[%u0#0, %u0#1] as %u : tensor<32xf32>)
          {n = 2 : i32, devices = {CORE_0 = ["/CPU:0", "/GPU:1"]}} {
        %read0 = "tf.ReadVariableOp"(%r0) : (tensor<*x!tf_type.resource<tensor<32xf32>>>) -> tensor<32xf32>
        // expected-remark@above {{ID: 1}}
        "tf.AssignVariableOp"(%r1, %u) : (tensor<*x!tf_type.resource<tensor<32xf32>>>, tensor<32xf32>) -> ()
        // expected-remark@above {{ID: 2}}

         data_format = "NCHW",
         epsilon = 1.001000e-05 : f32,
         is_training = false
       } : (tensor<?x64x112x112xf32>, tensor<64xf32>, tensor<64xf32>, tensor<64xf32>, tensor<64xf32>)
        -> (tensor<?x64x112x112xf32>, tensor<64xf32>, tensor<64xf32>, tensor<64xf32>, tensor<64xf32>, tensor<*xf32>)

  // CHECK: "tf.FusedBatchNormV3"
  // CHECK-SAME: data_format = "NHWC"

  %0 = "tf.TensorListFromTensor"(%arg0, %arg1) : (tensor<3x10xf32>, tensor<1xi32>) -> tensor<!tf_type.variant<tensor<10xf32>>>
  %1 = "tf.TensorListSetItem"(%0, %arg2, %arg3) : (tensor<!tf_type.variant<tensor<10xf32>>>, tensor<i32>, tensor<10xf32>) -> tensor<!tf_type.variant<tensor<10xf32>>>

  %5 = "stablehlo.concatenate"(%4, %1) {dimension = 0 : i64} : (tensor<?xf32>,  tensor<?xf32>) -> tensor<?xf32>
  %6 = "quantfork.stats"(%5) {layerStats = dense<[-1.5726943, 4.6875381]> : tensor<2xf32>} : (tensor<?xf32>) -> tensor<?xf32>
  func.return  %3, %6 : tensor<?xf32>, tensor<?xf32>
}

// -----

        -> !tf_res
      %read = "tf.ReadVariableOp"(%id2) : (!tf_res) -> tensor<32xf32>
      %id3 = "tf.Identity"(%read) : (tensor<32xf32>) -> tensor<32xf32>
      tf_executor.yield
    }
    tf_executor.fetch %island : !tf_executor.control
  }
  func.return
}

// -----
!tf_res = tensor<*x!tf_type.resource<tensor<32xf32>>>

// Tesets that the pass can propagate through tf.If's branches.

}

// CHECK-DAG: name: "bar"
func.func @bar() -> tensor<10xf32> {
  %0 = tf_executor.graph {
    %1:2 = tf_executor.island wraps "tf.Const"() {device = "", dtype = "tfdtype$DT_FLOAT", value = dense<2.000000e+00> : tensor<10xf32>} : () -> tensor<10xf32> loc("const_2")
    tf_executor.fetch %1#0 : tensor<10xf32>
  }
  func.return %0 : tensor<10xf32>

      %read1 = "tf.ReadVariableOp"(%arg1) : (tensor<*x!tf_type.resource<tensor<32xf32>>>) -> tensor<32xf32>
      %var_handle = "tf.VarHandleOp"() {container = "c", shared_name = "v0"} : () -> tensor<*x!tf_type.resource<tensor<32xf32>>>
      %read2 = "tf.ReadVariableOp"(%var_handle) : (tensor<*x!tf_type.resource<tensor<32xf32>>>) -> tensor<32xf32>

    %assign1_control = tf_executor.island wraps "tf.AssignVariableOp"(%arg1, %read0) : (tensor<*x!tf_type.resource<tensor<32xf32>>>, tensor<32xf32>) -> ()
    %assign2_control = tf_executor.island wraps "tf.AssignVariableOp"(%arg0, %read2) : (tensor<*x!tf_type.resource<tensor<32xf32>>>, tensor<32xf32>) -> ()

  %4 = "tfl.minimum"(%0, %cst) : (tensor<32xf32>, tensor<32xf32>) -> tensor<32xf32>
  %5 = "tfl.minimum"(%1, %cst) : (tensor<32xf32>, tensor<32xf32>) -> tensor<32xf32>
  %6 = "tfl.minimum"(%2, %cst) : (tensor<32xf32>, tensor<32xf32>) -> tensor<32xf32>
  %7 = "tfl.minimum"(%3, %cst) : (tensor<32xf32>, tensor<32xf32>) -> tensor<32xf32>

func.func private @sum_reducer(%arg0: tensor<*xf32>, %arg1: tensor<*xf32>) -> tensor<*xf32> {
  %0 = "tf.AddV2"(%arg0, %arg1) {device = ""} : (tensor<*xf32>, tensor<*xf32>) -> tensor<*xf32>
  func.return %0 : tensor<*xf32>
}

func.func @xla_func_0(%arg0: tensor<7xf32>, %arg1: tensor<f32>) -> tensor<10xf32> {
  %cst = "tf.Const"() {value = dense<0> : tensor<1x2xi32>} : () -> tensor<1x2xi32>