// CHECK:  "tf.BatchFunction"
  // CHECK-SAME: allowed_batch_sizes = [6]
  // CHECK-SAME: batch_timeout_micros = 100000 : i64
  // CHECK-SAME: batching_queue = ""
  // CHECK-SAME: container = ""
  // CHECK-SAME: enable_large_batch_splitting = false
  // CHECK-SAME: max_batch_size = 6 : i64
  // CHECK-SAME: max_enqueued_batches = 10 : i64
  // CHECK-SAME: num_batch_threads = 2 : i64
  // CHECK-SAME: shared_name = "batch/"

    functionalTestBucketProvider: FunctionalTestBucketProvider,
    val testCoverage: TestCoverage,
    val stage: Stage
) : Project({
    this.id(testCoverage.asId(model))
    this.name = testCoverage.asName()
}) {
    val functionalTests: List<BaseGradleBuildType> = functionalTestBucketProvider.createFunctionalTestsFor(stage, testCoverage)
    init {
        functionalTests.forEach(this::buildType)
    }

# UNKNOWN-SAME:  outputs = "Add"
# UNKNOWN:           %[[add:.*]], %[[add_control:.*]] = tf_executor.island wraps "tf.Add"(%[[ARG_0]], %[[ARG_1]])
# UNKNOWN:           fetch %[[add]]

# DYNAMIC-LABEL: func @main
# DYNAMIC-SAME:  (%[[ARG_0:[a-z0-9]+]]: tensor<?x1x?xi32>, %[[ARG_1:[a-z0-9]+]]: tensor<1x?x1xi32>) -> tensor<*xi32>
# DYNAMIC-SAME:  control_outputs = ""
# DYNAMIC-SAME:  inputs = "input0,input1"

  # multiple return statements.
  #
  # CHECK:      func {{@[a-zA-Z_0-9]+}}(
  # CHECK-SAME:   %arg0: tensor<f32> {tf._user_specified_name = "x", tf_saved_model.index_path = [0]}
  # CHECK-SAME: ) -> (
  # CHECK-SAME:   tensor<1xf32> {tf_saved_model.index_path = ["x"]})
  # CHECK-SAME: attributes {{.*}} tf_saved_model.exported_names = ["f0006_multiple_return_statements"]

  // CHECK-SAME: Tin = [f32]
  // CHECK-SAME: Tout = [f32]
  // CHECK-SAME: allowed_batch_sizes = [6]
  // CHECK-SAME: batch_timeout_micros = 100000 : i64
  // CHECK-SAME: batching_queue = ""
  // CHECK-SAME: container = ""
  // CHECK-SAME: enable_large_batch_splitting = false
  // CHECK-SAME: max_batch_size = 6 : i64
  // CHECK-SAME: max_enqueued_batches = 10 : i64

// CHECK: func @add(
// CHECK-SAME: {tf_saved_model.index_path = ["input1"]}
// CHECK-SAME: {tf_saved_model.index_path = ["input2"]}
// CHECK-SAME: {tf_saved_model.index_path = ["result"]}
// CHECK-SAME: tf.entry_function = {inputs = "input1:0,input2:0", outputs = "result:0"}
// CHECK-SAME: tf_saved_model.exported_names = ["add"]

// CHECK: func @sub(
// CHECK-SAME: {tf_saved_model.index_path = ["input2"]}

    // CHECK: %[[CALL:.+]] = "tf.XlaCallModule"(%[[ARG0]], %[[ARG1]])
    // CHECK-SAME: _entry_function = @composite_dot_general_fn_1
    // CHECK-SAME: _original_entry_function = "composite_dot_general_fn_1"
    // CHECK: return %[[CALL]]
  }

  // CHECK: @composite_dot_general_fn_1
  // CHECK-SAME: %[[ARG2:[^:[:space:]]+]]
  // CHECK-SAME: %[[ARG3:[^:[:space:]]+]]

}

// CHECK-LABEL: func private @then_removed_const_args_0
// CHECK-SAME: ([[x:%.*]]: tensor<i32>)
// CHECK: [[const:%.*]] = "tf.Const"
// CHECK-SAME: value = dense<10> : tensor<i32>
// CHECK: [[r:%.*]] = "tf.StatefulPartitionedCall"([[x]], [[const]])
// CHECK-SAME: f = @then}
// CHECK: return [[r]]

// CHECK-LABEL: func private @else_removed_const_args_0
// CHECK-SAME: ([[x:%.*]]: tensor<i32>)
// CHECK: [[const:%.*]] = "tf.Const"

  }
}

// CHECK-LABEL: func @conv2d_unmatching_unit
// CHECK: "tf.PartitionedCall"
// CHECK-SAME: f = @composite_conv2d_fn_1
// Check that the `_tfl_quant_trait` attribute exists since the unit is not in `unit_wise_quantization_specs`.
// CHECK-SAME: _tfl_quant_trait = "fully_quantizable"
// CHECK-SAME: loc(callsite("Model/conv2d@conv2d_unmatching_unit"("Conv2D") at "QuantizationUnit({{.*}})"))

// -----

// disabled by having `_quantization_method = "no_quantization { }"`.
// DISABLE-ALL-DOT-GENERAL-SAME: _entry_function = @composite_dot_general_fn_1
// DISABLE-ALL-DOT-GENERAL-SAME: _original_entry_function
// DISABLE-ALL-DOT-GENERAL-SAME: _quantization_method = "no_quantization { }"
// DISABLE-ALL-DOT-GENERAL-SAME: _tfl_quant_trait = "fully_quantizable"

// DISABLE-ALL-DOT-GENERAL: return %[[XLA_CALL_MODULE:.+]] : tensor<1x1x64xf32>