Error in Kernel launch statement in CUDA - c++

Question

I am doing a small project in image processing using CUDA.I am trying to use Gaussian blurring to blur an image.Everything is fine but I cannot figure out why the kernel launch statement is showing this strange error:
Here is my complete code, if it can be of any help:
#include<time.h>
#include<stdlib.h>
#include<stdio.h>
#include<string.h>
#include<math.h>
#include<cuda_runtime.h>
#include<device_launch_parameters.h>
#include <helper_cuda.h>
#include <helper_cuda_gl.h>
#include<helper_image.h>
#include< helper_cuda_gl.h>
#include<helper_cuda_drvapi.h>
unsigned int width, height;
int mask[3][3] = { 1, 2, 1,
2, 3, 2,
1, 2, 1,
};
int getPixel(unsigned char *arr, int col, int row)
{
int sum = 0;
for (int j = -1; j <= 1; j++)
{
for (int i = -1; i <= 1; i++)
{
int color = arr[(row + j)*width + (col + i)];
sum += color*mask[i + 1][j + 1];
}
}
return sum / 15;
}
void h_blur(unsigned char * arr, unsigned char * result){
int offset = 2 * width;
for (int row = 2; row < height - 3; row++)
{
for (int col = 2; col < width - 3; col++)
{
result[offset + col] = getPixel(arr, col, row);
}
offset += width;
}
}
__global__ void d_blur(unsigned char *arr, unsigned char * result, int width, int height)
{
int col = blockIdx.x*blockDim.x + threadIdx.x;
int row = blockIdx.y*blockDim.y + threadIdx.y;
if (row < 2 || col < 2 || row >= height - 3 || col >= width - 3)
return;
int mask[3][3] = { 1, 2, 1, 2, 3, 2, 1, 2, 1 };
int sum = 0;
for (int j = -1; j <= 1; j++)
{
int color = arr[(row + j)*width + (col + i)];
sum += color*mask[i + 1][j + 1];
}
result[row*width + col] = sum / 15;
}
int main(int argc, char ** argv)
{
unsigned char *d_resultPixels;
unsigned char *h_resultPixels;
unsigned char *h_pixels = NULL;
unsigned char *d_pixels = NULL;
char *srcPath = "C:\ProgramData\NVIDIA Corporation\CUDA Samples\v6.5\3_Imaging\dxtc\data\lena_std.ppm";
char *h_ResultPath = "C:\ProgramData\NVIDIA Corporation\CUDA Samples\v6.5\3_Imaging\dxtc\data\lena_std.ppm";
char *d_ResultPath = "C:\ProgramData\NVIDIA Corporation\CUDA Samples\v6.5\3_Imaging\dxtc\data\lena_std.ppm";
sdkLoadPGM(srcPath, &h_pixels, &width, &height);
int ImageSize = sizeof(unsigned char) * width * height;
h_resultPixels = (unsigned char *)malloc(ImageSize);
cudaMalloc((void**)&d_pixels, ImageSize);
cudaMalloc((void**)&d_resultPixels, ImageSize);
cudaMemcpy(d_pixels, h_pixels, ImageSize, cudaMemcpyHostToDevice);
dim3 block(16, 16);
dim3 grid(width / 16, height / 16);
d_blur << < grid, block >> >(d_pixels, d_resultPixels, width, height);
cudaThreadSynchronize();
cudaMemcpy(h_resultPixels, d_resultPixels, ImageSize, cudaMemcpyDeviceToHost);
sdkSavePGM(d_ResultPath, h_resultPixels, width, height);
printf("Press enter to exit ...\n");
getchar();
}

Answer 1

As you are trying to run this in Visual Studio, you need to update the Intellisense. Also,you can refer the following link for a better Image Convolution Operation in CUDA.
2D Image Convolution in CUDA