matrixAddition a simple cuda program, not working. please help

Accelerated Computing CUDA CUDA Programming and Performance
1

Hey,

Below is the code which I have written for a simple matrix adition:

#include<stdio.h>
#include<cuda.h>

const int N = 4;
const int blocksize = 2;

global void matrixAdd(float *a, float b, float c, int N)
{
int i = threadIdx.x;
//int j = blockIdx.yblockDim.y + threadIdx.y;
//int index = i +jN;

if(i<<N )
	c[i]=a[i]+b[i];

}

int main()
{
float a, b, c;
a=(float )malloc(NNsizeof(float));
b=(float )malloc(NNsizeof(float));
c=(float )malloc(NNsizeof(float));

for ( int i = 0; i < N*N; ++i ) {
  a[i] = 7.0; b[i] = 3.5; }

float *ad, *bd, *cd;
const int size = N*N*sizeof(float);
cudaMalloc( (void**)&ad, size );
cudaMalloc( (void**)&bd, size );
cudaMalloc( (void**)&cd, size );

cudaMemcpy(ad,a,size,cudaMemcpyHostToDevice);
cudaMemcpy(ad,a,size,cudaMemcpyHostToDevice);

//dim3 dimBlock = (blocksize, blocksize);
//dim3 dimGrid = (N/dimBlock.x, N/dimBlock.y);

matrixAdd<<<1,16>>>(ad,bd,cd,N);

cudaMemcpy(c,cd,size,cudaMemcpyDeviceToHost);

for ( int i = 0; i < N*N; ++i ) {
  printf("%f",c[i]); }

cudaFree(ad);
cudaFree(bd);
cudaFree(cd);

free(a);
free(B);
free©;

return 0;

}

When I compile with nvcc, I get a warning which says that the lines dim3 dimBlock = (blocksize, blocksize), dim3 dimGrid = (N/dimBlock.x, N/dimBlock.y); have no effect. Even when I try to directly pass the number of threads to the kernet, the output is not desirable.

Please help.

2

Got it. there would not be = with dim3. and I by mistake had put left shift instead of less than sign. god!!1