EXPECT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
  if (!forward_input) {
    TFE_DeleteTensorHandle(n);
  }
  TFE_DeleteOp(add_op);

  TF_Tensor* t = TFE_TensorHandleResolve(retval, status);
  if (async) {
    if (forward_input) {
      // Since the input was forwarded, we released the input handle right away
      // and hence expect the input to be forwarded to the return tensor.
      EXPECT_EQ(orig_ptr, TF_TensorData(t));

    //   |      dz|          |
    //   |        |          |
    //   |     Const_3       |
    //   |                   |
    //   |        ^          |
    //   |       z|          |     // MatMul Forward Graph
    //   |        |          |
    //   |      MatMul       |
    //   |     /       \     |
    //   |    ^         ^    |
    //   |    |         |    |
    //   |---x|        y|----|

# This is the same as the official TensorFlow builds.
# See https://developer.nvidia.com/cuda-gpus#compute
# `compute_XY` enables PTX embedding in addition to SASS. PTX
# is forward compatible beyond the current compute capability major
# release while SASS is only forward compatible inside the current
# major release. Example: sm_80 kernels can run on sm_89 GPUs but
# not on sm_90 GPUs. compute_80 kernels though can also run on sm_90 GPUs.