// 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 -triple x86_64-apple-darwin10 -fopenmp -x c++ -emit-llvm %s -o - -DUNTIEDRT | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s -DUNTIEDRT
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK2
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -fopenmp-enable-irbuilder -x c++ -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK3
// RUN: %clang_cc1 -fopenmp -fopenmp-enable-irbuilder -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-enable-irbuilder -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK4

// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp-simd -x c++ -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -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__
};

struct S {
  int a;
  S() : a(0) {}
  S(const S &s) : a(s.a) {}
  ~S() {}
};
int a;
int main() {
  char b;
  S s[2];
  int arr[10][a];
#pragma omp task shared(a, b, s) priority(b)
  {
    a = 15;
    b = a;
    s[0].a = 10;
  }
#pragma omp task shared(a, s) depend(in : a, b, s, arr[:])
  {
    a = 15;
    s[1].a = 10;
  }
#pragma omp task untied
  {
#pragma omp critical
    a = 1;
  }
#pragma omp task untied depend(out : s[0], arr[4:][b])
  {
    a = 1;
  }
#pragma omp task untied depend(mutexinoutset: s[0], arr[4:][b])
  {
    a = 1;
  }
#pragma omp task final(true) depend(inout: a, s[1], arr[:a][3:])
  {
    a = 2;
  }
#pragma omp task final(true)
  {
    a = 2;
  }
  const bool flag = false;
#pragma omp task final(flag)
  {
    a = 3;
  }
  int c __attribute__((aligned(128)));
#pragma omp task final(b) shared(c)
  {
    a = 4;
    c = 5;
  }
#pragma omp task untied firstprivate(c) allocate(omp_pteam_mem_alloc:c)
  {
    S s1, s2;
#ifdef UNTIEDRT
#pragma omp allocate(s2) allocator(omp_pteam_mem_alloc)
#endif
    s2.a = 0;
#pragma omp task
    a = c = 4;
#pragma omp taskyield
    s1 = S();
    s2.a = 10;
#pragma omp taskwait
  }
  return a;
}


// s1 = S();


struct S1 {
  int a;
  S1() { taskinit(); }
  void taskinit() {
#pragma omp task
    a = 0;
  }
} s1;


#ifdef UNTIEDRT
// FIXME: There is a buffer overflow in IrBuilder mode.
template <typename T = void>
void foobar() {
  float a;
#pragma omp parallel
#pragma omp single
  {
    double b;
#pragma omp task
    a += b;
  }
}

void xxxx() {
  foobar();
}


// Copy `a` to the list of shared variables

// Allocate task.
// Copy shared vars.

// Copy firstprivate value of `b`.
#endif // UNTIEDRT
#endif
// CHECK1-LABEL: define {{[^@]+}}@main
// CHECK1-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[B:%.*]] = alloca i8, align 1
// CHECK1-NEXT:    [[S:%.*]] = alloca [2 x %struct.S], align 4
// CHECK1-NEXT:    [[SAVED_STACK:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 8
// CHECK1-NEXT:    [[AGG_CAPTURED1:%.*]] = alloca [[STRUCT_ANON_0:%.*]], align 8
// CHECK1-NEXT:    [[DOTDEP_ARR_ADDR:%.*]] = alloca [4 x %struct.kmp_depend_info], align 8
// CHECK1-NEXT:    [[DEP_COUNTER_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AGG_CAPTURED3:%.*]] = alloca [[STRUCT_ANON_2:%.*]], align 1
// CHECK1-NEXT:    [[AGG_CAPTURED4:%.*]] = alloca [[STRUCT_ANON_4:%.*]], align 1
// CHECK1-NEXT:    [[DOTDEP_ARR_ADDR5:%.*]] = alloca [2 x %struct.kmp_depend_info], align 8
// CHECK1-NEXT:    [[DEP_COUNTER_ADDR11:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AGG_CAPTURED12:%.*]] = alloca [[STRUCT_ANON_6:%.*]], align 1
// CHECK1-NEXT:    [[DOTDEP_ARR_ADDR13:%.*]] = alloca [2 x %struct.kmp_depend_info], align 8
// CHECK1-NEXT:    [[DEP_COUNTER_ADDR19:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AGG_CAPTURED20:%.*]] = alloca [[STRUCT_ANON_8:%.*]], align 1
// CHECK1-NEXT:    [[DOTDEP_ARR_ADDR21:%.*]] = alloca [3 x %struct.kmp_depend_info], align 8
// CHECK1-NEXT:    [[DEP_COUNTER_ADDR27:%.*]] = alloca i64, align 8
// CHECK1-NEXT:    [[AGG_CAPTURED28:%.*]] = alloca [[STRUCT_ANON_10:%.*]], align 1
// CHECK1-NEXT:    [[FLAG:%.*]] = alloca i8, align 1
// CHECK1-NEXT:    [[AGG_CAPTURED29:%.*]] = alloca [[STRUCT_ANON_12:%.*]], align 1
// CHECK1-NEXT:    [[C:%.*]] = alloca i32, align 128
// CHECK1-NEXT:    [[AGG_CAPTURED30:%.*]] = alloca [[STRUCT_ANON_14:%.*]], align 8
// CHECK1-NEXT:    [[AGG_CAPTURED31:%.*]] = alloca [[STRUCT_ANON_16:%.*]], align 1
// CHECK1-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK1-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// CHECK1-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], 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 @_ZN1SC1Ev(%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:    [[TMP1:%.*]] = load i32, i32* @a, align 4
// CHECK1-NEXT:    [[TMP2:%.*]] = zext i32 [[TMP1]] to i64
// CHECK1-NEXT:    [[TMP3:%.*]] = call i8* @llvm.stacksave()
