func.return %0 : tensor<10x10xf32>

func.func @unfold_large_constant_splat() -> (tensor<10x10xf32>, tensor<1000x1000xf32>) {
  %0 = arith.constant dense<0.00000e+00> : tensor<10x10xf32>
  %1 = arith.constant dense<1.00000e+00> : tensor<1000x1000xf32>
  func.return %0, %1 : tensor<10x10xf32>, tensor<1000x1000xf32>

  // CHECK-DAG: %cst = arith.constant dense<0.000000e+00> : tensor<10x10xf32>
  // CHECK-DAG: %cst_0 = arith.constant dense<1000> : tensor<2xi64>

func.func @main(tensor<40x37xf32>, tensor<40x37xf32>) -> 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>

# CHECK:"tf.MlirPassthroughOp"
# CHECK: mlir_module = "\0Afunc @main(%arg0 : tensor<10xf32>, %arg1 : tensor<10xf32>) -> tensor<10x10xf32> {\0A %add = \22tf.Add\22(%arg0, %arg1) : (tensor<10xf32>, tensor<10xf32>) -> tensor<10xf32>\0A %ret = \22magic.op\22(%add, %add) : (tensor<10xf32>, tensor<10xf32>) -> tensor<10x10xf32>\0A return %ret : tensor<10x10xf32>\0A}\0A"}> {device = ""} : (tensor<10xf32>, tensor<10xf32>) -> tensor<*xf32>

node {
  name: "x"
  op: "Placeholder"

func.func @main(%arg0: tensor<40x37xf32>, %arg1: tensor<40x37xf32>) -> tensor<40x40xf32> {
// CHECK: [[NONE:%.*]] = "tfl.no_value"() <{value}> : () -> none
// CHECK: "tfl.fully_connected"(%arg0, %arg1, [[NONE]])
// CHECK-SAME: (tensor<40x37xf32>, tensor<40x37xf32>, none) -> (tensor<40x40xf32>, tensor<40x40xf32>)
  %cst = "tfl.no_value"() {value = unit} : () -> none

  %pi_0 = "tf.TPUPartitionedInput"(%arg0, %arg1) {_XlaSharding = "123", partition_dim = 0 : i64} : (tensor<10x3xf32>, tensor<10x3xf32>) -> tensor<20x3xf32>
  %ri = "tf.TPUReplicatedInput"(%pi_0) : (tensor<20x3xf32>) -> tensor<20x3xf32>
  // CHECK: return [[RI]]
  func.return %ri : tensor<20x3xf32>
}

// -----

// CHECK-LABEL:func @partitioned_2d_resource

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

  %0:2 = "tfl.fully_connected"(%arg0, %arg1, %cst) {fused_activation_function = "NONE", keep_num_dims = false, weights_format = "SHUFFLED4x16INT8"} : (tensor<40x37xf32>, tensor<40x37xf32>, none) -> (tensor<40x40xf32>, tensor<40x40xf32>)
  func.return %0 : tensor<40x40xf32>

    } : (tensor<2x2xf32>, tensor<2x2xf32>) -> tensor<2x2xf32>
    %2 = "quantfork.stats"(%1) {layerStats = dense<[0.000000e+00, 6.000000e+00]> : tensor<2xf32>} : (tensor<2x2xf32>) -> tensor<2x2xf32>
    return %2 : tensor<2x2xf32>
  }

  // CHECK-LABEL: composite_dot_general
  func.func private @composite_dot_general(%arg0: tensor<2x2xf32>, %arg1: tensor<2x2xf32>) -> tensor<2x2xf32> {

  %cst2 = arith.constant dense<3.0> : tensor<23x2xf32>
  %0 = "tf.Conv2D"(%arg0, %cst0) {T = "tfdtype$DT_FLOAT", data_format = "NHWC", dilations = [1, 2, 3, 1], padding = "SAME", strides = [1, 4, 5, 1]} : (tensor<1x112x112x3xf32>, tensor<1x3x3x2xf32>) -> tensor<1x28x23x2xf32>
  %1 = "tf.Mul"(%0, %cst2) : (tensor<1x28x23x2xf32>, tensor<23x2xf32>) -> tensor<1x28x23x2xf32>

  func.return %1 : tensor<1x28x23x2xf32>