%0 = stablehlo.constant dense<2.000000e+00> : tensor<167x64xf32>
  %1 = stablehlo.constant dense<2.000000e+00> : tensor<64xf32>
  %2 = stablehlo.dot_general %arg0, %0, contracting_dims = [2] x [0], precision = [DEFAULT, DEFAULT] : (tensor<1x1x167xf32>, tensor<167x64xf32>) -> tensor<1x1x64xf32>
  %3 = stablehlo.broadcast_in_dim %1, dims = [2] : (tensor<64xf32>) -> tensor<1x1x64xf32>
  %4 = stablehlo.add %2, %3 : tensor<1x1x64xf32>
  func.return %4: tensor<1x1x64xf32>
}

  %0 = "tfl.unidirectional_sequence_lstm"(%arg0,...

  %1 = "tf.AddV2"(%arg0, %0) : (tensor<f32>, tensor<4xf32>) -> tensor<4xf32>
  %2 = "tf.AddV2"(%0, %arg0) : (tensor<4xf32>, tensor<f32>) -> tensor<4xf32>

  // If operand has the same shape as a result, we can fold it.
  %3 = "tf.AddV2"(%arg1, %0) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>
  %4 = "tf.AddV2"(%0, %arg1) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>

  // CHECK: %[[CONST:.*]] = "tf.Const"()

  func.return %0#0 : tensor<?x?x?x?xf32>
}

// -----

// CHECK-LABEL: fusedBatchNormV3_training_dynamic_unsupported1

    // CHECK: %[[MUL:.*]] = "tf.Mul"{{.*}} (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
    // CHECK: %[[UNKNOWN:.*]] = "tf.Unknown"(%[[MUL]], %[[MUL]]) : (tensor<1xf32>, tensor<1xf32>) -> tensor<*xf32>
    // CHECK: return %[[UNKNOWN]] : tensor<*xf32>
    %0 = "tf.Mul"(%arg0, %arg0) : (tensor<1xf32>, tensor<1xf32>) -> tensor<*xf32>
    %1 = "tf.Unknown"(%0, %0) : (tensor<*xf32>, tensor<*xf32>) -> tensor<*xf32>

  // expected-error @+1 {{requires mean to be a 1D float tensor}}
  %0:5 = "tf.FusedBatchNorm"(%arg0, %arg1, %arg2, %arg3, %arg4) {T = "tfdtype$DT_FLOAT", data_format = "NHWC", epsilon = 0.001 : f32, is_training = false} : (tensor<8x8x8x8xf32>, tensor<8xf32>, tensor<8xf32>, tensor<?x8xf32>, tensor<8xf32>) -> (tensor<8x8x8x8xf32>, tensor<8xf32>, tensor<8xf32>, tensor<?x8xf32>, tensor<8xf32>)

  // Use other output
  %3:6 = "tf.FusedBatchNormV3"( %2#0, %arg1, %arg2, %arg3, %arg4) {T = "tfdtype$DT_FLOAT", U = "tfdtype$DT_FLOAT", data_format = "NHWC", epsilon = 0.001 : f32, is_training = false} : (tensor<8x8x8x8xf32>, tensor<8xf32>, tensor<8xf32>, tensor<8xf32>, tensor<8xf32>) -> (tensor<8x8x8x8xf32>, tensor<8xf32>, tensor<8xf32>, tensor<8xf32>, tensor<8xf32>, tensor<8xf32>)

  %4 = "tfl.minimum"(%0, %cst) : (tensor<32xf32>, tensor<32xf32>) -> tensor<32xf32>
  %5 = "tfl.minimum"(%1, %cst) : (tensor<32xf32>, tensor<32xf32>) -> tensor<32xf32>
  %6 = "tfl.minimum"(%2, %cst) : (tensor<32xf32>, tensor<32xf32>) -> tensor<32xf32>
  %7 = "tfl.minimum"(%3, %cst) : (tensor<32xf32>, tensor<32xf32>) -> tensor<32xf32>

}

// CHECK-LABEL: func @add_f32
func.func @add_f32(%arg0: tensor<3xf32>, %arg1: tensor<3xf32>) -> tensor<3xf32> {
  // CHECK-DAG: [[ADD:%.+]] = "tf.AddV2"(%arg0, %arg1) : (tensor<3xf32>, tensor<3xf32>) -> tensor<3xf32>
  %add = "tf.Add"(%arg0, %arg1) : (tensor<3xf32>, tensor<3xf32>) -> tensor<3xf32>
  func.return %add : tensor<3xf32>
}

// CHECK-LABEL: func @BiasAddGrad_NHWC

  %1 = "tf.Mul"(%arg1, %arg1) : (tensor<2xf32>, tensor<2xf32>) -> tensor<2xf32>
  %2 = "tf.Div"(%arg1, %arg1) : (tensor<2xf32>, tensor<2xf32>) -> tensor<2xf32>

  // CHECK: "tf.If"{{.+}}else_branch = @tf.IfRegion_else{{.+}}then_branch = @tf.IfRegion_then
  %3 = "tf.IfRegion"(%arg0) ({
     %4 = "tf.Select"(%arg0, %0, %1) : (tensor<i1>, tensor<2xf32>, tensor<2xf32>) -> tensor<2xf32>
     "tf.Yield"(%4) : (tensor<2xf32>) -> ()