-		  && __string2_1bptr_p (src) && n <= 8			      \
-		  ? __mempcpy_small (dest, __mempcpy_args (src), n)	      \
-		  : __mempcpy (dest, src, n)))
-#   endif
-/* In glibc we use this function frequently but for namespace reasons
-   we have to use the name `__mempcpy'.  */
-#   define mempcpy(dest, src, n) __mempcpy (dest, src, n)
-#  endif
-
-#  if !__GNUC_PREREQ (3, 0) || defined _FORCE_INLINES
-#   if _STRING_ARCH_unaligned

  TF_RETURN_IF_ERROR(GetValue(theta, &theta_tensor));

  // Get number of elements and fill data.
  int num_elems = TF_TensorElementCount(theta_tensor);
  vector<float> theta_data(num_elems);
  memcpy(theta_data.data(), TF_TensorData(theta_tensor),
         TF_TensorByteSize(theta_tensor));

  // Initialize space for the numerical gradient.
  vector<float> dtheta_approx(num_elems);

TFE_TensorHandle* TestScalarTensorHandle(TFE_Context* ctx, float value) {
  float data[] = {value};
  TF_Status* status = TF_NewStatus();
  TF_Tensor* t = TFE_AllocateHostTensor(ctx, TF_FLOAT, nullptr, 0, status);
  memcpy(TF_TensorData(t), &data[0], TF_TensorByteSize(t));
  TFE_TensorHandle* th = TFE_NewTensorHandleFromTensor(ctx, t, status);
  CHECK_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
  TF_DeleteTensor(t);

  *len = debug_str.size();
  char* ret = static_cast<char*>(malloc(*len + 1));
  memcpy(ret, debug_str.c_str(), *len + 1);
  return ret;
}

char* TF_FunctionDebugString(TF_Function* func, size_t* len) {
  const auto& debug_str = DebugString(func->record->fdef());
  *len = debug_str.size();
  char* ret = static_cast<char*>(malloc(*len + 1));
  memcpy(ret, debug_str.c_str(), *len + 1);
  return ret;
}

  TF_Tensor* t = TFE_TensorHandleResolve(retvals[0], status);
  ASSERT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
  float product[4] = {0};
  EXPECT_EQ(sizeof(product), TF_TensorByteSize(t));
  memcpy(&product[0], TF_TensorData(t), TF_TensorByteSize(t));
  TF_DeleteTensor(t);
  EXPECT_EQ(7, product[0]);
  EXPECT_EQ(10, product[1]);
  EXPECT_EQ(15, product[2]);
  EXPECT_EQ(22, product[3]);

  EXPECT_EQ(TF_FLOAT, TFE_TensorHandleDataType(h));

  TF_Tensor* t = TFE_TensorHandleResolve(h, status.get());
  ASSERT_EQ(16, TF_TensorByteSize(t));
  float data[4] = {0};
  memcpy(&data[0], TF_TensorData(t), TF_TensorByteSize(t));
  EXPECT_EQ(1.0, data[0]);
  EXPECT_EQ(2.0, data[1]);
  EXPECT_EQ(3.0, data[2]);
  EXPECT_EQ(4.0, data[3]);
  TF_DeleteTensor(t);
  TFE_DeleteTensorHandle(h);

  ASSERT_EQ(TF_GetCode(status), TF_OK) << TF_Message(status);
  TFE_DeleteTensorHandle(retval_task0);
  float product[4] = {0};
  EXPECT_EQ(sizeof(product), TF_TensorByteSize(t));
  memcpy(&product[0], TF_TensorData(t), TF_TensorByteSize(t));
  TF_DeleteTensor(t);
  EXPECT_EQ(7, product[0]);
  EXPECT_EQ(10, product[1]);
  EXPECT_EQ(15, product[2]);
  EXPECT_EQ(22, product[3]);

  ASSERT_EQ(TF_OK, TF_GetCode(status.get())) << TF_Message(status.get());
  TF_Tensor* result_tensor = TFE_TensorHandleResolve(result_t, status.get());

  // Copy Tensor data into an array.
  float result_data[4] = {0};
  memcpy(&result_data[0], TF_TensorData(result_tensor),
         TF_TensorByteSize(result_tensor));

  int data_len = 4;  // length of result_data
  for (int i = 0; i < data_len; i++) {
    EXPECT_EQ(result_data[i], 0);
  }

                                           const int64_t* dims, int num_dims) {
  TF_Status* status = TF_NewStatus();
  TF_Tensor* t = TFE_AllocateHostTensor(ctx, datatype, dims, num_dims, status);
  memcpy(TF_TensorData(t), data, TF_TensorByteSize(t));
  TFE_TensorHandle* th = TFE_NewTensorHandleFromTensor(ctx, t, status);
  CHECK_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);
  TF_DeleteTensor(t);
  TF_DeleteStatus(status);

  ASSERT_EQ(TF_GetCode(status), TF_OK) << TF_Message(status);
  TFE_DeleteTensorHandle(retvals[0]);
  float sum = 0;
  EXPECT_EQ(sizeof(sum), TF_TensorByteSize(t));
  memcpy(&sum, TF_TensorData(t), TF_TensorByteSize(t));
  TF_DeleteTensor(t);
  EXPECT_EQ(sum, 6.0);

  TFE_DeleteTensorHandle(h0);
  TFE_DeleteTensorHandle(h1);
  TFE_DeleteTensorHandle(h2);