module {
  func.func @simpleTest(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>, %arg2: tensor<1xf32>, %arg3: tensor<1xf32>) -> tensor<2x1xf32> {
    %0 = func.call @func_0_GPU_FLOAT(%arg0, %arg1, %arg2) {tac.interface_name = "func_0"} : (tensor<1xf32>, tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
    %1 = func.call @func_1_GPU_FLOAT(%arg0, %arg3) {tac.interface_name = "func_1"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>

  %2 = chlo.broadcast_add %1, %bias : (
      tensor<?x2x2x1xf32>, tensor<1xf32>) ->tensor<?x2x2x1xf32>
  return %2 : tensor<?x2x2x1xf32>
}

// -----

// CHECK-LABEL: func @dot_general_add_add
func.func @dot_general_add_add(
    %lhs: tensor<?x?x6xi8>, %rhs: tensor<6x8xi8>,
    %zp_offset: tensor<8xi32>, %bias: tensor<8xi32>
  ) -> tensor<?x?x8xi32> {
  // CHECK: %[[dot:.*]] = "mhlo.dot_general"

    %cst = "tf.Const"() <{value = dense<true> : tensor<i1>}> {device = ""} : () -> tensor<i1>
    %cst_0 = "tf.Const"() <{value = dense<[0.117216609, 0.933735609, 0.0728900209]> : tensor<3xf32>}> {device = ""} : () -> tensor<3xf32>

  %cst_1 = arith.constant dense<0> : tensor<4xi32>
  %cst_2 = arith.constant dense<0.000000e+00> : tensor<1xf32>
  %0 = "tfl.quantize"(%cst_2) {qtype = tensor<1x!quant.uniform<i32:f32, 1.0>>, volatile} : (tensor<1xf32>) -> tensor<1x!quant.uniform<i32:f32, 1.0>>
  %1 = "tfl.dequantize"(%0) : (tensor<1x!quant.uniform<i32:f32, 1.0>>) -> tensor<1xf32>
  %cst_3 = arith.constant dense<[[[[1.0]], [[1.0]], [[1.0]]]]> : tensor<1x3x1x1xf32>

  %0 = "tfr.cast"(%arg0) : (tensor<1x3x!quant.uniform<i8:f32:1, {0.1:1, 0.2:2, 0.3:3}>>) -> !tfr.tensor
  %scale, %zp = tfr.quant_qparam(%0) : (!tfr.tensor) -> (!tfr.tensor, !tfr.tensor)
  %1 = "tfr.cast"(%scale) : (!tfr.tensor) -> tensor<3xf32>
  %2 = "tfr.cast"(%zp) : (!tfr.tensor) -> tensor<3xi32>
  func.return %1, %2 : tensor<3xf32>, tensor<3xi32>

    %cst = "tf.Const"() {value = dense<3.00000000e-1> : tensor<2x3xf32>} : () -> tensor<2x3xf32>
    %cst_0 = "tf.Const"() {value = dense<4.00000000e-1> : tensor<3xf32>} : () -> tensor<3xf32>
    %0 = "quantfork.stats"(%arg0) {layerStats = dense<[6.00000000e-6, 9.00000000e-1]> : tensor<2xf32>} : (tensor<?x2xf32>) -> tensor<?x2xf32>

  // CHECK: %[[VAL:.*]] = "tf.Const"() <{value = dense<[1.000000e+00, 2.000000e+00, 3.000000e+00]> : tensor<3xf32>}> : () -> tensor<3xf32>
  %value = "tf.Const"() {value = dense<[1.0, 2.0, 3.0]> : tensor<3xf32>} : () -> tensor<3xf32>
  // CHECK: %[[READ_VAR:.*]] = "tf.ReadVariableOp"(%[[VAR]])
  // CHECK: %[[UPDATE_SLICE:.*]] = "tf.Reshape"(%[[VAL]]
  // CHECK-SAME: -> tensor<1x3xf32>

    // CHECK-DAG: %[[SIGN:.*]] = "tf.Sign"(%[[PROX]]) : (tensor<4xf32>) -> tensor<4xf32>
    // CHECK-DAG: %[[ABS:.*]] = "tf.Abs"(%[[PROX]]) : (tensor<4xf32>) -> tensor<4xf32>
    // CHECK-DAG: %[[SCALED_L1:.*]] = "tf.Mul"(%[[ADAGRAD_LR]], %[[L1]]) : (tensor<4xf32>, tensor<f32>) -> tensor<4xf32>
    // CHECK-DAG: %[[PROX_NEW:.*]] = "tf.Sub"(%[[ABS]], %[[SCALED_L1]]) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>

      "tfl.yield"(%wrap_result): (tensor<1xf32>)->()
      }): (tensor<1xf32>, tensor<1xf32>) -> (tensor<1xf32>)
  %tmp3 = "tfl.add"(%const, %tmp2) { fused_activation_function = "NONE" } : (tensor<1xf32>, tensor<1xf32>) -> (tensor<1xf32>)
  %tmp4 = "tf.AddV2"(%tmp2, %tmp2) { device = "" } : (tensor<1xf32>, tensor<1xf32>) -> (tensor<1xf32>)

  %1 = "tf.TPUCompileMlirAndExecute"(%0) {metadata = "metadata", mlir_module = "mlir_module", operandSegmentSizes = array<i32: 1, 0>, producer_name = "producer_name"} : (tensor<f32>) -> tensor<i32>
  func.return %1 : tensor<i32>
}

// -----

func.func @executeop_input_same_execute_op(%arg0: tensor<i32>, %arg1: tensor<2xf32>) -> (tensor<i32>) {