safer-kernel.cpp

#define CUDA_KERNEL_GUARD(i, n) for(int i = blockIdx.x * blockDim.x + threadIdx.x; i < n;  i += blockDim.x * gridDim.x)

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