test/OpenMP/parallel_private_codegen.cpp

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK2
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -DLAMBDA -triple x86_64-unknown-linux -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK3
// RUN: %clang_cc1 -verify -fopenmp -x c++ -fblocks -DBLOCKS -triple x86_64-unknown-linux -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK4

// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-unknown-unknown -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -std=c++11 -DLAMBDA -triple x86_64-unknown-linux -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -fblocks -DBLOCKS -triple x86_64-unknown-linux -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// expected-no-diagnostics
#ifndef HEADER
#define HEADER

enum omp_allocator_handle_t {
  omp_null_allocator = 0,
  omp_default_mem_alloc = 1,
  omp_large_cap_mem_alloc = 2,
  omp_const_mem_alloc = 3,
  omp_high_bw_mem_alloc = 4,
  omp_low_lat_mem_alloc = 5,
  omp_cgroup_mem_alloc = 6,
  omp_pteam_mem_alloc = 7,
  omp_thread_mem_alloc = 8,
  KMP_ALLOCATOR_MAX_HANDLE = __UINTPTR_MAX__
};

template <class T>
struct S {
  T f;
  S(T a) : f(a) {}
  S() : f() {}
  operator T() { return T(); }
  ~S() {}
};

volatile int g __attribute__((aligned(128))) = 1212;

struct SS {
  int a;
  int b : 4;
  int &c;
  SS(int &d) : a(0), b(0), c(d) {
#pragma omp parallel private(a, b, c)
#ifdef LAMBDA
    [&]() {
      ++this->a, --b, (this)->c /= 1;
#pragma omp parallel private(a, b, c)
      ++(this)->a, --b, this->c /= 1;
    }();
#elif defined(BLOCKS)
    ^{
      ++a;
      --this->b;
      (this)->c /= 1;
#pragma omp parallel private(a, b, c)
      ++(this)->a, --b, this->c /= 1;
    }();
#else
    ++this->a, --b, c /= 1;
#endif
  }
};

template<typename T>
struct SST {
  T a;
  SST() : a(T()) {
#pragma omp parallel private(a) allocate(omp_large_cap_mem_alloc:a)
#ifdef LAMBDA
    [&]() {
      [&]() {
        ++this->a;
#pragma omp parallel private(a)
        ++(this)->a;
      }();
    }();
#elif defined(BLOCKS)
    ^{
      ^{
        ++a;
#pragma omp parallel private(a)
        ++(this)->a;
      }();
    }();
#else
    ++(this)->a;
#endif
  }
};

template <typename T>
T tmain() {
  S<T> test;
  SST<T> sst;
  T t_var __attribute__((aligned(128))) = T();
  T vec[] __attribute__((aligned(128))) = {1, 2};
  S<T> s_arr[] __attribute__((aligned(128))) = {1, 2};
  S<T> var __attribute__((aligned(128))) (3);
#pragma omp parallel private(t_var, vec, s_arr, var)
  {
    vec[0] = t_var;
    s_arr[0] = var;
  }
  return T();
}

int main() {
  static int sivar;
  SS ss(sivar);
#ifdef LAMBDA
  [&]() {
#pragma omp parallel private(g, sivar)
  {



    g = 1;
    sivar = 2;


    [&]() {
      g = 2;
      sivar = 4;
    }();
  }
  }();
  return 0;
#elif defined(BLOCKS)
  ^{
#pragma omp parallel private(g, sivar)
  {
    g = 1;
    sivar = 20;
    ^{
      g = 2;
      sivar = 40;
    }();
  }
  }();
  return 0;


#else
  S<float> test;
  int t_var = 0;
  int vec[] = {1, 2};
  S<float> s_arr[] = {1, 2};
  S<float> var(3);
#pragma omp parallel private(t_var, vec, s_arr, var, sivar)
  {
    vec[0] = t_var;
    s_arr[0] = var;
    sivar = 3;
  }
  return tmain<int>();
#endif
}







#endif

// CHECK1-LABEL: define {{[^@]+}}@main
// CHECK1-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[SS:%.*]] = alloca [[STRUCT_SS:%.*]], align 8
// CHECK1-NEXT:    [[TEST:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK1-NEXT:    [[T_VAR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK1-NEXT:    [[S_ARR:%.*]] = alloca [2 x %struct.S], align 4
// CHECK1-NEXT:    [[VAR:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK1-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// CHECK1-NEXT:    call void @_ZN2SSC1ERi(%struct.SS* nonnull align 8 dereferenceable(16) [[SS]], i32* nonnull align 4 dereferenceable(4) @_ZZ4mainE5sivar)
// CHECK1-NEXT:    call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TEST]])
// CHECK1-NEXT:    store i32 0, i32* [[T_VAR]], align 4
// CHECK1-NEXT:    [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK1-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const.main.vec to i8*), i64 8, i1 false)
// CHECK1-NEXT:    [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i64 0, i64 0
// CHECK1-NEXT:    call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], float 1.000000e+00)
// CHECK1-NEXT:    [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYINIT_BEGIN]], i64 1
// CHECK1-NEXT:    call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], float 2.000000e+00)
// CHECK1-NEXT:    call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]], float 3.000000e+00)
// CHECK1-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 0, void (i32*, i32*, ...)* bitcast (void (i32*, i32*)* @.omp_outlined. to void (i32*, i32*, ...)*))
// CHECK1-NEXT:    [[CALL:%.*]] = call i32 @_Z5tmainIiET_v()
// CHECK1-NEXT:    store i32 [[CALL]], i32* [[RETVAL]], align 4
// CHECK1-NEXT:    call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4:[0-9]+]]
// CHECK1-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 2
// CHECK1-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1:       arraydestroy.body:
// CHECK1-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP1]], [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK1-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK1-NEXT:    call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
// CHECK1-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK1-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1:       arraydestroy.done1:
// CHECK1-NEXT:    call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK1-NEXT:    ret i32 [[TMP2]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2SSC1ERi
// CHECK1-SAME: (%struct.SS* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32* nonnull align 4 dereferenceable(4) [[D:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK1-NEXT:    [[D_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store i32* [[D]], i32** [[D_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[D_ADDR]], align 8
// CHECK1-NEXT:    call void @_ZN2SSC2ERi(%struct.SS* nonnull align 8 dereferenceable(16) [[THIS1]], i32* nonnull align 4 dereferenceable(4) [[TMP0]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    call void @_ZN1SIfEC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca float, align 4
// CHECK1-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store float [[A]], float* [[A_ADDR]], align 4
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK1-NEXT:    call void @_ZN1SIfEC2Ef(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], float [[TMP0]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[T_VAR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK1-NEXT:    [[S_ARR:%.*]] = alloca [2 x %struct.S], align 4
// CHECK1-NEXT:    [[VAR:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK1-NEXT:    [[SIVAR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i32 0, i32 0
// CHECK1-NEXT:    [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 2
// CHECK1-NEXT:    br label [[ARRAYCTOR_LOOP:%.*]]
// CHECK1:       arrayctor.loop:
// CHECK1-NEXT:    [[ARRAYCTOR_CUR:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
// CHECK1-NEXT:    call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
