for i := uint64(257); i >= 256; i-- {
		dummy()
	}

	// s390x:"CLGIJ\t[$]2, R[0-9]+, [$]0, "
	for i := uint64(1024); i > 0; i-- {
		dummy()
	}
}

// Signed 32-bit compare-and-branch.
func si32(x, y chan int32) {
	// s390x:"CRJ\t[$](2|4), R[0-9]+, R[0-9]+, "
	for <-x < <-y {
		dummy()
	}

	// s390x:"CL?RJ\t[$]8, R[0-9]+, R[0-9]+, "
	for <-x == <-y {
		dummy()
	}
}

func.func @add_v2_uint32(%arg0: tensor<ui32>, %arg1: tensor<ui32>) -> tensor<ui32> {
  %0 = "tf.AddV2"(%arg0, %arg1) : (tensor<ui32>, tensor<ui32>) -> tensor<ui32>
  func.return %0 : tensor<ui32>

  // CHECK-LABEL: add_v2_uint32
  // CHECK:  %[[CAST:.*]] = "tf.Cast"(%arg0) <{Truncate = false}> : (tensor<ui32>) -> tensor<i32>
  // CHECK:  %[[CAST1:.*]] = "tf.Cast"(%arg1) <{Truncate = false}> : (tensor<ui32>) -> tensor<i32>

func.func @testUnimplementedOp() -> (tensor<i32>, tensor<i32>) {
  %0 = arith.constant dense<1> : tensor<i32>
  %1 = arith.constant dense<2> : tensor<i32>
  %2 = "tf.Maximum"(%0, %1) {_output_shapes = ["tfshape$"]} : (tensor<i32>, tensor<i32>) -> tensor<i32>
  %3 = "tf.Minimum"(%0, %1) {random_attr = "hello"} : (tensor<i32>, tensor<i32>) -> tensor<i32>

  func.return %0 : tensor<? x i32>
}

// CHECK-LABEL: testPow
func.func @testPow(tensor<? x i32>, tensor<? x i32>) -> tensor<? x i32> {
^bb0(%arg0: tensor<? x i32>, %arg1: tensor<? x i32>):
  // CHECK: tfl.pow %arg0, %arg1
  %0 = tfl.pow %arg0, %arg1 : tensor<? x i32>
  func.return %0#0 : tensor<? x i32>
}

// CHECK-LABEL: testAtan2

    %1 = func.call @WhileOp_cond(%arg0, %arg1, %cst) : (tensor<*xi32>, tensor<*xf32>, tensor<i32>) -> tensor<i1>
    "tfl.yield"(%1) : (tensor<i1>) -> ()
  },  {
  ^bb0(%arg0: tensor<*xi32>, %arg1: tensor<*xf32>):
    // CHECK: call @WhileOp_body
    // CHECK-SAME: (tensor<*xi32>, tensor<*xf32>, tensor<i32>)

  %8 = "tf.AddV2"(%arg0, %cst_2) {T = i32, device = ""} : (tensor<*xi32>, tensor<i32>) -> tensor<*xi32>
  func.return %8, %arg1, %0, %arg3, %7 : tensor<*xi32>, tensor<*xi32>, tensor<*xi32>, tensor<*xf32>, tensor<*xf32>
}

func.func @while_cond_10_frozen0(%arg0: tensor<*xi32>, %arg1: tensor<*xi32>, %arg2: tensor<*xi32>, %arg3: tensor<*xf32>, %arg4: tensor<*xf32>) -> tensor<*xi1> {

  "tf_device.replicate" (%arg0, %arg0, %arg0, %arg0, %arg0) ({
// expected-error@-1 {{'tf_device.replicate' op expects number of block arguments (2) to be equal to number of replicated inputs (3) / 'n' (3) + number of packed inputs (2)}}
  ^entry(%input0: tensor<*xi32>, %input1: tensor<*xi32>):
    tf_device.return
  }) {n = 3 : i32, operandSegmentSizes = array<i32: 3, 2>} : (tensor<*xi32>, tensor<*xi32>, tensor<*xi32>, tensor<*xi32>, tensor<*xi32>) -> ()

func.func private @unmatched_then(%x: tensor<*xi32>, %y: tensor<*xi32>) -> (tensor<*xi32>, tensor<*xi32>) {
  func.return %x, %x : tensor<*xi32>, tensor<*xi32>
}

func.func private @unmatched_else(%x: tensor<i32>, %y: tensor<i32>) -> (tensor<i32>, tensor<i32>) {
  func.return %y, %y : tensor<i32>, tensor<i32>
}

// CHECK-LABEL: unmatched_then/tfrt_dedup_results
// CHECK: return {{%.*}} : tensor<*xi32>

  %graph:2 = tf_executor.graph {
    %island:3 = tf_executor.island {
      %add1 = "tf.Add"(%arg0, %arg1) : (tensor<*xi32>, tensor<i32>) -> tensor<*xi32>
      %add2 = "tf.Add"(%add1, %arg1) : (tensor<*xi32>, tensor<i32>) -> tensor<*xi32>
      tf_executor.yield %add1, %add2 : tensor<*xi32>, tensor<*xi32>
    }
    tf_executor.fetch %island#0, %island#1 : tensor<*xi32>, tensor<*xi32>
  }

// CHECK: "tf.While"
// CHECK-SAME: (tensor<i32>, tensor<i32>, tensor<i32>, tensor<!tf_type.variant>) -> (tensor<i32>, tensor<i32>, tensor<i32>, tensor<!tf_type.variant>)

func.func @otherVariantWhileBody(%arg0: tensor<i32>, %arg1: tensor<i32>, %arg2: tensor<i32>, %arg3: tensor<!tf_type.variant>) -> (tensor<i32>, tensor<i32>, tensor<i32>, tensor<!tf_type.variant>) {
  %0 = "tf.Const"() {value = dense<1> : tensor<i32>} : () -> tensor<i32>