# addition to this core set of ops, user libraries which are loaded (via
# TF_LoadLibrary/tf.load_op_library) register their ops and kernels with this
# shared object directly.
#
# For example, from Python tf.load_op_library loads a custom op library (via
# dlopen() on Linux), the library finds libtensorflow_framework.so (no

    *   Added 8-bit and 16-bit support for `floor_div` and `floor_mod`.
    *   Added 16-bit and 32-bit int support for the built-in op `bitcast`.
    *   Added 8-bit/16-bit/32-bit int/uint support for the built-in op `bitwise_xor`
    *   Added int16 indices support for built-in op `gather` and `gather_nd`.
    *   Added 8-bit/16-bit/32-bit int/uint support for the built-in op `right_shift`

  }

  AbstractOperationPtr check_numerics_op(ctx->CreateOperation());
  ForwardOperation forward_op;
  Status s = Reset(check_numerics_op.get(), "CheckNumerics",
                   /*raw_device_name=*/nullptr, &forward_op);
  ASSERT_EQ(errors::OK, s.code()) << s.message();
  if (isa<TracingOperation>(check_numerics_op.get())) {
    s = dyn_cast<TracingOperation>(check_numerics_op.get())
            ->SetOpName("check_numerics");

        return;
      } else if (execution_state_ == ExecutionState::kReadyToExecute) {
        // op_outputs_ may have been std::moved
        op_outputs_ = std::vector<TensorHandlePtr>();
        Execute(context_, operation_name_, std::move(op_inputs_), attributes_,
                expected_max_outputs_, &op_outputs_, status_.get());
        execution_state_ = ExecutionState::kHasResult;
      }
    }

      }
      grad_inputs[i] = grad_input;
    }
    return absl::OkStatus();
  }
  ~IdentityNGradientFunction() override {}
};
}  // namespace

GradientFunction* IdentityNRegisterer(const ForwardOperation& op) {
  return new IdentityNGradientFunction;
}

}  // namespace gradients

      "      name: 'read0'"
      "      op: 'ReadVariableOp'"
      "      input: 'var'"
      "      device: '/job:localhost/replica:0/task:0/device:CPU:0'"
      "      attr {"
      "        key: 'dtype'"
      "        value {"
      "          type: DT_FLOAT"
      "        }"
      "      }"
      "    }"
      "    node_def {"
      "      name: 'read1'"
      "      op: 'ReadVariableOp'"
      "      input: 'var'"

build:mkl_aarch64_threadpool -c opt

# CUDA: This config refers to building CUDA op kernels with nvcc.
build:cuda --repo_env TF_NEED_CUDA=1
build:cuda --crosstool_top=@local_config_cuda//crosstool:toolchain
build:cuda --@local_config_cuda//:enable_cuda

# CUDA: This config refers to building CUDA op kernels with clang.
build:cuda_clang --config=cuda

    std::vector<const Node*>* body_nodes)
    TF_EXCLUSIVE_LOCKS_REQUIRED(fn_body->mu) {
  if (num_opers == -1) {
    for (const Node* node : fn_body->graph.op_nodes()) {
      const auto& iter = input_nodes.find(node);
      if (iter == input_nodes.end()) {
        // This node is not referenced in inputs. Add it to the body.
        body_nodes->push_back(node);
      } else {