core: rework code locality

- to reduce binaries size of FFmpeg Windows wrapper
- MinGW linker doesn't support -ffunction-sections (used for FFmpeg Windows wrapper)
- move code to improve locality with its used dependencies
- move UMat::dot() to matmul.dispatch.cpp (Mat::dot() is already there)
- move UMat::inv() to lapack.cpp
- move UMat::mul() to arithm.cpp
- move UMat:eye() to matrix_operations.cpp (near setIdentity() implementation)
- move normalize(): convert_scale.cpp => norm.cpp
- move convertAndUnrollScalar(): arithm.cpp => copy.cpp
- move scalarToRawData(): array.cpp => copy.cpp
- move transpose(): matrix_operations.cpp => matrix_transform.cpp
- move flip(), rotate(): copy.cpp => matrix_transform.cpp (rotate90 uses flip and transpose)
- add 'OPENCV_CORE_EXCLUDE_C_API' CMake variable to exclude compilation of C-API functions from the core module
- matrix_wrap.cpp: add compile-time checks for CUDA/OpenGL calls
- the steps above allow to reduce FFmpeg wrapper size for ~1.5Mb (initial size of OpenCV part is about 3Mb)

backport is done to improve merge experience (less conflicts)
backport of commit: 65eb946756

modules/core/src/arithm.cpp

@@ -57,24 +57,6 @@ namespace cv
 *                                   logical operations                                   *
 \****************************************************************************************/
 
-void convertAndUnrollScalar( const Mat& sc, int buftype, uchar* scbuf, size_t blocksize )
-{
-    int scn = (int)sc.total(), cn = CV_MAT_CN(buftype);
-    size_t esz = CV_ELEM_SIZE(buftype);
-    getConvertFunc(sc.depth(), buftype)(sc.ptr(), 1, 0, 1, scbuf, 1, Size(std::min(cn, scn), 1), 0);
-    // unroll the scalar
-    if( scn < cn )
-    {
-        CV_Assert( scn == 1 );
-        size_t esz1 = CV_ELEM_SIZE1(buftype);
-        for( size_t i = esz1; i < esz; i++ )
-            scbuf[i] = scbuf[i - esz1];
-    }
-    for( size_t i = esz; i < blocksize*esz; i++ )
-        scbuf[i] = scbuf[i - esz];
-}
-
-
 enum { OCL_OP_ADD=0, OCL_OP_SUB=1, OCL_OP_RSUB=2, OCL_OP_ABSDIFF=3, OCL_OP_MUL=4,
        OCL_OP_MUL_SCALE=5, OCL_OP_DIV_SCALE=6, OCL_OP_RECIP_SCALE=7, OCL_OP_ADDW=8,
        OCL_OP_AND=9, OCL_OP_OR=10, OCL_OP_XOR=11, OCL_OP_NOT=12, OCL_OP_MIN=13, OCL_OP_MAX=14,
@@ -1041,9 +1023,7 @@ static BinaryFuncC* getRecipTab()
     return recipTab;
 }
 
-}
-
-void cv::multiply(InputArray src1, InputArray src2,
+void multiply(InputArray src1, InputArray src2,
                   OutputArray dst, double scale, int dtype)
 {
     CV_INSTRUMENT_REGION();
@@ -1052,7 +1032,7 @@ void cv::multiply(InputArray src1, InputArray src2,
               true, &scale, std::abs(scale - 1.0) < DBL_EPSILON ? OCL_OP_MUL : OCL_OP_MUL_SCALE);
 }
 
-void cv::divide(InputArray src1, InputArray src2,
+void divide(InputArray src1, InputArray src2,
                 OutputArray dst, double scale, int dtype)
 {
     CV_INSTRUMENT_REGION();
@@ -1060,7 +1040,7 @@ void cv::divide(InputArray src1, InputArray src2,
     arithm_op(src1, src2, dst, noArray(), dtype, getDivTab(), true, &scale, OCL_OP_DIV_SCALE);
 }
 
-void cv::divide(double scale, InputArray src2,
+void divide(double scale, InputArray src2,
                 OutputArray dst, int dtype)
 {
     CV_INSTRUMENT_REGION();
@@ -1068,13 +1048,17 @@ void cv::divide(double scale, InputArray src2,
     arithm_op(src2, src2, dst, noArray(), dtype, getRecipTab(), true, &scale, OCL_OP_RECIP_SCALE);
 }
 
+UMat UMat::mul(InputArray m, double scale) const
+{
+    UMat dst;
+    multiply(*this, m, dst, scale);
+    return dst;
+}
+
 /****************************************************************************************\
 *                                      addWeighted                                       *
 \****************************************************************************************/
 
-namespace cv
-{
-
 static BinaryFuncC* getAddWeightedTab()
 {
     static BinaryFuncC addWeightedTab[] =
@@ -1879,6 +1863,9 @@ void cv::inRange(InputArray _src, InputArray _lowerb,
     }
 }
 
+
+#ifndef OPENCV_EXCLUDE_C_API
+
 /****************************************************************************************\
 *                                Earlier API: cvAdd etc.                                 *
 \****************************************************************************************/
@@ -2141,4 +2128,5 @@ cvMaxS( const void* srcarr1, double value, void* dstarr )
     cv::max( src1, value, dst );
 }
 
+#endif  // OPENCV_EXCLUDE_C_API
 /* End of file. */