// -----

func.func @pack_CPU(%arg0: tensor<100xf32>, %arg1: tensor<100xf32>) -> tensor<2x100xf32> attributes {tac.device = "CPU", tac.interface_name = "func_2"} {
  // CHECK: tac.cost = 1.000000e+02
  %0 = "tfl.pack"(%arg0, %arg1) {axis = 0 : i32, tac.device = "CPU", values_count = 2 : i32} : (tensor<100xf32>, tensor<100xf32>) -> tensor<2x100xf32>
  func.return %0 : tensor<2x100xf32>
}

    func.return %2 : tensor<2x100xf32>
  }
  func.func @func_2_CPU_FLOAT(%arg0: tensor<100xf32>, %arg1: tensor<100xf32>) -> tensor<2x100xf32> attributes {tac.cost = 2.000000e+01 : f32, tac.device = "CPU", tac.inference_type = "FLOAT", tac.interface_name = "func_2"} {

  }

  // CHECK-LABEL: pack
  func.func @pack(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>) -> tensor<2x1xf32> {
    %0 = "tfl.pack"(%arg0, %arg1) {axis = 0 : i32, values_count = 2 : i32} : (tensor<1xf32>, tensor<1xf32>) -> tensor<2x1xf32>
    func.return %0 : tensor<2x1xf32>
    // CHECK: %[[VAL_0:.*]] = arith.constant dense<[2, 1]> : tensor<2xi32>

  %3 = "tf.PreventGradient"(%1) : (tensor<10x10xi32>) -> tensor<10x10xi32>
  %4 = "tf.AddV2"(%2, %3) {device = ""} : (tensor<10x10xi32>, tensor<10x10xi32>) -> tensor<10x10xi32>
  func.return %4 : tensor<10x10xi32>

// CHECK-LABEL: preventGradient
// CHECK-NOT: %2 = "tf.PreventGradient"(%0) : (tensor<10x10xi32>) -> tensor<10x10xi32>

  %ch0 = tfrt.new.chain

  %a1 = tfrt_fallback_async.const_dense_tensor dense<[[2, 2], [2, 2]]> : tensor<2x2xi32>
  %a2 = tfrt_fallback_async.const_dense_tensor dense<[[3, 3], [3, 3]]> : tensor<2x2xi32>
  %b = tfrt_fallback_async.const_dense_tensor dense<[[1, 1], [1, 1]]> : tensor<2x2xi32>

  // Two batch_size=2 batches get concatenated.

func.func @main(%arg0: tensor<10xi32>, %arg1: tensor<10xi32>) -> tensor<10xi32>
attributes {tf.entry_function = {inputs = "input0,input1", outputs = "Add"}} {
  %graph = tf_executor.graph {
    %2:2 = tf_executor.island wraps "tf.Add"(%arg0, %arg1) {T = "tfdtype$DT_INT32", device = ""} : (tensor<10xi32>, tensor<10xi32>) -> tensor<10xi32> loc("Add")
    tf_executor.fetch %2 : tensor<10xi32>
  }
  func.return %graph : tensor<10xi32>
}

  func.func @matmul(%arg0: tensor<2x12xf32>) -> (tensor<*xf32>) {
    %cst_0 = "tf.Const"() {value = dense<0.000000e+00> : tensor<12x2xf32>} : () -> tensor<12x2xf32>
    %1 = "tf.PartitionedCall"(%arg0, %cst_0) {_tfl_quant_trait = "fully_quantizable", config = "", config_proto = "", executor_type = "", f = @composite_matmul_fn_1} : (tensor<2x12xf32>, tensor<12x2xf32>) -> tensor<*xf32>
    func.return %1: tensor<*xf32>
  }

  %2 = "tf.Reshape"(%0, %cst_0) : (tensor<1x2xf32>, tensor<2xi64>) -> tensor<2x1xf32>
  func.return %1, %2 : tensor<2x1xf32>, tensor<2x1xf32>

// CHECK:  %cst = arith.constant
// CHECK:  %[[FQ:.*]] = "tf.FakeQuantWithMinMaxVars"(%arg0, %arg1, %arg2)
// CHECK:  %[[R1:.*]] = "tf.Reshape"(%[[FQ]], %cst)
// CHECK-SAME: tensor<2x1xf32>
// CHECK:  %[[R2:.*]] = "tf.Reshape"(%[[FQ]], %cst)

  func.func @matmul(%arg0: tensor<2x12xf32>) -> (tensor<*xf32>) {
    %cst_0 = "tf.Const"() {value = dense<0.000000e+00> : tensor<12x2xf32>} : () -> tensor<12x2xf32>
    %1 = "tf.PartitionedCall"(%arg0, %cst_0) {_tfl_quant_trait = "fully_quantizable", config = "", config_proto = "", executor_type = "", f = @composite_matmul_fn_1} : (tensor<2x12xf32>, tensor<12x2xf32>) -> tensor<*xf32>
    func.return %1: tensor<*xf32>
  }

  %2 = "tf.Reshape"(%0, %cst_0) : (tensor<1x2xf32>, tensor<2xi64>) -> tensor<2x1xf32>
  func.return %1, %2 : tensor<2x1xf32>, tensor<2x1xf32>

// CHECK:  %cst = arith.constant
// CHECK:  %[[FQ:.*]] = "tf.FakeQuantWithMinMaxVars"(%arg0, %arg1, %arg2)
// CHECK:  %[[R1:.*]] = "tf.Reshape"(%[[FQ]], %cst)
// CHECK-SAME: tensor<2x1xf32>
// CHECK:  %[[R2:.*]] = "tf.Reshape"(%[[FQ]], %cst)