}

// -----

func.func @unsorted_segment_sum(%arg0: tensor<8xf32>, %arg1: tensor<8xi32>) -> tensor<8xf32> {
  %num_segments = "tf.Const"() {value = dense<8> : tensor<i32>} : () -> tensor<i32>
  %0 = "tf.UnsortedSegmentSum"(%arg0, %arg1, %num_segments) : (tensor<8xf32>, tensor<8xi32>, tensor<i32>) -> tensor<8xf32>
  func.return %0 : tensor<8xf32>
  // CHECK-LABEL: unsorted_segment_sum

  BUCKETIZE = 147,
  RANDOM_UNIFORM = 148,
  MULTINOMIAL = 149,
  GELU = 150,
  DYNAMIC_UPDATE_SLICE = 151,
  RELU_0_TO_1 = 152,
  UNSORTED_SEGMENT_PROD = 153,
  UNSORTED_SEGMENT_MAX = 154,
  UNSORTED_SEGMENT_SUM = 155,
  ATAN2 = 156,
  UNSORTED_SEGMENT_MIN = 157,
  SIGN = 158,
  BITCAST = 159,
  BITWISE_XOR = 160,
  RIGHT_SHIFT = 161,
  // All Operators start with STABLEHLO_ prefixes are subject to change

// -----

// CHECK-LABEL: testUnsortedSegmentSum
func.func @testUnsortedSegmentSum(%arg0: tensor<8xf32>, %arg1: tensor<8xi32>,  %arg2: tensor<i32>) -> tensor<8xf32> {
  // CHECK: "tfl.unsorted_segment_sum"(%arg0, %arg1, %arg2)
  %0 = "tfl.unsorted_segment_sum"(%arg0, %arg1, %arg2) : (tensor<8xf32>, tensor<8xi32>, tensor<i32>) -> tensor<8xf32>
  func.return %0 : tensor<8xf32>
  // CHECK: return %0 : tensor<8xf32>
}

// -----

//===----------------------------------------------------------------------===//

// -----

// CHECK-LABEL: @unsorted_segment_sum
// CHECK-SAME: [[DATA:%.*]]: tensor<8x16x64xf32>
// CHECK-SAME: [[SI:%.*]]: tensor<8x16xi32>
func.func @unsorted_segment_sum(%data: tensor<8x16x64xf32>, %segment_ids : tensor<8x16xi32>) -> (tensor<4x64xf32>) {

    TFL_I32Tensor:$segment_ids,
    TFL_I32Tensor:$num_segments
  );

  let results = (outs TFL_TensorOf<[F32, I32]>:$output);
}

def TFL_UnsortedSegmentSumOp: TFL_Op<"unsorted_segment_sum", [
    Pure, PredOpTrait<"input and output must have same element type",
      TFL_TCresVTEtIsSameAsOp<0, 0>>]> {

  let summary = "UnsortedSegmentSum operator";

  let description = [{

        *   (since v2.7) Stateful ops used in `tf.data.Dataset`
        *   (since v2.7) `tf.convert_to_tensor` when fed with (sparse)
            `tf.IndexedSlices` (because it uses `tf.math.unsorted_segment_sum`)
        *   (since v2.7) `tf.gather` backprop (because `tf.convert_to_tensor`
            reduces `tf.gather`'s (sparse) `tf.IndexedSlices` gradients into its
            dense `params` input)

  let description = [{
Read
[the section on segmentation](https://tensorflow.org/api_docs/python/tf/math#Segmentation)
for an explanation of segments.

This operator is similar to `tf.math.unsorted_segment_sum`,
Instead of computing the sum over segments, it computes the maximum such that:

\\(output_i = \max_{j...} data[j...]\\) where max is over tuples `j...` such
that `segment_ids[j...] == i`.

    "BUCKETIZE",
    "RANDOM_UNIFORM",
    "MULTINOMIAL",
    "GELU",
    "DYNAMIC_UPDATE_SLICE",
    "RELU_0_TO_1",
    "UNSORTED_SEGMENT_PROD",
    "UNSORTED_SEGMENT_MAX",
    "UNSORTED_SEGMENT_SUM",
    "ATAN2",
    "UNSORTED_SEGMENT_MIN",
    "SIGN",
    "BITCAST",
    "BITWISE_XOR",
    "RIGHT_SHIFT",
    "STABLEHLO_LOGISTIC",
    "STABLEHLO_ADD",
    "STABLEHLO_DIVIDE",