void invSqrt64f(const double* src, double* dst, int len)
{
CV_INSTRUMENT_REGION()
CALL_HAL(invSqrt64f, cv_hal_invSqrt64f, src, dst, len);
CV_IPP_RUN_FAST(CV_INSTRUMENT_FUN_IPP(ippsInvSqrt_64f_A50, src, dst, len) >= 0);
CV_CPU_DISPATCH(invSqrt64f, (src, dst, len),
CV_CPU_DISPATCH_MODES_ALL);
}
void sqrt32f(const float* src, float* dst, int len)
{
CV_INSTRUMENT_REGION()
CALL_HAL(sqrt32f, cv_hal_sqrt32f, src, dst, len);
CV_IPP_RUN_FAST(CV_INSTRUMENT_FUN_IPP(ippsSqrt_32f_A21, src, dst, len) >= 0);
CV_CPU_DISPATCH(sqrt32f, (src, dst, len),
CV_CPU_DISPATCH_MODES_ALL);
}
void magnitude32f(const float* x, const float* y, float* mag, int len)
{
CV_INSTRUMENT_REGION()
CALL_HAL(magnitude32f, cv_hal_magnitude32f, x, y, mag, len);
CV_IPP_RUN_FAST(CV_INSTRUMENT_FUN_IPP(ippsMagnitude_32f, x, y, mag, len) >= 0);
CV_CPU_DISPATCH(magnitude32f, (x, y, mag, len),
CV_CPU_DISPATCH_MODES_ALL);
}
void magnitude64f(const double* x, const double* y, double* mag, int len)
{
CV_INSTRUMENT_REGION()
CALL_HAL(magnitude64f, cv_hal_magnitude64f, x, y, mag, len);
CV_IPP_RUN_FAST(CV_INSTRUMENT_FUN_IPP(ippsMagnitude_64f, x, y, mag, len) >= 0);
CV_CPU_DISPATCH(magnitude64f, (x, y, mag, len),
CV_CPU_DISPATCH_MODES_ALL);
}
void log64f(const double *src, double *dst, int n)
{
CV_INSTRUMENT_REGION()
CALL_HAL(log64f, cv_hal_log64f, src, dst, n);
CV_IPP_RUN_FAST(CV_INSTRUMENT_FUN_IPP(ippsLn_64f_A50, src, dst, n) >= 0);
CV_CPU_DISPATCH(log64f, (src, dst, n),
CV_CPU_DISPATCH_MODES_ALL);
}
void log32f(const float *src, float *dst, int n)
{
CV_INSTRUMENT_REGION()
CALL_HAL(log32f, cv_hal_log32f, src, dst, n);
CV_IPP_RUN_FAST(CV_INSTRUMENT_FUN_IPP(ippsLn_32f_A21, src, dst, n) >= 0);
CV_CPU_DISPATCH(log32f, (src, dst, n),
CV_CPU_DISPATCH_MODES_ALL);
}
inline int arithm_ipp_not8u(const uchar* src1, size_t step1, uchar* dst, size_t step, int width, int height)
{
if (!CV_IPP_CHECK_COND)
return 0;
if (height == 1)
step1 = step = width * sizeof(dst[0]);
if (0 <= CV_INSTRUMENT_FUN_IPP(ippiNot_8u_C1R, src1, (int)step1, dst, (int)step, ippiSize(width, height)))
{
CV_IMPL_ADD(CV_IMPL_IPP);
return 1;
}
setIppErrorStatus();
return 0;
}
if( mask[x+2] )
dst[x+2] = src[x+2];
if( mask[x+3] )
dst[x+3] = src[x+3];
}
#endif
for( ; x < size.width; x++ )
if( mask[x] )
dst[x] = src[x];
}
}
template<> void
copyMask_<uchar>(const uchar* _src, size_t sstep, const uchar* mask, size_t mstep, uchar* _dst, size_t dstep, Size size)
{
CV_IPP_RUN_FAST(CV_INSTRUMENT_FUN_IPP(ippiCopy_8u_C1MR, _src, (int)sstep, _dst, (int)dstep, ippiSize(size), mask, (int)mstep) >= 0)
