range normalization; it is not used for the norm normalization.
+
+    :param normType: normalization type (see the details below).
+
+    :param dtype: when negative, the output array has the same type as ``src``; otherwise, it has the same number of channels as  ``src`` and the depth ``=CV_MAT_DEPTH(dtype)``.
+
+    :param mask: optional operation mask.
+
+    :param norm_buf: Optional buffer to avoid extra memory allocations. It is resized automatically.
+
+    :param cvt_buf: Optional buffer to avoid extra memory allocations. It is resized automatically.
+
+.. seealso:: :ocv:func:`normalize`
+
+
+
+gpu::meanStdDev
+-------------------
+Computes a mean value and a standard deviation of matrix elements.
+
+.. ocv:function:: void gpu::meanStdDev(const GpuMat& mtx, Scalar& mean, Scalar& stddev)
+.. ocv:function:: void gpu::meanStdDev(const GpuMat& mtx, Scalar& mean, Scalar& stddev, GpuMat& buf)
+
+    :param mtx: Source matrix.  ``CV_8UC1``  matrices are supported for now.
+
+    :param mean: Mean value.
+
+    :param stddev: Standard deviation value.
+
+    :param buf: Optional buffer to avoid extra memory allocations. It is resized automatically.
+
+.. seealso:: :ocv:func:`meanStdDev`
+
+
+
+gpu::rectStdDev
+-------------------
+Computes a standard deviation of integral images.
+
+.. ocv:function:: void gpu::rectStdDev(const GpuMat& src, const GpuMat& sqr, GpuMat& dst, const Rect& rect, Stream& stream = Stream::Null())
+
+    :param src: Source image. Only the ``CV_32SC1`` type is supported.
+
+    :param sqr: Squared source image. Only  the ``CV_32FC1`` type is supported.
+
+    :param dst: Destination image with the same type and size as  ``src`` .
+
+    :param rect: Rectangular window.
+
+    :param stream: Stream for the asynchronous version.

modules/gpuarithm/include/opencv2/gpuarithm.hpp

@@ -222,12 +222,6 @@ CV_EXPORTS void normalize(const GpuMat& src, GpuMat& dst, double alpha = 1, doub
 CV_EXPORTS void normalize(const GpuMat& src, GpuMat& dst, double a, double b,
                           int norm_type, int dtype, const GpuMat& mask, GpuMat& norm_buf, GpuMat& cvt_buf);
 
-//! computes mean value and standard deviation of all or selected array elements
-//! supports only CV_8UC1 type
-CV_EXPORTS void meanStdDev(const GpuMat& mtx, Scalar& mean, Scalar& stddev);
-//! buffered version
-CV_EXPORTS void meanStdDev(const GpuMat& mtx, Scalar& mean, Scalar& stddev, GpuMat& buf);
-
 //! computes norm of array
 //! supports NORM_INF, NORM_L1, NORM_L2
 //! supports all matrices except 64F
@@ -275,8 +269,11 @@ CV_EXPORTS int countNonZero(const GpuMat& src, GpuMat& buf);
 //! reduces a matrix to a vector
 CV_EXPORTS void reduce(const GpuMat& mtx, GpuMat& vec, int dim, int reduceOp, int dtype = -1, Stream& stream = Stream::Null());
 
-//! applies fixed threshold to the image
-CV_EXPORTS double threshold(const GpuMat& src, GpuMat& dst, double thresh, double maxval, int type, Stream& stream = Stream::Null());
+//! computes mean value and standard deviation of all or selected array elements
+//! supports only CV_8UC1 type
+CV_EXPORTS void meanStdDev(const GpuMat& mtx, Scalar& mean, Scalar& stddev);
+//! buffered version
+CV_EXPORTS void meanStdDev(const GpuMat& mtx, Scalar& mean, Scalar& stddev, GpuMat& buf);
 
