// swap in and out to exercise copy-up and copy-down
	input8, output8 = output8, input8
	input16, output16 = output16, input16
	input32, output32 = output32, input32
	input64, output64 = output64, input64
	in := 0
	out := 13
	for i := range input8 {
		input8[i] = u8(in)
		output8[i] = u8(out)
		outputS[i] = u8(out)
		input16[i] = u16(in)
		output16[i] = u16(out)
		input32[i] = u32(in)
		output32[i] = u32(out)

// CHECK: %[[lstm:.*]] = "tfl.unidirectional_sequence_lstm"(%[[input_0]], %[[input_1]], %[[input_2]], %[[input_3]], %[[input_4]], %[[input_5]], %[[input_6]], %[[input_7]], %[[input_8]],
// CHECK-SAME: %[[input_9]], %[[input_10]], %[[input_11]], %[[input_12]], %[[input_13]], %[[input_14]], %[[input_15]], %[[input_16]], %[[input_17]], %[[input_18]], %[[input_19]]
// CHECK-SAME: effective_hidden_scale_intermediate = tensor<!quant.uniform<i8:f32, 0.0039215686274509803:-1>>

// 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]],
// CHECK-SAME: %[[input_9]], %[[input_9]], %[[input_9]], %[[input_9]]) <{
// CHECK-SAME: asymmetric_quantize_inputs = false,
// CHECK-SAME: cell_clip = 1.000000e+01 : f32,

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

  %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>

        
        input2 = getResourceFile("2.txt")
        output2 = signing.signatureType.fileFor(input2)
        input2Artifact = new DefaultPublishArtifact(input2.name, "Text File", "txt", null, null, input2)
        
        [output1, output2].each { output ->
            assert !output.exists() || output.delete()
        }
        
        assert input1.text && input2.text  // don't care what it is, just need some
    }
    

  }

  // Builds a SignatureDef with the provided `inputs` and `outputs`.
  SignatureDef BuildSignatureDef(const std::unordered_set<string>& inputs,
                                 const std::unordered_set<string>& outputs) {
    SignatureDef signature_def;
    for (const string& input : inputs) {
      (*signature_def.mutable_inputs())[input].set_name(input);
    }
    for (const string& output : outputs) {

      }
    }
  }
}
node {
  name: "Add"
  op: "Add"
  input: "input0"
  input: "input1"
  attr {
    key: "T"
    value {
      type: DT_INT32
    }
  }
}
node {
  name: "input0"
  op: "Placeholder"
  attr {
    key: "dtype"
    value {
      type: DT_INT32
    }
  }
}
node {
  name: "input1"
  op: "Placeholder"
  attr {
    key: "dtype"
    value {

  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
  // ------------------------------------