// CHECK1-NEXT:    [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYCTOR_CUR]], i64 1
// CHECK1-NEXT:    [[ARRAYCTOR_DONE:%.*]] = icmp eq %struct.S* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
// CHECK1-NEXT:    br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
// CHECK1:       arrayctor.cont:
// CHECK1-NEXT:    call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]])
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, i32* [[T_VAR]], align 4
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC]], i64 0, i64 0
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[ARRAYIDX]], align 4
// CHECK1-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP1:%.*]] = bitcast %struct.S* [[ARRAYIDX1]] to i8*
// CHECK1-NEXT:    [[TMP2:%.*]] = bitcast %struct.S* [[VAR]] to i8*
// CHECK1-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP1]], i8* align 4 [[TMP2]], i64 4, i1 false)
// CHECK1-NEXT:    store i32 3, i32* [[SIVAR]], align 4
// CHECK1-NEXT:    call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4]]
// CHECK1-NEXT:    [[ARRAY_BEGIN2:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN2]], i64 2
// CHECK1-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1:       arraydestroy.body:
// CHECK1-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP3]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK1-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK1-NEXT:    call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
// CHECK1-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN2]]
// CHECK1-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE3:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1:       arraydestroy.done3:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    call void @_ZN1SIfED2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z5tmainIiET_v
// CHECK1-SAME: () #[[ATTR5:[0-9]+]] comdat {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[TEST:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK1-NEXT:    [[SST:%.*]] = alloca [[STRUCT_SST:%.*]], align 4
// CHECK1-NEXT:    [[T_VAR:%.*]] = alloca i32, align 128
// CHECK1-NEXT:    [[VEC:%.*]] = alloca [2 x i32], align 128
// CHECK1-NEXT:    [[S_ARR:%.*]] = alloca [2 x %struct.S.0], align 128
// CHECK1-NEXT:    [[VAR:%.*]] = alloca [[STRUCT_S_0]], align 128
// CHECK1-NEXT:    call void @_ZN1SIiEC1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]])
// CHECK1-NEXT:    call void @_ZN3SSTIiEC1Ev(%struct.SST* nonnull align 4 dereferenceable(4) [[SST]])
// CHECK1-NEXT:    store i32 0, i32* [[T_VAR]], align 128
// CHECK1-NEXT:    [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK1-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 128 [[TMP0]], i8* align 128 bitcast ([2 x i32]* @__const._Z5tmainIiET_v.vec to i8*), i64 8, i1 false)
// CHECK1-NEXT:    [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i64 0, i64 0
// CHECK1-NEXT:    call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], i32 1)
// CHECK1-NEXT:    [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYINIT_BEGIN]], i64 1
// CHECK1-NEXT:    call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], i32 2)
// CHECK1-NEXT:    call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR]], i32 3)
// CHECK1-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 0, void (i32*, i32*, ...)* bitcast (void (i32*, i32*)* @.omp_outlined..2 to void (i32*, i32*, ...)*))
// CHECK1-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// CHECK1-NEXT:    call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4]]
// CHECK1-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i64 2
// CHECK1-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1:       arraydestroy.body:
// CHECK1-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP1]], [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK1-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK1-NEXT:    call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
// CHECK1-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK1-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1:       arraydestroy.done1:
// CHECK1-NEXT:    call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK1-NEXT:    ret i32 [[TMP2]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2SSC2ERi
// CHECK1-SAME: (%struct.SS* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32* nonnull align 4 dereferenceable(4) [[D:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK1-NEXT:    [[D_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store i32* [[D]], i32** [[D_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_SS:%.*]], %struct.SS* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    store i32 0, i32* [[A]], align 8
// CHECK1-NEXT:    [[B:%.*]] = getelementptr inbounds [[STRUCT_SS]], %struct.SS* [[THIS1]], i32 0, i32 1
// CHECK1-NEXT:    [[BF_LOAD:%.*]] = load i8, i8* [[B]], align 4
// CHECK1-NEXT:    [[BF_CLEAR:%.*]] = and i8 [[BF_LOAD]], -16
// CHECK1-NEXT:    store i8 [[BF_CLEAR]], i8* [[B]], align 4
// CHECK1-NEXT:    [[C:%.*]] = getelementptr inbounds [[STRUCT_SS]], %struct.SS* [[THIS1]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[D_ADDR]], align 8
// CHECK1-NEXT:    store i32* [[TMP0]], i32** [[C]], align 8
// CHECK1-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.SS*)* @.omp_outlined..1 to void (i32*, i32*, ...)*), %struct.SS* [[THIS1]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..1
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.SS* [[THIS:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK1-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[TMP:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[B:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[C:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[_TMP1:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store i32* [[A]], i32** [[TMP]], align 8
// CHECK1-NEXT:    store i32* [[C]], i32** [[_TMP1]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[TMP1]], align 4
// CHECK1-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP2]], 1
// CHECK1-NEXT:    store i32 [[INC]], i32* [[TMP1]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load i32, i32* [[B]], align 4
// CHECK1-NEXT:    [[DEC:%.*]] = add nsw i32 [[TMP3]], -1
// CHECK1-NEXT:    store i32 [[DEC]], i32* [[B]], align 4
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32*, i32** [[_TMP1]], align 8
// CHECK1-NEXT:    [[TMP5:%.*]] = load i32, i32* [[TMP4]], align 4
// CHECK1-NEXT:    [[DIV:%.*]] = sdiv i32 [[TMP5]], 1
// CHECK1-NEXT:    store i32 [[DIV]], i32* [[TMP4]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    store float 0.000000e+00, float* [[F]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca float, align 4
// CHECK1-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store float [[A]], float* [[A_ADDR]], align 4
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK1-NEXT:    store float [[TMP0]], float* [[F]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ev
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    call void @_ZN1SIiEC2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN3SSTIiEC1Ev
// CHECK1-SAME: (%struct.SST* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SST*, align 8
// CHECK1-NEXT:    store %struct.SST* [[THIS]], %struct.SST** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.SST*, %struct.SST** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    call void @_ZN3SSTIiEC2Ev(%struct.SST* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ei