 //! computes the standard deviation of integral images
 //! supports only CV_32SC1 source type and CV_32FC1 sqr type
@@ -287,6 +284,9 @@ CV_EXPORTS void rectStdDev(const GpuMat& src, const GpuMat& sqr, GpuMat& dst, co
 CV_EXPORTS void copyMakeBorder(const GpuMat& src, GpuMat& dst, int top, int bottom, int left, int right, int borderType,
                                const Scalar& value = Scalar(), Stream& stream = Stream::Null());
 
+//! applies fixed threshold to the image
+CV_EXPORTS double threshold(const GpuMat& src, GpuMat& dst, double thresh, double maxval, int type, Stream& stream = Stream::Null());
+
 //! computes the integral image
 //! sum will have CV_32S type, but will contain unsigned int values
 //! supports only CV_8UC1 source type

modules/gpuarithm/perf/perf_arithm.cpp

+/*M///////////////////////////////////////////////////////////////////////////////////////
+//
+//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
+//
+//  By downloading, copying, installing or using the software you agree to this license.
+//  If you do not agree to this license, do not download, install,
+//  copy or use the software.
+//
+//
+//                           License Agreement
+//                For Open Source Computer Vision Library
+//
+// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
+// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
+// Third party copyrights are property of their respective owners.
+//
+// Redistribution and use in source and binary forms, with or without modification,
+// are permitted provided that the following conditions are met:
+//
+//   * Redistribution's of source code must retain the above copyright notice,
+//     this list of conditions and the following disclaimer.
+//
+//   * Redistribution's in binary form must reproduce the above copyright notice,
+//     this list of conditions and the following disclaimer in the documentation
+//     and/or other materials provided with the distribution.
+//
+//   * The name of the copyright holders may not be used to endorse or promote products
+//     derived from this software without specific prior written permission.
+//
+// This software is provided by the copyright holders and contributors "as is" and
+// any express or implied warranties, including, but not limited to, the implied
+// warranties of merchantability and fitness for a particular purpose are disclaimed.
+// In no event shall the Intel Corporation or contributors be liable for any direct,
+// indirect, incidental, special, exemplary, or consequential damages
+// (including, but not limited to, procurement of substitute goods or services;
+// loss of use, data, or profits; or business interruption) however caused
+// and on any theory of liability, whether in contract, strict liability,
+// or tort (including negligence or otherwise) arising in any way out of
+// the use of this software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#include "perf_precomp.hpp"
+
+using namespace std;
+using namespace testing;
+using namespace perf;
+
+//////////////////////////////////////////////////////////////////////
+// GEMM
+
+CV_FLAGS(GemmFlags, 0, cv::GEMM_1_T, cv::GEMM_2_T, cv::GEMM_3_T)
