%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>

  %2 = "tf.AddN"(%arg0, %1, %1) : (tensor<2xi32>, tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
  %3 = "tf.AddN"(%1, %arg0, %1) : (tensor<2xi32>, tensor<2xi32> , tensor<2xi32>) -> tensor<2xi32>
  %4 = "tf.AddN"(%1, %1) : (tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
  %5 = "tf.AddN"(%arg0, %1, %0) : (tensor<2xi32>, tensor<2xi32>, tensor<2xi32>) -> tensor<2xi32>
  func.return %2, %3, %4, %5: tensor<2xi32>, tensor<2xi32>, tensor<2xi32>, tensor<2xi32>
}

  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

  %0:2 = "tf.IdentityN"(%arg0, %arg1) : (tensor<1xi32>, tensor<1xf32>) -> (tensor<1xi32>, tensor<1xf32>)
  func.return %0#0, %0#1: tensor<1xi32>, tensor<1xf32>
}

// -----

// CHECK-LABEL: func @stopgradient
func.func @stopgradient(%arg0: tensor<1xi32>) -> tensor<1xi32> {
  // CHECK-NEXT:  return %arg0 : tensor<1xi32>
  %0 = "tf.StopGradient"(%arg0) : (tensor<1xi32>) -> tensor<1xi32>
  func.return %0: tensor<1xi32>

// 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

// CHECK:           [[VAL_5:%.*]] = call @func_1_GPU_FLOAT([[VAL_0]], [[VAL_3]]) {tac.device = "GPU", tac.inference_type = "FLOAT", tac.interface_name = "func_1"} : (tensor<100xf32>, tensor<100xf32>) -> tensor<100xf32>

// CHECK:           %[[VAL_3:.*]] = "tf.LeftShift"(%[[VAL_1]], %[[VAL_0]]) : (tensor<4xi32>, tensor<1xi32>) -> tensor<4xi32>
// CHECK:           return %[[VAL_2]], %[[VAL_3]] : tensor<4xi32>, tensor<4xi32>
// CHECK:         }
func.func @broadcast_shift_left(%arg0: tensor<1xi32>, %arg1: tensor<4xi32>) -> (tensor<4xi32>, tensor<4xi32>) {

  func.return %3 : tensor<2xi32>

  // CHECK: %[[CST:.*]] = arith.constant dense<1> : tensor<2xi32>
  // CHECK: return %[[CST]] : tensor<2xi32>
}

// CHECK-LABEL: @concat_3_tensors_1_empty
func.func @concat_3_tensors_1_empty() -> tensor<?xi32> {
  %0 = arith.constant dense<1> : tensor<2xi32>
  %1 = arith.constant dense<1> : tensor<2xi32>
  %2 = arith.constant dense<[]> : tensor<0xi32>

    %s0 = "tf.Const"() {value = dense<[501, 1, 32, 1280]> : tensor<4xi32>} : () -> tensor<4xi32>
    %s1 = "tf.Const"() {value = dense<[  1, 1,  1, 1280]> : tensor<4xi32>} : () -> tensor<4xi32>

    // CHECK: "tf.BroadcastGradientArgs"
    // CHECK-NOT: _xla_outside_compilation
    %r0, %r1 = "tf.BroadcastGradientArgs"(%s0, %s1) {} : (tensor<4xi32>, tensor<4xi32>) -> (tensor<1xi32>, tensor<3xi32>)
    tf_device.return

module{
  func.func @main(%arg0: tensor<10xf32>) -> tensor<10xf32> {
    return %arg0 : tensor<10xf32>
  }
  func.func @func1(%arg0: tensor<10xf32>, %arg1: tensor<10xf32>) -> tensor<10xf32> {
    %0 = stablehlo.add %arg0, %arg1 : tensor<10xf32>
    %1 = stablehlo.add %arg0, %arg1 : tensor<10xf32>
    return %0 : tensor<10xf32>
  }
})mlir";