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK1-NEXT:    call void @_ZN1SIiEC2Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]], i32 [[TMP0]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..2
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[T_VAR:%.*]] = alloca i32, align 128
// CHECK1-NEXT:    [[VEC:%.*]] = alloca [2 x i32], align 128
// CHECK1-NEXT:    [[S_ARR:%.*]] = alloca [2 x %struct.S.0], align 128
// CHECK1-NEXT:    [[VAR:%.*]] = alloca [[STRUCT_S_0:%.*]], align 128
// CHECK1-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK1-NEXT:    [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i64 2
// CHECK1-NEXT:    br label [[ARRAYCTOR_LOOP:%.*]]
// CHECK1:       arrayctor.loop:
// CHECK1-NEXT:    [[ARRAYCTOR_CUR:%.*]] = phi %struct.S.0* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
// CHECK1-NEXT:    call void @_ZN1SIiEC1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
// CHECK1-NEXT:    [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYCTOR_CUR]], i64 1
// CHECK1-NEXT:    [[ARRAYCTOR_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
// CHECK1-NEXT:    br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
// CHECK1:       arrayctor.cont:
// CHECK1-NEXT:    call void @_ZN1SIiEC1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR]])
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, i32* [[T_VAR]], align 128
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC]], i64 0, i64 0
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[ARRAYIDX]], align 128
// CHECK1-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP1:%.*]] = bitcast %struct.S.0* [[ARRAYIDX1]] to i8*
// CHECK1-NEXT:    [[TMP2:%.*]] = bitcast %struct.S.0* [[VAR]] to i8*
// CHECK1-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 128 [[TMP1]], i8* align 128 [[TMP2]], i64 4, i1 false)
// CHECK1-NEXT:    call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4]]
// CHECK1-NEXT:    [[ARRAY_BEGIN2:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN2]], i64 2
// CHECK1-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1:       arraydestroy.body:
// CHECK1-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP3]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK1-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK1-NEXT:    call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
// CHECK1-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN2]]
// CHECK1-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE3:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1:       arraydestroy.done3:
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiED1Ev
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    call void @_ZN1SIiED2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ev
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    store i32 0, i32* [[F]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN3SSTIiEC2Ev
// CHECK1-SAME: (%struct.SST* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SST*, align 8
// CHECK1-NEXT:    store %struct.SST* [[THIS]], %struct.SST** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.SST*, %struct.SST** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_SST:%.*]], %struct.SST* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    store i32 0, i32* [[A]], align 4
// CHECK1-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.SST*)* @.omp_outlined..3 to void (i32*, i32*, ...)*), %struct.SST* [[THIS1]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..3
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.SST* [[THIS:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SST*, align 8
// CHECK1-NEXT:    [[TMP:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT:    store %struct.SST* [[THIS]], %struct.SST** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load %struct.SST*, %struct.SST** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[TMP1]], align 4
// CHECK1-NEXT:    [[DOTA__VOID_ADDR:%.*]] = call i8* @__kmpc_alloc(i32 [[TMP2]], i64 4, i8* inttoptr (i64 2 to i8*))
// CHECK1-NEXT:    [[DOTA__ADDR:%.*]] = bitcast i8* [[DOTA__VOID_ADDR]] to i32*
// CHECK1-NEXT:    store i32* [[DOTA__ADDR]], i32** [[TMP]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4
// CHECK1-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP4]], 1
// CHECK1-NEXT:    store i32 [[INC]], i32* [[TMP3]], align 4
// CHECK1-NEXT:    [[TMP5:%.*]] = bitcast i32* [[DOTA__ADDR]] to i8*
// CHECK1-NEXT:    call void @__kmpc_free(i32 [[TMP2]], i8* [[TMP5]], i8* inttoptr (i64 2 to i8*))
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ei
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[F]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiED2Ev
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@main
// CHECK2-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[SS:%.*]] = alloca [[STRUCT_SS:%.*]], align 8
// CHECK2-NEXT:    [[TEST:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK2-NEXT:    [[T_VAR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK2-NEXT:    [[S_ARR:%.*]] = alloca [2 x %struct.S], align 4
// CHECK2-NEXT:    [[VAR:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK2-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// CHECK2-NEXT:    call void @_ZN2SSC1ERi(%struct.SS* nonnull align 8 dereferenceable(16) [[SS]], i32* nonnull align 4 dereferenceable(4) @_ZZ4mainE5sivar)
// CHECK2-NEXT:    call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TEST]])
// CHECK2-NEXT:    store i32 0, i32* [[T_VAR]], align 4
// CHECK2-NEXT:    [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK2-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const.main.vec to i8*), i64 8, i1 false)
// CHECK2-NEXT:    [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i64 0, i64 0
// CHECK2-NEXT:    call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], float 1.000000e+00)
// CHECK2-NEXT:    [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYINIT_BEGIN]], i64 1
// CHECK2-NEXT:    call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], float 2.000000e+00)
// CHECK2-NEXT:    call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]], float 3.000000e+00)
// CHECK2-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 0, void (i32*, i32*, ...)* bitcast (void (i32*, i32*)* @.omp_outlined. to void (i32*, i32*, ...)*))
// CHECK2-NEXT:    [[CALL:%.*]] = call i32 @_Z5tmainIiET_v()
// CHECK2-NEXT:    store i32 [[CALL]], i32* [[RETVAL]], align 4
// CHECK2-NEXT:    call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4:[0-9]+]]
// CHECK2-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 2
// CHECK2-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2:       arraydestroy.body:
// CHECK2-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP1]], [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK2-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK2-NEXT:    call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
// CHECK2-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK2-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2:       arraydestroy.done1:
// CHECK2-NEXT:    call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK2-NEXT:    ret i32 [[TMP2]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2SSC1ERi
