// RUN: flatbuffer_translate -mlir-to-tflite-flatbuffer %s | flatbuffer_to_string - | FileCheck %s

func.func @main(%arg0: tensor<i32>, %arg1: tensor<i32>) -> tensor<!tf_type.variant<tensor<*xi32>>> {
  %0 = "tfl.custom"(%arg0, %arg1) {custom_code = "TensorListReserve", custom_option = #tfl<const_bytes : "0x02">} : (tensor<i32>, tensor<i32>) -> tensor<!tf_type.variant<tensor<*xi32>>>
  func.return %0 : tensor<!tf_type.variant<tensor<*xi32>>>
}

// RUN: tf-quant-opt %s -quant-insert-quantized-functions='quantization-method=weight_only target-opset=XLA' | FileCheck %s

// Empty module
module {
  func.func @simple_fn(%arg0: tensor<*xf32>) -> tensor<*xf32> {
    func.return %arg0 : tensor<*xf32>
  }
}

// CHECK-NOT: func private @internal_dequantize_f32
// CHECK-NOT: func private @internal_conv3d_fn
// CHECK-NOT: func private @internal_batch_matmul_fn

// RUN: odml-to-stablehlo-opt %s -stablehlo-composite-legalize-tfl-custom | FileCheck %s
// RUN: tf_tfl_translate --enable-hlo-to-tf-conversion --input-mlir %s -o - | flatbuffer_translate --tflite-flatbuffer-to-mlir - -o - | FileCheck %s --check-prefix=CHECK-ROUNDTRIP

module {
  func.func public @main(%arg0: tensor<3x3xf32>, %arg1: tensor<3x3xf32>, %arg2: tensor<1x100x32x4xf32>,

// RUN: flatbuffer_translate -mlir-to-tflite-flatbuffer %s -o - | flatbuffer_translate -output-arrays=mul,exp,div  --tflite-flatbuffer-to-mlir - -o - | FileCheck %s
// Confirm output-arrays works.

func.func @main(tensor<4xf32>) -> tensor<4xf32> {
^bb0(%arg0: tensor<4xf32>):
  %0 = "tfl.pseudo_const" () {value = dense<1.0> : tensor<4xf32>} : () -> tensor<4xf32> loc("Const")

// RUN: flatbuffer_translate -mlir-to-tflite-flatbuffer %s -emit-custom-ops -emit-builtin-tflite-ops=false -o - | flatbuffer_to_string - | FileCheck %s

func.func @main() -> tensor<4xi4> {
  // CHECK: {
  // CHECK:   version: 3,
  // CHECK:   operator_codes: [  ],
  // CHECK:   subgraphs: [ {
  // CHECK:     tensors: [ {
  // CHECK:       shape: [ 4 ],
  // CHECK:       type: INT4,
  // CHECK:       buffer: 1,
  // CHECK:       name: "Const",

// RUN: tac-translate -input-mlir -output-mlir -device-specs=NNAPI %s -o - 2>&1 | FileCheck %s

module {
  // CHECK-LABEL: main
  func.func @main(%arg0: tensor<4xf32>, %arg1: tensor<4xf32>) -> tensor<4xf32> {
    %0 = "tfl.squared_difference"(%arg0, %arg1) : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>
    func.return %0 : tensor<4xf32>
    // CHECK:  [[VAL_0:%.*]] = tfl.sub %arg0, %arg1 {fused_activation_function = "NONE"} : tensor<4xf32>

// RUN: tf-opt %s --tf-name-anonymous-iterators --split-input-file | FileCheck %s

// CHECK-LABEL: gives_a_name_to_anonymous_iterators
func.func private @gives_a_name_to_anonymous_iterators() {
  // CHECK: "tf.Iterator"
  // CHECK-SAME: output_shapes{{.*}}200x28x28x1{{.*}}200x10
  // CHECK-SAME: output_types = [f32, f32]
  // CHECK-SAME: shared_name = "_iterator1"
  %0 = "tf.AnonymousIteratorV3"() {output_shapes = [
    #tf_type.shape<200x28x28x1>,

// RUN: tf-opt %s -allow-unregistered-dialect --tf-strip-tf-attributes --split-input-file | FileCheck %s

// CHECK-LABEL: strips_attributes
// CHECK-NOT: tf
func.func @strips_attributes(%arg0: tensor<32x28x28x1xf32> {tf._user_specified_name = "x"},
                             %arg1: tensor<3x3x1x5xf32> {tf._user_specified_name = "w1"},
                             %arg2: tensor<5xf32> {tf._user_specified_name = "b1"},

# RUN: tf-mlir-translate -graphdef-to-mlir -tf-enable-shape-inference-on-import=false %s -o - | FileCheck %s

node {
  name: "_tf.PartitionedCall"
  op: "PartitionedCall"
  attr {
    key: "Tin"
    value {
      list {
      }
    }
  }
  attr {
    key: "Tout"
    value {
      list {
        type: DT_FLOAT
      }
    }
  }
  attr {
    key: "f"
    value {
      func {
        name: "foo"
      }

# RUN: tf-mlir-translate -graphdef-to-splatted-mlir %s -o - | FileCheck %s

# CHECK: tf.Const
# CHECK-SAME: value = dense<""> : tensor<3x!tf_type.string>

node {
  name: "save/SaveV2/shape_and_slices"
  op: "Const"
  attr {
    key: "_output_shapes"
    value {
      list {
        shape {
          dim {
            size: 3
          }
        }
      }
    }
  }
  attr {
    key: "dtype"
    value {