"tf.Yield"(%2) : (tensor<i1>) -> ()
  }, {
  ^body(%barg0: tensor<*xf32>):
    %2 = "tf.SomeOp"(%barg0) : (tensor<*xf32>) -> tensor<*xf32>
    "tf.Yield"(%2) : (tensor<*xf32>) -> ()
  }) {is_stateless = false, shape_invariant} : (tensor<4xf32>) -> (tensor<*xf32>)

  func.return %0, %1 : tensor<*xf32>, tensor<*xf32>
}

// Test that both passes drop the shape_invariant attribute from
// While/WhileRegion ops within a cluster.

  %cst = arith.constant dense<[1, 2]> : tensor<2xi32>
  %0 = "tfl.mean"(%arg0, %cst) {keep_dims = false} : (tensor<1x48x48x512xf32>, tensor<2xi32>) -> tensor<1x512xf32>
  func.return %0 : tensor<1x512xf32>
}

// CHECK:       func @mean_4d_no_keepdim([[VAL_0:%.*]]: tensor<1x48x48x512xf32>) -> tensor<1x512xf32> {
// CHECK:           [[VAL_1:%.*]] = "tfl.pseudo_const"(){{.*}}dense<[1, 512]> : tensor<2xi32>

  %2 = "tfl.add"(%arg0, %arg3) {fused_activation_function = "RELU6", per_device_costs = {CPU = 5.0 : f32, GPU = 1.0 : f32}, tac.device = "GPU"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
  %3 = "tfl.pack"(%1, %2) {axis = 0 : i32, per_device_costs = {CPU = 2.0 : f32, GPU = -1.0 : f32}, values_count = 2 : i32, tac.device = "CPU"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<2x1xf32>

// CHECK: while_1([[ARG0:%[^ :]*]]: tensor<i32>, [[ARG1:%[^ :]*]]: tensor<1xf32>)
func.func @while_1(%arg0: tensor<i32>, %arg1: tensor<1xf32>) -> tensor<1xf32> {
  // CHECK: [[CST:%[^ ]*]] = arith.constant dense<1> : tensor<i32>
  // CHECK: "tfl.while"([[ARG0]], [[ARG1]])
  // CHECK: (tensor<i32>, tensor<1xf32>) -> (tensor<i32>, tensor<1xf32>)
  %0:2 = "tfl.while"(%arg0, %arg1) (
    // cond
    {

//RUN: tf_tfl_translate --enable-stablehlo-conversion --input-mlir %s -o /tmp/temp.stablehlo; [ -f /tmp/temp.stablehlo ]


module {
func.func @main(%arg0: tensor<2xi32>) -> tensor<2xi32> {
  %0 = "tf.Mul"(%arg0, %arg0) : (tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
  func.return %0 : tensor<2xi32>
}

module {
  func.func @main(%arg0: tensor<2xi32>) -> tensor<2xi32> {
  %0 = "tfl.custom"(%arg0) {custom_code = "stablehlo.reshape", custom_option = #tfl<const_bytes : "0x00000100002401">} : (tensor<2xi32>) -> tensor<2xi32>
  func.return %0 : tensor<2xi32>
  }
}

// CHECK:       module {
// CHECK-NEXT:    func @main(%arg0: tensor<2xi32>) -> tensor<2xi32> {

func.func @main(%arg0: tensor<2xi32>) -> tensor<2xi32> {
  %cst = "tfl.pseudo_const"() {value = dense<[1, 2]> : tensor<2xi32>} : () -> tensor<?xi32>
  %0 = "tfl.add"(%arg0, %cst) {fused_activation_function = "NONE"} : (tensor<2xi32>, tensor<?xi32>) -> tensor<2xi32>
  func.return %0 : tensor<2xi32>
}


// CHECK:    tensors: [ {
// CHECK-NEXT:      shape: [ 2 ],

loc(#loc10)\0A    %2 = \22tf.Reshape\22(%1#0, %arg3) {_xla_outside_compilation = \220\22} : (tensor<1x1120x?xi32>, tensor<2xi32>) -> tensor<1120x?xi32> loc(#loc11)\0A    %3 = \22tf.Shape\22(%2) {_xla_outside_compilation = \220\22} : (tensor<1120x?xi32>) -> tensor<2xi32> loc(#loc12)\0A    return %1#1, %1#2, %2, %3 : tensor<1x1120x?xi32>, tensor<1x1120x?xi32>, tensor<1120x?xi32>, tensor<2xi32> loc(#loc9)\0A  } loc(#loc9)\0A} loc(#loc)\0A#loc = loc(unknown)\0A#loc4 = loc(\22Split:\22)\0A#loc5 = loc(\22split\22)\0A#loc6...

// CHECK-LABEL: fuseMulIntoPerTensorConv2dWithQDQs
func.func @fuseMulIntoPerTensorConv2dWithQDQs(%arg0: tensor<256x32x32x3xf32>) -> tensor<256x8x7x3xf32> {
  %cst = arith.constant dense<1.5> : tensor<3xf32>
  %cst_0 = arith.constant dense<[1.0, 2.0, 3.0]> : tensor<3xf32>
  %w = arith.constant dense<2.0> : tensor<3x3x3x3xf32>

module {
func.func @main(%arg0 : tensor<5xf32>, %arg1 : tensor<f32>, %arg2 : tensor<f32>) -> tensor<5xf32> {
  %0 = "tf.ClipByValue"(%arg0, %arg1, %arg2) : (tensor<5xf32>, tensor<f32>, tensor<f32>) -> tensor<5xf32>
  func.return %0 : tensor<5xf32>
}