// CHECK-LABEL: @qu8
  // CHECK: <{qtype = tensor<3x!quant.uniform<u8<1:255>:f32, 1.000000e+00>>, value = dense<1> : tensor<3xi8>}> : () -> tensor<3x!quant.uniform<u8<1:255>:f32, 1.000000e+00>>
  %0 = "tfl.pseudo_qconst"() { qtype = tensor<3x!quant.uniform<u8<1:255>:f32, 1.0>>, value = dense<1> : tensor<3xi8>} : () -> tensor<3x!quant.uniform<u8<1:255>:f32, 1.0>>
  func.return %0 : tensor<3x!quant.uniform<u8<1:255>:f32, 1.0>>
}

// CHECK-LABEL: @quantize_constant
// CHECK-SAME: %[[ARG0:.*]]: tensor<1x3xf32>
func.func @quantize_constant(%arg0: tensor<1x3xf32>) -> tensor<1x2xf32> {
  // CHECK-DAG: %[[QCST:.*]] = stablehlo.constant() <{value = dense<-78> : tensor<3x2xi8>}> : () -> tensor<3x2x!quant.uniform<i8<-127:127>:f32, 5.000000e-03>>
  // CHECK-DAG: %[[Q1:.*]] = stablehlo.uniform_quantize %[[ARG0]]
  // CHECK-NOT: "quantfork.qcast"
  // CHECK: %[[DOT:.*]] = stablehlo.dot %[[Q1]], %[[QCST]]

// CHECK-LABEL: func @DynamicStitch_uint8
func.func @DynamicStitch_uint8(%arg0: tensor<2x2xui8>) -> tensor<2x2xui8> {
  // CHECK-NOT: tf.DynamicStitch

  %indices = "tf.Const"() {value = dense<[1, 0]> : tensor<2xi32>} : () -> tensor<2xi32>
  %0 = "tf.DynamicStitch"(%indices, %arg0) : (tensor<2xi32>, tensor<2x2xui8>) -> tensor<2x2xui8>
  func.return %0 : tensor<2x2xui8>
}

// CHECK-LABEL: func @DynamicStitch_scalar_item

func.func @tensorlistConst(%arg0 : tensor<1xi32>) -> tensor<2x3xi32> {
  // CHECK-DAG: %[[ELEMENT0:.*]] = "tf.Const"() <{value = dense<[0, 1, 2]> : tensor<3xi32>}> : () -> tensor<3xi32>
  // CHECK-DAG: %[[ELEMENT1:.*]] = "tf.Const"() <{value = dense<[3, 4, 5]> : tensor<3xi32>}> : () -> tensor<3xi32>
  // CHECK: %[[LIST:.*]] = "tf.Pack"(%[[ELEMENT0]], %[[ELEMENT1]]) <{axis = 0 : i64}> : (tensor<3xi32>, tensor<3xi32>) -> tensor<2x3xi32>

func.func @testVariableShapeWrongResultDim(%arg0: tensor<*x!tf_type.resource<tensor<1x32x32x16xf32>>>) -> tensor<2x3xi32> {
  // expected-error @+1 {{requires 1D type for result}}
  %0 = "tf.VariableShape"(%arg0) {output = "tfdtype$DT_INT32"} : (tensor<*x!tf_type.resource<tensor<1x32x32x16xf32>>>) -> tensor<2x3xi32>
  func.return %0 : tensor<2x3xi32>
}

// -----

// CHECK-NEXT:      %20 = mhlo.dynamic_reshape %2, %19 : (tensor<2x3x4x?xf32>, tensor<3xi32>) -> tensor<2x3x?xf32>
// CHECK-NEXT:      %21 = "tfl.batch_matmul"(%11, %20) <{adj_x = false, adj_y = false, asymmetric_quantize_inputs = false}> : (tensor<2x?x3xf32>, tensor<2x3x?xf32>) -> tensor<2x?x?xf32>
// CHECK-NEXT:      %22 = "tfl.shape"(%arg0) : (tensor<2x2x?x3xf32>) -> tensor<4xi32>

func.func @cast_i1_to_i8() -> tensor<2xi8> {
  %cst = arith.constant dense<[false, true]> : tensor<2xi1>
  %0 = "tfl.cast"(%cst) : (tensor<2xi1>) -> tensor<2xi8>
  func.return %0 : tensor<2xi8>

// CHECK: %[[CST:.*]] = arith.constant dense<[0, 1]> : tensor<2xi8>
// CHECK:  return %[[CST]]
}

// CHECK-LABEL: @cast_i1_to_ui8
func.func @cast_i1_to_ui8() -> tensor<2xui8> {

  // CHECK-LABEL: testSameOperandsAndResultTypeResolveRefBinary
  func.func @testSameOperandsAndResultTypeResolveRefBinary(%lhs: tensor<2x3x?x?xf32>, %rhs: tensor<2x?x5x?xf32>) -> (tensor<?x?x?x?xf32>) {
    // CHECK: (tensor<2x3x?x?xf32>, tensor<2x?x5x?xf32>) -> tensor<2x3x5x?xf32>
    %0 = "tf.ReluGrad"(%lhs, %rhs) : (tensor<2x3x?x?xf32>, tensor<2x?x5x?xf32>) -> tensor<?x?x?x?xf32>
    func.return %0 : tensor<?x?x?x?xf32>
  }

\007N\273\347?\026IrX\227\356\325?t\031)?\031*\352?\234\327\267\360\217\207\315?l|\005\257\236G\343?|\243\302\237\234|\302?\202\331\024c\376\311\330?\027G\365\300\204V\350?P\022a\377\025\221\266?x\204\326I\334\307\305?Xb\177\262\263\325\345?(\034\223XI\n\342?\000\005\356\325\342w\323?\244\034\211\221bR\347?\250!|\272\341\324\275?\216+\235x\\\204\325?\262\266T\233\323i\356?\316\005R\270\2516\332?`\356\r\tn%\260?\335mb\320o\363\357?p\235#t\276q\306? U\320\003\344[\332?~O\266\340\341\026\325? \0219...