// CHECK-LABEL: func @main(%arg0: tensor<1xi32>, %arg1: tensor<1xi32>) -> tensor<1xi32>
  func.func @main(%arg0: tensor<1xi32>, %arg1: tensor<1xi32>) -> tensor<*xi32> {
    // CHECK: %[[RESULT:.*]] = "tf.AddV2"
    // CHECK-SAME: (tensor<1xi32>, tensor<1xi32>) -> tensor<1xi32>
    // CHECK: return %[[RESULT]] : tensor<1xi32>
    %0 = "tf.Cast"(%arg0) : (tensor<1xi32>) -> tensor<*xi32>
    %1 = "tf.Cast"(%arg1) : (tensor<1xi32>) -> tensor<*xi32>

// CHECK:  return
}

func.func @addV2(%arg0: tensor<1xi32>, %arg1: tensor<1xi32>) -> tensor<1xi32> {
  %0 = "tf.AddV2"(%arg0, %arg1) : (tensor<1xi32>, tensor<1xi32>) -> tensor<1xi32>
  func.return %0 : tensor<1xi32>

// CHECK-LABEL: addV2
// CHECK:  tfl.add %arg0, %arg1 {fused_activation_function = "NONE"} : tensor<1xi32>
}

func.func @addV2I16(%arg0: tensor<1xi16>, %arg1: tensor<1xi16>) -> tensor<1xi16> {

// -----

func.func @testFusedActivationFunction(%arg0: tensor<4xi32>, %arg1: tensor<4xi32>) -> (tensor<4xi32>, tensor<4xi32>, tensor<4xi32>, tensor<4xi32>, tensor<4xi32>, tensor<4xi32>) {
  // CHECK: "NONE"
  %0 = tfl.add %arg0, %arg1 {fused_activation_function = "NONE"} : tensor<4xi32>
  // CHECK: "RELU"
  %1 = tfl.add %arg0, %arg1 {fused_activation_function = "RELU"} : tensor<4xi32>
  // CHECK: "RELU_N1_TO_1"

// CHECK:           }) : (tensor<1x?xf32>, tensor<1x0xf32>, tensor<1x0xf32>, tensor<1x0xf32>, tensor<1x0xf32>, tensor<1x3xf32>, tensor<1x3xf32>, tensor<1x3xf32>, tensor<1x3xf32>, none, none, none, tensor<1xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xf32>, tensor<3x1xf32>, tensor<3xf32>, tensor<1x3xf32>, tensor<1x1xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xf32>) -> tensor<1x3xf32>

  %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>
}

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

// -----

func.func @testBroadcastGradientArgsIncompatibleInputType(%s0: tensor<4xi32>, %s1: tensor<4xi64>) -> (tensor<1xi32>, tensor<0xi32>) {

    ```mlir
      %2 = "tf.A"(%arg0) : (tensor<?xi32>) -> tensor<?xi32>
      %3 = "tf.B"(%2) {device = "tpu0"} : (tensor<?xi32>) -> tensor<?xi32>
      %4 = "tf.C"(%2, %3) {device = "tpu0"} : (tensor<?xi32>, tensor<?xi32>) -> tensor<?xi32>
      %5 = "tf.D"(%4) : (tensor<?xi32>) -> tensor<?xi32>
    ```

    After the pass, we will have:

    ```mlir
      %0 = "tf.A"(%arg0) : (tensor<?xi32>) -> tensor<?xi32>

// CHECK-DAG: %[[BROADCAST_DIM:.+]] = arith.constant dense<{{\[3, 2, 1, 1\]}}> : tensor<4xi32>
// CHECK-DAG: %[[EXPAND_DIM1:.+]] = arith.constant dense<3> : tensor<1xi32>
// CHECK-DAG: %[[EXPAND_DIM0:.+]] = arith.constant dense<2> : tensor<1xi32>
// CHECK: %[[EXPAND0:.+]] = "tfl.expand_dims"(%[[ARG0]], %[[EXPAND_DIM0]]) : (tensor<1x2x!quant.uniform<i8:f32, 2.000000e+00:3>>, tensor<1xi32>) -> tensor<1x2x1x!quant.uniform<i8:f32, 2.000000e+00:3>>

  // expected-remark@above {{Sinks: {}}}
}

// -----

func.func @add(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>) -> tensor<1xf32> {
  // expected-remark@above {{ID: 2}}
  %sum = "tf.Add"(%arg0, %arg1) : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
  // expected-remark@above {{ID: 0}}
  func.return %sum : tensor<1xf32>
  // expected-remark@above {{ID: 1}}
  // expected-remark@above {{Sinks: {}}}
}

    // CHECK:      "tf._TPUCompileMlir"(%[[ARG_0_SHAPE]], %[[ARG_2_SHAPE]])

    func.return %0: tensor<8xi32>
  }
  func.func @_func(%arg0: tensor<*xi32>, %arg1: tensor<8xi32>, %arg2: tensor<*xi32>, %arg3: tensor<8xi32>) -> tensor<8xi32> {
    func.return %arg1 : tensor<8xi32>
  }
}

// -----