// CHECK1-NEXT:    store i8* [[TMP3]], i8** [[SAVED_STACK]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = mul nuw i64 10, [[TMP2]]
// CHECK1-NEXT:    [[VLA:%.*]] = alloca i32, i64 [[TMP4]], align 16
// CHECK1-NEXT:    store i64 [[TMP2]], i64* [[__VLA_EXPR0]], align 8
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK1-NEXT:    store i8* [[B]], i8** [[TMP5]], align 8
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 1
// CHECK1-NEXT:    store [2 x %struct.S]* [[S]], [2 x %struct.S]** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8, i8* [[B]], align 1
// CHECK1-NEXT:    [[CONV:%.*]] = sext i8 [[TMP7]] to i32
// CHECK1-NEXT:    [[TMP8:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 33, i64 40, i64 16, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast i8* [[TMP8]] to %struct.kmp_task_t_with_privates*
// CHECK1-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP9]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP10]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP12:%.*]] = load i8*, i8** [[TMP11]], align 8
// CHECK1-NEXT:    [[TMP13:%.*]] = bitcast %struct.anon* [[AGG_CAPTURED]] to i8*
// CHECK1-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP12]], i8* align 8 [[TMP13]], i64 16, i1 false)
// CHECK1-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP10]], i32 0, i32 4
// CHECK1-NEXT:    [[TMP15:%.*]] = bitcast %union.kmp_cmplrdata_t* [[TMP14]] to i32*
// CHECK1-NEXT:    store i32 [[CONV]], i32* [[TMP15]], align 8
// CHECK1-NEXT:    [[TMP16:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP8]])
// CHECK1-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[AGG_CAPTURED1]], i32 0, i32 0
// CHECK1-NEXT:    store [2 x %struct.S]* [[S]], [2 x %struct.S]** [[TMP17]], align 8
// CHECK1-NEXT:    [[TMP18:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 1, i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.1*)* @.omp_task_entry..2 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP19:%.*]] = bitcast i8* [[TMP18]] to %struct.kmp_task_t_with_privates.1*
// CHECK1-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_1:%.*]], %struct.kmp_task_t_with_privates.1* [[TMP19]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP20]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
// CHECK1-NEXT:    [[TMP23:%.*]] = bitcast %struct.anon.0* [[AGG_CAPTURED1]] to i8*
// CHECK1-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP22]], i8* align 8 [[TMP23]], i64 8, i1 false)
// CHECK1-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [4 x %struct.kmp_depend_info], [4 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP25:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO:%.*]], %struct.kmp_depend_info* [[TMP24]], i64 0
// CHECK1-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP25]], i32 0, i32 0
// CHECK1-NEXT:    store i64 ptrtoint (i32* @a to i64), i64* [[TMP26]], align 8
// CHECK1-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP25]], i32 0, i32 1
// CHECK1-NEXT:    store i64 4, i64* [[TMP27]], align 8
// CHECK1-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP25]], i32 0, i32 2
// CHECK1-NEXT:    store i8 1, i8* [[TMP28]], align 8
// CHECK1-NEXT:    [[TMP29:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i64 1
// CHECK1-NEXT:    [[TMP30:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP29]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP31:%.*]] = ptrtoint i8* [[B]] to i64
// CHECK1-NEXT:    store i64 [[TMP31]], i64* [[TMP30]], align 8
// CHECK1-NEXT:    [[TMP32:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP29]], i32 0, i32 1
// CHECK1-NEXT:    store i64 1, i64* [[TMP32]], align 8
// CHECK1-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP29]], i32 0, i32 2
// CHECK1-NEXT:    store i8 1, i8* [[TMP33]], align 8
// CHECK1-NEXT:    [[TMP34:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i64 2
// CHECK1-NEXT:    [[TMP35:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP34]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP36:%.*]] = ptrtoint [2 x %struct.S]* [[S]] to i64
// CHECK1-NEXT:    store i64 [[TMP36]], i64* [[TMP35]], align 8
// CHECK1-NEXT:    [[TMP37:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP34]], i32 0, i32 1
// CHECK1-NEXT:    store i64 8, i64* [[TMP37]], align 8
// CHECK1-NEXT:    [[TMP38:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP34]], i32 0, i32 2
// CHECK1-NEXT:    store i8 1, i8* [[TMP38]], align 8
// CHECK1-NEXT:    [[TMP39:%.*]] = mul nsw i64 0, [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP39]]
// CHECK1-NEXT:    [[TMP40:%.*]] = mul nsw i64 9, [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP40]]
// CHECK1-NEXT:    [[TMP41:%.*]] = getelementptr i32, i32* [[ARRAYIDX2]], i32 1
// CHECK1-NEXT:    [[TMP42:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
