func.return %0 : tensor<4xf32>
}

func.func @f64() -> tensor<4xf64> {
  // CHECK-LABEL: @f64
  // CHECK: value = dense<[1.000000e+00, 2.000000e+00, 3.000000e+00, 4.000000e+00]> : tensor<4xf64>
  %0 = "tfl.pseudo_const"() { value = dense<[1.0, 2.0, 3.0, 4.0]> : tensor<4xf64> } : () -> tensor<4xf64>
  func.return %0 : tensor<4xf64>
}

func.func @i8() -> tensor<4xi8> {
  // CHECK-LABEL: @i8

  func.return %0 : tensor<4xf32>
}

func.func @f64() -> tensor<4xf64> {
  // CHECK-LABEL: @f64
  // CHECK: value = dense<[1.000000e+00, 2.000000e+00, 3.000000e+00, 4.000000e+00]> : tensor<4xf64>
  %0 = "tfl.pseudo_const"() { value = dense<[1.0, 2.0, 3.0, 4.0]> : tensor<4xf64> } : () -> tensor<4xf64>
  func.return %0 : tensor<4xf64>
}

func.func @i8() -> tensor<4xi8> {
  // CHECK-LABEL: @i8

    // CHECK-NOT: tf.BesselI0e
    %0 = "tf.BesselI0e"(%arg0) : (tensor<3xf16>) -> (tensor<3xf16>)
    %1 = "tf.BesselI0e"(%arg1) : (tensor<3xf32>) -> (tensor<3xf32>)
    %2 = "tf.BesselI0e"(%arg2) : (tensor<3xf64>) -> (tensor<3xf64>)
    func.return %0, %1, %2 : tensor<3xf16>, tensor<3xf32>, tensor<3xf64>
  }

  // CHECK-LABEL: bessel_i1e

}

// CHECK-LABEL: func @testEmptyFloat
func.func @testEmptyFloat() -> (tensor<5xf64>) {
  %0 = "tf.Const"() { value = dense<5> : tensor<i32> } : () -> tensor<i32>

  // CHECK: [[VAL:%.+]] = "tf.Const"() <{value =  dense<0.000000e+00> : tensor<5xf64>}>
  // CHECK: return [[VAL]]
  %1 = "tf.Empty"(%0) : (tensor<i32>) -> (tensor<5xf64>)
  func.return %1 : tensor<5xf64>
}

// CHECK-LABEL: func @testEmptyf16

    %range_nume = "tf.Sub"(%r_max_f64, %r_min_f64) : (tensor<1xf64>, tensor<1xf64>) -> tensor<1xf64>
    %range_deno = "tf.Sub"(%i8_max_f64, %i8_min_f64) : (tensor<f64>, tensor<f64>) -> tensor<f64>

    %scale_f64 = "tf.Div"(%range_nume, %range_deno) : (tensor<1xf64>, tensor<f64>) -> tensor<1xf64>
    %scale = "tf.Cast"(%scale_f64) : (tensor<1xf64>) -> tensor<1xf32>

    // Add comparison with minimum if needed

  func.return %0 : tensor<2x?x?x1xf32>
  // CHECK-LABEL: einsum_matmul_dynamic_size
  // CHECK-DAG: %[[cst:.*]] = arith.constant dense<[2, -1, 1, 1]> : tensor<4xi64>
  // CHECK: %[[v0:.*]] = "tf.Reshape"(%arg1, %cst) : (tensor<2x?xf32>, tensor<4xi64>) -> tensor<2x?x1x1xf32>
  // CHECK: %[[v1:.*]] = "tf.BatchMatMulV2"(%arg0, %0) <{adj_x = false, adj_y = false}> : (tensor<2x?x?x?xf32>, tensor<2x?x1x1xf32>) -> tensor<2x?x?x1xf32>

  %1 = mhlo.constant dense<0.000000e+00> : tensor<f32>
  %2 = "mhlo.pad"(%arg0, %1) {edge_padding_high = dense<[0, 0, 1, 1]> : tensor<4xi64>, edge_padding_low = dense<[0, 0, 1, 1]> : tensor<4xi64>, interior_padding = dense<0> : tensor<4xi64>} : (tensor<1x3x6x6xf32>, tensor<f32>) -> tensor<1x3x8x8xf32>
  %3 = "mhlo.reduce_window"(%2, %1) ({
  ^bb0(%arg1: tensor<f32>, %arg2: tensor<f32>):

// CHECK-LABEL: broadcast_to_to_reshape_i64
func.func @broadcast_to_to_reshape_i64(%arg0: tensor<4x4x4xf32>, %arg1 : tensor<4xi64>) -> tensor<1x4x4x4xf32> {
  %0 = "tfl.broadcast_to"(%arg0, %arg1) : (tensor<4x4x4xf32>, tensor<4xi64>) -> tensor<1x4x4x4xf32>
  // CHECK: "tfl.cast"
  // CHECK-SAME: (tensor<4xi64>) -> tensor<4xi32>
  // CHECK-NEXT: "tfl.reshape"
  // CHECK-SAME: (tensor<4x4x4xf32>, tensor<4xi32>) -> tensor<1x4x4x4xf32>

  %values = "tf.Const"() {value = dense<[1, 2, 3, 4]> : tensor<4xi64>} : () -> tensor<4xi64>
  "tf.LookupTableImportV2"(%handle, %keys, %values) {device = ""} : (tensor<!tf_type.resource>, tensor<4x!tf_type.string>, tensor<4xi64>) -> ()

func.return %0 : tensor<2x?x2x4xf32>

// CHECK-LABEL:     convert_dot_general_dynamic_batch_dim
// CHECK:           %0 = "tfl.pseudo_const"() <{value = dense<[0, 1, 3, 2]> : tensor<4xi64>}> : () -> tensor<4xi64>
// CHECK-NEXT:      %1 = "tfl.cast"(%0) : (tensor<4xi64>) -> tensor<4xi32>
// CHECK-NEXT:      %2 = "tfl.transpose"(%arg1, %1) : (tensor<2x?x4x3xf32>, tensor<4xi32>) -> tensor<2x?x3x4xf32>