%0:4 = "tfl.basic_lstm"(%arg0, %arg1, %arg2, %arg3, %arg4) {fused_activation_function = "RELU", cell_clip = 1.0 : f32, proj_clip = 2.0 : f32} : (tensor<1x384xf32>, tensor<1x96xf32>, tensor<384x480xf32>, tensor<384xf32>, tensor<1x96xf32>) -> (tensor<1x96xf32>, tensor<1x96xf32>, tensor<1x480xf32>, tensor<1x384xf32>)
  func.return %0#0 : tensor<1x96xf32>

^bb0(%arg0: tensor<40x37xf32>, %arg1: tensor<40x37xf32>):
  %cst = arith.constant dense<1.0> : tensor<40xf32>
  %0:2 = "tfl.fully_connected"(%arg0, %arg1, %cst) {fused_activation_function = "NONE", keep_num_dims = false, weights_format = "DEFAULT"} : (tensor<40x37xf32>, tensor<40x37xf32>, tensor<40xf32>) -> (tensor<40x40xf32>, tensor<40x40xf32>)
  func.return %0 : tensor<40x40xf32>

^bb0(%arg0: tensor<40x37xf32>, %arg1: tensor<40x37xf32>):
  %cst = arith.constant dense<1.0> : tensor<40xf32>
  %0:2 = "tfl.fully_connected"(%arg0, %arg1, %cst) {fused_activation_function = "NONE", keep_num_dims = false, weights_format = "DEFAULT"} : (tensor<40x37xf32>, tensor<40x37xf32>, tensor<40xf32>) -> (tensor<40x40xf32>, tensor<40x40xf32>)
  func.return %0 : tensor<40x40xf32>

}

func.func @fully_connected(%arg0: tensor<1x37xf32>, %arg1: tensor<40x37xf32>, %arg2: tensor<40xf32>) -> tensor<1x40xf32> {
  // CHECK: _arithmetic_count = 3000 : i64
  %0 = "tfl.fully_connected"(%arg0, %arg1, %arg2) {fused_activation_function = "NONE", keep_num_dims = false, weights_format = "DEFAULT"} : (tensor<1x37xf32>, tensor<40x37xf32>, tensor<40xf32>) -> tensor<1x40xf32>
  func.return %0 : tensor<1x40xf32>
}

  // CHECK-SAME:      : (tensor<40x37xf32>) -> tensor<40x37xf32>
  // CHECK-NEXT:    %[[cst:.*]] = "tfl.pseudo_const"() <{value = dense<
  // CHECK-SAME:      1.000000e+00> : tensor<40xf32>}> : () -> tensor<40xf32>
  // CHECK-NEXT:    %[[fc:.*]]:2 = "tfl.fully_connected"(%[[stat]], %arg1,
  // CHECK-NEXT:    %[[stat1:.*]] = "quantfork.stats"(%[[fc]]#0)
  // CHECK-SAME:    <{axis = 1 : i64,