"vhlo.return_v1"(%1112) : (tensor<i1>) -> ()
    }) : (tensor<448xf32>, tensor<448xi32>) -> (tensor<448xf32>, tensor<448xi32>)
  return %0 : tensor<448xf32>
}

//CHECK:func.func private @sort(%arg0: tensor<448xf32>, %arg1: tensor<448xi32>) -> tensor<448xf32> {
//CHECK-NEXT:  %0:2 = "vhlo.sort_v1"(%arg0, %arg1) <{dimension = #vhlo.integer_v1<0 : i64>, is_stable = #vhlo.bool_v1<true>}> ({

// CHECK-SAME:                                      %[[VAL_0:.*]]: tensor<10x8xi32>,
// CHECK-SAME:                                      %[[VAL_1:.*]]: tensor<10x8xi32>) -> tensor<10x8xi32> {
// CHECK:           %[[VAL_2:.*]] = "tf.Mod"(%[[VAL_0]], %[[VAL_1]]) : (tensor<10x8xi32>, tensor<10x8xi32>) -> tensor<10x8xi32>
// CHECK:           return %[[VAL_2]] : tensor<10x8xi32>
// CHECK:         }

// CHECK: return %cst : tensor<i32>
}

func.func @identity(%arg0: tensor<10xi32>, %arg1: tensor<20xi32>, %arg2: tensor<30xi32>) -> (tensor<10xi32>, tensor<20xi32>, tensor<30xi32>, tensor<*xi32>) {
  %0 = "tf.Identity"(%arg0) : (tensor<10xi32>) -> tensor<10xi32>
  %1:2 = "tf.IdentityN"(%arg1,%arg2) : (tensor<20xi32>, tensor<30xi32>) -> (tensor<20xi32>, tensor<30xi32>)
  %2 = "tf.Identity"(%arg0) : (tensor<10xi32>) -> tensor<*xi32>

    %1 = "tf.StatefulPartitionedCall"(%arg0) {config = "", config_proto = "", executor_type = "", f = @stateful_partitioned_call_func} : (tensor<20xi32>) -> tensor<*xi32>
    // CHECK: tf.TPUPartitionedCall
    // CHECK-SAME: (tensor<20xi32>, tensor<?xi32>) -> tensor<20xi32>

  func.return %3: tensor<2x8xi32>

  // CHECK: %[[CONST:.*]] = "tf.Const"
  // CHECK-SAME: value = dense<[2, 8]> : tensor<2xi32>
  // CHECK: %[[RES:.*]] = "tf.Reshape"(%arg0, %[[CONST]]) {device = "/job:localhost/replica:0/task:0/device:GPU:0"}
  // CHECK: return %[[RES]] : tensor<2x8xi32>
}

// CHECK-LABEL: testReshapeToSelfShape

    %11 = "tf.Einsum"(%8, %10) {device = "", equation = "ab,bc->ac"} : (tensor<2x3xi32>, tensor<3x4xi32>) -> tensor<2x4xi32>
    %12 = "tf.Cast"(%11) {Truncate = false, device = ""} : (tensor<2x4xi32>) -> tensor<2x4xf32>
    %13 = "tf.Mul"(%12, %cst_0) {device = ""} : (tensor<2x4xf32>, tensor<f32>) -> tensor<2x4xf32>

  %12 = "tf.Transpose"(%11, %6) {device = ""} : (tensor<4x2xi32>, tensor<2xi32>) -> tensor<2x4xi32>
  %13 = "tf.Reshape"(%arg0, %1) {device = ""} : (tensor<1x1x2x1xf32>, tensor<1xi32>) -> tensor<2xf32>
  %14 = "tf.ScatterNd"(%12, %13, %3) {device = ""} : (tensor<2x4xi32>, tensor<2xf32>, tensor<4xi32>) -> tensor<1x2x4x1xf32>
  %15 = "tf.Identity"(%14) {device = ""} : (tensor<1x2x4x1xf32>) -> tensor<1x2x4x1xf32>

  %replica_groups = "tf.Const" () {
    value = dense<[[0, 2, 4, 6], [1, 3, 5, 7]]> : tensor<2x4xi32>
  } : () -> tensor<2x4xi32>

  // CHECK: mhlo.cross-replica-sum
  // CHECK-SAME: replica_groups = dense<{{\[}}[0, 2, 4, 6], [1, 3, 5, 7]]> : tensor<2x4xi64>
  %result = "tf.CrossReplicaSum" (%input, %replica_groups) : (tensor<10xf32>, tensor<2x4xi32>) -> tensor<10xf32>
  func.return %result : tensor<10xf32>
}

// -----