cudaThreadSynchronize() requirement

I have a cuda program like this :

for (int i=0;i<100000;i++) {
  if (i%2 == 0) {
    bind_x(x) // bind x to texture
    kernel_code<<A,B>>(M,x,y) // calculate y = M*x
  }
  else {
    bind_x(y)
    kernel_code<<A,B>>(M,y,x) // calculate x = M*y
  }

  cudaThreadSynchronize();

  if (i%2 == 0)
    u开发者_开发知识库nbind_x(x)
  else 
    unbind_x(y) // unbind x from texture
}

I heard that if I do not put cudaThreadSynchronize(); cpu will continue to run without waiting for the kernel to end so ... Should I call cudaThreadSynchronize() before unbind_x(). I try to run with& without, the result is the same ?!? (And in theory It shouldn't)

---

Any CUDA operation (except special asynchronious operations) will cause cudaThreadSynchronize() automatically. So, results should be the same.