THMMY.gr

int main(){
    int i,j;
    int ii,jj;
    float **F1, **T, **F;
    int sizeF1, sizeT, sizeF;
    float **Y;
    
    printf("Give me F size and T size\n"); // take input data
    scanf("%d %d",&sizeF1, &sizeT);
    F1=(float **) malloc (sizeF1*sizeF1*sizeof(float));
    T=(float **) malloc (sizeT*sizeT*sizeof(float));
    Y=(float **) malloc ((sizeF1+sizeT-1)*(sizeF1+sizeT-1)*sizeof(float));
    
    for(i=0;i<sizeF1;i++)   //fill arrays with random values
       for(j=0;j<sizeF1;j++)
          F1[i][j]=(float)(rand() % 1000);
       
   for(i=0;i<sizeT;i++)
       for(j=0;j<sizeT;j++)
          T[i][j]=(float)(rand() % 1000);

    /**== Copy the contents of the F table inside the pF table ==**/
    for (i=0;i<mF;i++) {
		for(j=0;j<nF;j++){
			pF[(i+mT-1)*(nF + 2*nT -2)+nT-1+j]=F[i*nF+j];
		}
    }

	CUDA_SAFE_CALL(cudaMallocPitch((void **)&dev_pF,&pitchF,(nF + 2*nT -2)*sizeof(int),mF + 2*mT -2));

	
	CUDA_SAFE_CALL(cudaMemcpy2D((void *)(dev_pF),pitchF,(void *)pF,(nF + 2*nT -2)*sizeof(int),(nF + 2*nT -2)*sizeof(int),(mF + 2*mT -2),cudaMemcpyHostToDevice));

pF[i][j]

                        int *rF=(int *)((char *)pF + (pitchF)*(i));
                        rF[j];

   int result;

Y[i*(nF+nT-1)+j]+=pF[(i+ii)*(nF+2*nT-2)+j+jj]*T[ii*nT+ jj];

error while loading shared libraries: libcudart.so.3: wrong ELF class: ELFCLASS32

#include<stdio.h>
#include<cuda.h>
#define height 50
#define width 50

// Device code
__global__ void kernel(float* devPtr, int pitch)
{
    for (int r = 0; r < height; ++r) {
        float* row = (float*)((char*)devPtr + r * pitch);
        for (int c = 0; c < width; ++c) {
             float element = row[c];
        }
    }
}

//Host Code
int main()
{

float* devPtr;
size_t pitch;
cudaMallocPitch((void**)&devPtr, &pitch, width * sizeof(float), height);
kernel<<<100, 512>>>(devPtr, pitch);
return 0;
}

cudaThreadSynchronize();

	kernel<<<grid,block>>>(dev_Y,dev_pF,dev_T,mT,nT,mF,nF,pitchF,pitchY,pitchT);
	cudaThreadSynchronize();