// CHECK2-SAME: (%struct.SS* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32* nonnull align 4 dereferenceable(4) [[D:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK2-NEXT:    [[D_ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    store i32* [[D]], i32** [[D_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[D_ADDR]], align 8
// CHECK2-NEXT:    call void @_ZN2SSC2ERi(%struct.SS* nonnull align 8 dereferenceable(16) [[THIS1]], i32* nonnull align 4 dereferenceable(4) [[TMP0]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    call void @_ZN1SIfEC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT:    [[A_ADDR:%.*]] = alloca float, align 4
// CHECK2-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    store float [[A]], float* [[A_ADDR]], align 4
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK2-NEXT:    call void @_ZN1SIfEC2Ef(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], float [[TMP0]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[T_VAR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK2-NEXT:    [[S_ARR:%.*]] = alloca [2 x %struct.S], align 4
// CHECK2-NEXT:    [[VAR:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK2-NEXT:    [[SIVAR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i32 0, i32 0
// CHECK2-NEXT:    [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 2
// CHECK2-NEXT:    br label [[ARRAYCTOR_LOOP:%.*]]
// CHECK2:       arrayctor.loop:
// CHECK2-NEXT:    [[ARRAYCTOR_CUR:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
// CHECK2-NEXT:    call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
// CHECK2-NEXT:    [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYCTOR_CUR]], i64 1
// CHECK2-NEXT:    [[ARRAYCTOR_DONE:%.*]] = icmp eq %struct.S* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
// CHECK2-NEXT:    br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
// CHECK2:       arrayctor.cont:
// CHECK2-NEXT:    call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]])
// CHECK2-NEXT:    [[TMP0:%.*]] = load i32, i32* [[T_VAR]], align 4
// CHECK2-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC]], i64 0, i64 0
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[ARRAYIDX]], align 4
// CHECK2-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i64 0, i64 0
// CHECK2-NEXT:    [[TMP1:%.*]] = bitcast %struct.S* [[ARRAYIDX1]] to i8*
// CHECK2-NEXT:    [[TMP2:%.*]] = bitcast %struct.S* [[VAR]] to i8*
// CHECK2-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP1]], i8* align 4 [[TMP2]], i64 4, i1 false)
// CHECK2-NEXT:    store i32 3, i32* [[SIVAR]], align 4
// CHECK2-NEXT:    call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4]]
// CHECK2-NEXT:    [[ARRAY_BEGIN2:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN2]], i64 2
// CHECK2-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2:       arraydestroy.body:
// CHECK2-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP3]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK2-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK2-NEXT:    call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
// CHECK2-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN2]]
// CHECK2-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE3:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2:       arraydestroy.done3:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    call void @_ZN1SIfED2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z5tmainIiET_v
// CHECK2-SAME: () #[[ATTR5:[0-9]+]] comdat {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[TEST:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK2-NEXT:    [[SST:%.*]] = alloca [[STRUCT_SST:%.*]], align 4
// CHECK2-NEXT:    [[T_VAR:%.*]] = alloca i32, align 128
// CHECK2-NEXT:    [[VEC:%.*]] = alloca [2 x i32], align 128
// CHECK2-NEXT:    [[S_ARR:%.*]] = alloca [2 x %struct.S.0], align 128
// CHECK2-NEXT:    [[VAR:%.*]] = alloca [[STRUCT_S_0]], align 128
// CHECK2-NEXT:    call void @_ZN1SIiEC1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]])
// CHECK2-NEXT:    call void @_ZN3SSTIiEC1Ev(%struct.SST* nonnull align 4 dereferenceable(4) [[SST]])
// CHECK2-NEXT:    store i32 0, i32* [[T_VAR]], align 128
// CHECK2-NEXT:    [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK2-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 128 [[TMP0]], i8* align 128 bitcast ([2 x i32]* @__const._Z5tmainIiET_v.vec to i8*), i64 8, i1 false)
// CHECK2-NEXT:    [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i64 0, i64 0
// CHECK2-NEXT:    call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], i32 1)
// CHECK2-NEXT:    [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYINIT_BEGIN]], i64 1
// CHECK2-NEXT:    call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], i32 2)
// CHECK2-NEXT:    call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR]], i32 3)
// CHECK2-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 0, void (i32*, i32*, ...)* bitcast (void (i32*, i32*)* @.omp_outlined..2 to void (i32*, i32*, ...)*))
// CHECK2-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// CHECK2-NEXT:    call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4]]
// CHECK2-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i64 2
// CHECK2-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2:       arraydestroy.body:
// CHECK2-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP1]], [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK2-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK2-NEXT:    call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
// CHECK2-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK2-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2:       arraydestroy.done1:
// CHECK2-NEXT:    call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK2-NEXT:    ret i32 [[TMP2]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2SSC2ERi
// CHECK2-SAME: (%struct.SS* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32* nonnull align 4 dereferenceable(4) [[D:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK2-NEXT:    [[D_ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    store i32* [[D]], i32** [[D_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_SS:%.*]], %struct.SS* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT:    store i32 0, i32* [[A]], align 8
// CHECK2-NEXT:    [[B:%.*]] = getelementptr inbounds [[STRUCT_SS]], %struct.SS* [[THIS1]], i32 0, i32 1
// CHECK2-NEXT:    [[BF_LOAD:%.*]] = load i8, i8* [[B]], align 4
// CHECK2-NEXT:    [[BF_CLEAR:%.*]] = and i8 [[BF_LOAD]], -16
// CHECK2-NEXT:    store i8 [[BF_CLEAR]], i8* [[B]], align 4
// CHECK2-NEXT:    [[C:%.*]] = getelementptr inbounds [[STRUCT_SS]], %struct.SS* [[THIS1]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[D_ADDR]], align 8
// CHECK2-NEXT:    store i32* [[TMP0]], i32** [[C]], align 8
// CHECK2-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.SS*)* @.omp_outlined..1 to void (i32*, i32*, ...)*), %struct.SS* [[THIS1]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..1
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.SS* [[THIS:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK2-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[TMP:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[B:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[C:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[_TMP1:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[TMP0:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    store i32* [[A]], i32** [[TMP]], align 8
