module {
  func.func public @main(%arg0: tensor<3x3xf32>, %arg1: tensor<3x3xf32>, %arg2: tensor<1x100x32x4xf32>,
      %arg3: tensor<1x500x4x4xf32>, %arg4: tensor<1x500x4x4xf32>, %arg5: tensor<1x1x100x500xf32>, %arg6: tensor<f32>)
      -> tensor<1x100x32x4xf32> {

func.func private @"map/while/LoopCond_cond"(%arg0: tensor<*xi32>, %arg1: tensor<*xi32>, %arg2: tensor<f32>, %arg3: tensor<i32>, %arg4: tensor<2x!tf_type.resource<tensor<*x!tf_type.string>>>, %arg5: tensor<f32>, %arg6: tensor<2x!tf_type.resource<tensor<*xui8>>>) -> tensor<i1> {
  %outputs = "tf.Less"(%arg0, %arg3) {device = ""} : (tensor<*xi32>, tensor<i32>) -> tensor<*xi1>

    %cst = "tf.Const"() {value = dense<127> : tensor<i32>} : () -> tensor<i32>
    %cst_0 = "tf.Const"() {value = dense<-128> : tensor<i32>} : () -> tensor<i32>
    %0 = "tf.Cast"(%arg0) {Truncate = false} : (tensor<1x2240x2240x3xi8>) -> tensor<1x2240x2240x3xi32>

// CHECK: %[[NONE:.+]] = "tfl.no_value"() <{value}> : () -> none
// CHECK: "tfl.lstm"(%arg0, %arg1, %arg2, %arg3, %arg4, %arg5, %arg6, %arg7, %arg8, %[[NONE]], %[[NONE]], %[[NONE]], %arg9, %arg10, %arg11, %arg12, %arg13, %[[NONE]], %arg19, %arg20, %arg15, %arg16, %arg17, %arg18)
}

func.func @keepCustomFlexOps(%arg0: tensor<1x10xf32>) -> tensor<1x10xf32> {

func.func @decompose_adam_with_complex_inputs(%arg0: tensor<!tf_type.resource<tensor<2xcomplex<f32>>>>, %arg1: tensor<!tf_type.resource<tensor<2xcomplex<f32>>>>, %arg2: tensor<!tf_type.resource<tensor<2xcomplex<f32>>>>, %arg3: tensor<complex<f32>>, %arg4: tensor<complex<f32>>, %arg5: tensor<complex<f32>>, %arg6: tensor<complex<f32>>, %arg7: tensor<complex<f32>>, %arg8: tensor<complex<f32>>, %arg9: tensor<2xcomplex<f32>>) attributes {tf.entry_function = {control_outputs...

  func.func @while_shape_invariant_body_func_propagate(%arg0: tensor<*xf32>, %arg1: tensor<*x!tf_type.resource>, %arg2: tensor<!tf_type.resource>, %arg3: tensor<?xi32>) -> (tensor<*xf32>, tensor<*x!tf_type.resource>, tensor<!tf_type.resource>, tensor<?xi32>) {
    %0 = "tf.SomeOp"(%arg3) : (tensor<?xi32>) -> tensor<?xi32>
    func.return %arg0, %arg1, %arg2, %0 : tensor<*xf32>, tensor<*x!tf_type.resource>, tensor<!tf_type.resource>, tensor<?xi32>

// CHECK-LABEL: testLiftDotConcatLHSAndRHS
func.func @testLiftDotConcatLHSAndRHS(%arg0: tensor<1x72x128xf32>, %arg1: tensor<1x128x72xf32>, %arg2: tensor<1x72x128xf32>, %arg3: tensor<1x128x72xf32>, %arg4: tensor<1x72x128xf32>, %arg5: tensor<1x128x72xf32>, %arg6: tensor<1x72x128xf32>, %arg7: tensor<1x128x72xf32>) -> tensor<4x72x72xf32> {
  %0 = "mhlo.dot_general"(%arg0, %arg1) {
    dot_dimension_numbers = #mhlo.dot<
      lhs_batching_dimensions = [0],

  func.return %4 : tensor<128x128x!quant.uniform<u8:f32, 0.2:125>>

// CHECK: "tfl.custom_tf"
// CHECK-NEXT: ^bb0(%arg4: tensor<128x128xf32>, %arg5: tensor<1xf32>, %arg6: tensor<1xf32>, %arg7: tensor<1xi32>):
// CHECK-NEXT:   "tf.LayerNorm"(%arg4, %arg5, %arg6, %arg7) {_tfl_quant_trait = "fully_quantizable", device = ""} : (tensor<128x128xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xi32>) -> tensor<128x128xf32>

// CHECK:      %[[RELU6_0:.*]] = "tf.Relu6"

// CHECK-LABEL: func private @quantized_conv2d_with_bias_and_relu6_fn_0
// CHECK-SAME: (%arg0: tensor<1x2x2x3xi8>, %arg1: tensor<2x2x3x2xi8>, %arg2: tensor<2xi32>, %arg3: tensor<f32>, %arg4: tensor<i32>, %arg5: tensor<2xf32>, %arg6: tensor<2xi32>, %arg7: tensor<2xf32>, %arg8: tensor<2xi32>, %arg9: tensor<f32>, %arg10: tensor<i32>) -> tensor<*xi8>
// CHECK:      %[[CONV2D_0:.*]] = "tf.Conv2D"

  "tf.AssignVariableOp"(%arg0, %arg2) : (tensor<*x!tf_type.resource<tensor<32xf32>>>, tensor<32xf32>) -> ()
  // CHECK-NEXT: "tf.AssignVariableOp"(%[[ARG_5]], %[[ARG_6]])
  "tf.AssignVariableOp"(%arg5, %arg6) : (tensor<*x!tf_type.resource<tensor<2xf32>>>, tensor<2xf32>) -> ()
  %read1 = "tf.ReadVariableOp"(%arg1) : (tensor<*x!tf_type.resource<tensor<64xf32>>>) -> tensor<64xf32>