%8 = "tf.Identity"(%arg1) {device = ""} : (tensor<i32>) -> tensor<i32>
    %9 = "tf.Identity"(%2) {device = ""} : (tensor<i32>) -> tensor<i32>
    %10 = "tf.AddV2"(%arg0, %0) {device = ""} : (tensor<i32>, tensor<i32>) -> tensor<i32>
    %11 = "tf.Identity"(%10) {device = ""} : (tensor<i32>) -> tensor<i32>

  %0 = "arith.constant"() {value = 42 : i32} : () -> i32
  %1 = "arith.constant"() {value = 41 : i32} : () -> i32
  %2 = "tfr.build_list"(%0, %1) : (i32, i32) -> !tfr.attr
  %3 = "tfr.build_list"(%0, %1) : (i32, i32) -> !tfr.attr
  %4 = "tfr.build_list"(%2, %3) : (!tfr.attr, !tfr.attr) -> !tfr.attr
  func.return %4 : !tfr.attr

// CHECK-NEXT: %[[c:.*]] = tfr.constant {{\[}}[42 : i32, 41 : i32], [42 : i32, 41 : i32]] -> !tfr.attr

func.func @invalid_switchN(%arg0: tensor<*xi32>, %arg1: tensor<i32>) -> i32 {
  %result = tf_executor.graph {
    %1:3 = "tf_executor._SwitchN"(%arg0, %arg1) {num_outs = 2} : (tensor<*xi32>, tensor<i32>) -> (i32, tensor<i32>, !tf_executor.control)
// expected-error@-1 {{'tf_executor._SwitchN' op expects outputs to have tensor type but got 'i32'}}
    tf_executor.fetch %1#0 : i32
  }
  func.return %result : i32
}

// -----

  %1 = "tfl.max_pool_2d"(%0) {filter_height = 1 : i32, filter_width = 1 : i32, fused_activation_function = "RELU6", padding = "SAME", stride_h = 1 : i32, stride_w = 1 : i32} : (tensor<1x6x6x16xf32>) -> tensor<1x1x1x16xf32>
  func.return %1 : tensor<1x1x1x16xf32>

// MIN-MAX-CHECK-NEXT:  [[lhs:%.*]], {{.*}}, {{.*}}, {{.*}} = "tf.CustomAggregator"(%arg0) <{calibration_method = 1 : i32, id = "composite_conv2d_with_relu6_fn_arg_0_calibration_method_1",...

func.func @pseudo_const() -> tensor<i32> {
  // CHECK: %[[CST:.*]] = arith.constant dense<1> : tensor<i32>
  // CHECK: return %[[CST]]
  %0 = "tfl.pseudo_const"() {value = dense<1> : tensor<i32>} : () -> tensor<i32>
  func.return %0 : tensor<i32>
}


// CHECK-LABEL: @range_int
func.func @range_int() -> tensor<?xi32> {
  %cst = arith.constant dense<0> : tensor<i32>
  %cst_1 = arith.constant dense<4> : tensor<i32>

    // CHECK-NEXT: %4 = mhlo.convert %3 : tensor<i32>
    // CHECK-NEXT: %5 = "mhlo.slice"(%1) <{limit_indices = dense<2> : tensor<1xi64>, start_indices = dense<1> : tensor<1xi64>, strides = dense<1> : tensor<1xi64>}> : (tensor<4xi32>) -> tensor<1xi32>
    // CHECK-NEXT: %6 = mhlo.reshape %5 : (tensor<1xi32>) -> tensor<i32>
    // CHECK-NEXT: %7 = mhlo.convert %6 : tensor<i32>

  %conv = "tfl.conv_2d"(%0, %w, %b) {
    dilation_h_factor = 1 : i32, dilation_w_factor = 1 : i32, fused_activation_function = "RELU",
    padding = "SAME", stride_h = 1 : i32, stride_w = 1 : i32
  } : (tensor<1x5x5x2xf32>, tensor<3x1x1x2xf32>, tensor<3xf32>) -> tensor<1x5x5x3xf32>
  %conv2 = "tfl.conv_2d"(%0, %w, %b2) {
    dilation_h_factor = 1 : i32, dilation_w_factor = 1 : i32, fused_activation_function = "RELU",

  %cst_0 = "tf.Const"() { value = dense<3> : tensor<i32> } : () -> tensor<i32>
  %cst_1 = arith.constant dense<4> : tensor<2x2xi32>
  %cst_2 = arith.constant dense<0> : tensor<2x2xi32>
  %0 = "tf.SpaceToBatchND"(%arg0, %cst, %cst_1) : (tensor<1x128x128xf32>, tensor<2xi32>, tensor<2x2xi32>) -> tensor<4x68x68xf32>
  %1 = "tf.ExpandDims"(%0, %cst_0) : (tensor<4x68x68xf32>, tensor<i32>) -> tensor<4x68x68x1xf32>

// PerTensor-DAG: %[[zp:.*]] = "tf.Const"() <{value = dense<0> : tensor<i32>}> : () -> tensor<i32>
// PerTensor: %[[out:.*]] = "tf.PartitionedCall"(%arg0, %[[q_w]], %[[scale]], %[[zp]]) <{config = "", config_proto = "", executor_type = "",
// PerTensor-SAME: f = @quantized_matmul_fn_0}> : (tensor<2x12xf32>, tensor<12x2xi8>, tensor<f32>, tensor<i32>) -> tensor<*xf32>
// PerTensor: return %[[out]]

// PerChannel-LABEL: func @matmul