%begins = "tf.Const"() {value = dense<[-1]> : tensor<1xi64>} : () -> (tensor<1xi64>)
  %sizes = "tf.Const"() {value = dense<[2]> : tensor<1xi64>} : () -> (tensor<1xi64>)
  // expected-error @+1 {{requires 0 <= begin[i] <= begin[i] + size[i] <= Di}}
  %0 = "tf.Slice"(%arg0, %begins, %sizes) : (tensor<4xi32>, tensor<1xi64>, tensor<1xi64>) -> tensor<2xi32>
  func.return %0 : tensor<2xi32>
}

// -----

  %cst = "tf.Const"() <{value = dense<0.000000e+00> : tensor<f32>}> : () -> tensor<f32>
  %cst_0 = "tf.Const"() <{value = dense<1> : tensor<1xi64>}> : () -> tensor<1xi64>
  %fill = "tf.Fill"(%cst_0, %cst) : (tensor<1xi64>, tensor<f32>) -> tensor<1xf32>
  tf_device.replicate([%0, %fill] as %arg_r0: tensor<1xf32>) {n = 2 : i32} {
    %1 = "tf_device.launch"() <{device = "TPU_REPLICATED_HOST_0"}> ({

    // expected-remark@+1 {{Cost: 2}}

module {
  func.func @main() -> tensor<1xi64> {
  %0 = "tfl.custom"() {custom_code = "stablehlo.constant", custom_option = #tfl<const_bytes : "0x76616C75650001020109010101062C022401">} : () -> tensor<1xi64>
  func.return %0 : tensor<1xi64>
  }
}

// CHECK:  module {
// CHECK-NEXT:    func @main() -> tensor<1xi64> {
// CHECK-NEXT:    %[[c0:.+]] = stablehlo.constant dense<2> : tensor<1xi64>
// CHECK-NEXT:    return %[[c0]] : tensor<1xi64>

  %names: tensor<0x!tf_type.string>,
  %sparse_keys: tensor<0x!tf_type.string>,
  %dense_keys: tensor<1x!tf_type.string>,
  %ragged_keys: tensor<0x!tf_type.string>,
  %dense_default: tensor<0xi64>) -> tensor<?xi64> {

  %dense_value =
    "tf.ParseExampleV2"(%serialized, %names, %sparse_keys, %dense_keys, %ragged_keys, %dense_default)
    // CHECK: Tdense = [i64]
    // CHECK-SAME: dense_shapes = [#corert.shape<>]

  // CHECK-SAME: <{calibration_methods = [1 : i32, 1 : i32], ids = ["0", "1"], output_file_path = "main_0.pb"}> : (tensor<f32>, tensor<f32>, tensor<0xi64>, tensor<f32>, tensor<f32>, tensor<0xi64>) -> ()
  // CHECK: return

  %cst0 = mhlo.constant dense<[1, 2, 3, 4]> : tensor<4xi32>
  // CHECK: %[[BROADCAST:.*]] = "mhlo.broadcast_in_dim"(%[[CONST]]) <{broadcast_dimensions = dense<3> : tensor<1xi64>}> : (tensor<4xi32>) -> tensor<1x1x2x4xi32>
  %0 = "mhlo.broadcast_in_dim"(%cst0) <{broadcast_dimensions = dense<3> : tensor<1xi64>}> : (tensor<4xi32>) -> tensor<1x1x2x4xi32>
  // CHECK: %[[MUL:.*]] = mhlo.multiply %[[BROADCAST]], %[[ARG]] : tensor<1x1x2x4xi32>

  // NOT-CHECK-DAG:    %[[LHS_BCAST:.+]] = "mhlo.dynamic_broadcast_in_dim"(%arg0, %[[RESULT_EXTENTS]]) <{broadcast_dimensions = dense<0> : tensor<1xi64>}>
  // NOT-CHECK-DAG:    %[[RHS_BCAST:.+]] = "mhlo.dynamic_broadcast_in_dim"(%arg1, %[[RESULT_EXTENTS]]) <{broadcast_dimensions = dense<0> : tensor<1xi64>}>
  // NOT-CHECK-NEXT:   %[[RESULT:.+]] = mhlo.compare EQ, %[[LHS_BCAST]], %[[RHS_BCAST]]
  // NOT-CHECK-NEXT:   shape.assuming_yield %[[RESULT]]

    %dimension = "tf.Const"() { value = dense<3> : tensor<1xi64> } : () -> tensor<1xi64>
    %6 = "tf.Sum"(%3, %dimension) { keep_dims = true }: (tensor<1x3x2x2xf32>, tensor<1xi64>) -> tensor<1x3x2x1xf32>
    return %5, %6 : tensor<1x3x2x2xf32>, tensor<1x3x2x1xf32>
  }

// CHECK-LABEL: func @conv_with_multiple_uses

      %out, %ctl = tf_executor.island wraps "tf.Const"() {device = "", value = dense<[1]> : tensor<1xi64>} : () -> tensor<1xi64>
      // expected-error @+1 {{Validation failed for the initializer function: NoOp. All initializer function's fetches should be tf_executor::ControlType. Got: tensor<1xi64>.}}
      tf_executor.fetch %out : tensor<1xi64>
    }
    return
  }