// CHECK-SAME:      <[-1.000000e+00, 1.000000e+00]> : tensor<2xf32>}>
  // CHECK-SAME:      : (tensor<40x37xf32>) -> tensor<40x37xf32>
  // CHECK-NEXT:    %[[cst:.*]] = "tfl.pseudo_const"() <{value = dense<
  // CHECK-SAME:      1.000000e+00> : tensor<40xf32>}> : () -> tensor<40xf32>
  // CHECK-NEXT:    %[[fc:.*]]:2 = "tfl.fully_connected"(%[[stat]], %arg1,

module {
  // CHECK-LABEL: func @main
  // CHECK-SAME: %[[ARG_0:.*]]: tensor<10xf32>, %[[ARG_1:.*]]: tensor<10xf32>, %[[ARG_2:.*]]: tensor<6xi32>
  func.func @main(
      %arg0: tensor<10xf32>, %arg1: tensor<10xf32>, %arg2: tensor<6xi32>
    ) -> (tensor<10xf32>, tensor<6xi32>) {
    // CHECK: %[[CAST_0:.*]] = "tf.Cast"(%[[ARG_0]]) <{Truncate = false}> : (tensor<10xf32>) -> tensor<10xbf16>

      %outputs_9, %control_10 = tf_executor.island wraps "tf.Mul"(%outputs_7, %outputs) {T = "tfdtype$DT_FLOAT", _tpu_replicate = "cluster", device = "", name = "mul"} : (tensor<0xf32>, tensor<f32>) -> tensor<0xf32>
      %outputs_11, %control_12 = tf_executor.island wraps "tf.Placeholder"() {device = "", dtype = "tfdtype$DT_FLOAT", name = "y", shape = "tfshape$dim { }"} : () -> tensor<0xf32>

// CHECK-LABEL: import_stats_skip
func.func @import_stats_skip(%arg0: tensor<4xf32>, %cst: tensor<i32>) -> (tensor<2xf32>,tensor<2xf32>) {
  %0:2 = "tfl.split"(%cst, %arg0) {num_splits = 2 : i32} : (tensor<i32>, tensor<4xf32>) -> (tensor<2xf32>, tensor<2xf32>)
    loc(fused["skip1", "skip2.cc":10:8, callsite("op" at "skip3.cc":10:8)])
  func.return %0#0, %0#1 : tensor<2xf32>, tensor<2xf32>

// CHECK-NEXT: "tfl.split"
// CHECK-NEXT: return
}

    return
  }
  // CHECK-LABEL: func private @foo.impl
  func.func private @foo.impl(%arg0: tensor<1xf32>, %arg1: tensor<2xf32>) -> (tensor<2xf32>, tensor<1xf32>) {
    return %arg1, %arg0 : tensor<2xf32>, tensor<1xf32>
  }

  // CHECK-DAG: %[[CST_0:.+]] = mhlo.constant dense<[1.000000e-01, 2.000000e-01]> : tensor<2xf32>
  // CHECK-DAG: %[[CST_1:.+]] = mhlo.constant dense<[3.000000e-01, 4.000000e-01]> : tensor<2xf32>
  // CHECK: %[[CST_BCAST:.+]] = "mhlo.broadcast_in_dim"(%[[CST_0]]) <{broadcast_dimensions = dense<3> : tensor<1xi64>}> : (tensor<2xf32>) -> tensor<1x1x3x2xf32>

    } : (tensor<2x2xf32>, tensor<2x2xf32>) -> tensor<2x2xf32>
    %2 = "quantfork.stats"(%1) {layerStats = dense<[0.000000e+00, 6.000000e+00]> : tensor<2xf32>} : (tensor<2x2xf32>) -> tensor<2x2xf32>
    return %2 : tensor<2x2xf32>
  }

  // CHECK-LABEL: composite_dot_general
  func.func private @composite_dot_general(%arg0: tensor<2x2xf32>, %arg1: tensor<2x2xf32>) -> tensor<2x2xf32> {

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>

// -----