// CHECK-LABEL: func @parallel_execute_with_tiled_input
  // CHECK-SAME: (%[[ARG_0:[a-z0-9]*]]: tensor<128x10xf32>, %[[ARG_1:[a-z0-9]*]]: tensor<128x10xf32>, %[[ARG_2:[a-z0-9]*]]: tensor<*xi32>, %[[ARG_3:[a-z0-9]*]]: tensor<*xi32>)
  func.func @parallel_execute_with_tiled_input(%arg0: tensor<128x10xf32>, %arg1: tensor<128x10xf32>, %arg2: tensor<*xi32>, %arg3: tensor<*xi32>) -> (tensor<*xi32>, tensor<*xi1>) {
    // CHECK: tf_device.replicate

  %4 = "tfl.relu"(%3) {tac.device = "GPU", tac.inference_type = "FLOAT"} : (tensor<128x128xf32>) -> tensor<128x128xf32>
  %5 = "tfl.pseudo_const"() {value = dense<1.000000e+00> : tensor<128x128xf32>} : () -> tensor<128x128xf32>
  %6 = "tfl.pseudo_const"() {value = dense<1.000000e+00> : tensor<128xf32>} : () -> tensor<128xf32>

// CHECK-LABEL: @ShardingAttr
func.func @ShardingAttr(%arg0: tensor<128x10xf32> {mhlo.sharding = "\08\03\1A\02\01\02\22\02\00\01"}, %arg1: tensor<10x1024xf32> {mhlo.sharding = "\08\01\1A\01\01\22\01\00"}, %arg2: tensor<128x1024xf32> {mhlo.sharding = ""}) -> (tensor<128x10xf32>, tensor<10x1024xf32>, tensor<128x1024xf32>) {

    %1 = "tf.PartitionedCall"(%arg0, %cst_0) {_tfl_quant_trait = "fully_quantizable", config = "", config_proto = "", executor_type = "", f = @composite_matmul_fn_1} : (tensor<2x12xf32>, tensor<12x2xf32>) -> tensor<*xf32>
    func.return %1: tensor<*xf32>
  }

    %1 = "tf.PartitionedCall"(%arg0, %cst_0) {_tfl_quant_trait = "fully_quantizable", config = "", config_proto = "", executor_type = "", f = @composite_matmul_fn_1} : (tensor<2x12xf32>, tensor<12x2xf32>) -> tensor<*xf32>
    func.return %1: tensor<*xf32>
  }

      %2 = "tf.Cast"(%arg0) {Truncate = false} : (tensor<1x8x2xi32>) -> tensor<1x8x2xf32>
      tf_device.return %2 : tensor<1x8x2xf32>
    // CHECK: () -> tensor<1x8x2xf32>
    }) {device = "/device:CPU:0"} : () -> tensor<*xf32>
    // CHECK: "tf.Cast"(%{{.*}}) <{Truncate = false}> : (tensor<1x8x2xf32>) -> tensor<*xf32>
    // CHECK: (tensor<i32>, tensor<1x8x2xf32>) -> (tensor<1x8x1xf32>, tensor<1x8x1xf32>)

  %1 = "tf.TensorListGetItem"(%0, %arg2, %arg1) {device = "/job:localhost/replica:0/task:0/device:GPU:0"} : (tensor<!tf_type.variant<tensor<1x32xf32>>>, tensor<i32>, tensor<2xi32>) -> tensor<1x32xf32>
  %2 = "tf.TensorListGetItem"(%0, %arg3, %arg1) {device = "/job:localhost/replica:0/task:0/device:GPU:0"} : (tensor<!tf_type.variant<tensor<1x32xf32>>>, tensor<i32>, tensor<2xi32>) -> tensor<1x32xf32>

  %2 = "tf.BatchToSpaceND"(%arg0, %0, %1) {device = ""} : (tensor<3x5x2xf32>, tensor<1xi32>, tensor<1x2xi32>) -> tensor<1x8x2xf32>

  // CHECK: return [[VAL8]] : tensor<1x8x2xf32>
  func.return %2 : tensor<1x8x2xf32>
}

func.func @fake_quant_with_min_max_args(%arg0 : tensor<?x?xf32>) -> tensor<?x?xf32> {

  // tf.XlaReduceScatter legalization
  //===--------------------------------------------------------------------===//
  // CHECK-LABEL: func @xla_reduce_scatter
  func.func @xla_reduce_scatter(%arg0: tensor<128x128xf32>) -> tensor<64x128xf32> {
      %cst = "tf.Const"() {value = dense<0> : tensor<i32>} : () -> tensor<i32>
      %cst_0 = "tf.Const"() {value = dense<[[0, 4], [1, 5], [2, 6], [3, 7]]> : tensor<4x2xi32>} : () -> tensor<4x2xi32>

// result shapes.
// CHECK-LABEL: func @testShapeInvariantWhile
func.func @testShapeInvariantWhile(%arg0: tensor<1x2x3xf32>) -> tensor<1x8x3xf32> {
  %0 = "tf.While"(%arg0) {cond = @cond, body = @body, is_stateless = false, shape_invariant} : (tensor<1x2x3xf32>) -> tensor<1x8x3xf32>
  func.return %0 : tensor<1x8x3xf32>
}

// -----
// WhileRegion tests

// Simple While region
// CHECK-LABEL: testValidWhileRegion