%0 = "tf.Const"() {value = dense<[]> : tensor<0xf32>} : () -> tensor<0xf32>

  %2 = "tf.Const"() {value = dense<0.0> : tensor<2x2xf32>} : () -> tensor<2x2xf32>
  %3 = "tf.Const"() {value = dense<0.0> : tensor<4x4xf32>} : () -> tensor<4x4xf32>
  "tf.SendTPUEmbeddingGradients"(%2, %3) {_tpu_embedding_layer = "call1", config = "\0A\0B\0C\0D", operandSegmentSizes = array<i32: 2, 0>} : (tensor<2x2xf32>, tensor<4x4xf32>) -> ()

module{
  func.func @main(%arg0: tensor<10xf32>) -> tensor<10xf32> {
    return %arg0 : tensor<10xf32>
  }
  func.func @func1(%arg0: tensor<10xf32>, %arg1: tensor<10xf32>) -> tensor<10xf32> {
    %0 = stablehlo.add %arg0, %arg1 : tensor<10xf32>
    %1 = stablehlo.add %arg0, %arg1 : tensor<10xf32>
    return %0 : tensor<10xf32>
  }
})mlir";

^bb0(%arg0: tensor<40x37xf32>, %arg1: tensor<40x37xf32>):
  %cst = arith.constant dense<1.0> : tensor<40xf32>
  %0:2 = "tfl.fully_connected"(%arg0, %arg1, %cst) {fused_activation_function = "NONE", keep_num_dims = false, weights_format = "DEFAULT"} : (tensor<40x37xf32>, tensor<40x37xf32>, tensor<40xf32>) -> (tensor<40x40xf32>, tensor<40x40xf32>)
  func.return %0 : tensor<40x40xf32>

func.func @transpose_simple_1d() -> tensor<2xf32> {
  %0 = stablehlo.constant dense<[0.000000e+0, 1.000000e+0]> : tensor<2xf32>
  %1 = stablehlo.transpose %0, dims = [0] : (tensor<2xf32>) -> tensor<2xf32>
  return %1 : tensor<2xf32>
}
// CHECK-DAG: %[[CONST_0:.+]] = stablehlo.constant dense<[0.000000e+00, 1.000000e+00]> : tensor<2xf32>
// CHECK-NOT: transpose
// CHECK: return %[[CONST_0]] : tensor<2xf32>

// -----

  %1 = stablehlo.constant dense<[4.0, 6.0]> : tensor<2xf32>
  %2 = stablehlo.divide %0, %1 : tensor<2xf32>
  return %2 : tensor<2xf32>
}

// CHECK-LABEL: foldDivLHSSplat
// CHECK: stablehlo.constant dense<[5.000000e-01, 0.333333343]> : tensor<2xf32>

// -----

func.func @foldDivRHSSplat() -> tensor<2xf32> {
  %0 = stablehlo.constant dense<[4.0, 6.0]> : tensor<2xf32>
  %1 = stablehlo.constant dense<2.0> : tensor<2xf32>

  %1 = "quantfork.stats"(%0) {bitsNum = 8 : i64, layerStats = dense<[-2.0, 2.0]> : tensor<2xf32>, narrowRange = false} : (tensor<2x3xf32>) -> tensor<2x3xf32>
  %2 = stablehlo.convert %1 : (tensor<2x3xf32>) -> (tensor<2x3xf32>)
  func.return %2 : tensor<2x3xf32>
}

// -----

// CHECK-LABEL: func @dot_redundant_stats

// CHECK-DAG: %[[CAST_0:.*]] = "tf.Cast"(%[[ARG_0]]) <{Truncate = false}> : (tensor<2xbf16>) -> tensor<2xf32>
// CHECK-DAG: %[[CAST_1:.*]] = "tf.Cast"(%[[ARG_1]]) <{Truncate = false}> : (tensor<2xbf16>) -> tensor<2xf32>
// CHECK: %[[ADD:.*]] = "tf.AddV2"(%[[CAST_0]], %[[CAST_1]]) : (tensor<2xf32>, tensor<2xf32>) -> tensor<2xf32>

    tf_executor.graph {
      %out, %ctl = tf_executor.island wraps "tf.VarHandleOp"() {shared_name = "var_0"} : () -> tensor<!tf_type.resource<tensor<2xf32>>>
      %out_0, %ctl_0 = tf_executor.island wraps "tf.ReadVariableOp"(%out) : (tensor<!tf_type.resource<tensor<2xf32>>>) -> tensor<2xf32>
      %out_1, %ctl_1 = tf_executor.island wraps "tf.Const"() {value = dense<"var_0"> : tensor<1x!tf_type.string>} : () -> tensor<1x!tf_type.string>

    %cst_0 = "tf.Const"() {value = dense<1.000000e+00> : tensor<2xf32>} : () -> tensor<2xf32>
    %var_0 = "tf.VarHandleOp"() {shared_name = "var_0"} : () -> tensor<!tf_type.resource<tensor<2xf32>>>
    "tf.AssignVariableOp"(%var_0, %cst_0) : (tensor<!tf_type.resource<tensor<2xf32>>>, tensor<2xf32>) -> ()
    %add_0 = "tf.Identity"(%cst_0) : (tensor<2xf32>) -> tensor<2xf32>

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>