// CHECK2-NEXT:    store i32* [[C]], i32** [[_TMP1]], align 8
// CHECK2-NEXT:    [[TMP1:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[TMP1]], align 4
// CHECK2-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP2]], 1
// CHECK2-NEXT:    store i32 [[INC]], i32* [[TMP1]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load i32, i32* [[B]], align 4
// CHECK2-NEXT:    [[DEC:%.*]] = add nsw i32 [[TMP3]], -1
// CHECK2-NEXT:    store i32 [[DEC]], i32* [[B]], align 4
// CHECK2-NEXT:    [[TMP4:%.*]] = load i32*, i32** [[_TMP1]], align 8
// CHECK2-NEXT:    [[TMP5:%.*]] = load i32, i32* [[TMP4]], align 4
// CHECK2-NEXT:    [[DIV:%.*]] = sdiv i32 [[TMP5]], 1
// CHECK2-NEXT:    store i32 [[DIV]], i32* [[TMP4]], align 4
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT:    store float 0.000000e+00, float* [[F]], align 4
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT:    [[A_ADDR:%.*]] = alloca float, align 4
// CHECK2-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    store float [[A]], float* [[A_ADDR]], align 4
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK2-NEXT:    store float [[TMP0]], float* [[F]], align 4
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ev
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    call void @_ZN1SIiEC2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN3SSTIiEC1Ev
// CHECK2-SAME: (%struct.SST* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SST*, align 8
// CHECK2-NEXT:    store %struct.SST* [[THIS]], %struct.SST** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.SST*, %struct.SST** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    call void @_ZN3SSTIiEC2Ev(%struct.SST* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ei
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    call void @_ZN1SIiEC2Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]], i32 [[TMP0]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..2
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[T_VAR:%.*]] = alloca i32, align 128
// CHECK2-NEXT:    [[VEC:%.*]] = alloca [2 x i32], align 128
// CHECK2-NEXT:    [[S_ARR:%.*]] = alloca [2 x %struct.S.0], align 128
// CHECK2-NEXT:    [[VAR:%.*]] = alloca [[STRUCT_S_0:%.*]], align 128
// CHECK2-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK2-NEXT:    [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i64 2
// CHECK2-NEXT:    br label [[ARRAYCTOR_LOOP:%.*]]
// CHECK2:       arrayctor.loop:
// CHECK2-NEXT:    [[ARRAYCTOR_CUR:%.*]] = phi %struct.S.0* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
// CHECK2-NEXT:    call void @_ZN1SIiEC1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
// CHECK2-NEXT:    [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYCTOR_CUR]], i64 1
// CHECK2-NEXT:    [[ARRAYCTOR_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
// CHECK2-NEXT:    br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
// CHECK2:       arrayctor.cont:
// CHECK2-NEXT:    call void @_ZN1SIiEC1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR]])
// CHECK2-NEXT:    [[TMP0:%.*]] = load i32, i32* [[T_VAR]], align 128
// CHECK2-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC]], i64 0, i64 0
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[ARRAYIDX]], align 128
// CHECK2-NEXT:    [[ARRAYIDX1:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i64 0, i64 0
// CHECK2-NEXT:    [[TMP1:%.*]] = bitcast %struct.S.0* [[ARRAYIDX1]] to i8*
// CHECK2-NEXT:    [[TMP2:%.*]] = bitcast %struct.S.0* [[VAR]] to i8*
// CHECK2-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 128 [[TMP1]], i8* align 128 [[TMP2]], i64 4, i1 false)
// CHECK2-NEXT:    call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4]]
// CHECK2-NEXT:    [[ARRAY_BEGIN2:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN2]], i64 2
// CHECK2-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2:       arraydestroy.body:
// CHECK2-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP3]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK2-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK2-NEXT:    call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
// CHECK2-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN2]]
// CHECK2-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE3:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2:       arraydestroy.done3:
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiED1Ev
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    call void @_ZN1SIiED2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ev
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT:    store i32 0, i32* [[F]], align 4
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN3SSTIiEC2Ev
// CHECK2-SAME: (%struct.SST* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SST*, align 8
// CHECK2-NEXT:    store %struct.SST* [[THIS]], %struct.SST** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.SST*, %struct.SST** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_SST:%.*]], %struct.SST* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT:    store i32 0, i32* [[A]], align 4
// CHECK2-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.SST*)* @.omp_outlined..3 to void (i32*, i32*, ...)*), %struct.SST* [[THIS1]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..3
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.SST* [[THIS:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SST*, align 8
// CHECK2-NEXT:    [[TMP:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT:    store %struct.SST* [[THIS]], %struct.SST** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[TMP0:%.*]] = load %struct.SST*, %struct.SST** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[TMP1:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[TMP1]], align 4
// CHECK2-NEXT:    [[DOTA__VOID_ADDR:%.*]] = call i8* @__kmpc_alloc(i32 [[TMP2]], i64 4, i8* inttoptr (i64 2 to i8*))
// CHECK2-NEXT:    [[DOTA__ADDR:%.*]] = bitcast i8* [[DOTA__VOID_ADDR]] to i32*
// CHECK2-NEXT:    store i32* [[DOTA__ADDR]], i32** [[TMP]], align 8
// CHECK2-NEXT:    [[TMP3:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4
// CHECK2-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP4]], 1
// CHECK2-NEXT:    store i32 [[INC]], i32* [[TMP3]], align 4
// CHECK2-NEXT:    [[TMP5:%.*]] = bitcast i32* [[DOTA__ADDR]] to i8*
// CHECK2-NEXT:    call void @__kmpc_free(i32 [[TMP2]], i8* [[TMP5]], i8* inttoptr (i64 2 to i8*))
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ei
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT:    [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[F]], align 4
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiED2Ev
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT:    store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@main
// CHECK3-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[SS:%.*]] = alloca [[STRUCT_SS:%.*]], align 8
// CHECK3-NEXT:    [[REF_TMP:%.*]] = alloca [[CLASS_ANON:%.*]], align 1
// CHECK3-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// CHECK3-NEXT:    call void @_ZN2SSC1ERi(%struct.SS* nonnull align 8 dereferenceable(16) [[SS]], i32* nonnull align 4 dereferenceable(4) @_ZZ4mainE5sivar)
