Hi,
This is my code, initializing a matrix d_ref and copying it to device. I’m not sure if I’m using cudaMallocPitch and cudaMemcpy2D correctly but I tried to use cudaMemcpy2D.
[b]The problem I had is solved.
[/b]
and is it the best way of doing this job?
Thanks in advance.
__host__
float *d_ref;
float **h_ref = new float* [width];
for (int i=0;i<width;i++)
h_ref[i]= new float [height];
for (int i=0;i<width;i++){
for (int j=0;j<height;j++){
h_ref[i][j]=ref_list[j][i]; //transpose
}
}
size_t ref_pitch;
cudaMallocPitch(&d_ref, &ref_pitch, width * sizeof(float), height);
cudaMemcpy2D(d_ref, ref_pitch, *h_ref, n_com*sizeof(float),n_com*sizeof(float), refLength, cudaMemcpyHostToDevice);
lowerBound<<<grid, block>>>(d_ref, ...
__global__ void lowerBound (float* d_ref, ....
float* ref = (float*)((char*)d_ref + blockIdx.x * ref_pitch);
cuPrintf(" %f \n",ref[threadIdx.x]);