+#define ALL_GEMM_FLAGS Values(GemmFlags(0), GemmFlags(cv::GEMM_1_T), GemmFlags(cv::GEMM_2_T), GemmFlags(cv::GEMM_3_T), \
+                              GemmFlags(cv::GEMM_1_T | cv::GEMM_2_T), GemmFlags(cv::GEMM_1_T | cv::GEMM_3_T), GemmFlags(cv::GEMM_1_T | cv::GEMM_2_T | cv::GEMM_3_T))
+
+DEF_PARAM_TEST(Sz_Type_Flags, cv::Size, MatType, GemmFlags);
+
+PERF_TEST_P(Sz_Type_Flags, GEMM,
+            Combine(Values(cv::Size(512, 512), cv::Size(1024, 1024)),
+                    Values(CV_32FC1, CV_32FC2, CV_64FC1),
+                    ALL_GEMM_FLAGS))
+{
+    const cv::Size size = GET_PARAM(0);
+    const int type = GET_PARAM(1);
+    const int flags = GET_PARAM(2);
+
+    cv::Mat src1(size, type);
+    declare.in(src1, WARMUP_RNG);
+
+    cv::Mat src2(size, type);
+    declare.in(src2, WARMUP_RNG);
+
+    cv::Mat src3(size, type);
+    declare.in(src3, WARMUP_RNG);
+
+    if (PERF_RUN_GPU())
+    {
+        declare.time(5.0);
+
+        const cv::gpu::GpuMat d_src1(src1);
+        const cv::gpu::GpuMat d_src2(src2);
+        const cv::gpu::GpuMat d_src3(src3);
+        cv::gpu::GpuMat dst;
+
+        TEST_CYCLE() cv::gpu::gemm(d_src1, d_src2, 1.0, d_src3, 1.0, dst, flags);
+
+        GPU_SANITY_CHECK(dst, 1e-6);
+    }
+    else
+    {
+        declare.time(50.0);
+
+        cv::Mat dst;
+
+        TEST_CYCLE() cv::gemm(src1, src2, 1.0, src3, 1.0, dst, flags);
+
+        CPU_SANITY_CHECK(dst);
+    }
+}
+
+//////////////////////////////////////////////////////////////////////
+// MulSpectrums
+
+CV_FLAGS(DftFlags, 0, cv::DFT_INVERSE, cv::DFT_SCALE, cv::DFT_ROWS, cv::DFT_COMPLEX_OUTPUT, cv::DFT_REAL_OUTPUT)
+
+DEF_PARAM_TEST(Sz_Flags, cv::Size, DftFlags);
+
+PERF_TEST_P(Sz_Flags, MulSpectrums,
+            Combine(GPU_TYPICAL_MAT_SIZES,
+                    Values(0, DftFlags(cv::DFT_ROWS))))
+{
+    const cv::Size size = GET_PARAM(0);
+    const int flag = GET_PARAM(1);
+
+    cv::Mat a(size, CV_32FC2);
+    cv::Mat b(size, CV_32FC2);
+    declare.in(a, b, WARMUP_RNG);
+
+    if (PERF_RUN_GPU())
+    {
+        const cv::gpu::GpuMat d_a(a);
+        const cv::gpu::GpuMat d_b(b);
+        cv::gpu::GpuMat dst;
+
+        TEST_CYCLE() cv::gpu::mulSpectrums(d_a, d_b, dst, flag);
+
+        GPU_SANITY_CHECK(dst);
+    }
+    else
+    {
+        cv::Mat dst;
+
+        TEST_CYCLE() cv::mulSpectrums(a, b, dst, flag);
+
+        CPU_SANITY_CHECK(dst);
+    }
+}
+
+//////////////////////////////////////////////////////////////////////
+// MulAndScaleSpectrums
+
+PERF_TEST_P(Sz, MulAndScaleSpectrums,
+            GPU_TYPICAL_MAT_SIZES)
+{
+    const cv::Size size = GetParam();
+
+    const float scale = 1.f / size.area();
+
+    cv::Mat src1(size, CV_32FC2);
+    cv::Mat src2(size, CV_32FC2);
+    declare.in(src1,src2, WARMUP_RNG);
+
+    if (PERF_RUN_GPU())
+    {
+        const cv::gpu::GpuMat d_src1(src1);
+        const cv::gpu::GpuMat d_src2(src2);
+        cv::gpu::GpuMat dst;
+
+        TEST_CYCLE() cv::gpu::mulAndScaleSpectrums(d_src1, d_src2, dst, cv::DFT_ROWS, scale, false);
+
+        GPU_SANITY_CHECK(dst);
+    }
+    else
+    {
+        FAIL_NO_CPU();
+    }
+}
+
+//////////////////////////////////////////////////////////////////////
+// Dft
+
+PERF_TEST_P(Sz_Flags, Dft,
+            Combine(GPU_TYPICAL_MAT_SIZES,
