(tensor<37x40xf32>, tensor<37x40xf32>) -> tensor<40x40xf32>
  func.return %0 : tensor<40x40xf32>
// CHECK-LABEL: matmul_transposed_a
// CHECK: %[[CST_0:.*]] = arith.constant dense<[1, 0]> : tensor<2xi32>
// CHECK: %[[ARG_0:.*]] = "tfl.transpose"(%arg0, %[[CST_0]]) : (tensor<37x40xf32>, tensor<2xi32>) -> tensor<40x37xf32>

  %0 = "tf.BatchMatMulV2"(%arg0, %arg3) {adj_x = false, adj_y = false} : (tensor<?x8x8xf32>, tensor<8x40xf32>) -> tensor<?x8x40xf32>
  %1 = "tf.Add"(%0, %arg5) : (tensor<?x8x40xf32>, tensor<40xf32>) -> tensor<?x8x40xf32>
  %2 = "tf.BatchMatMulV2"(%1, %arg4) {adj_x = false, adj_y = true} : (tensor<?x8x40xf32>, tensor<10x40xf32>) -> tensor<?x8x10xf32>
  %3 = "tf.Add"(%2, %arg1) : (tensor<?x8x10xf32>, tensor<8x10xf32>) -> tensor<?x8x10xf32>

// CHECK-LABEL: @MinimumOfReluAnd6ToRelu6
func.func @MinimumOfReluAnd6ToRelu6(%arg0: tensor<40x40xf32>) -> tensor<40x40xf32> {
  %cst = arith.constant dense<6.0> : tensor<f32>
  %2 = "tfl.relu"(%arg0) : (tensor<40x40xf32>) -> tensor<40x40xf32>
  %3 = "tfl.minimum"(%2, %cst) : (tensor<40x40xf32>, tensor<f32>) -> tensor<40x40xf32>
  func.return %3 : tensor<40x40xf32>

  // CHECK: %[[rs1:.*]] = "tfl.relu6"(%arg0
  // CHECK: return %[[rs1]]
}

  %0 = "tfl.fully_connected"(%arg0, %arg1, %arg2) {fused_activation_function = "NONE", keep_num_dims = false, weights_format = "DEFAULT"} : (tensor<2x2x10xf32>, tensor<40x40xf32>, none) -> tensor<1x40xf32>
  func.return %0 : tensor<1x40xf32>
}

// -----

func.func @testFullyConnectedWith3DFilter(%arg0: tensor<1x37xf32>, %arg1: tensor<40x2x37xf32>, %arg2: tensor<40xf32>) -> tensor<1x40xf32> {

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

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-LABEL: tensorlistSetItem
func.func @tensorlistSetItem(%arg0: tensor<3x10xf32>, %arg1: tensor<1xi32>, %arg2: tensor<i32>, %arg3: tensor<10xf32>) -> tensor<3x10xf32> {
  %0 = "tf.TensorListFromTensor"(%arg0, %arg1) : (tensor<3x10xf32>, tensor<1xi32>) -> tensor<!tf_type.variant<tensor<10xf32>>>

  %2 = "tf.TensorListStack"(%0, %arg1) : (tensor<!tf_type.variant<tensor<10xf32>>>, tensor<1xi32>) -> tensor<3x10xf32>
  func.return %1, %2 : tensor<10xf32>, tensor<3x10xf32>

// CHECK:  %0 = "tf.Gather"(%arg0, %arg2) <{validate_indices = true}> : (tensor<3x10xf32>, tensor<i32>) -> tensor<10xf32>
// CHECK: return %0, %arg0 : tensor<10xf32>, tensor<3x10xf32>
}

// -----

// CHECK-LABEL: func @tensorlistGetItemWithUnknownRank

  %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>