EXPECT_EQ(X, dxy_dyValue);

  TF_DeleteTensor(fetchValues[0]);
  TF_DeleteTensor(fetchValues[1]);
}

// REGISTER_OP for CApiAttributesTest test cases.
// Registers two ops, each with a single attribute called 'v'.
// The attribute in one op will have a type 'type', the other
// will have list(type).
#define ATTR_TEST_REGISTER_OP(type)                           \

    // Get transpose attrs
    bool t_a;
    TF_RETURN_IF_ERROR(forward_attrs_.Get("transpose_a", &t_a));

    bool t_b;
    TF_RETURN_IF_ERROR(forward_attrs_.Get("transpose_b", &t_b));

    // Conj each input
    AbstractTensorHandle* conj_output;
    std::string name = "Conj_A_MatMul_Grad";
    TF_RETURN_IF_ERROR(
        SafeConj(ctx, forward_inputs_[0], &conj_output, name.c_str()));

    *   Added a new `rerandomize_each_iteration` argument for the `tf.data.Dataset.random()` operation, which controls whether the sequence of generated random numbers should be re-randomized every epoch or not (the default behavior). If `seed` is set and `rerandomize_each_iteration=True`, the `random()` operation will produce a different (deterministic) sequence of numbers every epoch.

  // (as in the case of ConstOp kernel creation on GPU, which involves copying a
  // CPU tensor to GPU).
  // Setting a larger thread pool does not help with the Swift caller, as we use
  // a different TFE context for each thread of execution (for running graph
  // functions, and their send/recvs corountines).
  config.set_inter_op_parallelism_threads(1);

  TF_Buffer* ret = TF_NewBuffer();
  TF_CHECK_OK(MessageToBuffer(config, ret));

//
// First we filter the tape to just the subset of operations we want to
// differentiate. In the process of doing so we count how many times each Tensor
// is used as an input to an op (so we know when we're done computing gradients
// for that Tensor). We also count, for each tape entry, how many of its output
// Tensors need gradients to be computed (Tensors which are not used do not need
// any gradients to be computed).
//

        'device at: https://developer.nvidia.com/cuda-gpus. Each capability '
        'can be specified as "x.y" or "compute_xy" to include both virtual and'
        ' binary GPU code, or as "sm_xy" to only include the binary '
        'code.\nPlease note that each additional compute capability '
        'significantly increases your build time and binary size, and that '

build:macos --features=archive_param_file

# Settings for MacOS on ARM CPUs.
build:macos_arm64 --cpu=darwin_arm64
build:macos_arm64 --macos_minimum_os=11.0

# iOS configs for each architecture and the fat binary builds.
build:ios --apple_platform_type=ios
build:ios --apple_bitcode=embedded --copt=-fembed-bitcode
build:ios --copt=-Wno-c++11-narrowing
build:ios_armv7 --config=ios