+                    Values(0, DftFlags(cv::DFT_ROWS), DftFlags(cv::DFT_INVERSE))))
+{
+    declare.time(10.0);
+
+    const cv::Size size = GET_PARAM(0);
+    const int flag = GET_PARAM(1);
+
+    cv::Mat src(size, CV_32FC2);
+    declare.in(src, WARMUP_RNG);
+
+    if (PERF_RUN_GPU())
+    {
+        const cv::gpu::GpuMat d_src(src);
+        cv::gpu::GpuMat dst;
+
+        TEST_CYCLE() cv::gpu::dft(d_src, dst, size, flag);
+
+        GPU_SANITY_CHECK(dst, 1e-6, ERROR_RELATIVE);
+    }
+    else
+    {
+        cv::Mat dst;
+
+        TEST_CYCLE() cv::dft(src, dst, flag);
+
+        CPU_SANITY_CHECK(dst);
+    }
+}
+
+//////////////////////////////////////////////////////////////////////
+// Convolve
+
+DEF_PARAM_TEST(Sz_KernelSz_Ccorr, cv::Size, int, bool);
+
+PERF_TEST_P(Sz_KernelSz_Ccorr, Convolve,
+            Combine(GPU_TYPICAL_MAT_SIZES,
+                    Values(17, 27, 32, 64),
+                    Bool()))
+{
+    declare.time(10.0);
+
+    const cv::Size size = GET_PARAM(0);
+    const int templ_size = GET_PARAM(1);
+    const bool ccorr = GET_PARAM(2);
+
+    const cv::Mat image(size, CV_32FC1);
+    const cv::Mat templ(templ_size, templ_size, CV_32FC1);
+    declare.in(image, templ, WARMUP_RNG);
+
+    if (PERF_RUN_GPU())
+    {
+        cv::gpu::GpuMat d_image = cv::gpu::createContinuous(size, CV_32FC1);
+        d_image.upload(image);
+
+        cv::gpu::GpuMat d_templ = cv::gpu::createContinuous(templ_size, templ_size, CV_32FC1);
+        d_templ.upload(templ);
+
+        cv::gpu::GpuMat dst;
+        cv::gpu::ConvolveBuf d_buf;
+
+        TEST_CYCLE() cv::gpu::convolve(d_image, d_templ, dst, ccorr, d_buf);
+
+        GPU_SANITY_CHECK(dst);
+    }
+    else
+    {
+        if (ccorr)
+            FAIL_NO_CPU();
+
+        cv::Mat dst;
+
+        TEST_CYCLE() cv::filter2D(image, dst, image.depth(), templ);
+
+        CPU_SANITY_CHECK(dst);
+    }
+}
+
+//////////////////////////////////////////////////////////////////////
+// Integral
+
+PERF_TEST_P(Sz, Integral,
+            GPU_TYPICAL_MAT_SIZES)
+{
+    const cv::Size size = GetParam();
+
+    cv::Mat src(size, CV_8UC1);
+    declare.in(src, WARMUP_RNG);
+
+    if (PERF_RUN_GPU())
+    {
+        const cv::gpu::GpuMat d_src(src);
+        cv::gpu::GpuMat dst;
+        cv::gpu::GpuMat d_buf;
+
+        TEST_CYCLE() cv::gpu::integralBuffered(d_src, dst, d_buf);
+
+        GPU_SANITY_CHECK(dst);
+    }
+    else
+    {
+        cv::Mat dst;
+
+        TEST_CYCLE() cv::integral(src, dst);
+
+        CPU_SANITY_CHECK(dst);
+    }
+}
+
+//////////////////////////////////////////////////////////////////////
+// IntegralSqr
+
+PERF_TEST_P(Sz, IntegralSqr,
+            GPU_TYPICAL_MAT_SIZES)
+{
+    const cv::Size size = GetParam();
+
+    cv::Mat src(size, CV_8UC1);
+    declare.in(src, WARMUP_RNG);
+
+    if (PERF_RUN_GPU())
+    {
+        const cv::gpu::GpuMat d_src(src);
+        cv::gpu::GpuMat dst;
+
+        TEST_CYCLE() cv::gpu::sqrIntegral(d_src, dst);
+
+        GPU_SANITY_CHECK(dst);
+    }
+    else
+    {
+        FAIL_NO_CPU();
+    }
+}

modules/gpuarithm/src/precomp.hpp

@@ -49,7 +49,6 @@
 
 #include "opencv2/gpuarithm.hpp"
 #include "opencv2/core/utility.hpp"
-#include "opencv2/core/core_c.h"
 
 #include "opencv2/core/gpu_private.hpp"