// CHECK1-NEXT:    [[TMP43:%.*]] = ptrtoint i32* [[TMP41]] to i64
// CHECK1-NEXT:    [[TMP44:%.*]] = sub nuw i64 [[TMP43]], [[TMP42]]
// CHECK1-NEXT:    [[TMP45:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i64 3
// CHECK1-NEXT:    [[TMP46:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP45]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP47:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
// CHECK1-NEXT:    store i64 [[TMP47]], i64* [[TMP46]], align 8
// CHECK1-NEXT:    [[TMP48:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP45]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP44]], i64* [[TMP48]], align 8
// CHECK1-NEXT:    [[TMP49:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP45]], i32 0, i32 2
// CHECK1-NEXT:    store i8 1, i8* [[TMP49]], align 8
// CHECK1-NEXT:    store i64 4, i64* [[DEP_COUNTER_ADDR]], align 8
// CHECK1-NEXT:    [[TMP50:%.*]] = bitcast %struct.kmp_depend_info* [[TMP24]] to i8*
// CHECK1-NEXT:    [[TMP51:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP18]], i32 4, i8* [[TMP50]], i32 0, i8* null)
// CHECK1-NEXT:    [[TMP52:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.3*)* @.omp_task_entry..4 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP53:%.*]] = bitcast i8* [[TMP52]] to %struct.kmp_task_t_with_privates.3*
// CHECK1-NEXT:    [[TMP54:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_3:%.*]], %struct.kmp_task_t_with_privates.3* [[TMP53]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP55:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP54]], i32 0, i32 2
// CHECK1-NEXT:    store i32 0, i32* [[TMP55]], align 8
// CHECK1-NEXT:    [[TMP56:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP52]])
// CHECK1-NEXT:    [[TMP57:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.5*)* @.omp_task_entry..6 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP58:%.*]] = bitcast i8* [[TMP57]] to %struct.kmp_task_t_with_privates.5*
// CHECK1-NEXT:    [[TMP59:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_5:%.*]], %struct.kmp_task_t_with_privates.5* [[TMP58]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP60:%.*]] = getelementptr inbounds [2 x %struct.kmp_depend_info], [2 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR5]], i64 0, i64 0
// CHECK1-NEXT:    [[ARRAYIDX6:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP61:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP60]], i64 0
// CHECK1-NEXT:    [[TMP62:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP61]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP63:%.*]] = ptrtoint %struct.S* [[ARRAYIDX6]] to i64
// CHECK1-NEXT:    store i64 [[TMP63]], i64* [[TMP62]], align 8
// CHECK1-NEXT:    [[TMP64:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP61]], i32 0, i32 1
// CHECK1-NEXT:    store i64 4, i64* [[TMP64]], align 8
// CHECK1-NEXT:    [[TMP65:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP61]], i32 0, i32 2
// CHECK1-NEXT:    store i8 3, i8* [[TMP65]], align 8
// CHECK1-NEXT:    [[TMP66:%.*]] = load i8, i8* [[B]], align 1
// CHECK1-NEXT:    [[TMP67:%.*]] = sext i8 [[TMP66]] to i64
// CHECK1-NEXT:    [[TMP68:%.*]] = mul nsw i64 4, [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX7:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP68]]
// CHECK1-NEXT:    [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX7]], i64 [[TMP67]]
// CHECK1-NEXT:    [[TMP69:%.*]] = load i8, i8* [[B]], align 1
// CHECK1-NEXT:    [[TMP70:%.*]] = sext i8 [[TMP69]] to i64
// CHECK1-NEXT:    [[TMP71:%.*]] = mul nsw i64 9, [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP71]]
// CHECK1-NEXT:    [[ARRAYIDX10:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX9]], i64 [[TMP70]]
// CHECK1-NEXT:    [[TMP72:%.*]] = getelementptr i32, i32* [[ARRAYIDX10]], i32 1
// CHECK1-NEXT:    [[TMP73:%.*]] = ptrtoint i32* [[ARRAYIDX8]] to i64
// CHECK1-NEXT:    [[TMP74:%.*]] = ptrtoint i32* [[TMP72]] to i64
// CHECK1-NEXT:    [[TMP75:%.*]] = sub nuw i64 [[TMP74]], [[TMP73]]
// CHECK1-NEXT:    [[TMP76:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP60]], i64 1
// CHECK1-NEXT:    [[TMP77:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP76]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP78:%.*]] = ptrtoint i32* [[ARRAYIDX8]] to i64
// CHECK1-NEXT:    store i64 [[TMP78]], i64* [[TMP77]], align 8
// CHECK1-NEXT:    [[TMP79:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP76]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP75]], i64* [[TMP79]], align 8
// CHECK1-NEXT:    [[TMP80:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP76]], i32 0, i32 2
// CHECK1-NEXT:    store i8 3, i8* [[TMP80]], align 8
// CHECK1-NEXT:    store i64 2, i64* [[DEP_COUNTER_ADDR11]], align 8
