you're running the same code that you're testing:

    *   Use an up to date [tf-nightly](https://pypi.org/project/tf-nightly/)
        `pip install -U tf-nightly`
    *   Rebase your pull request onto a recent pull from
        [TensorFlow's](https://github.com/tensorflow/tensorflow) master branch.

2.  If you are changing the code and the docstring of a class/function/method,
    then you will need to

  EXPECT_TRUE(executed);
  ASSERT_TRUE(TF_GetCode(status.get()) == TF_OK) << TF_Message(status.get());
  TFE_DeleteTensorHandle(retval);

  // Explicit placement still forces the op onto the requested device
  matmul.reset(MatMulOp(context.get(), hcustom0.get(), hcpu.get()));
  TFE_OpSetDevice(matmul.get(), "/job:localhost/replica:0/task:0/device:CPU:0",
                  status.get());

  //
  // TFE_OpGetDevice(op) records the original placement of the operation. It may
  // be an empty string if no device was explicitly requested, but will
  // otherwise be the name of this custom device. Ops are placed onto a custom
  // device if any of their inputs are on that custom device, but custom devices
  // are free to set a bad status in order to require explicit placement.
  void (*execute)(const TFE_Op* op, int* num_outputs,

-		     ? (char *) memcpy (dest, src, n)			      \
-		     : strncpy (dest, src, n))				      \
-		  : strncpy (dest, src, n)))
-# endif
-#endif
-
-
 /* Append no more than N characters from SRC onto DEST.  */
 #ifndef _HAVE_STRING_ARCH_strncat
 # ifdef _USE_STRING_ARCH_strchr
@@ -780,380 +438,29 @@ __stpcpy_small (char *__dest,
 		       : (*((char *) __mempcpy (strchr (__dest, '\0'),	      \

  TensorHandlePtr value_one(FloatTensorHandle(1., status.get()));
  TensorHandlePtr value_two(FloatTensorHandle(2., status.get()));
  {
    // Try to pack two TensorHandles onto a parallel device with a single
    // component.
    ASSERT_EQ(TF_GetCode(status.get()), TF_OK) << TF_Message(status.get());
    std::array<TFE_TensorHandle*, 2> components{value_one.get(),