%8 = "tfl.add"(%2, %3) {fused_activation_function = "NONE"} : (tensor<4xi32>, tensor<4xi32>) -> tensor<4xi32>

  func.return %5, %6, %7, %8 : tensor<i32>, tensor<4xi32>, tensor<4xi32>, tensor<4xi32>
}

// CHECK-LABEL: @sub_float
func.func @sub_float() -> (tensor<f32>, tensor<4xf32>, tensor<4xf32>, tensor<4xf32>) {
  %0 = arith.constant dense<4.5> : tensor<f32>
  %1 = arith.constant dense<1.5> : tensor<f32>

// CHECK-NEXT:      %6 = "tfl.pseudo_const"() <{value = dense<1> : tensor<i32>}> : () -> tensor<i32>
// CHECK-NEXT:      %7 = "tfl.unsorted_segment_prod"(%3, %4, %6) : (tensor<4xi32>, tensor<4xi32>, tensor<i32>) -> tensor<1xi32>
// CHECK-NEXT:      %8 = "tfl.unsorted_segment_prod"(%3, %5, %6) : (tensor<4xi32>, tensor<4xi32>, tensor<i32>) -> tensor<1xi32>

func.func @squaredDifference(%arg0: tensor<4xf32>, %arg1: tensor<4xf32>) -> tensor<4xf32> {
  %0 = "tfl.squared_difference"(%arg0, %arg1) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>
  func.return %0 : tensor<4xf32>
}

// CHECK:       func @squaredDifference(%arg0: tensor<4xf32>, %arg1: tensor<4xf32>) -> tensor<4xf32> {
// CHECK:         %0 = "tf.Sub"(%arg0, %arg1) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>

// CHECK: %[[v5:.*]] = "tf.Gather"(%3, %[[cst_1]]) <{validate_indices = true}> : (tensor<3xi32>, tensor<2xi32>) -> tensor<2xi32>
// CHECK: %[[v6:.*]] = "tf.Gather"(%4, %[[cst_2]]) <{validate_indices = true}> : (tensor<4xi32>, tensor<1xi32>) -> tensor<1xi32>
// CHECK: %[[v7:.*]] = "tf.Concat"(%[[cst_3]], %5, %6) : (tensor<i32>, tensor<2xi32>, tensor<1xi32>) -> tensor<3xi32>

  %0 = "tf.BroadcastTo"(%input, %shape) : (tensor<3xi32>, tensor<2xi32>) -> tensor<*xi32>
  func.return %0: tensor<*xi32>

// CHECK-LABEL: broadcast_to_i32_low_dim_with_unknown_output
// CHECK:  %0 = "tf.BroadcastTo"(%arg0, %arg1) : (tensor<3xi32>, tensor<2xi32>) -> tensor<*xi32>
// CHECK:  return %0 : tensor<*xi32>
}

  // CHECK-NEXT: mhlo.xor
  %0 = "tf.BitwiseXor"(%arg0, %arg1) : (tensor<4xui32>, tensor<4xui32>) -> tensor<4xui32>
  func.return %0: tensor<4xui32>
}

// CHECK-LABEL: func @bitwise_and
func.func @bitwise_and(%arg0: tensor<4xi32>, %arg1: tensor<4xi32>) -> tensor<4xi32> {
  // CHECK-NEXT: mhlo.and
  %0 = "tf.BitwiseAnd"(%arg0, %arg1) : (tensor<4xi32>, tensor<4xi32>) -> tensor<4xi32>

  %2 = "tf.AddN"(%arg0, %1, %1) : (tensor<2xi32>, tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
  %3 = "tf.AddN"(%1, %arg0, %1) : (tensor<2xi32>, tensor<2xi32> , tensor<2xi32>) -> tensor<2xi32>
  %4 = "tf.AddN"(%1, %1) : (tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
  %5 = "tf.AddN"(%arg0, %1, %0) : (tensor<2xi32>, tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
  func.return %2, %3, %4, %5: tensor<2xi32>, tensor<2xi32>, tensor<2xi32>, tensor<2xi32>
}

// CHECK-LABEL: func @testBroadcastGradientArgs
func.func @testBroadcastGradientArgs(%s0: tensor<4xi32>, %s1: tensor<4xi32>) -> (tensor<1xi32>, tensor<0xi32>) {
  // CHECK:     tf.BroadcastGradientArgs
  %r0, %r1 = "tf.BroadcastGradientArgs"(%s0, %s1) : (tensor<4xi32>, tensor<4xi32>) -> (tensor<1xi32>, tensor<0xi32>)
  func.return %r0, %r1 : tensor<1xi32>, tensor<0xi32>
}

// -----

// CHECK-LABEL: @acos

  %s2 = "tf.Const"() {value = dense<[501, 1, 32, 1280]> : tensor<4xi32>} : () -> tensor<4xi32>
  %s3 = "tf.Const"() {value = dense<[  1, 1,  1, 1280]> : tensor<4xi32>} : () -> tensor<4xi32>
  %r2, %r3 = "tf.BroadcastGradientArgs"(%s2, %s3) {} : (tensor<4xi32>, tensor<4xi32>) -> (tensor<1xi32>, tensor<3xi32>)
  // CHECK-DAG: %[[R2:.*]] = "tf.Const"() <{value = dense<1> : tensor<1xi32>}> : () -> tensor<1xi32>

// CHECK:           %[[VAL_3:.*]] = "tf.LeftShift"(%[[VAL_1]], %[[VAL_0]]) : (tensor<4xi32>, tensor<1xi32>) -> tensor<4xi32>
// CHECK:           return %[[VAL_2]], %[[VAL_3]] : tensor<4xi32>, tensor<4xi32>
// CHECK:         }
func.func @broadcast_shift_left(%arg0: tensor<1xi32>, %arg1: tensor<4xi32>) -> (tensor<4xi32>, tensor<4xi32>) {