float dA_vals[4][9] = {{24, 15, 6, 24, 15, 6, 24, 15, 6},
                         {18, 15, 12, 18, 15, 12, 18, 15, 12},
                         {24, 24, 24, 15, 15, 15, 6, 6, 6},
                         {18, 18, 18, 15, 15, 15, 12, 12, 12}};
  float dB_vals[4][9] = {{12, 12, 12, 15, 15, 15, 18, 18, 18},
                         {12, 15, 18, 12, 15, 18, 12, 15, 18},

  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]);

  TFE_DeleteTensorHandle(h0_task0);
  TFE_DeleteTensorHandle(h1_task0);
  TFE_DeleteTensorHandle(h0_task1);
  TFE_DeleteTensorHandle(h1_task1);

  auto* retval_task0 =
      TFE_TensorHandleCopyToDevice(retvals[0], ctx, local_device_name, status);
  ASSERT_EQ(TF_OK, TF_GetCode(status)) << TF_Message(status);

  CheckTFE_TensorHandleHasFloats(retval_task0, {7, 10, 15, 22});

  TFE_DeleteTensorHandle(retval_task0);
  TFE_DeleteTensorHandle(h0_task0);
  TFE_DeleteTensorHandle(retvals[0]);

  TFE_DeleteOp(matmul);

  TFE_Executor* executor = TFE_ContextGetExecutorForThread(ctx);

  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]);
  TF_DeleteStatus(status);
}
TEST(CAPI, Executor_MatMul_CPU) { Executor_MatMul_CPU(false); }
TEST(CAPI, Executor_MatMul_CPUAsync) { Executor_MatMul_CPU(true); }

  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]);
  TF_DeleteStatus(status);
}
TEST(CAPI, Execute_MatMul_CPU) { Execute_MatMul_CPU(false); }
TEST(CAPI, Execute_MatMul_CPUAsync) { Execute_MatMul_CPU(true); }

  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]);

  TFE_DeleteTensorHandle(h0_task0);
  TFE_DeleteTensorHandle(h1_task0);
  if (packed_handle) {
    TFE_DeleteTensorHandle(packed_handle);
  }

// check the data type.
typedef std::pair<string, DataType> IOSpec;

const char* kFeedStackToString = "File \"feed.cc\", line 10, in alpha";
const char* kNegStackToString = "File \"neg.cc\", line 15, in beta";

std::vector<IOSpec> M(const std::initializer_list<string>& names) {
  std::vector<IOSpec> v;
  for (const string& name : names) {
    v.push_back(IOSpec(name, DT_INVALID));
  }
  return v;
}