for( ; size.height--; mask += mstep, _src += sstep, _dst += dstep )
{
const uchar* src = (const uchar*)_src;
uchar* dst = (uchar*)_dst;
int x = 0;
#if CV_SIMD128
{
v_uint8x16 v_zero = v_setzero_u8();
for( ; x <= size.width - 16; x += 16 )
{
v_uint8x16 v_src = v_load(src + x),
v_dst = v_load(dst + x),
v_nmask = v_load(mask + x) == v_zero;
static bool ipp_norm(Mat &src, int normType, Mat &mask, double &result)
{
CV_INSTRUMENT_REGION_IPP();
#if IPP_VERSION_X100 >= 700
size_t total_size = src.total();
int rows = src.size[0], cols = rows ? (int)(total_size/rows) : 0;
if( (src.dims == 2 || (src.isContinuous() && mask.isContinuous()))
&& cols > 0 && (size_t)rows*cols == total_size )
{
if( !mask.empty() )
{
IppiSize sz = { cols, rows };
int type = src.type();
typedef IppStatus (CV_STDCALL* ippiMaskNormFuncC1)(const void *, int, const void *, int, IppiSize, Ipp64f *);
ippiMaskNormFuncC1 ippiNorm_C1MR =
normType == NORM_INF ?
(type == CV_8UC1 ? (ippiMaskNormFuncC1)ippiNorm_Inf_8u_C1MR :
type == CV_16UC1 ? (ippiMaskNormFuncC1)ippiNorm_Inf_16u_C1MR :
type == CV_32FC1 ? (ippiMaskNormFuncC1)ippiNorm_Inf_32f_C1MR :
0) :
normType == NORM_L1 ?
(type == CV_8UC1 ? (ippiMaskNormFuncC1)ippiNorm_L1_8u_C1MR :
type == CV_16UC1 ? (ippiMaskNormFuncC1)ippiNorm_L1_16u_C1MR :
type == CV_32FC1 ? (ippiMaskNormFuncC1)ippiNorm_L1_32f_C1MR :
0) :
normType == NORM_L2 || normType == NORM_L2SQR ?
(type == CV_8UC1 ? (ippiMaskNormFuncC1)ippiNorm_L2_8u_C1MR :
type == CV_16UC1 ? (ippiMaskNormFuncC1)ippiNorm_L2_16u_C1MR :
type == CV_32FC1 ? (ippiMaskNormFuncC1)ippiNorm_L2_32f_C1MR :
0) : 0;
if( ippiNorm_C1MR )
{
Ipp64f norm;
if( CV_INSTRUMENT_FUN_IPP(ippiNorm_C1MR, src.ptr(), (int)src.step[0], mask.ptr(), (int)mask.step[0], sz, &norm) >= 0 )
{
result = (normType == NORM_L2SQR ? (double)(norm * norm) : (double)norm);
return true;
}
}
typedef IppStatus (CV_STDCALL* ippiMaskNormFuncC3)(const void *, int, const void *, int, IppiSize, int, Ipp64f *);
ippiMaskNormFuncC3 ippiNorm_C3CMR =
normType == NORM_INF ?
(type == CV_8UC3 ? (ippiMaskNormFuncC3)ippiNorm_Inf_8u_C3CMR :
type == CV_16UC3 ? (ippiMaskNormFuncC3)ippiNorm_Inf_16u_C3CMR :
type == CV_32FC3 ? (ippiMaskNormFuncC3)ippiNorm_Inf_32f_C3CMR :
0) :
normType == NORM_L1 ?
(type == CV_8UC3 ? (ippiMaskNormFuncC3)ippiNorm_L1_8u_C3CMR :
type == CV_16UC3 ? (ippiMaskNormFuncC3)ippiNorm_L1_16u_C3CMR :
type == CV_32FC3 ? (ippiMaskNormFuncC3)ippiNorm_L1_32f_C3CMR :
0) :
normType == NORM_L2 || normType == NORM_L2SQR ?
