func.func private @quantize_gather_fn(%arg: tensor<3x4x2xf32>) -> tensor<2x3x2x2xf32> attributes {tf._original_func_name = "main_0"} {
    %cst = "tf.Const"() {value = dense<1> : tensor<2x3x2xi32>} : () -> tensor<2x3x2xi32>
    %0 = "quantfork.stats"(%arg) {layerStats = dense<[4.00000000e-6, 9.80000000e-1]> : tensor<2xf32>} : (tensor<3x4x2xf32>) -> tensor<3x4x2xf32>

  // CHECK: %cst_0 = arith.constant dense<0.000000e+00> : tensor<6xf32>
  // CHECK: %cst_1 = arith.constant dense<{{\[\[}}0, 0], [3, 3], [3, 3], [0, 0]]> : tensor<4x2xi32>
  // CHECK: %0 = "tf.Pad"(%arg0, %cst_1) : (tensor<1x224x224x3xf32>, tensor<4x2xi32>) -> tensor<*xf32>

func.func @decompose_scalar_updates(%arg0: tensor<!tf_type.resource<tensor<4x3xi32>>>, %arg1: tensor<2xi32>, %arg2: tensor<i32>) {
  "tf_device.cluster"() ({
    // CHECK-NOT: ResourceScatterUpdate
    // CHECK-NOT: BroadcastTo
    // CHECK: TensorScatterUpdate
    "tf.ResourceScatterUpdate"(%arg0, %arg1, %arg2) : (tensor<!tf_type.resource<tensor<4x3xi32>>>, tensor<2xi32>, tensor<i32>) -> ()
    tf_device.return
  }) : () -> ()

}

// CHECK-LABEL: quantize_float_placeholder_only
func.func @quantize_float_placeholder_only(%arg0: tensor<f32>, %arg1: tensor<2x3xi32>, %arg2: tensor<2x3xf32>) -> (tensor<f32>, tensor<2x3xi32>, tensor<2x3xf32>) {
  func.return %arg0, %arg1, %arg2: tensor<f32>, tensor<2x3xi32>, tensor<2x3xf32>

// CHECK-NEXT: %[[q:.*]] = "tfl.quantize"(%arg0)
// CHECK-NEXT: %[[dq:.*]] = "tfl.dequantize"(%[[q]])

//
//   %indices0 = "tf.Const"() {value = dense<4> : tensor<i32>}
//   %indices1 = "tf.Const"() {value = dense<[[3, 2], [1, 0]]> :
//   tensor<2x2xi32>} %0 = "tf.DynamicStitch"(%indices0, %indices1, %arg0,
//   %arg1)
//     : (tensor<i32>, tensor<2x2xi32>, tensor<2xf32>, tensor<2x2x2xf32>)
//     -> tensor<5x2xf32>
//
// is lowered to
//
//   %shape = "tf.Const"() {value = dense<[-1, 2]> : tensor<2xi64>}