// CHECK1-NEXT:    [[TMP81:%.*]] = bitcast %struct.kmp_depend_info* [[TMP60]] to i8*
// CHECK1-NEXT:    [[TMP82:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP59]], i32 0, i32 2
// CHECK1-NEXT:    store i32 0, i32* [[TMP82]], align 8
// CHECK1-NEXT:    [[TMP83:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP57]], i32 2, i8* [[TMP81]], i32 0, i8* null)
// CHECK1-NEXT:    [[TMP84:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.7*)* @.omp_task_entry..8 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP85:%.*]] = bitcast i8* [[TMP84]] to %struct.kmp_task_t_with_privates.7*
// CHECK1-NEXT:    [[TMP86:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_7:%.*]], %struct.kmp_task_t_with_privates.7* [[TMP85]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP87:%.*]] = getelementptr inbounds [2 x %struct.kmp_depend_info], [2 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR13]], i64 0, i64 0
// CHECK1-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP88:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP87]], i64 0
// CHECK1-NEXT:    [[TMP89:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP88]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP90:%.*]] = ptrtoint %struct.S* [[ARRAYIDX14]] to i64
// CHECK1-NEXT:    store i64 [[TMP90]], i64* [[TMP89]], align 8
// CHECK1-NEXT:    [[TMP91:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP88]], i32 0, i32 1
// CHECK1-NEXT:    store i64 4, i64* [[TMP91]], align 8
// CHECK1-NEXT:    [[TMP92:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP88]], i32 0, i32 2
// CHECK1-NEXT:    store i8 4, i8* [[TMP92]], align 8
// CHECK1-NEXT:    [[TMP93:%.*]] = load i8, i8* [[B]], align 1
// CHECK1-NEXT:    [[TMP94:%.*]] = sext i8 [[TMP93]] to i64
// CHECK1-NEXT:    [[TMP95:%.*]] = mul nsw i64 4, [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP95]]
// CHECK1-NEXT:    [[ARRAYIDX16:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX15]], i64 [[TMP94]]
// CHECK1-NEXT:    [[TMP96:%.*]] = load i8, i8* [[B]], align 1
// CHECK1-NEXT:    [[TMP97:%.*]] = sext i8 [[TMP96]] to i64
// CHECK1-NEXT:    [[TMP98:%.*]] = mul nsw i64 9, [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX17:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP98]]
// CHECK1-NEXT:    [[ARRAYIDX18:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX17]], i64 [[TMP97]]
// CHECK1-NEXT:    [[TMP99:%.*]] = getelementptr i32, i32* [[ARRAYIDX18]], i32 1
// CHECK1-NEXT:    [[TMP100:%.*]] = ptrtoint i32* [[ARRAYIDX16]] to i64
// CHECK1-NEXT:    [[TMP101:%.*]] = ptrtoint i32* [[TMP99]] to i64
// CHECK1-NEXT:    [[TMP102:%.*]] = sub nuw i64 [[TMP101]], [[TMP100]]
// CHECK1-NEXT:    [[TMP103:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP87]], i64 1
// CHECK1-NEXT:    [[TMP104:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP103]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP105:%.*]] = ptrtoint i32* [[ARRAYIDX16]] to i64
// CHECK1-NEXT:    store i64 [[TMP105]], i64* [[TMP104]], align 8
// CHECK1-NEXT:    [[TMP106:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP103]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP102]], i64* [[TMP106]], align 8
// CHECK1-NEXT:    [[TMP107:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP103]], i32 0, i32 2
// CHECK1-NEXT:    store i8 4, i8* [[TMP107]], align 8
// CHECK1-NEXT:    store i64 2, i64* [[DEP_COUNTER_ADDR19]], align 8
// CHECK1-NEXT:    [[TMP108:%.*]] = bitcast %struct.kmp_depend_info* [[TMP87]] to i8*
// CHECK1-NEXT:    [[TMP109:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP86]], i32 0, i32 2
// CHECK1-NEXT:    store i32 0, i32* [[TMP109]], align 8
// CHECK1-NEXT:    [[TMP110:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP84]], i32 2, i8* [[TMP108]], i32 0, i8* null)
// CHECK1-NEXT:    [[TMP111:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 3, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.9*)* @.omp_task_entry..10 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP112:%.*]] = bitcast i8* [[TMP111]] to %struct.kmp_task_t_with_privates.9*
// CHECK1-NEXT:    [[TMP113:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_9:%.*]], %struct.kmp_task_t_with_privates.9* [[TMP112]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP114:%.*]] = getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR21]], i64 0, i64 0
// CHECK1-NEXT:    [[TMP115:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i64 0
// CHECK1-NEXT:    [[TMP116:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP115]], i32 0, i32 0
// CHECK1-NEXT:    store i64 ptrtoint (i32* @a to i64), i64* [[TMP116]], align 8
// CHECK1-NEXT:    [[TMP117:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP115]], i32 0, i32 1
