// CHECK:           })
// CHECK-SAME:        -> tensor<2x4x6x7xf32>
// CHECK:           %[[RESULT:.*]] = mhlo.divide %[[DIVIDEND]], %[[DIVISOR]] : tensor<2x4x6x7xf32>
// CHECK:           return %[[RESULT]] : tensor<2x4x6x7xf32>
// CHECK:         }
func.func @avgpool_same_padding(%arg0: tensor<2x12x21x7xf32>) -> tensor<2x4x6x7xf32> {

}

func.func @einsum_reshapetail(%arg0: tensor<3x4x5xf32>, %arg1: tensor<5x6x2xf32>) -> tensor<3x4x6x2xf32> {
  %0 = "tf.Einsum"(%arg0, %arg1) {T = "tfdtype$DT_FLOAT", equation = "bfd,dnh->bfnh"}: (tensor<3x4x5xf32>, tensor<5x6x2xf32>) -> tensor<3x4x6x2xf32>
  func.return %0 : tensor<3x4x6x2xf32>
  // CHECK-LABEL: einsum_reshapetail
  // CHECK-DAG: %[[cst:.*]] = arith.constant dense<[5, 12]> : tensor<2xi64>

// CHECK-SAME:      %arg0: tensor<2x4x4x1xf32>,
// CHECK-SAME:      %arg1: tensor<2x4x4x2xf32>) -> tensor<2x4x4x1xf32> attributes {tf._implements = "DenseImageWarp"} {
// CHECK-NEXT:    %0 = "tfl.custom"(%arg0, %arg1) <{custom_code = "DenseImageWarp", custom_option = #tfl<const_bytes : "0x">}> : (tensor<2x4x4x1xf32>, tensor<2x4x4x2xf32>) -> tensor<2x4x4x1xf32>
// CHECK-NEXT:    return %0 : tensor<2x4x4x1xf32>
// CHECK-NEXT:  }
}

// -----

// -----

// 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>

  // CHECK: return %[[RESULT]] : tensor<2x3x4x6xf32>
}

// -----

func.func @batchMatMulTwoDimAdjXY(%arg0: tensor<2x3x5x4xf32>, %arg1: tensor<2x3x6x5xf32>) -> tensor<2x3x4x6xf32> {
  %0 = "tf.BatchMatMul"(%arg0, %arg1) {adj_x = true, adj_y = true} : (tensor<2x3x5x4xf32>, tensor<2x3x6x5xf32>) -> tensor<2x3x4x6xf32>
  func.return %0 : tensor<2x3x4x6xf32>

  // CHECK-LABEL: batchMatMulTwoDimAdjXY

# functions are converted.

# CHECK:      func @main(%arg0: tensor<*x!tf_type.resource>, %arg1: tensor<*x!tf_type.resource<tensor<3x3x1x32xf32>>>, %arg2: tensor<*xf32>, %arg3: tensor<2x4x6x8xi32>) -> (tensor<*xf32>, tensor<*xf32>)
# CHECK-SAME: _xla_compile_device_type = "GPU"
# CHECK-SAME: allow_soft_placement
# CHECK-SAME: control_outputs = ""
# CHECK-SAME: inputs = "args_0,args_1,args_2,args_3"

    func.return %result : tensor<10x24x24x64xf32>
  }

  // CHECK-LABEL: @max_pool_grad_same
  func.func @max_pool_grad_same(%orig_input: tensor<2x13x25x7xf32>, %orig_output: tensor<2x4x7x7xf32>, %grad: tensor<2x4x7x7xf32>) -> tensor<2x13x25x7xf32> {
    // CHECK: padding = dense<{{\[\[}}0, 0], [0, 1], [1, 1], [0, 0]]> : tensor<4x2xi64>
    %result = "tf.MaxPoolGrad"(%orig_input, %orig_output, %grad) {
      data_format = "NHWC",

func.func @testBiasAdd(%arg0: tensor<2x3x5x7xf32>, %arg1: tensor<5x7xf32>) -> tensor<2x3x5x7xf32> {
  // expected-error @+1 {{requires bias operand to have rank exactly one}}
  %0 = "tf.BiasAdd"(%arg0, %arg1) {data_format = "NHWC"} : (tensor<2x3x5x7xf32>, tensor<5x7xf32>) -> tensor<2x3x5x7xf32>
  func.return %0 : tensor<2x3x5x7xf32>
}

// -----

func.func @testBiasAdd(%arg0: tensor<2x3x5x7xf32>, %arg1: tensor<5xf32>) -> tensor<2x3x5x7xf32> {

// 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) ({