(type == CV_8UC3 ? (ippiMaskNormFuncC3)ippiNorm_L2_8u_C3CMR :
type == CV_16UC3 ? (ippiMaskNormFuncC3)ippiNorm_L2_16u_C3CMR :
type == CV_32FC3 ? (ippiMaskNormFuncC3)ippiNorm_L2_32f_C3CMR :
0) : 0;
if( ippiNorm_C3CMR )
{
Ipp64f norm1, norm2, norm3;
if( CV_INSTRUMENT_FUN_IPP(ippiNorm_C3CMR, src.data, (int)src.step[0], mask.data, (int)mask.step[0], sz, 1, &norm1) >= 0 &&
CV_INSTRUMENT_FUN_IPP(ippiNorm_C3CMR, src.data, (int)src.step[0], mask.data, (int)mask.step[0], sz, 2, &norm2) >= 0 &&
CV_INSTRUMENT_FUN_IPP(ippiNorm_C3CMR, src.data, (int)src.step[0], mask.data, (int)mask.step[0], sz, 3, &norm3) >= 0)
{
Ipp64f norm =
normType == NORM_INF ? std::max(std::max(norm1, norm2), norm3) :
normType == NORM_L1 ? norm1 + norm2 + norm3 :
normType == NORM_L2 || normType == NORM_L2SQR ? std::sqrt(norm1 * norm1 + norm2 * norm2 + norm3 * norm3) :
0;
result = (normType == NORM_L2SQR ? (double)(norm * norm) : (double)norm);
return true;
}
}
}
else
{
IppiSize sz = { cols*src.channels(), rows };
int type = src.depth();
typedef IppStatus (CV_STDCALL* ippiNormFuncHint)(const void *, int, IppiSize, Ipp64f *, IppHintAlgorithm hint);
typedef IppStatus (CV_STDCALL* ippiNormFuncNoHint)(const void *, int, IppiSize, Ipp64f *);
ippiNormFuncHint ippiNormHint =
normType == NORM_L1 ?
(type == CV_32FC1 ? (ippiNormFuncHint)ippiNorm_L1_32f_C1R :
0) :
normType == NORM_L2 || normType == NORM_L2SQR ?
(type == CV_32FC1 ? (ippiNormFuncHint)ippiNorm_L2_32f_C1R :
0) : 0;
ippiNormFuncNoHint ippiNorm =
normType == NORM_INF ?
(type == CV_8UC1 ? (ippiNormFuncNoHint)ippiNorm_Inf_8u_C1R :
type == CV_16UC1 ? (ippiNormFuncNoHint)ippiNorm_Inf_16u_C1R :
type == CV_16SC1 ? (ippiNormFuncNoHint)ippiNorm_Inf_16s_C1R :
type == CV_32FC1 ? (ippiNormFuncNoHint)ippiNorm_Inf_32f_C1R :
0) :
normType == NORM_L1 ?
(type == CV_8UC1 ? (ippiNormFuncNoHint)ippiNorm_L1_8u_C1R :
type == CV_16UC1 ? (ippiNormFuncNoHint)ippiNorm_L1_16u_C1R :
type == CV_16SC1 ? (ippiNormFuncNoHint)ippiNorm_L1_16s_C1R :
0) :
normType == NORM_L2 || normType == NORM_L2SQR ?