// CHECK1-NEXT:    store i64 4, i64* [[TMP117]], align 8
// CHECK1-NEXT:    [[TMP118:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP115]], i32 0, i32 2
// CHECK1-NEXT:    store i8 3, i8* [[TMP118]], align 8
// CHECK1-NEXT:    [[ARRAYIDX22:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 1
// CHECK1-NEXT:    [[TMP119:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i64 1
// CHECK1-NEXT:    [[TMP120:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP119]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP121:%.*]] = ptrtoint %struct.S* [[ARRAYIDX22]] to i64
// CHECK1-NEXT:    store i64 [[TMP121]], i64* [[TMP120]], align 8
// CHECK1-NEXT:    [[TMP122:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP119]], i32 0, i32 1
// CHECK1-NEXT:    store i64 4, i64* [[TMP122]], align 8
// CHECK1-NEXT:    [[TMP123:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP119]], i32 0, i32 2
// CHECK1-NEXT:    store i8 3, i8* [[TMP123]], align 8
// CHECK1-NEXT:    [[TMP124:%.*]] = mul nsw i64 0, [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX23:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP124]]
// CHECK1-NEXT:    [[ARRAYIDX24:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX23]], i64 3
// CHECK1-NEXT:    [[TMP125:%.*]] = load i32, i32* @a, align 4
// CHECK1-NEXT:    [[TMP126:%.*]] = sext i32 [[TMP125]] to i64
// CHECK1-NEXT:    [[LEN_SUB_1:%.*]] = sub nsw i64 [[TMP126]], 1
// CHECK1-NEXT:    [[TMP127:%.*]] = load i32, i32* @a, align 4
// CHECK1-NEXT:    [[TMP128:%.*]] = sext i32 [[TMP127]] to i64
// CHECK1-NEXT:    [[LB_ADD_LEN:%.*]] = add nsw i64 -1, [[TMP128]]
// CHECK1-NEXT:    [[TMP129:%.*]] = mul nsw i64 [[LB_ADD_LEN]], [[TMP2]]
// CHECK1-NEXT:    [[ARRAYIDX25:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP129]]
// CHECK1-NEXT:    [[ARRAYIDX26:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX25]], i64 [[LEN_SUB_1]]
// CHECK1-NEXT:    [[TMP130:%.*]] = getelementptr i32, i32* [[ARRAYIDX26]], i32 1
// CHECK1-NEXT:    [[TMP131:%.*]] = ptrtoint i32* [[ARRAYIDX24]] to i64
// CHECK1-NEXT:    [[TMP132:%.*]] = ptrtoint i32* [[TMP130]] to i64
// CHECK1-NEXT:    [[TMP133:%.*]] = sub nuw i64 [[TMP132]], [[TMP131]]
// CHECK1-NEXT:    [[TMP134:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i64 2
// CHECK1-NEXT:    [[TMP135:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP134]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP136:%.*]] = ptrtoint i32* [[ARRAYIDX24]] to i64
// CHECK1-NEXT:    store i64 [[TMP136]], i64* [[TMP135]], align 8
// CHECK1-NEXT:    [[TMP137:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP134]], i32 0, i32 1
// CHECK1-NEXT:    store i64 [[TMP133]], i64* [[TMP137]], align 8
// CHECK1-NEXT:    [[TMP138:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP134]], i32 0, i32 2
// CHECK1-NEXT:    store i8 3, i8* [[TMP138]], align 8
// CHECK1-NEXT:    store i64 3, i64* [[DEP_COUNTER_ADDR27]], align 8
// CHECK1-NEXT:    [[TMP139:%.*]] = bitcast %struct.kmp_depend_info* [[TMP114]] to i8*
// CHECK1-NEXT:    [[TMP140:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP111]], i32 3, i8* [[TMP139]], i32 0, i8* null)
// CHECK1-NEXT:    [[TMP141:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 3, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.11*)* @.omp_task_entry..12 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP142:%.*]] = bitcast i8* [[TMP141]] to %struct.kmp_task_t_with_privates.11*
// CHECK1-NEXT:    [[TMP143:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_11:%.*]], %struct.kmp_task_t_with_privates.11* [[TMP142]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP144:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP141]])
// CHECK1-NEXT:    store i8 0, i8* [[FLAG]], align 1
// CHECK1-NEXT:    [[TMP145:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 1, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.13*)* @.omp_task_entry..14 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP146:%.*]] = bitcast i8* [[TMP145]] to %struct.kmp_task_t_with_privates.13*
// CHECK1-NEXT:    [[TMP147:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_13:%.*]], %struct.kmp_task_t_with_privates.13* [[TMP146]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP148:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP145]])
// CHECK1-NEXT:    [[TMP149:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[AGG_CAPTURED30]], i32 0, i32 0
// CHECK1-NEXT:    store i32* [[C]], i32** [[TMP149]], align 8
// CHECK1-NEXT:    [[TMP150:%.*]] = load i8, i8* [[B]], align 1
// CHECK1-NEXT:    [[TOBOOL:%.*]] = icmp ne i8 [[TMP150]], 0
// CHECK1-NEXT:    [[TMP151:%.*]] = select i1 [[TOBOOL]], i32 2, i32 0
// CHECK1-NEXT:    [[TMP152:%.*]] = or i32 [[TMP151]], 1
