func.func @float_depthwise_conv_no_bias(%arg0: tensor<1x3x4x3xf32>, %arg1: tensor<2x3x3x1xf32>) -> (tensor<*xf32>, tensor<*xf32>, tensor<*xf32>) {
  %0 = "tf.DepthwiseConv2dNative"(%arg0, %arg1) {
    data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [],
    padding = "SAME", strides = [1, 1, 2, 1]
  } : (tensor<1x3x4x3xf32>, tensor<2x3x3x1xf32>) -> tensor<*xf32>

func.func @QuantizeGatherWeightOnly(%arg0: tensor<3xi32>) -> tensor<3x3x3x3xf32> {
  %w = arith.constant dense<1.270000e+02> : tensor<64x3x3x3xf32>
  %emb = "tfl.gather"(%w, %arg0) {axis = 0 : i32, batch_dims = 0 : i32} : (tensor<64x3x3x3xf32>, tensor<3xi32>) -> tensor<3x3x3x3xf32>
  %emb_s = "quantfork.stats"(%emb) {layerStats = dense<[0.000000e+00, 1.000000e+01]> : tensor<2xf32>} : (tensor<3x3x3x3xf32>) -> tensor<3x3x3x3xf32>
  func.return %emb_s : tensor<3x3x3x3xf32>

  %w = arith.constant dense<127.0> : tensor<3x3x3x3xf32>
  %b = arith.constant dense<0.0> : tensor<3xf32>
  %conv = "tfl.conv_2d"(%arg0, %w, %b) {dilation_h_factor = 1 : i32, dilation_w_factor = 1 : i32, fused_activation_function = "RELU", padding = "SAME", stride_h = 1 : i32, stride_w = 1 : i32} : (tensor<1x5x5x3xf32>, tensor<3x3x3x3xf32>, tensor<3xf32>) -> tensor<1x5x5x3xf32>
  func.return %conv : tensor<1x5x5x3xf32>

func.func @QuantizeGatherWeightOnly(%arg0: tensor<3xi32>) -> tensor<3x3x3x3xf32> {
  %w = arith.constant dense<1.270000e+02> : tensor<64x3x3x3xf32>
  %emb = "tfl.gather"(%w, %arg0) {axis = 0 : i32, batch_dims = 0 : i32} : (tensor<64x3x3x3xf32>, tensor<3xi32>) -> tensor<3x3x3x3xf32>
  %emb_s = "quantfork.stats"(%emb) {layerStats = dense<[0.000000e+00, 1.000000e+01]> : tensor<2xf32>} : (tensor<3x3x3x3xf32>) -> tensor<3x3x3x3xf32>
  func.return %emb_s : tensor<3x3x3x3xf32>

  %3 = "tfl.pseudo_const"() {value = dense<1.000000e+00> : tensor<16x3x3x16xf32>} : () -> tensor<16x3x3x16xf32>
  %4 = "tfl.pseudo_const"() {value = dense<1.000000e+00> : tensor<16xf32>} : () -> tensor<16xf32>

  %0 = "tf.Const"() {value = dense<0.111111112> : tensor<3x3x1x1xf32>} : () -> tensor<3x3x1x1xf32>
  %1 = "tf.Const"() {value = dense<1.000000e+00> : tensor<1x520x520x1xf32>} : () -> tensor<1x520x520x1xf32>
  %2 = "tf.DepthwiseConv2dNative"(%1, %0) {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1]} : (tensor<1x520x520x1xf32>, tensor<3x3x1x1xf32>) -> tensor<1x520x520x1xf32>

// CHECK: %0 = "tfl.transpose"(%arg0, %cst) : (tensor<1x1x3x3xf32>, tensor<4xi32>) -> tensor<1x3x3x1xf32>
// CHECK{LITERAL}: %cst_0 = arith.constant dense<[[0, 0], [0, 1], [0, 1], [0, 0]]> : tensor<4x2xi32>
// CHECK: %1 = "tfl.pad"(%0, %cst_0) : (tensor<1x3x3x1xf32>, tensor<4x2xi32>) -> tensor<1x4x4x1xf32>

  %0 = "mhlo.broadcast_in_dim"(%arg0) <{broadcast_dimensions = dense<[1, 2, 3]> : tensor<3xi64>, name = "broadcast.0"}> : (tensor<8x1x16xf32>) -> tensor<3x8x8x16xf32>
  func.return %0 : tensor<3x8x8x16xf32>
}

// CHECK-LABEL:   func @broadcast_in_dim_general_case(
// CHECK-SAME:                                        %[[VAL_0:.*]]: tensor<3x1x16xf32>) -> tensor<3x8x8x16xf32> {

    %6 = "tf.Cast"(%3) {Truncate = false} : (tensor<2x3x3x1xi32>) -> tensor<2x3x3x1xf32>
    %7 = "tf.DepthwiseConv2dNative"(%5, %6) {dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 2, 2, 1]} : (tensor<1x3x4x3xf32>, tensor<2x3x3x1xf32>) -> tensor<1x2x2x3xf32>
    %8 = "tf.Cast"(%7) : (tensor<1x2x2x3xf32>) -> tensor<1x2x2x3xi32>