// RUN: flatbuffer_translate -mlir-to-tflite-flatbuffer %s -o - | flatbuffer_translate --tflite-flatbuffer-to-mlir - -o - | FileCheck %s
// Confirm function references in if ops are preserved
func.func @main(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>) -> tensor<1xf32> {
// CHECK:   %{{.*}} = "tf.If"(%{{.*}}, %{{.*}}, %{{.*}}) <{else_branch = @cond_false, is_stateless = false, then_branch = @cond_true}> : (tensor<1xi1>, tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>

// RUN: tf-opt %s -tfl-prepare-quantize-dynamic-range -tfl-quantize="enable-dynamic-range-quantization=true enable-weight-only-quantization=true" | FileCheck --check-prefix=PerChannelWeightOnly %s
// RUN: tf-opt %s -tfl-prepare-quantize-dynamic-range="enable-dynamic-range-per-channel-quantization=false" -tfl-quantize="enable-dynamic-range-quantization=true" | FileCheck --check-prefix=PerTensor %s

// RUN: odml-to-stablehlo-opt %s -tfl-parse-stablehlo-ops | FileCheck %s

module {
  func.func @main(%arg0: tensor<1x2xi32>) -> tensor<1x2x2xi32> {
  %0 = "tfl.custom"(%arg0) {custom_code = "stablehlo.broadcast_in_dim", custom_option = #tfl<const_bytes : "0x62726F6164636173745F64696D656E73696F6E73000201020119010101072C022401">} : (tensor<1x2xi32>) -> tensor<1x2x2xi32>
  func.return %0 : tensor<1x2x2xi32>
  }
}

// CHECK:      module {

// RUN: odml-to-stablehlo-opt %s -tfl-parse-stablehlo-ops | FileCheck -dump-input always %s

module {
  func.func @main(%arg0: tensor<2xi32>) -> tensor<2xi32> {
  %0 = "tfl.custom"(%arg0) {custom_code = "stablehlo.reshape", custom_option = #tfl<const_bytes : "0x00000100002401">} : (tensor<2xi32>) -> tensor<2xi32>
  func.return %0 : tensor<2xi32>
  }
}

// CHECK:       module {
// CHECK-NEXT:    func @main(%arg0: tensor<2xi32>) -> tensor<2xi32> {

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

func.func @main(%arg0 : tensor<!tf_type.variant<tensor<2xi32>>>, %arg1: tensor<!tf_type.variant<tensor<*xi32>>>) -> tensor<!tf_type.variant<tensor<2xi32>>> {
  func.return %arg0 : tensor<!tf_type.variant<tensor<2xi32>>>
}

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

func.func @main() {
  tf_executor.graph {
    // CHECK:       key: "emptylist"
    // CHECK-NEXT:  value {
    // CHECK-NEXT:    list {
    // CHECK-NEXT:    }
    // CHECK-NEXT:  }
    // CHECK:       key: "typelist"
    // CHECK-NEXT:  value {
    // CHECK-NEXT:    list {
    // CHECK-NEXT:      type: DT_INT32
    // CHECK-NEXT:      type: DT_FLOAT
    // CHECK-NEXT:    }

// RUN: tf-tfrt-opt %s -tf-restore-splitting | FileCheck %s

// CHECK-LABEL: func @single_restore
// CHECK-SAME:    (%[[ARG0:.*]]: {{.*}})
func.func @single_restore(%arg0: tensor<!tf_type.string>) -> (tensor<*xf32>, tensor<*xi32>) {
  %0 = "tf.Const"() {value = dense<["foo", "bar"]> : tensor<2x!tf_type.string>} : () -> tensor<2x!tf_type.string>
  %1 = "tf.Const"() {value = dense<""> : tensor<2x!tf_type.string>} : () -> tensor<2x!tf_type.string>

# RUN: tf-mlir-translate -graphdef-to-mlir -tf-enable-shape-inference-on-import=false %s -tf-input-arrays=input -tf-input-data-types=DT_FLOAT -tf-output-arrays=output_node -o - | FileCheck %s

node {
  name: "input"
  op: "Placeholder"
  attr {
    key: "dtype"
    value {
      type: DT_FLOAT
    }
  }
  attr {
    key: "shape"
    value {
      shape {
        dim {
          size: 1
        }
      }
    }
  }
}

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

# Verify that the _input_shapes attribute of the FunctionDef is respected.
# This also checks that the output type is correctly inferred based on
# that.
#CHECK: func private @identity_function0(%arg0: tensor<i32>) -> tensor<i32>

node {
  name: "Placeholder"
  op: "Placeholder"
  attr {
    key: "dtype"
    value {
      type: DT_BOOL

// RUN: tf-opt %s -tf-layout-optimization=force-data-format=NCHW -verify-diagnostics | FileCheck %s --dump-input=always

// CHECK-LABEL: func @transposeConv2D
func.func @transposeConv2D(%arg0: tensor<1x3x32x32xf32>, %arg1: tensor<1x1x3x8xf32>) -> tensor<1x8x32x32xf32> {

  // Convert input: NCHW -> NHWC
  %0 = "tf.Const"() {value = dense<[0, 2, 3, 1]> : tensor<4xi32>} : () -> tensor<4xi32>