%0 = tfl.sub %arg0, %arg1 {fused_activation_function = "RELU6"} : tensor<? x i32>
  func.return %0#0 : tensor<? x i32>
}

// CHECK-LABEL: testSubInt64
func.func @testSubInt64(tensor<? x i64>, tensor<? x i64>) -> tensor<? x i64> {
^bb0(%arg0: tensor<? x i64>, %arg1: tensor<? x i64>):
  // CHECK: tfl.sub %arg0, %arg1 {fused_activation_function = "RELU6"}

  // CHECK: "tfl.unidirectional_sequence_lstm"(%arg0, %arg1, %arg2, %arg3, %arg4, %arg5, %arg6, %arg7, %arg8, %arg9, %arg10, %arg11, %arg12, %arg13, %arg14, %arg15, %arg16, %arg17, %arg18, %arg19, %arg20, %arg21, %arg22, %arg23) <{fused_activation_function = "NONE", time_major = false}>...

// CHECK: %[[NONE:.+]] = "tfl.no_value"() <{value}> : () -> none
// CHECK: "tfl.lstm"(%arg0, %arg1, %arg2, %arg3, %arg4, %arg5, %arg6, %arg7, %arg8, %[[NONE]], %[[NONE]], %[[NONE]], %arg9, %arg10, %arg11, %arg12, %arg13, %[[NONE]], %arg19, %arg20, %arg15, %arg16, %arg17, %arg18)
}

func.func @keepCustomFlexOps(%arg0: tensor<1x10xf32>) -> tensor<1x10xf32> {

module {
  func.func public @main(%arg0: tensor<3x3xf32>, %arg1: tensor<3x3xf32>, %arg2: tensor<1x100x32x4xf32>,
      %arg3: tensor<1x500x4x4xf32>, %arg4: tensor<1x500x4x4xf32>, %arg5: tensor<1x1x100x500xf32>, %arg6: tensor<f32>)
      -> tensor<1x100x32x4xf32> {

  }
  func.func @partitioned_called_func(%arg0: tensor<?xi32>) -> (tensor<?xi32>) {
    func.return %arg0 : tensor<?xi32>
  }
  func.func @stateful_partitioned_call_func(%arg0: tensor<?xi32>) -> (tensor<?xi32>) {
    func.return %arg0 : tensor<?xi32>
  }
  func.func @tpu_partitioned_call_func(%arg0: tensor<?xi32>) -> (tensor<?xi32>) {
    func.return %arg0 : tensor<?xi32>
  }

  func.return %4 : tensor<128x128x!quant.uniform<u8:f32, 0.2:125>>

// CHECK: "tfl.custom_tf"
// CHECK-NEXT: ^bb0(%arg4: tensor<128x128xf32>, %arg5: tensor<1xf32>, %arg6: tensor<1xf32>, %arg7: tensor<1xi32>):
// CHECK-NEXT:   "tf.LayerNorm"(%arg4, %arg5, %arg6, %arg7) {_tfl_quant_trait = "fully_quantizable", device = ""} : (tensor<128x128xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xi32>) -> tensor<128x128xf32>

// CHECK-LABEL: testLiftDotConcatLHSAndRHS
func.func @testLiftDotConcatLHSAndRHS(%arg0: tensor<1x72x128xf32>, %arg1: tensor<1x128x72xf32>, %arg2: tensor<1x72x128xf32>, %arg3: tensor<1x128x72xf32>, %arg4: tensor<1x72x128xf32>, %arg5: tensor<1x128x72xf32>, %arg6: tensor<1x72x128xf32>, %arg7: tensor<1x128x72xf32>) -> tensor<4x72x72xf32> {
  %0 = "mhlo.dot_general"(%arg0, %arg1) {
    dot_dimension_numbers = #mhlo.dot<
      lhs_batching_dimensions = [0],

func.func @fusedBatchNormV3_training_mixedPrecision(%arg0: tensor<8x8x8x8xbf16>, %arg1: tensor<8xf32>, %arg2: tensor<8xf32>, %arg3: tensor<8xf32>, %arg4: tensor<8xf32>) -> (tensor<8x8x8x8xbf16>) {
  // CHECK: mhlo.convert %arg0 : (tensor<8x8x8x8xbf16>) -> tensor<8x8x8x8xf32>

//CHECK-NEXT: return %0 : tensor<i1>
//CHECK-NEXT:}

func.func @dynamic_update_slice(%arg0: tensor<4x4xi64>, %arg1: tensor<2x3xi64>, %arg2: tensor<i64>, %arg3: tensor<i64>) -> tensor<4x4xi64> {

    %cst = "tfl.no_value"() {value = unit} : () -> none