I am trying to solve a problem in which i am supposed to change a colour image to a greyscale image. For this purpose i am using CUDA parallel approach.
The kerne code i
__global__
void rgba_to_greyscale(const uchar4* const rgbaImage,
unsigned char* const greyImage,
int numRows, int numCols)
{
int rgba_x = blockIdx.x * blockDim.x + threadIdx.x;
int rgba_y = blockIdx.y * blockDim.y + threadIdx.y;
int pixel_pos = rgba_x+rgba_y*numCols;
uchar4 rgba = rgbaImage[pixel_pos];
unsigned char gray = (unsigned char)(0.299f * rgba.x + 0.587f * rgba.y + 0.114f * rgba.z);
greyImage[pixel_pos] = gray;
}
void your_rgba_to_greyscale(const uchar4 * const h_rgbaImage, uchar4 * const d_rgbaImage,
unsigned char* const d_greyImage, size_t numRows, size_t numCols)
{
//You must fill in the correct sizes for the blockSize and gridSize
//currently only one block with one thread is being launched
const dim3 blockSize(24, 24, 1); //TODO
const dim3 gridSize( numCols/24+1, numRows/24+1, 1); //TODO
rgba_to_greyscale<<>>(d_rgbaImage, d_greyImage, numRows, numCols);
cudaDeviceSynchronize(); checkCudaErrors(cudaGetLastError());
}