%8 = "tfl.mul"(%2, %3) {fused_activation_function = "NONE"} : (tensor<4xi32>, tensor<4xi32>) -> tensor<4xi32>

  func.return %5, %6, %7, %8 : tensor<i32>, tensor<4xi32>, tensor<4xi32>, tensor<4xi32>
}

// CHECK-LABEL: @add_dense_splat_int
func.func @add_dense_splat_int() -> tensor<4xi32> {
  %0 = arith.constant dense<[-10, -1, 42, 100]> : tensor<4xi32>

// CHECK-NEXT:      %18 = "tfl.pseudo_const"() <{value = dense<2> : tensor<1xi32>}> : () -> tensor<1xi32>
// CHECK-NEXT:      %19 = "tfl.concatenation"(%18, %17, %16) <{axis = 0 : i32, fused_activation_function = "NONE"}> : (tensor<1xi32>, tensor<1xi32>, tensor<1xi32>) -> tensor<3xi32>
// CHECK-NEXT:      %20 = mhlo.dynamic_reshape %2, %19 : (tensor<2x3x4x?xf32>, tensor<3xi32>) -> tensor<2x3x?xf32>

  %min = arith.constant dense<0.0> : tensor<16xf32>
  %max = arith.constant dense<255.0> : tensor<16xf32>
  %mini = "tf.Identity"(%min) : (tensor<16xf32>) -> tensor<16xf32>
  %maxi = "tf.Identity"(%max) : (tensor<16xf32>) -> tensor<16xf32>
  %fq = "tf.FakeQuantWithMinMaxVarsPerChannel"(%in, %mini, %maxi) {num_bits = 5, narrow_range = false} : (tensor<3x3x3x16xf32>, tensor<16xf32>, tensor<16xf32>) -> tensor<3x3x3x16xf32>

    %2 = stablehlo.reshape %1 : (tensor<i32>) -> tensor<1xi32>
    %3 = stablehlo.concatenate %2, %cst_0, %cst_1, %cst_2, dim = 0 : (tensor<1xi32>, tensor<1xi32>, tensor<1xi32>, tensor<1xi32>) -> tensor<4xi32>
    %4 = stablehlo.dynamic_broadcast_in_dim %arg2, %3, dims = [0, 1, 2, 3] : (tensor<1x1x1x2xf32>, tensor<4xi32>) -> tensor<?x3x4x2xf32>
    %5 = stablehlo.add %0, %4 : tensor<?x3x4x2xf32>

  %min = arith.constant dense<0.0> : tensor<16xf32>
  %max = arith.constant dense<15.0> : tensor<16xf32>
  %mini = "tf.Identity"(%min) : (tensor<16xf32>) -> tensor<16xf32>
  %maxi = "tf.Identity"(%max) : (tensor<16xf32>) -> tensor<16xf32>
  %fq = "tf.FakeQuantWithMinMaxVarsPerChannel"(%in, %mini, %maxi) {num_bits = 3, narrow_range = false} : (tensor<3x3x3x16xf32>, tensor<16xf32>, tensor<16xf32>) -> tensor<3x3x3x16xf32>

  %119 = "tf.StridedSlice"(%116, %16, %15, %16) {begin_mask = 0 : i64, device = "", ellipsis_mask = 0 : i64, end_mask = 1 : i64, new_axis_mask = 0 : i64, shrink_axis_mask = 0 : i64} : (tensor<1xi32>, tensor<1xi32>, tensor<1xi32>, tensor<1xi32>) -> tensor<0xi32>

    %4 = "tf.LayerNorm"(%a1, %a2, %a3, %a4) {_tfl_quant_trait = "fully_quantizable", device = ""} : (tensor<128x128xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xi32>) -> tensor<128x128xf32>
   "tfl.yield"(%4) : (tensor<128x128xf32>) -> ()
  }) {_tfl_quant_trait = "fully_quantizable", device = ""} : (tensor<128x128xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xi32>) -> tensor<128x128xf32>

// CHECK-LABEL: func @testBroadcastGradientArgs
func.func @testBroadcastGradientArgs(%s0: tensor<4xi32>, %s1: tensor<4xi32>) -> (tensor<1xi32>, tensor<0xi32>) {
  // CHECK:     tf.BroadcastGradientArgs
  %r0, %r1 = "tf.BroadcastGradientArgs"(%s0, %s1) : (tensor<4xi32>, tensor<4xi32>) -> (tensor<1xi32>, tensor<0xi32>)
  func.return %r0, %r1 : tensor<1xi32>, tensor<0xi32>
}

// -----

// CHECK-LABEL: @acos

    >} : (
      tensor<?x?x6xi8>, tensor<6x8xi8>
    ) -> tensor<?x?x8xi32>
  %1 = chlo.broadcast_add %0, %zp_offset : (
      tensor<?x?x8xi32>, tensor<8xi32>) -> tensor<?x?x8xi32>
  %2 = chlo.broadcast_add %1, %bias : (
      tensor<?x?x8xi32>, tensor<8xi32>) -> tensor<?x?x8xi32>
  return %2 : tensor<?x?x8xi32>
}

// -----

// CHECK-LABEL: func @dot_general_add_add_static

    %4 = "tf.LayerNorm"(%a1, %a2, %a3, %a4) {_tfl_quant_trait = "fully_quantizable", device = ""} : (tensor<128x128xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xi32>) -> tensor<128x128xf32>
   "tfl.yield"(%4) : (tensor<128x128xf32>) -> ()
  }) {_tfl_quant_trait = "fully_quantizable", device = ""} : (tensor<128x128xf32>, tensor<1xf32>, tensor<1xf32>, tensor<1xi32>) -> tensor<128x128xf32>