// CHECK-DAG: %[[input_23:.*]] = "tfl.dequantize"({{.*}}) : (tensor<2x!quant.uniform<i16<-32767:32767>:f32, 2.736719606284107E-5>>) -> tensor<2xf32>

// CHECK: %[[lstm:.*]] = "tfl.unidirectional_sequence_lstm"(%[[input_0]], %[[input_1]], %[[input_2]], %[[input_3]], %[[input_4]], %[[input_5]], %[[input_6]], %[[input_7]], %[[input_8]],

is used instead.

Operands are replicated inputs and packed inputs.

replicated_inputs: each group of `n` inputs corresponds to an input for a single
individual replica and is mapped to a single region argument. Inside one group
the operands are matching in order the `devices` attribute. Each replicated
input must have compatible shapes and types.
packed_inputs: each input corresponds to an input broadcasted across all

// CHECK-SAME: %[[input_0]],
// CHECK-SAME: %[[input_1]], %[[input_2]], %[[input_3]], %[[input_4]],
// CHECK-SAME: %[[input_5]], %[[input_6]], %[[input_7]], %[[input_8]],
// CHECK-SAME: %[[input_9]], %[[input_9]], %[[input_9]],
// CHECK-SAME: %[[input_10]], %[[input_11]], %[[input_12]], %[[input_13]],
// CHECK-SAME: %[[input_9]], %[[input_9]],
// CHECK-SAME: %[[input_14]], %[[input_15]],

            test {
                inputs1 = files("input1.txt")
                inputs2 = files("input2.txt", "input3.txt")
            }
        """

        when:
        succeeds "test", "--info"

        then:
        executedAndNotSkipped ':test'
        outputContains "Input property 'inputs1' file ${file("input2.txt")} has been removed."

  Init(2);
  // Create nested loop:
  //  while (input1 < 6) {
  //    inner_input1 = input1
  //    while (inner_input1 < 3) {
  //      input2 += 1
  //      inner_input1 += 2
  //    }
  //    input1 += input2
  //  }
  //
  // Expected execution with initial values input1 = input2 = 0:
  //
  // outer inner               inner_
  // step# step# input1 input2 input1
  // ------------------------------------

  %10 = "tf.opK"() : () -> tensor<*xi16>
  %11 = "tf.opL"() : () -> tensor<*xi64>
  tf_device.replicate([%0, %1, %2] as %input0: tensor<*xi1>, %9 as %input1: tensor<*xi8>, %10 as %input2: tensor<*xi16>, [%3, %4, %5] as %input3: tensor<*xi32>, [%6, %7, %8] as %input4: tensor<*xf32>, %11 as %input5: tensor<*xi64>) {n = 3 : i32} {
    tf_device.return
  }
  func.return

// CHECK:      %[[OP_A:[a-z0-9]*]] = "tf.opA"

// RUN: tac-translate -input-mlir -output-mlir -device-specs=GPU %s -o - 2>&1 | FileCheck %s

module {
func.func @main(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>, %arg2: tensor<1xf32>, %arg3: tensor<1xf32>) -> tensor<2x1xf32> attributes {tf.entry_function = {inputs = "input0,input1,input2,input3", outputs = "output"}} {
  %0 = "tfl.add"(%arg0, %arg1) {fused_activation_function = "RELU6"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>

  std::vector<TFE_TensorHandle*> compute_fn_inputs;
  TFE_TensorHandle* input_a = TestScalarTensorHandle(ctx, 2.0f);
  TFE_TensorHandle* input_b = TestScalarTensorHandle(ctx, 1.0f);
  compute_fn_inputs.push_back(input_a);
  compute_fn_inputs.push_back(input_b);

  TFE_Op* compute_fn_op = TF_ConcreteFunctionMakeCallOp(

        connection.queueIncoming(input1)
        connection.queueIncoming(input2)
        connection.queueIncoming(closeInput)
        received.await()
        daemonConnection.stop()

        then:
        1 * handler.onInput(input1)
        1 * handler.onInput(input2)
        1 * handler.onEndOfInput() >> { received.countDown() }
        0 * handler._
    }

}

// CHECK-LABEL: func @tensor_array_while_test
// CHECK-SAME: ([[in_chain:%.*]]: !tfrt.chain
func.func @tensor_array_while_test(%indices: tensor<?xi32>, %input_0: tensor<?x?x?xf32>, %input_1: tensor<?x?x?xf32>) -> (tensor<?x?x512xf32>, tensor<?x?x512xf32>) {
  %index = "tf.Const"() {device = "/device:CPU:0", value = dense<0> : tensor<i32>} : () -> (tensor<i32>)