# 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"
  attr {

module {
func.func @main(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>, %arg2: tensor<1xf32>, %arg3: tensor<1xf32>) -> tensor<2x1xf32> attributes {tf.entry_function = {inputs = "input0,input1,input2,input3", outputs = "output"}} {
  %0 = "tfl.add"(%arg0, %arg1) {fused_activation_function = "RELU6"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
  %1 = "tfl.mul"(%0, %arg2) {fused_activation_function = "RELU6"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>

    } : (tensor<10xf32>, tensor<10xf32>, tensor<6xi32>) -> (tensor<10xf32>, tensor<6xi32>)
    // CHECK: return %[[RESULT_CAST]], %[[RESULT]]#1 : tensor<10xf32>, tensor<6xi32>
    func.return %0#0, %0#1 : tensor<10xf32>, tensor<6xi32>
  }

  // CHECK-LABEL: func private @main_0
  // CHECK-SAME: %[[ARG_0:.*]]: tensor<10xbf16>, %[[ARG_1:.*]]: tensor<10xbf16>, %[[ARG_2:.*]]: tensor<6xi32>
  func.func private @main_0(

module {
  func.func @simpleTest(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>, %arg2: tensor<1xf32>, %arg3: tensor<1xf32>) -> tensor<2x1xf32> {
    %0 = func.call @func_0_GPU_FLOAT(%arg0, %arg1, %arg2) {tac.interface_name = "func_0"} : (tensor<1xf32>, tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
    %1 = func.call @func_1_GPU_FLOAT(%arg0, %arg3) {tac.interface_name = "func_1"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>

  %cst_2 = "tf.Const"() {value = dense<3> : tensor<1xi32>} : () -> tensor<1xi32>
  %cst_3 = "tf.Const"() {value = dense<4> : tensor<1xi32>} : () -> tensor<1xi32>
  %0 = "tf.XlaReduceWindow"(%arg0, %arg1, %cst_0, %cst_1, %cst_2, %cst_3, %cst) {computation = @sum_reducer} : (tensor<7xf32>, tensor<f32>, tensor<1xi32>, tensor<1xi32>, tensor<1xi32>, tensor<1xi32>, tensor<1x2xi32>) -> tensor<10xf32>

}

// CHECK-LABEL: add
func.func @add(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>) -> tensor<1xf32> {
  %0 = "tf.AddV2"(%arg0, %arg1) : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
  func.return %0: tensor<1xf32>
// CHECK: %[[ADD_0:.*]] = "tf.AddV2"(%arg0, %arg1) : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
// CHECK: return %[[ADD_0]] : tensor<1xf32>
}

// CHECK-LABEL: softmax

  func.return %1 : tensor<1xf32>
}

func.func @cond_true(%arg0: tensor<*xf32>, %arg1: tensor<*xf32>) -> tensor<*xf32> {
  %0 = tfl.add %arg0, %arg1 {fused_activation_function = "NONE"} : tensor<*xf32>
  func.return %0 : tensor<*xf32>
}

func.func @cond_false(%arg0: tensor<*xf32>, %arg1: tensor<*xf32>) -> tensor<*xf32> {

// CHECK-NEXT:   "tfl.yield"(%[[MY_CUSTOM]]) : (tensor<4xf32>) -> ()
// CHECK-NEXT: }) {fused_activation_function = "RELU", int_attr = 2 : i32} : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>
// CHECK-NEXT: %[[CUSTOM_2:.*]] = "tfl.custom_tf"(%[[MUL]], %[[CST]]) ({
// CHECK-NEXT: ^bb0(%arg1: tensor<4xf32>, %arg2: tensor<4xf32>):

// CHECK-NOT: tf.BatchFunction
// CHECK: %[[ADD0:.*]] = "tf.AddV2"(%[[ARG0]], %[[ARG1]])
// CHECK: return %[[ADD0]] : tensor<1xf32>

func.func private @batched_func(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>) -> tensor<1xf32> {
  %0 = "tf.Identity"(%arg0) : (tensor<1xf32>) -> tensor<1xf32>
  %1 = "tf.Identity"(%arg1) : (tensor<1xf32>) -> tensor<1xf32>

func.func @multiply(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>) -> tensor<1xf32> {
  %0 = "vhlo.multiply_v1"(%arg0, %arg1) : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
  func.return %0 : tensor<1xf32>
}

// CHECK:func.func private @multiply(%arg0: tensor<1xf32>, %arg1: tensor<1xf32>) -> tensor<1xf32> {
// CHECK: %0 = "vhlo.multiply_v1"(%arg0, %arg1) : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
// CHECK: return %0 : tensor<1xf32>
// CHECK:}