//CHECK-NEXT:}

func.func @iota() -> tensor<3x4xf32> {
 %0 = "vhlo.iota_v1" () <{iota_dimension = #vhlo.integer_v1<0 : i64>}> : () -> tensor<3x4xf32>
 return %0 : tensor<3x4xf32>
}

//CHECK:func.func private @iota() -> tensor<3x4xf32> {
//CHECK-NEXT: %0 = "vhlo.iota_v1"() <{iota_dimension = #vhlo.integer_v1<0 : i64>}> : () -> tensor<3x4xf32>
//CHECK-NEXT: return %0 : tensor<3x4xf32>
//CHECK-NEXT:}

  %4 = "tf.MatMul"(%arg0, %3) {device = "", transpose_a = false, transpose_b = false} : (tensor<2x3xf32>, tensor<3x4xf32>) -> tensor<2x4xf32>
  %5 = "tf.Identity"(%4) {device = ""} : (tensor<2x4xf32>) -> tensor<2x4xf32>
  %6 = "tf.Identity"(%5) {device = ""} : (tensor<2x4xf32>) -> tensor<2x4xf32>
  func.return %6 : tensor<2x4xf32>

  %1 = "tf.Reshape"(%arg0, %0) : (tensor<?x4xf32>, tensor<2xi32>) -> tensor<?x4xf32>

  // CHECK: return %arg0 : tensor<?x4xf32>
  func.return %1: tensor<?x4xf32>
}

// CHECK-LABEL: func @testReshapeNoOp
func.func @testReshapeNoOp(%arg0: tensor<2x4xf32>, %arg1: tensor<2xi32>) -> tensor<2x4xf32> {
  %0 = "tf.Reshape"(%arg0, %arg1) : (tensor<2x4xf32>, tensor<2xi32>) -> tensor<2x4xf32>

    %1 = arith.constant dense<[[2.3, 3.4, 4.5, 5.5]]> : tensor<1x4xf32>
    %2 = "tf.Add"(%0, %1) : (tensor<1x4xf32>, tensor<1x4xf32>) -> tensor<1x4xf32>
    %3 = tensor.cast %2 : tensor<1x4xf32> to tensor<1x?xf32>
    func.return %3 : tensor<1x?xf32>
}

// NOTE: Assertions have been autogenerated by utils/generate-test-checks.py
// CHECK-LABEL:   func @embedding(

// Note: Argument quantization sequence omitted.
// CHECK: stablehlo.dot_general %{{.+}}, %{{.+}}, contracting_dims = [1] x [0] : (tensor<1x1024xi8>, tensor<1024x3xi8>) -> tensor<1x3xi32>

// Note: Result dequantization sequence omitted.
// CHECK: return %{{.+}} : tensor<1x3xf32>

// -----

// Tests that a simple dot_general (lifted as a function) with CustomAggregators

func.func @QuantizeSlice(tensor<2x3x5x!quant.uniform<u8:f32, 0.1>>, tensor<3xi32>, tensor<3xi32>) -> tensor<?x3x5xf32> {
^bb0(%arg0: tensor<2x3x5x!quant.uniform<u8:f32, 0.1>>, %arg1: tensor<3xi32>, %arg2: tensor<3xi32>):
  %0 = "tfl.dequantize"(%arg0) : (tensor<2x3x5x!quant.uniform<u8:f32, 0.1>>) -> tensor<2x3x5xf32>
  %1 = "tfl.slice"(%0, %arg1, %arg2) : (tensor<2x3x5xf32>, tensor<3xi32>, tensor<3xi32>) -> tensor<?x3x5xf32>
  func.return %1 : tensor<?x3x5xf32>

  %8 = "tfl.mul"(%2, %3) {fused_activation_function = "NONE"} : (tensor<4xi32>, tensor<4xi32>) -> tensor<4xi32>

  func.return %5, %6, %7, %8 : tensor<i32>, tensor<4xi32>, tensor<4xi32>, tensor<4xi32>
}

// CHECK-LABEL: @add_dense_splat_int
func.func @add_dense_splat_int() -> tensor<4xi32> {
  %0 = arith.constant dense<[-10, -1, 42, 100]> : tensor<4xi32>

//
// Examples:
//   * If `xla_gather_op_output_type` == tensor<*xf32>, then it returns:
//     tensor<*xf32>.
//   * If `xla_gather_op_output_type` == tensor<3x5xi32> and `collapsed_dims` ==
//     {0}, then it returns: tensor<1x3x5xi32>.
//   * If `xla_gather_op_output_type` == tensor<3x5xf32> and `collapsed_dims` ==
//     {1, 3}, then it returns: tensor<3x1x5x1xf32>.
Type GetSliceOpOutputType(Type xla_gather_op_output_type,

// CHECK-NEXT:      %6 = "tfl.pseudo_const"() <{value = dense<[-1, -1, 0]> : tensor<3xi32>}> : () -> tensor<3xi32>
// CHECK-NEXT:      %7 = "tfl.pseudo_const"() <{value = dense<1> : tensor<i32>}> : () -> tensor<i32>
// CHECK-NEXT:      %8 = "tfl.unsorted_segment_prod"(%4, %5, %7) : (tensor<3xi32>, tensor<3xi32>, tensor<i32>) -> tensor<1xi32>

  func.return %2 : tensor<1x128x32xf32>

// CHECK-DAG:  [[VAL_1:%.*]] = arith.constant dense<0> : tensor<3xi32>
// CHECK-DAG:  [[VAL_2:%.*]] = arith.constant dense<[1, 128, 32]> : tensor<3xi32>
// CHECK:  [[VAL_3:%.*]] = "tfl.slice"(%arg0, [[VAL_1]], [[VAL_2]]) : (tensor<4x128x32xf32>, tensor<3xi32>, tensor<3xi32>) -> tensor<1x128x32xf32>
}

// -----

// CHECK-LABEL: @WhileCanonicalizeBug