%1 = stablehlo.transpose %arg0, dims = [1, 0] : (tensor<16x8xf32>) -> tensor<8x16xf32>
  %2 = "stablehlo.reduce_window"(%1, %0) ({
  ^bb0(%arg1: tensor<f32>, %arg2: tensor<f32>):
      %3 = stablehlo.maximum %arg1, %arg2 : tensor<f32>
      stablehlo.return %3 : tensor<f32>
  }) {window_dimensions = array<i64: 2, 2>, window_strides = array<i64: 2, 2>} : (tensor<8x16xf32>, tensor<f32>) -> tensor<4x8xf32>
  return %2 : tensor<4x8xf32>
}

    %16 = "tf.Mean"(%15, %8) {keep_dims = false} : (tensor<2x112x112x64xf32>, tensor<2xi32>) -> tensor<2x64xf32>
    %17 = "tf.MatMul"(%16, %arg3) {transpose_a = false, transpose_b = false} : (tensor<2x64xf32>, tensor<64x1001xf32>) -> tensor<2x1001xf32>
    %18 = "tf.BiasAdd"(%17, %arg4) {data_format = "NHWC"} : (tensor<2x1001xf32>, tensor<1001xf32>) -> tensor<2x1001xf32>

// Tests ops that variable shapes are correctly evaluated on static types.
// CHECK-LABEL: func @testVariableShape
func.func @testVariableShape(%arg0: tensor<!tf_type.resource<tensor<2x4xf32>>>) -> tensor<2xi32> {
  %0 = "tf.VariableShape"(%arg0) : (tensor<!tf_type.resource<tensor<2x4xf32>>>) -> tensor<2xi32>
  // CHECK:         [[cst:%.*]] = "tf.Const{{.*}} dense<{{\[}}2, 4]> : tensor<2xi32>
  // CHECK-NEXT:    return [[cst]] : tensor<2xi32>

  return
}
```

will be transformed to:

```mlir
func @main(%arg0: tensor<8x4xf32>) {
  // EmptyTensorList lowering
  %emptyi = "tf.Const"() {value = dense<0> : tensor<i32>} : () -> tensor<i32>
  %emptyf = "tf.Cast"(%emptyi) : (tensor<i32>) -> tensor<f32>
  %size_shape = "tf.Const"() {value = dense<[10, 8, 4]> : tensor<3xi32>} : () -> tensor<3xi32>

  return
}
```

will be transformed to:

```mlir
func @main(%arg0: tensor<8x4xf32>) {
  // EmptyTensorList lowering
  %emptyi = "tf.Const"() {value = dense<0> : tensor<i32>} : () -> tensor<i32>
  %emptyf = "tf.Cast"(%emptyi) : (tensor<i32>) -> tensor<f32>
  %size_shape = "tf.Const"() {value = dense<[10, 8, 4]> : tensor<3xi32>} : () -> tensor<3xi32>

// CHECK:           %[[VALUES:.*]], %[[INDICES:.*]] = "tf.TopKV2"(%[[ARG_0]], %[[K]]) <{sorted = true}> : (tensor<3x6xf32>, tensor<i32>) -> (tensor<3x6xf32>, tensor<3x6xi32>)
// CHECK:           return %[[VALUES]], %[[INDICES]] : tensor<3x6xf32>, tensor<3x6xi32>
// CHECK:         }
func.func @convert_sort_to_topk_iota_broadcast(%arg0: tensor<3x6xf32>) -> (tensor<3x6xf32>, tensor<3x6xi32>) {
  %0 = "mhlo.iota"() <{ iota_dimension = 0 : i64 }> : () -> tensor<6xi32>

    // CHECK-NOT: tf.TPUPartitionedOutputV2
    %partitioned_output:2 = "tf.TPUPartitionedOutputV2"(%computation) {_XlaSharding = "\08\03\1A\02\01\02\22\02\00\01", partition_dims = [1, 2]} : (tensor<3x4xf32>) -> (tensor<3x2xf32>, tensor<3x2xf32>)
    // CHECK: "tf.AssignVariableOp"(%arg0, %[[PARALLEL_EXECUTE_OUTPUT]]#0)

  %cst_weights = arith.constant dense<[[1.0, 1.0e38, 1.0, -1.0e38]]> : tensor<1x4xf32>
  %cst_bias = arith.constant dense<0.0> : tensor<1xf32>

  %0 = "tfl.fully_connected" (%cst_input, %cst_weights, %cst_bias) {fused_activation_function = "NONE", keep_num_dims = false, weights_format = "DEFAULT"} : (tensor<4xf32>, tensor<1x4xf32>, tensor<1xf32>) -> tensor<1xf32>

  func.return %0 : tensor<1xf32>

//                (tensor<4x2xf32>, tensor<4x2xf32>, tensor<4x2xf32>)
//
// will be converted into:
//
//   %0 = "mhlo.slice"(%input) {
//             limit_indices = dense<[4, 2]> : tensor<2xi64>,
//             start_indices = dense<0> : tensor<2xi64>,
//             strides = dense<1> : tensor<2xi64>} :
//        (tensor<4x6xf32>) -> tensor<4x2xf32>

// -----

// Tests that a float `stablehlo.reshape` is not converted to `tfl.reshape`.

func.func @reshape_float(%arg0: tensor<2x3x4xf32>) -> tensor<6x4xf32> {
  %0 = stablehlo.reshape %arg0 : (tensor<2x3x4xf32>) -> tensor<6x4xf32>
  return %0 : tensor<6x4xf32>
}
// CHECK-LABEL: reshape_float
// CHECK-NOT: tfl.reshape
// CHECK: stablehlo.reshape

// -----