// CHECK1-NEXT:    [[TMP153:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 [[TMP152]], i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.15*)* @.omp_task_entry..16 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP154:%.*]] = bitcast i8* [[TMP153]] to %struct.kmp_task_t_with_privates.15*
// CHECK1-NEXT:    [[TMP155:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_15:%.*]], %struct.kmp_task_t_with_privates.15* [[TMP154]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP156:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP155]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP157:%.*]] = load i8*, i8** [[TMP156]], align 8
// CHECK1-NEXT:    [[TMP158:%.*]] = bitcast %struct.anon.14* [[AGG_CAPTURED30]] to i8*
// CHECK1-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP157]], i8* align 8 [[TMP158]], i64 8, i1 false)
// CHECK1-NEXT:    [[TMP159:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP153]])
// CHECK1-NEXT:    [[TMP160:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 0, i64 256, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.19*)* @.omp_task_entry..21 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP161:%.*]] = bitcast i8* [[TMP160]] to %struct.kmp_task_t_with_privates.19*
// CHECK1-NEXT:    [[TMP162:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19:%.*]], %struct.kmp_task_t_with_privates.19* [[TMP161]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP163:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19]], %struct.kmp_task_t_with_privates.19* [[TMP161]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP164:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20:%.*]], %struct..kmp_privates.t.20* [[TMP163]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP165:%.*]] = load i32, i32* [[C]], align 128
// CHECK1-NEXT:    store i32 [[TMP165]], i32* [[TMP164]], align 128
// CHECK1-NEXT:    [[TMP166:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP162]], i32 0, i32 2
// CHECK1-NEXT:    store i32 0, i32* [[TMP166]], align 16
// CHECK1-NEXT:    [[TMP167:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP160]])
// CHECK1-NEXT:    [[TMP168:%.*]] = load i32, i32* @a, align 4
// CHECK1-NEXT:    store i32 [[TMP168]], i32* [[RETVAL]], align 4
// CHECK1-NEXT:    [[TMP169:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
// CHECK1-NEXT:    call void @llvm.stackrestore(i8* [[TMP169]])
// CHECK1-NEXT:    [[ARRAY_BEGIN32:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP170:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN32]], i64 2
// CHECK1-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1:       arraydestroy.body:
// CHECK1-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP170]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK1-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK1-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4:[0-9]+]]
// CHECK1-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN32]]
// CHECK1-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE33:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1:       arraydestroy.done33:
// CHECK1-NEXT:    [[TMP171:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK1-NEXT:    ret i32 [[TMP171]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SC1Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] 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 @_ZN1SC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry.
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates* noalias [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon*, align 8
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates* [[TMP1]], %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates*, %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon*
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META3:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META6:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META8:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META10:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !12
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT:    store %struct.anon* [[TMP8]], %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT:    store i32 15, i32* @a, align 4
// CHECK1-NEXT:    [[TMP11:%.*]] = load i32, i32* @a, align 4
// CHECK1-NEXT:    [[CONV_I:%.*]] = trunc i32 [[TMP11]] to i8
// CHECK1-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [[STRUCT_ANON:%.*]], %struct.anon* [[TMP10]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
// CHECK1-NEXT:    store i8 [[CONV_I]], i8* [[TMP13]], align 1
// CHECK1-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP10]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP15:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[TMP14]], align 8
