%cst = "tf.Const"() {value = dense<0> : tensor<1x2xi32>} : () -> tensor<1x2xi32>
  %cst_0 = "tf.Const"() {value = dense<1> : tensor<i32>} : () -> tensor<i32>
  %cst_1 = "tf.Const"() {value = dense<2> : tensor<1xi32>} : () -> tensor<1xi32>
  %cst_2 = "tf.Const"() {value = dense<4> : tensor<1x2xi32>} : () -> tensor<1x2xi32>
  %0 = "tf.SpaceToBatchND"(%arg0, %cst_1, %cst_2) : (tensor<1x128x3xf32>, tensor<1xi32>, tensor<1x2xi32>) -> tensor<2x68x3xf32>

func.func @L2NormalizePattern(%arg0: tensor<2xf32>) -> tensor<2xf32> {
  %cst = arith.constant dense<[0]> : tensor<1xi32>
  %0 = "tfl.square"(%arg0) : (tensor<2xf32>) -> tensor<2xf32>
  %1 = "tfl.sum"(%0, %cst) {keep_dims = false} : (tensor<2xf32>, tensor<1xi32>) -> tensor<f32>
  %2 = "tfl.rsqrt"(%1) : (tensor<f32>) -> tensor<f32>
  %3 = "tfl.mul"(%arg0, %2) {fused_activation_function = "NONE"} : (tensor<2xf32>, tensor<f32>) -> tensor<2xf32>

  func.return %0#0 : tensor<2xi32>
}

// -----

func.func @unpack(%arg0: tensor<2x3xi32>) -> tensor<2xi32> {
  // expected-error @+2 {{failed to infer returned types}}
  // expected-error @+1 {{op inferred type(s) 'tensor<2xi32>', 'tensor<2xi32>', 'tensor<2xi32>' are incompatible with return type(s) of operation 'tensor<2xi32>', 'tensor<2x1xi32>', 'tensor<2xi32>'}}

    %9 = "tf.Cast"(%8) {Truncate = false, device = ""} : (tensor<?x?x?x2xi32>) -> tensor<?x?x?x2xf32>
    %10 = "tf.Mul"(%9, %cst_1) {device = ""} : (tensor<?x?x?x2xf32>, tensor<2xf32>) -> tensor<?x?x?x2xf32>
    %11 = "tf.Round"(%10) {device = ""} : (tensor<?x?x?x2xf32>) -> tensor<?x?x?x2xf32>
    %12 = "tf.Cast"(%11) {Truncate = false, device = ""} : (tensor<?x?x?x2xf32>) -> tensor<?x?x?x2xi32>

  func.return %3 : tensor<2xi32>

  // CHECK: %[[CST:.*]] = arith.constant dense<1> : tensor<2xi32>
  // CHECK: return %[[CST]] : tensor<2xi32>
}

// CHECK-LABEL: @concat_3_tensors_1_empty
func.func @concat_3_tensors_1_empty() -> tensor<?xi32> {
  %0 = arith.constant dense<1> : tensor<2xi32>
  %1 = arith.constant dense<1> : tensor<2xi32>
  %2 = arith.constant dense<[]> : tensor<0xi32>

}

func.func @identity(%arg0: tensor<10xi32>, %arg1: tensor<20xi32>, %arg2: tensor<30xi32>) -> (tensor<10xi32>, tensor<20xi32>, tensor<30xi32>, tensor<*xi32>) {
  %0 = "tf.Identity"(%arg0) : (tensor<10xi32>) -> tensor<10xi32>
  %1:2 = "tf.IdentityN"(%arg1,%arg2) : (tensor<20xi32>, tensor<30xi32>) -> (tensor<20xi32>, tensor<30xi32>)
  %2 = "tf.Identity"(%arg0) : (tensor<10xi32>) -> tensor<*xi32>

  func.return %0 : tensor<?x?x?x?xi32>
}

// CHECK-LABEL:   func @add(
// CHECK-SAME:              %[[VAL_0:.*]]: tensor<2xi32>) -> tensor<2xi32> {
// CHECK:           %[[VAL_1:.*]] = "tf.AddV2"(%[[VAL_0]], %[[VAL_0]]) : (tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
// CHECK:           %[[VAL_2:.*]] = "tf.AddV2"(%[[VAL_1]], %[[VAL_0]]) : (tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
// CHECK:           return %[[VAL_2]] : tensor<2xi32>

     %t2 = "tf.Acosh"(%arg1) : (tensor<2xf32>) -> tensor<2xf32>
    "tf.Yield"(%t0, %t1, %t2) : (tensor<2xf32>, tensor<2xf32>, tensor<2xf32>) -> ()
    }, {
     %e0 = "tf.Neg"(%arg1) : (tensor<2xf32>) -> tensor<2xf32>
     %e1 = "tf.Relu"(%arg1) : (tensor<2xf32>) -> tensor<2xf32>
     %e2 = "tf.Sin"(%arg1) : (tensor<2xf32>) -> tensor<2xf32>
     "tf.Yield"(%e0, %e1, %e2) : (tensor<2xf32>, tensor<2xf32>, tensor<2xf32>) -> ()

// 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>

  // CHECK-DAG: %[[INDICES_3:.*]] = "tf.Mul"(%[[INDICES_2]], %arg0) : (tensor<5xi32>, tensor<5xi32>) -> tensor<5xi32>
  // CHECK-DAG: %[[INDICES_4:.*]] = "tf.TensorScatterAdd"(%[[cst_3]], %0, %[[UPDATES]]) : (tensor<5xi32>, tensor<5x1xi32>, tensor<5xi32>) -> tensor<5xi32>
  // CHECK-DAG: %[[INDICES_5:.*]] = "tf.AddV2"(%[[INDICES_3]], %[[INDICES_4]]) : (tensor<5xi32>, tensor<5xi32>) -> tensor<5xi32>