// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple s390x-linux-gnu -O1 -emit-llvm %s -o - \
// RUN:   | FileCheck %s
//
// Test __sync_ builtins for __int128 aligned to 16 bytes.

#include <stdint.h>

__int128 Ptr __attribute__((aligned(16)));
__int128 Val __attribute__((aligned(16)));
__int128 OldVal __attribute__((aligned(16)));

// CHECK-LABEL: @f1(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2:![0-9]+]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw add ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    store i128 [[TMP1]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f1() {
  return __sync_fetch_and_add(&Ptr, Val);
}

// CHECK-LABEL: @f2(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw sub ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    store i128 [[TMP1]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f2() {
  return __sync_fetch_and_sub(&Ptr, Val);
}

// CHECK-LABEL: @f3(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw or ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    store i128 [[TMP1]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f3() {
  return __sync_fetch_and_or(&Ptr, Val);
}

// CHECK-LABEL: @f4(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw and ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    store i128 [[TMP1]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f4() {
  return __sync_fetch_and_and(&Ptr, Val);
}

// CHECK-LABEL: @f5(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw xor ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    store i128 [[TMP1]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f5() {
  return __sync_fetch_and_xor(&Ptr, Val);
}

// CHECK-LABEL: @f6(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw nand ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    store i128 [[TMP1]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f6() {
  return __sync_fetch_and_nand(&Ptr, Val);
}

// CHECK-LABEL: @f7(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw add ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    [[TMP2:%.*]] = add i128 [[TMP1]], [[TMP0]]
// CHECK-NEXT:    store i128 [[TMP2]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f7() {
  return __sync_add_and_fetch(&Ptr, Val);
}

// CHECK-LABEL: @f8(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw sub ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    [[TMP2:%.*]] = sub i128 [[TMP1]], [[TMP0]]
// CHECK-NEXT:    store i128 [[TMP2]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f8() {
  return __sync_sub_and_fetch(&Ptr, Val);
}

// CHECK-LABEL: @f9(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw or ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    [[TMP2:%.*]] = or i128 [[TMP1]], [[TMP0]]
// CHECK-NEXT:    store i128 [[TMP2]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f9() {
  return __sync_or_and_fetch(&Ptr, Val);
}

// CHECK-LABEL: @f10(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw and ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    [[TMP2:%.*]] = and i128 [[TMP1]], [[TMP0]]
// CHECK-NEXT:    store i128 [[TMP2]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f10() {
  return __sync_and_and_fetch(&Ptr, Val);
}

// CHECK-LABEL: @f11(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw xor ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    [[TMP2:%.*]] = xor i128 [[TMP1]], [[TMP0]]
// CHECK-NEXT:    store i128 [[TMP2]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f11() {
  return __sync_xor_and_fetch(&Ptr, Val);
}

// CHECK-LABEL: @f12(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw nand ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    [[TMP2:%.*]] = and i128 [[TMP1]], [[TMP0]]
// CHECK-NEXT:    [[TMP3:%.*]] = xor i128 [[TMP2]], -1
// CHECK-NEXT:    store i128 [[TMP3]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f12() {
  return __sync_nand_and_fetch(&Ptr, Val);
}

// CHECK-LABEL: @f13(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @OldVal, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP2:%.*]] = cmpxchg ptr @Ptr, i128 [[TMP0]], i128 [[TMP1]] seq_cst seq_cst, align 16
// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { i128, i1 } [[TMP2]], 1
// CHECK-NEXT:    ret i1 [[TMP3]]
//
_Bool f13() {
  return __sync_bool_compare_and_swap(&Ptr, OldVal, Val);
}

// CHECK-LABEL: @f14(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @OldVal, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP2:%.*]] = cmpxchg ptr @Ptr, i128 [[TMP0]], i128 [[TMP1]] seq_cst seq_cst, align 16
// CHECK-NEXT:    [[TMP3:%.*]] = extractvalue { i128, i1 } [[TMP2]], 0
// CHECK-NEXT:    store i128 [[TMP3]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f14() {
  return __sync_val_compare_and_swap(&Ptr, OldVal, Val);
}

// CHECK-LABEL: @f15(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw xchg ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    store i128 [[TMP1]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f15() {
  return __sync_lock_test_and_set(&Ptr, Val);
}

// CHECK-LABEL: @f16(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    store atomic i128 0, ptr @Ptr release, align 16
// CHECK-NEXT:    ret void
//
void f16() {
  return __sync_lock_release(&Ptr);
}

// CHECK-LABEL: @f17(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[TMP0:%.*]] = load i128, ptr @Val, align 16, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = atomicrmw xchg ptr @Ptr, i128 [[TMP0]] seq_cst, align 16
// CHECK-NEXT:    store i128 [[TMP1]], ptr [[AGG_RESULT:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    ret void
//
__int128 f17() {
  return __sync_swap(&Ptr, Val);
}

// Test that a statement expression compiles.
// CHECK-LABEL: @f18(
// CHECK-NEXT:  entry:
// CHECK-NEXT:    [[T_ADDR:%.*]] = alloca i128, align 8
// CHECK-NEXT:    [[T:%.*]] = load i128, ptr [[TMP0:%.*]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    store i128 [[T]], ptr [[T_ADDR]], align 8, !tbaa [[TBAA2]]
// CHECK-NEXT:    [[TMP1:%.*]] = cmpxchg ptr [[T_ADDR]], i128 [[T]], i128 [[T]] seq_cst seq_cst, align 16
// CHECK-NEXT:    ret void
//
void f18(__int128 t) {
  __sync_bool_compare_and_swap(({int x = 1; &t;}), t, t);
}