// CHECK3-NEXT:    call void @"_ZZ4mainENK3$_0clEv"(%class.anon* nonnull align 1 dereferenceable(1) [[REF_TMP]])
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2SSC1ERi
// CHECK3-SAME: (%struct.SS* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32* nonnull align 4 dereferenceable(4) [[D:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] comdat align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK3-NEXT:    [[D_ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    store i32* [[D]], i32** [[D_ADDR]], align 8
// CHECK3-NEXT:    [[THIS1:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[D_ADDR]], align 8
// CHECK3-NEXT:    call void @_ZN2SSC2ERi(%struct.SS* nonnull align 8 dereferenceable(16) [[THIS1]], i32* nonnull align 4 dereferenceable(4) [[TMP0]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2SSC2ERi
// CHECK3-SAME: (%struct.SS* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32* nonnull align 4 dereferenceable(4) [[D:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK3-NEXT:    [[D_ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    store i32* [[D]], i32** [[D_ADDR]], align 8
// CHECK3-NEXT:    [[THIS1:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_SS:%.*]], %struct.SS* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT:    store i32 0, i32* [[A]], align 8
// CHECK3-NEXT:    [[B:%.*]] = getelementptr inbounds [[STRUCT_SS]], %struct.SS* [[THIS1]], i32 0, i32 1
// CHECK3-NEXT:    [[BF_LOAD:%.*]] = load i8, i8* [[B]], align 4
// CHECK3-NEXT:    [[BF_CLEAR:%.*]] = and i8 [[BF_LOAD]], -16
// CHECK3-NEXT:    store i8 [[BF_CLEAR]], i8* [[B]], align 4
// CHECK3-NEXT:    [[C:%.*]] = getelementptr inbounds [[STRUCT_SS]], %struct.SS* [[THIS1]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[D_ADDR]], align 8
// CHECK3-NEXT:    store i32* [[TMP0]], i32** [[C]], align 8
// CHECK3-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.SS*)* @.omp_outlined. to void (i32*, i32*, ...)*), %struct.SS* [[THIS1]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.SS* [[THIS:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK3-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[TMP:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[B:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[C:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[_TMP1:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[REF_TMP:%.*]] = alloca [[CLASS_ANON_0:%.*]], align 8
// CHECK3-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK3-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK3-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[TMP0:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    store i32* [[A]], i32** [[TMP]], align 8
// CHECK3-NEXT:    store i32* [[C]], i32** [[_TMP1]], align 8
// CHECK3-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 0
// CHECK3-NEXT:    store %struct.SS* [[TMP0]], %struct.SS** [[TMP1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 1
// CHECK3-NEXT:    [[TMP3:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK3-NEXT:    store i32* [[TMP3]], i32** [[TMP2]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 2
// CHECK3-NEXT:    store i32* [[B]], i32** [[TMP4]], align 8
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 3
// CHECK3-NEXT:    [[TMP6:%.*]] = load i32*, i32** [[_TMP1]], align 8
// CHECK3-NEXT:    store i32* [[TMP6]], i32** [[TMP5]], align 8
// CHECK3-NEXT:    call void @_ZZN2SSC1ERiENKUlvE_clEv(%class.anon.0* nonnull align 8 dereferenceable(32) [[REF_TMP]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZZN2SSC1ERiENKUlvE_clEv
// CHECK3-SAME: (%class.anon.0* nonnull align 8 dereferenceable(32) [[THIS:%.*]]) #[[ATTR2:[0-9]+]] align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %class.anon.0*, align 8
// CHECK3-NEXT:    store %class.anon.0* [[THIS]], %class.anon.0** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[THIS1:%.*]] = load %class.anon.0*, %class.anon.0** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [[CLASS_ANON_0:%.*]], %class.anon.0* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP1:%.*]] = load %struct.SS*, %struct.SS** [[TMP0]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[THIS1]], i32 0, i32 1
// CHECK3-NEXT:    [[TMP3:%.*]] = load i32*, i32** [[TMP2]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4
// CHECK3-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP4]], 1
// CHECK3-NEXT:    store i32 [[INC]], i32* [[TMP3]], align 4
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[THIS1]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = load i32*, i32** [[TMP5]], align 8
// CHECK3-NEXT:    [[TMP7:%.*]] = load i32, i32* [[TMP6]], align 4
// CHECK3-NEXT:    [[DEC:%.*]] = add nsw i32 [[TMP7]], -1
// CHECK3-NEXT:    store i32 [[DEC]], i32* [[TMP6]], align 4
// CHECK3-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[THIS1]], i32 0, i32 3
// CHECK3-NEXT:    [[TMP9:%.*]] = load i32*, i32** [[TMP8]], align 8
// CHECK3-NEXT:    [[TMP10:%.*]] = load i32, i32* [[TMP9]], align 4
// CHECK3-NEXT:    [[DIV:%.*]] = sdiv i32 [[TMP10]], 1
// CHECK3-NEXT:    store i32 [[DIV]], i32* [[TMP9]], align 4
// CHECK3-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.SS*)* @.omp_outlined..1 to void (i32*, i32*, ...)*), %struct.SS* [[TMP1]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_outlined..1
// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.SS* [[THIS:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK3-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[TMP:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[B:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[C:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[_TMP1:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK3-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK3-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[TMP0:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    store i32* [[A]], i32** [[TMP]], align 8
// CHECK3-NEXT:    store i32* [[C]], i32** [[_TMP1]], align 8
// CHECK3-NEXT:    [[TMP1:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[TMP1]], align 4
// CHECK3-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP2]], 1
// CHECK3-NEXT:    store i32 [[INC]], i32* [[TMP1]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load i32, i32* [[B]], align 4
// CHECK3-NEXT:    [[DEC:%.*]] = add nsw i32 [[TMP3]], -1
// CHECK3-NEXT:    store i32 [[DEC]], i32* [[B]], align 4
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32*, i32** [[_TMP1]], align 8
// CHECK3-NEXT:    [[TMP5:%.*]] = load i32, i32* [[TMP4]], align 4
// CHECK3-NEXT:    [[DIV:%.*]] = sdiv i32 [[TMP5]], 1
// CHECK3-NEXT:    store i32 [[DIV]], i32* [[TMP4]], align 4
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_outlined..2
// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[G:%.*]] = alloca i32, align 128
// CHECK3-NEXT:    [[SIVAR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[REF_TMP:%.*]] = alloca [[CLASS_ANON_1:%.*]], align 8
// CHECK3-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK3-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK3-NEXT:    store i32 1, i32* [[G]], align 128
// CHECK3-NEXT:    store i32 2, i32* [[SIVAR]], align 4
// CHECK3-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [[CLASS_ANON_1]], %class.anon.1* [[REF_TMP]], i32 0, i32 0
