Standard C:

void saxpy( int n, float a,
            float *x, float *y )
{
   for ( int i = 0; i < n; ++i )
      y[i] = a * x[i] + y[i];
}

int N = 1 << 20;

saxpy( N, 2.0, x, y );

C with CUDA Extensions:

__global__
void saxpy( int n, float a,
float *x, float *y )
{
   int i = blockIdx.x*blockDim.x + threadIdx.x;
   if ( i < n ) y[i] = a * x[i] + y[i];
}

int N = 1 << 20;
cudaMemcpy(x, d_x, N, cudaMemcpyHostToDevice);
cudaMemcpy(y, d_y, N, cudaMemcpyHostToDevice);

saxpy<<<4096,256>>>(N, 2.0, x, y);

cudaMemcpy(d_y, y, N, cudaMemcpyDeviceToHost);