// CHECK1-NEXT:    [[ARRAYIDX_I:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP15]], i64 0, i64 0
// CHECK1-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAYIDX_I]], i32 0, i32 0
// CHECK1-NEXT:    store i32 10, i32* [[A_I]], align 4
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..2
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.1* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.0*, align 8
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.1*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.1* [[TMP1]], %struct.kmp_task_t_with_privates.1** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.1*, %struct.kmp_task_t_with_privates.1** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_1:%.*]], %struct.kmp_task_t_with_privates.1* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.0*
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.1* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META13:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META16:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META18:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META20:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !22
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !22
// CHECK1-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !22
// CHECK1-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !22
// CHECK1-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !22
// CHECK1-NEXT:    store %struct.anon.0* [[TMP8]], %struct.anon.0** [[__CONTEXT_ADDR_I]], align 8, !noalias !22
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.anon.0*, %struct.anon.0** [[__CONTEXT_ADDR_I]], align 8, !noalias !22
// CHECK1-NEXT:    store i32 15, i32* @a, align 4
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_0:%.*]], %struct.anon.0* [[TMP10]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP12:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[TMP11]], align 8
// CHECK1-NEXT:    [[ARRAYIDX_I:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP12]], i64 0, i64 1
// CHECK1-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAYIDX_I]], i32 0, i32 0
// CHECK1-NEXT:    store i32 10, i32* [[A_I]], align 4
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..4
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.3* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.2*, align 8
// CHECK1-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.3*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.3* [[TMP1]], %struct.kmp_task_t_with_privates.3** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.3*, %struct.kmp_task_t_with_privates.3** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_3:%.*]], %struct.kmp_task_t_with_privates.3* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.2*
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.3* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META23:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META26:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META28:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META30:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !32
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK1-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !32
// CHECK1-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !32
// CHECK1-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !32
// CHECK1-NEXT:    store %struct.anon.2* [[TMP8]], %struct.anon.2** [[__CONTEXT_ADDR_I]], align 8, !noalias !32
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.anon.2*, %struct.anon.2** [[__CONTEXT_ADDR_I]], align 8, !noalias !32
// CHECK1-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK1-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK1-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK1-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK1-NEXT:    ]
// CHECK1:       .untied.done..i:
// CHECK1-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK1-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK1:       .untied.jmp..i:
// CHECK1-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK1-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !32
// CHECK1-NEXT:    [[TMP15:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !32
// CHECK1-NEXT:    [[TMP16:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP14]], i8* [[TMP15]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__3_EXIT:%.*]]
// CHECK1:       .untied.jmp.1.i:
// CHECK1-NEXT:    [[TMP17:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !32
// CHECK1-NEXT:    call void @__kmpc_critical(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], [8 x i32]* @.gomp_critical_user_.var) #[[ATTR4]]