(type == CV_8UC1 ? (ippiNormFuncNoHint)ippiNorm_L2_8u_C1R :
type == CV_16UC1 ? (ippiNormFuncNoHint)ippiNorm_L2_16u_C1R :
type == CV_16SC1 ? (ippiNormFuncNoHint)ippiNorm_L2_16s_C1R :
0) : 0;
if( ippiNormHint || ippiNorm )
{
Ipp64f norm;
IppStatus ret = ippiNormHint ? CV_INSTRUMENT_FUN_IPP(ippiNormHint, src.ptr(), (int)src.step[0], sz, &norm, ippAlgHintAccurate) :
CV_INSTRUMENT_FUN_IPP(ippiNorm, src.ptr(), (int)src.step[0], sz, &norm);
if( ret >= 0 )
{
result = (normType == NORM_L2SQR) ? norm * norm : norm;
return true;
}
}
}
}
#else
CV_UNUSED(src); CV_UNUSED(normType); CV_UNUSED(mask); CV_UNUSED(result);
#endif
return false;
}
static bool ipp_Deriv(InputArray _src, OutputArray _dst, int dx, int dy, int ksize, double scale, double delta, int borderType)
{
#ifdef HAVE_IPP_IW
CV_INSTRUMENT_REGION_IPP()
::ipp::IwiSize size(_src.size().width, _src.size().height);
IppDataType srcType = ippiGetDataType(_src.depth());
IppDataType dstType = ippiGetDataType(_dst.depth());
int channels = _src.channels();
bool useScale = false;
bool useScharr = false;
if(channels != _dst.channels() || channels > 1)
return false;
if(fabs(delta) > FLT_EPSILON || fabs(scale-1) > FLT_EPSILON)
useScale = true;
if(ksize <= 0)
{
ksize = 3;
useScharr = true;
}
IppiMaskSize maskSize = ippiGetMaskSize(ksize, ksize);
if((int)maskSize < 0)
return false;
#if IPP_VERSION_X100 <= 201703
// Bug with mirror wrap
if(borderType == BORDER_REFLECT_101 && (ksize/2+1 > size.width || ksize/2+1 > size.height))
return false;
#endif
IwiDerivativeType derivType = ippiGetDerivType(dx, dy, (useScharr)?false:true);
if((int)derivType < 0)
return false;
// Acquire data and begin processing
try
{
Mat src = _src.getMat();
Mat dst = _dst.getMat();
::ipp::IwiImage iwSrc = ippiGetImage(src);
::ipp::IwiImage iwDst = ippiGetImage(dst);
::ipp::IwiImage iwSrcProc = iwSrc;
::ipp::IwiImage iwDstProc = iwDst;
::ipp::IwiBorderSize borderSize(maskSize);
::ipp::IwiBorderType ippBorder(ippiGetBorder(iwSrc, borderType, borderSize));
if(!ippBorder)
return false;
if(srcType == ipp8u && dstType == ipp8u)
{
iwDstProc.Alloc(iwDst.m_size, ipp16s, channels);
useScale = true;
}
else if(srcType == ipp8u && dstType == ipp32f)
{
iwSrc -= borderSize;
iwSrcProc.Alloc(iwSrc.m_size, ipp32f, channels);
CV_INSTRUMENT_FUN_IPP(::ipp::iwiScale, iwSrc, iwSrcProc, 1, 0, ::ipp::IwiScaleParams(ippAlgHintFast));
iwSrcProc += borderSize;
}
if(useScharr)
CV_INSTRUMENT_FUN_IPP(::ipp::iwiFilterScharr, iwSrcProc, iwDstProc, derivType, maskSize, ::ipp::IwDefault(), ippBorder);
else
CV_INSTRUMENT_FUN_IPP(::ipp::iwiFilterSobel, iwSrcProc, iwDstProc, derivType, maskSize, ::ipp::IwDefault(), ippBorder);
if(useScale)
CV_INSTRUMENT_FUN_IPP(::ipp::iwiScale, iwDstProc, iwDst, scale, delta, ::ipp::IwiScaleParams(ippAlgHintFast));
}
catch (::ipp::IwException)
{
return false;
}
return true;
#else
CV_UNUSED(_src); CV_UNUSED(_dst); CV_UNUSED(dx); CV_UNUSED(dy); CV_UNUSED(ksize); CV_UNUSED(scale); CV_UNUSED(delta); CV_UNUSED(borderType);
return false;
#endif
}
