// CHECK: "tf.ConcatV2"(%[[INP0]], %[[INP1]], %[[AXIS]]) : (tensor<1x3x5xf32>, tensor<1x3x5xf32>, tensor<i64>) -> tensor<2x3x5xf32>

  %0 = "tf.Pack"(%arg0, %arg1) : (tensor<3x5xf32>, tensor<3x5xf32>) -> tensor<2x3x5xf32>
  func.return %0 : tensor<2x3x5xf32>
}

// CHECK-LABEL: func @square
func.func @square(%arg0: tensor<3xf32>) -> tensor<3xf32> {
  // CHECK: "tf.Mul"(%arg0, %arg0)

        tensor<1x5xf32>,
        tensor<2x5xf32>, tensor<2x5xf32>, tensor<2x5xf32>, tensor<2x5xf32>,
        tensor<2x4xf32>, tensor<2x4xf32>, tensor<2x4xf32>, tensor<2x4xf32>,
        tensor<2xf32>, tensor<2xf32>, tensor<2xf32>,
        tensor<2xf32>, tensor<2xf32>, tensor<2xf32>, tensor<2xf32>,
        tensor<4x2xf32>, tensor<4xf32>,
        tensor<1x4xf32>, tensor<1x2xf32>,

  %outputs =  "tf.Const"() {device = "/job:localhost/replica:0/task:0/device:CPU:0", value = dense<0> : tensor<i32>} : () -> tensor<i32>...

  %4 = "tf.MatMul"(%arg0, %3) {device = "", transpose_a = false, transpose_b = false} : (tensor<2x3xf32>, tensor<3x4xf32>) -> tensor<2x4xf32>
  %5 = "tf.Identity"(%4) {device = ""} : (tensor<2x4xf32>) -> tensor<2x4xf32>
  %6 = "tf.Identity"(%5) {device = ""} : (tensor<2x4xf32>) -> tensor<2x4xf32>
  func.return %6 : tensor<2x4xf32>

  %0 = "tf.BatchMatMul"(%arg0, %arg1) {adj_x = true, adj_y = true} : (tensor<5x4xf32>, tensor<6x5xf32>) -> tensor<4x6xf32>
  func.return %0 : tensor<4x6xf32>

  // CHECK-LABEL: batchMatMulMatrixAdjXY
  // CHECK: %[[MATMUL_1:.*]] = "tf.MatMul"(%arg0, %arg1) <{grad_a = false, grad_b = false, transpose_a = true, transpose_b = true}> : (tensor<5x4xf32>, tensor<6x5xf32>) -> tensor<4x6xf32>

    %2 = "quantfork.stats"(%1) {layerStats = dense<[5.00000000e-6, 7.00000000e-1]> : tensor<2xf32>} : (tensor<1x3xf32>) -> tensor<1x3xf32>
    return %2 : tensor<1x3xf32>
  }
// CHECK: func.func private @quantize_dot_general_with_bias_same_shape_fn(%[[ARG_0:.+]]: tensor<1x2xf32>) -> tensor<1x3xf32> attributes {tf._original_func_name = "main_0"}

  %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>

      %0 = tf_executor.graph {
        %read0, %read0_control = tf_executor.island wraps "tf.ReadVariableOp"(%arg0) : (tensor<*x!tf_type.resource<tensor<32xf32>>>) -> tensor<32xf32>
        %assign0_control = tf_executor.island(%read0_control) wraps "tf.AssignVariableOp"(%arg0, %arg1) : (tensor<*x!tf_type.resource<tensor<32xf32>>>, tensor<32xf32>) -> ()