// CHECK3-NEXT:    store i32* [[G]], i32** [[TMP0]], align 8
// CHECK3-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [[CLASS_ANON_1]], %class.anon.1* [[REF_TMP]], i32 0, i32 1
// CHECK3-NEXT:    store i32* [[SIVAR]], i32** [[TMP1]], align 8
// CHECK3-NEXT:    call void @"_ZZZ4mainENK3$_0clEvENKUlvE_clEv"(%class.anon.1* nonnull align 8 dereferenceable(16) [[REF_TMP]])
// CHECK3-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@main
// CHECK4-SAME: () #[[ATTR1:[0-9]+]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[SS:%.*]] = alloca [[STRUCT_SS:%.*]], align 8
// CHECK4-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// CHECK4-NEXT:    call void @_ZN2SSC1ERi(%struct.SS* nonnull align 8 dereferenceable(16) [[SS]], i32* nonnull align 4 dereferenceable(4) @_ZZ4mainE5sivar)
// CHECK4-NEXT:    [[TMP0:%.*]] = load i8*, i8** getelementptr inbounds ([[STRUCT___BLOCK_LITERAL_GENERIC:%.*]], %struct.__block_literal_generic* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global to %struct.__block_literal_generic*), i32 0, i32 3), align 8
// CHECK4-NEXT:    [[TMP1:%.*]] = bitcast i8* [[TMP0]] to void (i8*)*
// CHECK4-NEXT:    call void [[TMP1]](i8* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global to i8*))
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN2SSC1ERi
// CHECK4-SAME: (%struct.SS* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32* nonnull align 4 dereferenceable(4) [[D:%.*]]) unnamed_addr #[[ATTR2:[0-9]+]] comdat align 2 {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK4-NEXT:    [[D_ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    store i32* [[D]], i32** [[D_ADDR]], align 8
// CHECK4-NEXT:    [[THIS1:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[D_ADDR]], align 8
// CHECK4-NEXT:    call void @_ZN2SSC2ERi(%struct.SS* nonnull align 8 dereferenceable(16) [[THIS1]], i32* nonnull align 4 dereferenceable(4) [[TMP0]])
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@__main_block_invoke
// CHECK4-SAME: (i8* [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR2]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[BLOCK_ADDR:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>*, align 8
// CHECK4-NEXT:    store i8* [[DOTBLOCK_DESCRIPTOR]], i8** [[DOTBLOCK_DESCRIPTOR_ADDR]], align 8
// CHECK4-NEXT:    [[BLOCK:%.*]] = bitcast i8* [[DOTBLOCK_DESCRIPTOR]] to <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>*
// CHECK4-NEXT:    store <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>* [[BLOCK]], <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>** [[BLOCK_ADDR]], align 8
// CHECK4-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 0, void (i32*, i32*, ...)* bitcast (void (i32*, i32*)* @.omp_outlined. to void (i32*, i32*, ...)*))
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK4-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[G:%.*]] = alloca i32, align 128
// CHECK4-NEXT:    [[SIVAR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[BLOCK:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>, align 128
// CHECK4-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK4-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK4-NEXT:    store i32 1, i32* [[G]], align 128
// CHECK4-NEXT:    store i32 20, i32* [[SIVAR]], align 4
// CHECK4-NEXT:    [[BLOCK_ISA:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]], i32 0, i32 0
// CHECK4-NEXT:    store i8* bitcast (i8** @_NSConcreteStackBlock to i8*), i8** [[BLOCK_ISA]], align 128
// CHECK4-NEXT:    [[BLOCK_FLAGS:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]], i32 0, i32 1
// CHECK4-NEXT:    store i32 1073741824, i32* [[BLOCK_FLAGS]], align 8
// CHECK4-NEXT:    [[BLOCK_RESERVED:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]], i32 0, i32 2
// CHECK4-NEXT:    store i32 0, i32* [[BLOCK_RESERVED]], align 4
// CHECK4-NEXT:    [[BLOCK_INVOKE:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]], i32 0, i32 3
// CHECK4-NEXT:    store i8* bitcast (void (i8*)* @g_block_invoke to i8*), i8** [[BLOCK_INVOKE]], align 16
// CHECK4-NEXT:    [[BLOCK_DESCRIPTOR:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]], i32 0, i32 4
// CHECK4-NEXT:    store %struct.__block_descriptor* bitcast ({ i64, i64, i8*, i8* }* @__block_descriptor_tmp.1 to %struct.__block_descriptor*), %struct.__block_descriptor** [[BLOCK_DESCRIPTOR]], align 8
// CHECK4-NEXT:    [[BLOCK_CAPTURED:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]], i32 0, i32 7
// CHECK4-NEXT:    [[TMP0:%.*]] = load volatile i32, i32* [[G]], align 128
// CHECK4-NEXT:    store volatile i32 [[TMP0]], i32* [[BLOCK_CAPTURED]], align 128
// CHECK4-NEXT:    [[BLOCK_CAPTURED1:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]], i32 0, i32 5
// CHECK4-NEXT:    [[TMP1:%.*]] = load i32, i32* [[SIVAR]], align 4
// CHECK4-NEXT:    store i32 [[TMP1]], i32* [[BLOCK_CAPTURED1]], align 32
// CHECK4-NEXT:    [[TMP2:%.*]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]] to void ()*
// CHECK4-NEXT:    [[BLOCK_LITERAL:%.*]] = bitcast void ()* [[TMP2]] to %struct.__block_literal_generic*
// CHECK4-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT___BLOCK_LITERAL_GENERIC:%.*]], %struct.__block_literal_generic* [[BLOCK_LITERAL]], i32 0, i32 3
// CHECK4-NEXT:    [[TMP4:%.*]] = bitcast %struct.__block_literal_generic* [[BLOCK_LITERAL]] to i8*
// CHECK4-NEXT:    [[TMP5:%.*]] = load i8*, i8** [[TMP3]], align 8
// CHECK4-NEXT:    [[TMP6:%.*]] = bitcast i8* [[TMP5]] to void (i8*)*
// CHECK4-NEXT:    call void [[TMP6]](i8* [[TMP4]])
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@g_block_invoke
// CHECK4-SAME: (i8* [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR2]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[BLOCK_ADDR:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>*, align 8
// CHECK4-NEXT:    store i8* [[DOTBLOCK_DESCRIPTOR]], i8** [[DOTBLOCK_DESCRIPTOR_ADDR]], align 8
// CHECK4-NEXT:    [[BLOCK:%.*]] = bitcast i8* [[DOTBLOCK_DESCRIPTOR]] to <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>*
// CHECK4-NEXT:    store <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]], <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>** [[BLOCK_ADDR]], align 8
// CHECK4-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]], i32 0, i32 7
// CHECK4-NEXT:    store i32 2, i32* [[BLOCK_CAPTURE_ADDR]], align 128
// CHECK4-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, i32, [92 x i8], i32 }>* [[BLOCK]], i32 0, i32 5
// CHECK4-NEXT:    store i32 40, i32* [[BLOCK_CAPTURE_ADDR1]], align 32
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN2SSC2ERi
// CHECK4-SAME: (%struct.SS* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32* nonnull align 4 dereferenceable(4) [[D:%.*]]) unnamed_addr #[[ATTR2]] comdat align 2 {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK4-NEXT:    [[D_ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    store i32* [[D]], i32** [[D_ADDR]], align 8
// CHECK4-NEXT:    [[THIS1:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_SS:%.*]], %struct.SS* [[THIS1]], i32 0, i32 0
// CHECK4-NEXT:    store i32 0, i32* [[A]], align 8
// CHECK4-NEXT:    [[B:%.*]] = getelementptr inbounds [[STRUCT_SS]], %struct.SS* [[THIS1]], i32 0, i32 1
// CHECK4-NEXT:    [[BF_LOAD:%.*]] = load i8, i8* [[B]], align 4
// CHECK4-NEXT:    [[BF_CLEAR:%.*]] = and i8 [[BF_LOAD]], -16
