%1 = "tf.Transpose"(%arg0, %0) : (tensor<1x4x4x8xf32>, tensor<4xi32>) -> tensor<1x8x4x4xf32>
  %2 = "tf.Transpose"(%1, %0) : (tensor<1x8x4x4xf32>, tensor<4xi32>) -> tensor<1x4x8x4xf32>
  %3 = "tf.Transpose"(%arg1, %0) : (tensor<1x4x4x8xf32>, tensor<4xi32>) -> tensor<1x8x4x4xf32>
  %4 = "tf.Transpose"(%3, %0) : (tensor<1x8x4x4xf32>, tensor<4xi32>) -> tensor<1x4x8x4xf32>
  %5 = "tf.AddV2"(%2, %4) : (tensor<1x4x8x4xf32>, tensor<1x4x8x4xf32>) -> tensor<1x4x8x4xf32>

}
// CHECK: @main(%[[ARG:.+]]: tensor<1x8x4x4xf32>) -> tensor<1x8x4x4xf32>

// Contains the `stablehlo.transpose` op of the arg (e.g. [b, f, 0, 1] to
// [b, 0, 1, f]). The weight constant is folded into [0, 1, i, o] format.
// CHECK-DAG: %[[CST:.+]] = stablehlo.constant dense<3.000000e+00> : tensor<3x3x8x8xf32>
// CHECK: %[[TRANSPOSE_1:.+]] = stablehlo.transpose %arg0, dims = [0, 2, 3, 1] : (tensor<1x8x4x4xf32>) -> tensor<1x4x4x8xf32>

  %1 = "tf.AddV2"(%0, %0) : (tensor<1x4x4x8xf32>, tensor<1x4x4x8xf32>) -> tensor<1x4x4x8xf32>
  %2 = "tf.Const"() {value = dense<[0, 3, 1, 2]> : tensor<4xi32>} : () -> tensor<4xi32>
  %3 = "tf.Transpose"(%1, %2) : (tensor<1x4x4x8xf32>, tensor<4xi32>) -> tensor<1x8x4x4xf32>

  func.return %3 : tensor<1x8x4x4xf32>
}

// CHECK-LABEL: move_transpose_handle_broadcast

  return %2 : tensor<1x8x4x4xf32>
}

// CHECK-DAG: %[[CONST:.+]] = stablehlo.constant {{.*}} : tensor<8x8x3x3xf32>
// CHECK-DAG: %[[TRANSPOSE_0:.+]] = stablehlo.transpose %[[ARG]], dims = [0, 2, 3, 1] : (tensor<1x8x4x4xf32>) -> tensor<1x4x4x8xf32>

func.func @out_of_bounds_check(%arg0: tensor<1x4x4x8xf32>) -> tensor<1x4x4x8xf32> {
  %0 = "tf.Const"() {value = dense<[0, 3, 1, 2]> : tensor<4xi32>} : () -> tensor<4xi32>
  %1 = "tf.Const"() {value = dense<[0, 0x4141, 3, 1]> : tensor<4xi32>} : () -> tensor<4xi32>
  %2 = "tf.Transpose"(%arg0, %0) : (tensor<1x4x4x8xf32>, tensor<4xi32>) -> tensor<1x8x4x4xf32>

      %1 = "tf.XlaCallModule"(%0, %cst_0, %cst_1) <{Sout = [#tf_type.shape<1x4x4x3>], module = "", version = 9 : i64}> {_entry_function = @composite_fn_2, _original_entry_function = "composite_fn_2", _tfl_quant_trait = "fully_quantizable"} : (tensor<1x4x4x3xf32>, tensor<3x1x1x3xf32>, tensor<3xf32>) -> tensor<1x4x4x3xf32>
      return %1 : tensor<1x4x4x3xf32>

  func.return %2 : tensor<4x4x4xf32>
}

func.func @testSingleLstmFloat16(%arg0: tensor<4x4xf32>, %arg1: tensor<4xf32>, %arg2: tensor<4x4x4xf32>) -> tensor<4x4x4xf32> {
  // CHECK-LABEL: testSingleLstm
  // CHECK-DAG:  %[[CST_0:.*]] = "tfl.pseudo_const"() <{value = dense<0.000000e+00> : tensor<4x4xf16>}> : () -> tensor<4x4xf16>