%0 = "tfl.pseudo_const"() { value = dense<[1, 32, 32, 16]> : tensor<4xi32> } : () -> tensor<4xi32>
  %1 = "tfl.pseudo_qconst"() {qtype = tensor<16x!quant.uniform<i32:f32, 1.0>>, value = dense<1> : tensor<16xi32>} : () -> tensor<16x1x1x8x!quant.uniform<i32:f32, 1.0>>
  %2 = "tfl.pseudo_qconst"() {qtype = tensor<16x!quant.uniform<i32:f32, 1.0>>, value = dense<2> : tensor<16xi32>} : () -> tensor<16x!quant.uniform<i32:f32, 1.0>>

    %cst_11 = arith.constant dense<[0, 2, 3, 1]> : tensor<4xi32>
    %cst_12 = arith.constant dense<[0, 1, 3, 2]> : tensor<4xi32>
    %cst_18 = arith.constant dense<[0, 2, 1, 3]> : tensor<4xi32>
    %2112 = "tfl.transpose"(%arg0, %cst_11) : (tensor<1x4x1440x256xf32>, tensor<4xi32>) -> tensor<1x1440x256x4xf32>
    %2113 = "tfl.transpose"(%2112, %cst_18) : (tensor<1x1440x256x4xf32>, tensor<4xi32>) -> tensor<1x256x1440x4xf32>

  %4 = "tf.AddV2"(%padding, %padding) {device = ""} : (tensor<3x2xi32>, tensor<3x2xi32>) -> tensor<3x2xi32>
  %5 = "tf.AddV2"(%strides, %strides) {device = ""} : (tensor<3xi32>, tensor<3xi32>) -> tensor<3xi32>

  return %0 : tensor<8x4x14x14x16xf32>
}

// Check that the constants that are input to XlaConvV2's 3rd, 4th, 5th, 6th
// and 7th arguments are cloned with same value.

}

func.func @identity(%arg0: tensor<10xi32>, %arg1: tensor<20xi32>, %arg2: tensor<30xi32>) -> (tensor<10xi32>, tensor<20xi32>, tensor<30xi32>, tensor<*xi32>) {
  %0 = "tf.Identity"(%arg0) : (tensor<10xi32>) -> tensor<10xi32>
  %1:2 = "tf.IdentityN"(%arg1,%arg2) : (tensor<20xi32>, tensor<30xi32>) -> (tensor<20xi32>, tensor<30xi32>)
  %2 = "tf.Identity"(%arg0) : (tensor<10xi32>) -> tensor<*xi32>

  func.return %r0, %r1 : tensor<0xi32>, tensor<0xi32>
}

// -----

func.func @testBroadcastGradientArgsInvalidR1Size() -> (tensor<0xi32>, tensor<3xi32>) {
  %s0 = "tf.Const"() {value = dense<[4, 4]> : tensor<2xi32>} : () -> tensor<2xi32>
  %s1 = "tf.Const"() {value = dense<[1, 1]> : tensor<2xi32>} : () -> tensor<2xi32>

  %0 = "tfl.pseudo_const"() {value = dense<[1, 4, 384, 32]> : tensor<4xi32>} : () -> tensor<4xi32>
  // CHECK-NOT: tac.device tac.inference_type
  %1 = "tfl.pseudo_const"() {value = dense<[4, 384, 32]> : tensor<3xi32>} : () -> tensor<3xi32>
  // CHECK: tac.device = "CPU", tac.inference_type = "QUANTIZED_INT8"
  %2 = "tfl.reshape"(%arg0, %0) : (tensor<4x384x32x!quant.uniform<i8:f32, 0.2:-3>>, tensor<4xi32>) -> tensor<1x4x384x32x!quant.uniform<i8:f32, 0.2:-3>>

  // CHECK-LABEL: func @main(%arg0: tensor<1xi32>, %arg1: tensor<1xi32>) -> tensor<1xi32>
  func.func @main(%arg0: tensor<1xi32>, %arg1: tensor<1xi32>) -> tensor<*xi32> {
    // CHECK: %[[RESULT:.*]] = "tf.AddV2"
    // CHECK-SAME: (tensor<1xi32>, tensor<1xi32>) -> tensor<1xi32>
    // CHECK: return %[[RESULT]] : tensor<1xi32>
    %0 = "tf.Cast"(%arg0) : (tensor<1xi32>) -> tensor<*xi32>
    %1 = "tf.Cast"(%arg1) : (tensor<1xi32>) -> tensor<*xi32>

// CHECK-NEXT:      %6 = "tfl.pseudo_const"() <{value = dense<[-1, -1, 0]> : tensor<3xi32>}> : () -> tensor<3xi32>
// CHECK-NEXT:      %7 = "tfl.pseudo_const"() <{value = dense<1> : tensor<i32>}> : () -> tensor<i32>
// CHECK-NEXT:      %8 = "tfl.unsorted_segment_prod"(%4, %5, %7) : (tensor<3xi32>, tensor<3xi32>, tensor<i32>) -> tensor<1xi32>

// CHECK:           %[[VAL_3:.*]] = "tf.LeftShift"(%[[VAL_1]], %[[VAL_0]]) : (tensor<4xi32>, tensor<1xi32>) -> tensor<4xi32>
// CHECK:           return %[[VAL_2]], %[[VAL_3]] : tensor<4xi32>, tensor<4xi32>
// CHECK:         }
func.func @broadcast_shift_left(%arg0: tensor<1xi32>, %arg1: tensor<4xi32>) -> (tensor<4xi32>, tensor<4xi32>) {

// CHECK-NEXT: %[[s3:.*]] = "tfl.shape"(%arg1) : (tensor<?x?x4x!quant.uniform<u8:f32, 1.000000e+00>>) -> tensor<3xi32>
// CHECK-NEXT: %[[s2]], %[[s3]] : tensor<?xi32>, tensor<3xi32>
}

// CHECK-LABEL: QuantizeMultipleUsers
func.func @QuantizeMultipleUsers(%arg1: tensor<?x!quant.uniform<u8:f32, 1.0>>) -> (tensor<1xi32>,tensor<1xi32>) {