// dilations, etc...). This test only verifies that changing convolution data
// layout will update all the attributes.

// CHECK-LABEL: func @transposeConv2D
func.func @transposeConv2D(%input: tensor<1x3x32x32xf32>, %filter: tensor<1x1x3x8xf32>) -> tensor<1x8x7x6xf32> {

  // CHECK: %[[ARG_PERM:.*]] = "tf.Const"() <{value = dense<[0, 2, 3, 1]> : tensor<4xi64>}>
  // CHECK: %[[ARG_TRANSPOSE:[0-9]*]] = "tf.Transpose"(%arg0, %[[ARG_PERM]])

  // CHECK: %[[BROADCASTED:.*]] = "mhlo.broadcast_in_dim"(%arg0) <{broadcast_dimensions = dense<[1, 3]> : tensor<2xi64>}> : (tensor<4x8xf32>) -> tensor<7x4x3x8xf32>
  // CHECK: %[[RESULT:.*]] = mhlo.reshape %[[BROADCASTED]] : (tensor<7x4x3x8xf32>) -> tensor<28x24xf32>
  // CHECK: return %[[RESULT]] : tensor<28x24xf32>
  %multiples = "tf.Const"() { value = dense<[7,3]> : tensor<2xi64> } : () -> tensor<2xi64>

// CHECK: %[[CONV:.+]] = stablehlo.convolution(%[[TRANSPOSE_0]], %[[CONST]]) dim_numbers = [b, 0, 1, f]x[0, 1, i, o]->[b, 0, 1, f], window = {pad = {{\[\[}}1, 1], [1, 1]]} {batch_group_count = 1 : i64, feature_group_count = 1 : i64} : (tensor<1x4x4x8xf32>, tensor<3x3x8x8xf32>) -> tensor<1x4x4x8xf32>

// -----

// CHECK-LABEL: doubleTposeInputPermNotEqualNoChange
func.func @doubleTposeInputPermNotEqualNoChange(%arg0: tensor<2x4x3x5xf32>, %arg1: tensor<2x3x4x5xf32>) -> tensor<5x2x3x4xf32> {
  %perm = arith.constant dense<[3, 0, 2, 1]> : tensor<4xi32>
  %0 = "tfl.transpose"(%arg0, %perm) : (tensor<2x4x3x5xf32>, tensor<4xi32>) -> tensor<5x2x3x4xf32>
  %perm1 = arith.constant dense<[3, 0, 1, 2]> : tensor<4xi32>

    %20 = "tf.Mul"(%19, %cst_0) {device = ""} : (tensor<2x4x3x6xf32>, tensor<f32>) -> tensor<2x4x3x6xf32>
    %21 = "tf.Relu"(%20) {device = ""} : (tensor<2x4x3x6xf32>) -> tensor<2x4x3x6xf32>
    %22 = "tf.Minimum"(%21, %cst) {device = ""} : (tensor<2x4x3x6xf32>, tensor<f32>) -> tensor<2x4x3x6xf32>
    %23 = "tf.Identity"(%22) {device = ""} : (tensor<2x4x3x6xf32>) -> tensor<2x4x3x6xf32>

  } : (tensor<6x7x8xf32>, tensor<4xi32>, tensor<4xi32>, tensor<4xi32>) -> tensor<1x4x1x8xf32>
  func.return %0 : tensor<1x4x1x8xf32>

  // CHECK-DAG: %[[NEW_DIMS:.*]] = arith.constant dense<[6, 1, 7, 1, 8]> : tensor<5xi32>
  // CHECK-DAG: %[[BEGIN:.*]] = arith.constant dense<0> : tensor<5xi32>

  %result = "tf_device.launch"() ({
    %3 = "tf.Transpose"(%2, %1) : (tensor<1x8x4x4xf32>, tensor<4xi32>) -> tensor<1x4x4x8xf32>
    tf_device.return %3: tensor<1x4x4x8xf32>
  }) {device = "device"} : () -> tensor<1x4x4x8xf32>

  func.return %result : tensor<1x4x4x8xf32>

  // CHECK-DAG: %[[CONST1:.*]] = "tf.Const"() <{value = dense<[0, 3, 1, 2]> : tensor<4xi32>}>

func.func @FakeQuantWithMinMaxVarsPerChannel(tensor<1x2x3x8xf32>, tensor<8xf32>, tensor<8xf32>) -> tensor<1x2x3x8xf32> {
^bb0(%arg0: tensor<1x2x3x8xf32>, %arg1: tensor<8xf32>, %arg2: tensor<8xf32>):
  %0 = "tf.FakeQuantWithMinMaxVarsPerChannel"(%arg0, %arg1, %arg2) : (tensor<1x2x3x8xf32>, tensor<8xf32>, tensor<8xf32>) -> tensor<1x2x3x8xf32>
  func.return %0 : tensor<1x2x3x8xf32>
}

// -----

// CHECK:           }) : (tensor<5x4x3x7xf32>, tensor<2x2xi32>, tensor<2x5x3xf32>) -> tensor<5x4x3x7xf32>
// CHECK:           return %[[VAL_3]] : tensor<5x4x3x7xf32>
// CHECK:         }
func.func @convert_scatter_update_to_non_trailing_operand_dimensions(
  %arg0: tensor<5x4x3x7xf32>,
  %arg1: tensor<2x2xi32>,
  %arg2: tensor<2x5x3xf32>) -> tensor<5x4x3x7xf32>
{
  %0 = "mhlo.scatter"(%arg0, %arg1, %arg2) ({

}

func.func @split(%arg0: tensor<i32>, %arg1: tensor<1x4x3x3xf32>) -> tensor<1x4x3xf32> {
  %0:3 = "tf.Split"(%arg0, %arg1) : (tensor<i32>, tensor<1x4x3x3xf32>) -> (tensor<1x4x3xf32>, tensor<1x4x3xf32>, tensor<1x4x3xf32>)
  func.return %0#0 : tensor<1x4x3xf32>

  // CHECK-LABEL: split
  // CHECK: "tfl.split"(%arg0, %arg1) <{num_splits = 3 : i32}> : (tensor<i32>, tensor<1x4x3x3xf32>) -> (tensor<1x4x3xf32>, tensor<1x4x3xf32>, tensor<1x4x3xf32>)