static bool transform(cv::InputArray _src, cv::OutputArray _dst, cv::InputArray _lut,
const int tilesX, const int tilesY, const cv::Size & tileSize)
{
cv::ocl::Kernel k("transform", cv::ocl::imgproc::clahe_oclsrc);
if(k.empty())
return false;
int tile_size[2];
tile_size[0] = tileSize.width;
tile_size[1] = tileSize.height;
cv::UMat src = _src.getUMat();
_dst.create(src.size(), src.type());
cv::UMat dst = _dst.getUMat();
cv::UMat lut = _lut.getUMat();
size_t localThreads[3] = { 32, 8, 1 };
size_t globalThreads[3] = { (size_t)src.cols, (size_t)src.rows, 1 };
int idx = 0;
idx = k.set(idx, cv::ocl::KernelArg::ReadOnlyNoSize(src));
idx = k.set(idx, cv::ocl::KernelArg::WriteOnlyNoSize(dst));
idx = k.set(idx, cv::ocl::KernelArg::ReadOnlyNoSize(lut));
idx = k.set(idx, src.cols);
idx = k.set(idx, src.rows);
idx = k.set(idx, tile_size);
idx = k.set(idx, tilesX);
k.set(idx, tilesY);
return k.run(2, globalThreads, localThreads, false);
}
static bool calcLut(cv::InputArray _src, cv::OutputArray _dst,
const int tilesX, const int tilesY, const cv::Size tileSize,
const int clipLimit, const float lutScale)
{
cv::ocl::Kernel k("calcLut", cv::ocl::imgproc::clahe_oclsrc);
if(k.empty())
return false;
cv::UMat src = _src.getUMat();
_dst.create(tilesX * tilesY, 256, CV_8UC1);
cv::UMat dst = _dst.getUMat();
int tile_size[2];
tile_size[0] = tileSize.width;
tile_size[1] = tileSize.height;
size_t localThreads[3] = { 32, 8, 1 };
size_t globalThreads[3] = { tilesX * localThreads[0], tilesY * localThreads[1], 1 };
int idx = 0;
idx = k.set(idx, cv::ocl::KernelArg::ReadOnlyNoSize(src));
idx = k.set(idx, cv::ocl::KernelArg::WriteOnlyNoSize(dst));
idx = k.set(idx, tile_size);
idx = k.set(idx, tilesX);
idx = k.set(idx, clipLimit);
k.set(idx, lutScale);
return k.run(2, globalThreads, localThreads, false);
}
static bool calcLut(cv::InputArray _src, cv::OutputArray _dst,
const int tilesX, const int tilesY, const cv::Size tileSize,
const int clipLimit, const float lutScale)
{
cv::ocl::Kernel _k("calcLut", cv::ocl::imgproc::clahe_oclsrc);
bool is_cpu = cv::ocl::Device::getDefault().type() == cv::ocl::Device::TYPE_CPU;
cv::String opts;
if(is_cpu)
opts = "-D CPU ";
else
opts = cv::format("-D WAVE_SIZE=%d", _k.preferedWorkGroupSizeMultiple());
cv::ocl::Kernel k("calcLut", cv::ocl::imgproc::clahe_oclsrc, opts);
if(k.empty())
return false;
cv::UMat src = _src.getUMat();
_dst.create(tilesX * tilesY, 256, CV_8UC1);
cv::UMat dst = _dst.getUMat();
int tile_size[2];
tile_size[0] = tileSize.width;
tile_size[1] = tileSize.height;
size_t localThreads[3] = { 32, 8, 1 };
size_t globalThreads[3] = { tilesX * localThreads[0], tilesY * localThreads[1], 1 };
int idx = 0;
idx = k.set(idx, cv::ocl::KernelArg::ReadOnlyNoSize(src));
idx = k.set(idx, cv::ocl::KernelArg::WriteOnlyNoSize(dst));
idx = k.set(idx, tile_size);
idx = k.set(idx, tilesX);
idx = k.set(idx, clipLimit);
idx = k.set(idx, lutScale);
if (!k.run(2, globalThreads, localThreads, false))
return false;
return true;
}