func.return %cst : tensor<1x750xf32>

  // CHECK-DAG: %0 = mhlo.constant dense<7.680000e+02> : tensor<f32>
  // CHECK: %1 = "mhlo.broadcast_in_dim"(%0) <{broadcast_dimensions = dense<> : tensor<0xi64>}> : (tensor<f32>) -> tensor<1x750xf32>
  // CHECK: return %1 : tensor<1x750xf32>
}

// CHECK-LABEL: @unfold_splat_constant_integer
func.func @unfold_splat_constant_integer() -> tensor<1x750xi32> {

  // CHECK: "mhlo.all_reduce"
  // CHECK-SAME: channel_handle = #mhlo.channel_handle<handle = 10001, type = 1>
  // CHECK-SAME{LITERAL}: replica_groups = dense<[[0, 1]]> : tensor<1x2xi64>
  // CHECK: mhlo.add
  // CHECK: mhlo.return
  %0 = "tf.CollectiveReduceV2"(%input, %group_size, %group_key, %instance_key) {merge_op = "Add", final_op = "Id"} : (tensor<f32>, tensor<i32>, tensor<i32>, tensor<i32>) -> tensor<f32>

  // CHECK-DAG: %[[SCALE_BCAST:.+]] = "mhlo.broadcast_in_dim"(%[[SCALE]]) <{broadcast_dimensions = dense<1> : tensor<1xi64>}> : (tensor<256xf32>) -> tensor<4x256xf32>
  // CHECK-DAG: %[[OFFSET_BCAST:.+]] = "mhlo.broadcast_in_dim"(%[[OFFSET]]) <{broadcast_dimensions = dense<1> : tensor<1xi64>}> : (tensor<256xf32>) -> tensor<4x256xf32>

// CHECK: %[[XLA_CALL_MODULE:.+]] = "tf.XlaCallModule"(%[[CUSTOM_AGGREGATOR_0]], %[[CST]])
// CHECK-SAME: _entry_function = @composite_dot_general_fn_1, _original_entry_function = "composite_dot_general_fn_1"

  %2 = "mhlo.dynamic_broadcast_in_dim"(%cst_0, %1) <{broadcast_dimensions = dense<3> : tensor<1xi64>}> : (tensor<2xf32>, tensor<4xindex>) -> tensor<?x256x256x2xf32>
  %3 = mhlo.multiply %0, %2 : tensor<?x256x256x2xf32>
  %4 = "mhlo.dynamic_broadcast_in_dim"(%cst_1, %1) <{broadcast_dimensions = dense<3> : tensor<1xi64>}> : (tensor<2xf32>, tensor<4xindex>) -> tensor<?x256x256x2xf32>
  %5 = mhlo.add %3, %4 : tensor<?x256x256x2xf32>

  %cst = "tf.Const"() <{value = dense<0.000000e+00> : tensor<f32>}> : () -> tensor<f32>
  %cst_0 = "tf.Const"() <{value = dense<1> : tensor<1xi64>}> : () -> tensor<1xi64>
  %fill = "tf.Fill"(%cst_0, %cst) : (tensor<1xi64>, tensor<f32>) -> tensor<1xf32>
  tf_device.replicate([%0, %fill] as %arg_r0: tensor<1xf32>) {n = 2 : i32} {
    %1 = "tf_device.launch"() <{device = "TPU_REPLICATED_HOST_0"}> ({

module {
  func.func @main() -> tensor<1xi64> {
  %0 = "tfl.custom"() {custom_code = "stablehlo.constant", custom_option = #tfl<const_bytes : "0x76616C75650001020109010101062C022401">} : () -> tensor<1xi64>
  func.return %0 : tensor<1xi64>
  }
}

// CHECK:  module {
// CHECK-NEXT:    func @main() -> tensor<1xi64> {
// CHECK-NEXT:    %[[c0:.+]] = stablehlo.constant dense<2> : tensor<1xi64>
// CHECK-NEXT:    return %[[c0]] : tensor<1xi64>

  // CHECK-SAME: <{calibration_methods = [1 : i32, 1 : i32], ids = ["0", "1"], output_file_path = "main_0.pb"}> : (tensor<f32>, tensor<f32>, tensor<0xi64>, tensor<f32>, tensor<f32>, tensor<0xi64>) -> ()
  // CHECK: return

  %cst0 = mhlo.constant dense<[1, 2, 3, 4]> : tensor<4xi32>
  // CHECK: %[[BROADCAST:.*]] = "mhlo.broadcast_in_dim"(%[[CONST]]) <{broadcast_dimensions = dense<3> : tensor<1xi64>}> : (tensor<4xi32>) -> tensor<1x1x2x4xi32>
  %0 = "mhlo.broadcast_in_dim"(%cst0) <{broadcast_dimensions = dense<3> : tensor<1xi64>}> : (tensor<4xi32>) -> tensor<1x1x2x4xi32>
  // CHECK: %[[MUL:.*]] = mhlo.multiply %[[BROADCAST]], %[[ARG]] : tensor<1x1x2x4xi32>

  // NOT-CHECK-DAG:    %[[LHS_BCAST:.+]] = "mhlo.dynamic_broadcast_in_dim"(%arg0, %[[RESULT_EXTENTS]]) <{broadcast_dimensions = dense<0> : tensor<1xi64>}>
  // NOT-CHECK-DAG:    %[[RHS_BCAST:.+]] = "mhlo.dynamic_broadcast_in_dim"(%arg1, %[[RESULT_EXTENTS]]) <{broadcast_dimensions = dense<0> : tensor<1xi64>}>
  // NOT-CHECK-NEXT:   %[[RESULT:.+]] = mhlo.compare EQ, %[[LHS_BCAST]], %[[RHS_BCAST]]
  // NOT-CHECK-NEXT:   shape.assuming_yield %[[RESULT]]