Question

i began to implement some simple image processing using cuda but i have an error in my code
the error happens when i copy pixels from device to host

this is my try

#include "cuda_runtime.h"
#include "device_launch_parameters.h"
#include <opencv2\core\core.hpp>
#include <opencv2\highgui\highgui.hpp>
#include <stdio.h> 
using namespace cv;

unsigned char *h_pixels;
unsigned char *d_pixels;
int bufferSize;
int width,height;

const int BLOCK_SIZE = 32;
Mat image;

void get_pixels(const char* fileName)
{
    image = imread(fileName);
    bufferSize = image.size().width * image.size().height * 3 * sizeof(unsigned char);
    width = image.size().width;
    height = image.size().height;
    h_pixels = new unsigned char[bufferSize];
    memcpy(h_pixels,image.data,bufferSize);
}

__global__ void invert_image(unsigned char* pixels,int width,int height)
{
    int row = blockIdx.y * BLOCK_SIZE + threadIdx.y;
    int col = blockIdx.x * BLOCK_SIZE + threadIdx.x;
    int cidx = (row  * width + col) * 3;
    pixels[cidx] = 255 - pixels[cidx]; 
    pixels[cidx + 1] = 255 - pixels[cidx + 1]; 
    pixels[cidx + 2] = 255 - pixels[cidx + 2]; 

}
int main()
{
    get_pixels("D:\\photos\\z.jpg");

    cudaError_t err = cudaMalloc((void**)&d_pixels,bufferSize);
    err =  cudaMemcpy(d_pixels,h_pixels,bufferSize,cudaMemcpyHostToDevice);
    dim3 dimBlock(BLOCK_SIZE,BLOCK_SIZE);
    dim3 dimGrid(width/dimBlock.x,height/dimBlock.y);

    invert_image<<<dimBlock,dimGrid>>>(d_pixels,width,height);

    unsigned char *pixels = new unsigned char[bufferSize];


    err= cudaMemcpy(pixels,d_pixels,bufferSize,cudaMemcpyDeviceToHost);// unknown error 
    const char * errStr = cudaGetErrorString(err);
    cudaFree(d_pixels);
    image.data = pixels;
    namedWindow("display image");
    imshow("display image",image);
    waitKey();
    return 0;
}

also how can i find out error that occurs in cuda device
thanks for your help

Answer 1

• First of all be sure that the image file is read correctly.
• Check if the device memory is allocated with CUDA_SAFE_CALL(cudaMalloc(..))
• Check the dimensions of the image. If the dimension of the image is not multiples of BLOCKSIZE than you might be missing some indices and the image is not fully inverted.
• Call cudaDeviceSynchronize after the kernel call and check its return value.
• Do you get any error when you run the code without calling the kernel anyway?
• You are not freeing the h_pixels and might have a memory leak.
• Instead of using BLOCKSIZE in the kernel you might use “blockDim.x”. So calculating indices like “blockIdx.x * blockDim.x + threadIdx.x”
• Try to do not touch the memory area in the kernel code, namely comment out the memory updates at the kernel (the lines where you access the pixels array) and check if the program continues to fail. If it does not continue to fail you might be accessing out of the bounds.