// CHECK: tac.cost = 1.010000e+02
  %1 = "tfl.reshape"(%0, %cst) {tac.device = "CPU"} : (tensor<200xf32>, tensor<2xi64>) -> tensor<2x100xf32>
  func.return %1 : tensor<2x100xf32>
}

// -----

func.func @testConv2DCPU(tensor<256x32x32x3xf32>, tensor<16x3x3x3xf32>, tensor<16xf32>) -> tensor<256x32x32x16xf32> {

  func.return %0 : tensor<256x32x32x16xf32>
}

func.func @testConv2DDynamicShape(tensor<?x32x32x3xf32>, tensor<16x3x3x3xf32>, tensor<16xf32>) -> tensor<?x32x32x16xf32> {
^bb0(%arg0: tensor<?x32x32x3xf32>, %arg1: tensor<16x3x3x3xf32>, %arg2: tensor<16xf32>):
  // CHECK: _arithmetic_count = -1 : i64

    %4 = "quantfork.stats"(%2) {layerStats = dense<[-2795.36523, 4609.57373]> : tensor<2xf32>} : (tensor<*xf32>) -> tensor<*xf32>
    %5 = "tf.BiasAdd"(%4, %3) {data_format = "NHWC", device = ""} : (tensor<*xf32>, tensor<2xf32>) -> tensor<*xf32>
    %6 = "quantfork.stats"(%5) {layerStats = dense<[-2788.31055, 4616.62842]> : tensor<2xf32>} : (tensor<*xf32>) -> tensor<*xf32>

    %2 = "tf.Reshape"(%1, %cst_0) : (tensor<1x10xf32>, tensor<2xi32>) -> tensor<?x10xf32> loc(fused["Reshape:", "model/reshape"])
    %3 = "tf.AddV2"(%2, %cst) : (tensor<?x10xf32>, tensor<10xf32>) -> tensor<?x10xf32> loc(fused["AddV2:", "model/add"])
    func.return %3 : tensor<?x10xf32>
  }
}

// CHECK-LABEL: func @matmul_with_reshape_disable_quantization
// CHECK: "tf.PartitionedCall"

  // CHECK-SAME:      <[-1.000000e+00, 1.000000e+00]> : tensor<2xf32>}>
  // CHECK-SAME:      : (tensor<40x37xf32>) -> tensor<40x37xf32>
  // CHECK-NEXT:    %[[cst:.*]] = "tfl.pseudo_const"() <{value = dense<
  // CHECK-SAME:      1.000000e+00> : tensor<40xf32>}> : () -> tensor<40xf32>
  // CHECK-NEXT:    %[[fc:.*]]:2 = "tfl.fully_connected"(%[[stat]], %arg1,

# CHECK: mlir_module = "\0Afunc @main(%arg0 : tensor<10xf32>, %arg1 : tensor<10xf32>) -> tensor<10x10xf32> {\0A %add = \22tf.Add\22(%arg0, %arg1) : (tensor<10xf32>, tensor<10xf32>) -> tensor<10xf32>\0A %ret = \22magic.op\22(%add, %add) : (tensor<10xf32>, tensor<10xf32>) -> tensor<10x10xf32>\0A return %ret : tensor<10x10xf32>\0A}\0A"}> {device = ""} : (tensor<10xf32>, tensor<10xf32>) -> tensor<*xf32>

node {
  name: "x"
  op: "Placeholder"
  attr {

    %0 = "tf.ReadVariableOp"(%arg0) {device = ""} : (tensor<!tf_type.resource<tensor<*xf32>>>) -> tensor<*xf32>
    %1 = "tf.ReadVariableOp"(%arg1) {device = ""} : (tensor<!tf_type.resource<tensor<*xf32>>>) -> tensor<*xf32>
    %2 = "tf.Add"(%0, %1) {device = ""} : (tensor<*xf32>, tensor<*xf32>) -> tensor<*xf32>
    func.return %2 : tensor<*xf32>
  }
  // CHECK: "tf_saved_model.global_tensor"()
  // CHECK:    sym_name = "dense/kernel"

// CHECK-LABEL: func @main
func.func @main(%arg0 : tensor<10xf32>, %arg1 : tensor<10xf32>) -> tensor<10x10xf32> {
// CHECK-SAME: (%[[ARG0:.*]]: tensor<10xf32>, %[[ARG1:.*]]: tensor<10xf32>)
// CHECK-NEXT:    %[[ADD:.*]] = "tf.Add"(%[[ARG0]], %[[ARG1]]) : (tensor<10xf32>, tensor<10xf32>) -> tensor<10xf32>
// CHECK-NEXT:    %[[MAGIC:.*]] = "magic.op"(%[[ADD]], %[[ADD]]) : (tensor<10xf32>, tensor<10xf32>) -> tensor<10x10xf32>
// CHECK-NEXT:    return %[[MAGIC]]

module {
  // CHECK-LABEL: func @main
  // CHECK-SAME: %[[ARG_0:.*]]: tensor<10xf32>, %[[ARG_1:.*]]: tensor<10xf32>, %[[ARG_2:.*]]: tensor<6xi32>
  func.func @main(
      %arg0: tensor<10xf32>, %arg1: tensor<10xf32>, %arg2: tensor<6xi32>
    ) -> (tensor<10xf32>, tensor<6xi32>) {
    // CHECK: %[[CAST_0:.*]] = "tf.Cast"(%[[ARG_0]]) <{Truncate = false}> : (tensor<10xf32>) -> tensor<10xbf16>

      %outputs_9, %control_10 = tf_executor.island wraps "tf.Mul"(%outputs_7, %outputs) {T = "tfdtype$DT_FLOAT", _tpu_replicate = "cluster", device = "", name = "mul"} : (tensor<0xf32>, tensor<f32>) -> tensor<0xf32>
      %outputs_11, %control_12 = tf_executor.island wraps "tf.Placeholder"() {device = "", dtype = "tfdtype$DT_FLOAT", name = "y", shape = "tfshape$dim { }"} : () -> tensor<0xf32>