module {
  func.func @wrap_composite_func(%arg0: tensor<*xf32>, %arg1: tensor<*xf32>) -> tensor<*xf32> {
    %0 = "tf.PartitionedCall"(%arg0, %arg1) <{f = @composite_conv2d_with_relu6_fn}> {_tfl_quant_trait = "fully_quantizable"}
          : (tensor<*xf32>, tensor<*xf32>) -> tensor<*xf32>
    func.return %0 : tensor<*xf32>
  }

  func.func @no_composite_func(%arg0: tensor<*xf32>, %arg1: tensor<*xf32>) -> tensor<*xf32> {

//===----------------------------------------------------------------------===//

// CHECK-LABEL: conv2DBiasAdd_noActivation
func.func @conv2DBiasAdd_noActivation(%arg0: tensor<128xf32>, %arg1: tensor<1x1x3x128xf32>, %arg2: tensor<8x32x32x3xf32>) -> (tensor<*xf32>) {

  %0 = "tf.Pow"(%arg0, %arg1) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>

  // CHECK-DAG: %[[POW_ZERO:.*]] = "tf.Const"() <{value = dense<1.000000e+00> : tensor<4xf32>}> : () -> tensor<4xf32>
  %1 = "tf.Pow"(%arg0, %cst_zero) : (tensor<4xf32>, tensor<f32>) -> tensor<4xf32>

  // CHECK-NOT: "tf.Pow"
  %2 = "tf.Pow"(%arg0, %cst_one) : (tensor<4xf32>, tensor<f32>) -> tensor<4xf32>

// CHECK-NEXT: }

func.func @main(%arg0: tensor<i32>, %arg1: tensor<1xf32>) -> tensor<1xf32> {
  %0:2 = "tfl.while"(%arg0, %arg1) ({
  ^bb0(%arg2: tensor<*xi32>, %arg3: tensor<*xf32>):
    %1 = func.call @cond(%arg2, %arg3) : (tensor<*xi32>, tensor<*xf32>) -> tensor<i1>
    "tfl.yield"(%1) : (tensor<i1>) -> ()
  },  {
  ^bb0(%arg2: tensor<*xi32>, %arg3: tensor<*xf32>):

  // CHECK:      %[[READ0:.*]] = "tf.ReadVariableOp"(%arg0)
  // CHECK-NEXT: %[[READ2:.*]] = "tf.ReadVariableOp"(%arg2)
  // CHECK-NEXT: tf_device.replicate
  // CHECK-NEXT:   %[[READ1:.*]] = "tf.ReadVariableOp"(%arg1)
  // CHECK-NEXT:   "tf.OpA"(%[[READ0]], %[[READ1]], %[[READ2]])
  tf_device.replicate {n = 2 : i32} {
    %0 = "tf.ReadVariableOp"(%arg0) : (tensor<*x!tf_type.resource<tensor<f32>>>) -> tensor<f32>

func.func @no_embedding_ops(%arg0: tensor<2x2xf32>) -> (tensor<2x2xf32>) {
  // CHECK: tf.Add
  %0 = "tf.Add"(%arg0, %arg0) : (tensor<2x2xf32>, tensor<2x2xf32>) -> tensor<2x2xf32>
  func.return %0 : tensor<2x2xf32>
}

// CHECK-LABEL: func @nested_embedding_op
func.func @nested_embedding_op(%arg0: tensor<i1>, %arg1: tensor<512x256xf32>) -> (tensor<512x256xf32>) {
  %1 = "tf.IfRegion"(%arg0) ({

}

// CHECK-LABEL: RemoveTrival
// QDQ-LABEL: RemoveTrival
func.func @RemoveTrival(%arg0: tensor<384x512x!quant.uniform<i8:f32, 1.0:-128>>, %arg1: tensor<128x512x!quant.uniform<i8<-127:127>:f32, 1.0>>, %arg2: none) -> tensor<384x128x!quant.uniform<i8:f32, 2.0>> {

  func.return %id0, %id0, %arg1 : !tf_res, !tf_res, !tf_res
}

// expected-remark@below {{Region #0, Arg #0, ID 0 : 0}}
// expected-remark@below {{Region #0, Arg #1, ID 1 : 1}}
func.func @case_branch2(%arg0: !tf_res, %arg1: !tf_res) -> (!tf_res, !tf_res, !tf_res) {
  func.return %arg0, %arg0, %arg1 : !tf_res, !tf_res, !tf_res
}

// -----
// Test aliasing through WhileOp

func.func @transposeFusedBatchNormV3_f32(
  %arg0: tensor<1x28x28x64xf32>,
  %arg1: tensor<64xf32>
) -> tensor<1x28x28x64xf32> {

  // CHECK: "tf.FusedBatchNormV3"
  // CHECK-SAME: (%[[X_TRANSPOSE:[0-9]*]], %arg1, %arg1, %arg1, %arg1)
  // CHECK-SAME: data_format = "NCHW"
  %y, %batch_mean, %batch_var, %reserve_1, %reserve_2, %reserve_3
    = "tf.FusedBatchNormV3"(%arg0, %arg1, %arg1, %arg1, %arg1)
       {
         data_format = "NHWC",

  }

  func.func private @composite_dot_general_fn(%arg0: tensor<1x2xf32>, %arg1: tensor<2x3xf32>) -> tensor<1x3xf32> attributes {_from_xla_call_module} {
    %0 = stablehlo.dot_general %arg0, %arg1, contracting_dims = [1] x [0] : (tensor<1x2xf32>, tensor<2x3xf32>) -> tensor<1x3xf32>
    return %0 : tensor<1x3xf32>
  }
}

// CHECK-LABEL: quantize_dot_general_per_tensor
// CHECK-SAME: %[[ARG0:.+]]: tensor<1x2xf32>