// CHECK4-NEXT:    store i8 [[BF_CLEAR]], i8* [[B]], align 4
// CHECK4-NEXT:    [[C:%.*]] = getelementptr inbounds [[STRUCT_SS]], %struct.SS* [[THIS1]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[D_ADDR]], align 8
// CHECK4-NEXT:    store i32* [[TMP0]], i32** [[C]], align 8
// CHECK4-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.SS*)* @.omp_outlined..2 to void (i32*, i32*, ...)*), %struct.SS* [[THIS1]])
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_outlined..2
// CHECK4-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.SS* [[THIS:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK4-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[TMP:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[B:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[C:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[_TMP1:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[BLOCK:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, align 8
// CHECK4-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK4-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK4-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[TMP0:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    store i32* [[A]], i32** [[TMP]], align 8
// CHECK4-NEXT:    store i32* [[C]], i32** [[_TMP1]], align 8
// CHECK4-NEXT:    [[BLOCK_ISA:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 0
// CHECK4-NEXT:    store i8* bitcast (i8** @_NSConcreteStackBlock to i8*), i8** [[BLOCK_ISA]], align 8
// CHECK4-NEXT:    [[BLOCK_FLAGS:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 1
// CHECK4-NEXT:    store i32 1073741824, i32* [[BLOCK_FLAGS]], align 8
// CHECK4-NEXT:    [[BLOCK_RESERVED:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 2
// CHECK4-NEXT:    store i32 0, i32* [[BLOCK_RESERVED]], align 4
// CHECK4-NEXT:    [[BLOCK_INVOKE:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 3
// CHECK4-NEXT:    store i8* bitcast (void (i8*)* @g_block_invoke_2 to i8*), i8** [[BLOCK_INVOKE]], align 8
// CHECK4-NEXT:    [[BLOCK_DESCRIPTOR:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 4
// CHECK4-NEXT:    store %struct.__block_descriptor* bitcast ({ i64, i64, i8*, i8* }* @__block_descriptor_tmp.4 to %struct.__block_descriptor*), %struct.__block_descriptor** [[BLOCK_DESCRIPTOR]], align 8
// CHECK4-NEXT:    [[BLOCK_CAPTURED_THIS_ADDR:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 5
// CHECK4-NEXT:    store %struct.SS* [[TMP0]], %struct.SS** [[BLOCK_CAPTURED_THIS_ADDR]], align 8
// CHECK4-NEXT:    [[BLOCK_CAPTURED:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 6
// CHECK4-NEXT:    [[TMP1:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK4-NEXT:    store i32* [[TMP1]], i32** [[BLOCK_CAPTURED]], align 8
// CHECK4-NEXT:    [[BLOCK_CAPTURED2:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[B]], align 4
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[BLOCK_CAPTURED2]], align 8
// CHECK4-NEXT:    [[BLOCK_CAPTURED3:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 7
// CHECK4-NEXT:    [[TMP3:%.*]] = load i32*, i32** [[_TMP1]], align 8
// CHECK4-NEXT:    store i32* [[TMP3]], i32** [[BLOCK_CAPTURED3]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]] to void ()*
// CHECK4-NEXT:    [[BLOCK_LITERAL:%.*]] = bitcast void ()* [[TMP4]] to %struct.__block_literal_generic*
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT___BLOCK_LITERAL_GENERIC:%.*]], %struct.__block_literal_generic* [[BLOCK_LITERAL]], i32 0, i32 3
// CHECK4-NEXT:    [[TMP6:%.*]] = bitcast %struct.__block_literal_generic* [[BLOCK_LITERAL]] to i8*
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP5]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to void (i8*)*
// CHECK4-NEXT:    call void [[TMP8]](i8* [[TMP6]])
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@g_block_invoke_2
// CHECK4-SAME: (i8* [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR2]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[BLOCK_ADDR:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>*, align 8
// CHECK4-NEXT:    store i8* [[DOTBLOCK_DESCRIPTOR]], i8** [[DOTBLOCK_DESCRIPTOR_ADDR]], align 8
// CHECK4-NEXT:    [[BLOCK:%.*]] = bitcast i8* [[DOTBLOCK_DESCRIPTOR]] to <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>*
// CHECK4-NEXT:    store <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>** [[BLOCK_ADDR]], align 8
// CHECK4-NEXT:    [[BLOCK_CAPTURED_THIS:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 5
// CHECK4-NEXT:    [[THIS:%.*]] = load %struct.SS*, %struct.SS** [[BLOCK_CAPTURED_THIS]], align 8
// CHECK4-NEXT:    [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 6
// CHECK4-NEXT:    [[TMP0:%.*]] = load i32*, i32** [[BLOCK_CAPTURE_ADDR]], align 8
// CHECK4-NEXT:    [[TMP1:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK4-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP1]], 1
// CHECK4-NEXT:    store i32 [[INC]], i32* [[TMP0]], align 4
// CHECK4-NEXT:    [[BLOCK_CAPTURE_ADDR1:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[BLOCK_CAPTURE_ADDR1]], align 8
// CHECK4-NEXT:    [[DEC:%.*]] = add nsw i32 [[TMP2]], -1
// CHECK4-NEXT:    store i32 [[DEC]], i32* [[BLOCK_CAPTURE_ADDR1]], align 8
// CHECK4-NEXT:    [[BLOCK_CAPTURE_ADDR2:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, %struct.SS*, i32*, i32*, i32 }>* [[BLOCK]], i32 0, i32 7
// CHECK4-NEXT:    [[TMP3:%.*]] = load i32*, i32** [[BLOCK_CAPTURE_ADDR2]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4
// CHECK4-NEXT:    [[DIV:%.*]] = sdiv i32 [[TMP4]], 1
// CHECK4-NEXT:    store i32 [[DIV]], i32* [[TMP3]], align 4
// CHECK4-NEXT:    call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, %struct.SS*)* @.omp_outlined..3 to void (i32*, i32*, ...)*), %struct.SS* [[THIS]])
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_outlined..3
// CHECK4-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], %struct.SS* [[THIS:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.SS*, align 8
// CHECK4-NEXT:    [[A:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[TMP:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[B:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[C:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[_TMP1:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK4-NEXT:    store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK4-NEXT:    store %struct.SS* [[THIS]], %struct.SS** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[TMP0:%.*]] = load %struct.SS*, %struct.SS** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    store i32* [[A]], i32** [[TMP]], align 8
// CHECK4-NEXT:    store i32* [[C]], i32** [[_TMP1]], align 8
// CHECK4-NEXT:    [[TMP1:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[TMP1]], align 4
// CHECK4-NEXT:    [[INC:%.*]] = add nsw i32 [[TMP2]], 1
// CHECK4-NEXT:    store i32 [[INC]], i32* [[TMP1]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load i32, i32* [[B]], align 4
// CHECK4-NEXT:    [[DEC:%.*]] = add nsw i32 [[TMP3]], -1
// CHECK4-NEXT:    store i32 [[DEC]], i32* [[B]], align 4
// CHECK4-NEXT:    [[TMP4:%.*]] = load i32*, i32** [[_TMP1]], align 8
// CHECK4-NEXT:    [[TMP5:%.*]] = load i32, i32* [[TMP4]], align 4
// CHECK4-NEXT:    [[DIV:%.*]] = sdiv i32 [[TMP5]], 1
// CHECK4-NEXT:    store i32 [[DIV]], i32* [[TMP4]], align 4
// CHECK4-NEXT:    ret void
//
//