imgproc: enable GaussianBlur IPP parallel processing

This commit is contained in:
Alexander Alekhin 2020-04-16 18:17:22 +00:00
parent a1b09a3734
commit a3b109eca0
3 changed files with 26 additions and 6 deletions

View File

@ -208,8 +208,6 @@ T* allocSingletonNew() { return new(allocSingletonNewBuffer(sizeof(T))) T(); }
#define IPP_DISABLE_HOUGH 1 // improper integration/results
#define IPP_DISABLE_FILTER2D_BIG_MASK 1 // different results on masks > 7x7
#define IPP_DISABLE_GAUSSIANBLUR_PARALLEL 1 // not supported (2017u2 / 2017u3)
// Temporary disabled named IPP region. Performance
#define IPP_DISABLE_PERF_COPYMAKE 1 // performance variations
#define IPP_DISABLE_PERF_LUT 1 // there are no performance benefits (PR #2653)

View File

@ -12,3 +12,9 @@ ocv_add_dispatched_file(smooth SSE2 SSE4_1 AVX2)
ocv_add_dispatched_file(sumpixels SSE2 AVX2 AVX512_SKX)
ocv_add_dispatched_file(undistort SSE2 AVX2)
ocv_define_module(imgproc opencv_core WRAP java python js)
ocv_check_environment_variables(OPENCV_IPP_GAUSSIAN_BLUR)
option(OPENCV_IPP_GAUSSIAN_BLUR "Enable IPP optimizations for GaussianBlur (+8Mb in binary size)" OFF)
if(OPENCV_IPP_GAUSSIAN_BLUR)
ocv_append_source_file_compile_definitions(${CMAKE_CURRENT_SOURCE_DIR}/src/smooth.dispatch.cpp "ENABLE_IPP_GAUSSIAN_BLUR=1")
endif()

View File

@ -470,9 +470,14 @@ static bool openvx_gaussianBlur(InputArray _src, OutputArray _dst, Size ksize,
#endif
#if 0 //defined HAVE_IPP
#if defined ENABLE_IPP_GAUSSIAN_BLUR // see CMake's OPENCV_IPP_GAUSSIAN_BLUR option
#define IPP_DISABLE_GAUSSIAN_BLUR_LARGE_KERNELS_1TH 1
#define IPP_DISABLE_GAUSSIAN_BLUR_16SC4_1TH 1
#define IPP_DISABLE_GAUSSIAN_BLUR_32FC4_1TH 1
// IW 2017u2 has bug which doesn't allow use of partial inMem with tiling
#if IPP_DISABLE_GAUSSIANBLUR_PARALLEL
#if IPP_VERSION_X100 < 201900
#define IPP_GAUSSIANBLUR_PARALLEL 0
#else
#define IPP_GAUSSIANBLUR_PARALLEL 1
@ -555,6 +560,14 @@ static bool ipp_GaussianBlur(InputArray _src, OutputArray _dst, Size ksize,
return false;
const int threads = ippiSuggestThreadsNum(iwDst, 2);
if (IPP_DISABLE_GAUSSIAN_BLUR_LARGE_KERNELS_1TH && (threads == 1 && ksize.width > 25))
return false;
if (IPP_DISABLE_GAUSSIAN_BLUR_16SC4_1TH && (threads == 1 && src.type() == CV_16SC4))
return false;
if (IPP_DISABLE_GAUSSIAN_BLUR_32FC4_1TH && (threads == 1 && src.type() == CV_32FC4))
return false;
if(IPP_GAUSSIANBLUR_PARALLEL && threads > 1) {
bool ok;
ipp_gaussianBlurParallel invoker(iwSrc, iwDst, ksize.width, (float) sigma1, ippBorder, &ok);
@ -655,8 +668,6 @@ void GaussianBlur(InputArray _src, OutputArray _dst, Size ksize,
CV_OVX_RUN(true,
openvx_gaussianBlur(src, dst, ksize, sigma1, sigma2, borderType))
//CV_IPP_RUN_FAST(ipp_GaussianBlur(src, dst, ksize, sigma1, sigma2, borderType));
if(sdepth == CV_8U && ((borderType & BORDER_ISOLATED) || !_src.getMat().isSubmatrix()))
{
std::vector<ufixedpoint16> fkx, fky;
@ -681,6 +692,11 @@ void GaussianBlur(InputArray _src, OutputArray _dst, Size ksize,
}
}
#if defined ENABLE_IPP_GAUSSIAN_BLUR
// IPP is not bit-exact to OpenCV implementation
CV_IPP_RUN_FAST(ipp_GaussianBlur(src, dst, ksize, sigma1, sigma2, borderType));
#endif
sepFilter2D(src, dst, sdepth, kx, ky, Point(-1, -1), 0, borderType);
}