// CHECK1-NEXT:    store i32 1, i32* @a, align 4
// CHECK1-NEXT:    call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], [8 x i32]* @.gomp_critical_user_.var) #[[ATTR4]]
// CHECK1-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK1-NEXT:    br label [[CLEANUP_I]]
// CHECK1:       cleanup.i:
// CHECK1-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__3_EXIT]]
// CHECK1:       .omp_outlined..3.exit:
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..6
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.5* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.4*, align 8
// CHECK1-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.5*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.5* [[TMP1]], %struct.kmp_task_t_with_privates.5** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.5*, %struct.kmp_task_t_with_privates.5** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_5:%.*]], %struct.kmp_task_t_with_privates.5* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.4*
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.5* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META33:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META36:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META38:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META40:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !42
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK1-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !42
// CHECK1-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !42
// CHECK1-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !42
// CHECK1-NEXT:    store %struct.anon.4* [[TMP8]], %struct.anon.4** [[__CONTEXT_ADDR_I]], align 8, !noalias !42
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.anon.4*, %struct.anon.4** [[__CONTEXT_ADDR_I]], align 8, !noalias !42
// CHECK1-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK1-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK1-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK1-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK1-NEXT:    ]
// CHECK1:       .untied.done..i:
// CHECK1-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK1-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK1:       .untied.jmp..i:
// CHECK1-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK1-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !42
// CHECK1-NEXT:    [[TMP15:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !42
// CHECK1-NEXT:    [[TMP16:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP14]], i8* [[TMP15]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__5_EXIT:%.*]]
// CHECK1:       .untied.jmp.1.i:
// CHECK1-NEXT:    store i32 1, i32* @a, align 4
// CHECK1-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK1-NEXT:    br label [[CLEANUP_I]]
// CHECK1:       cleanup.i:
// CHECK1-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__5_EXIT]]
// CHECK1:       .omp_outlined..5.exit:
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..8
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.7* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.6*, align 8
// CHECK1-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.7*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.7* [[TMP1]], %struct.kmp_task_t_with_privates.7** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.7*, %struct.kmp_task_t_with_privates.7** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_7:%.*]], %struct.kmp_task_t_with_privates.7* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.6*
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.7* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META43:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META46:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META48:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META50:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !52
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK1-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !52
// CHECK1-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !52
// CHECK1-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !52
// CHECK1-NEXT:    store %struct.anon.6* [[TMP8]], %struct.anon.6** [[__CONTEXT_ADDR_I]], align 8, !noalias !52
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.anon.6*, %struct.anon.6** [[__CONTEXT_ADDR_I]], align 8, !noalias !52
// CHECK1-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK1-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK1-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK1-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK1-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK1-NEXT:    ]
// CHECK1:       .untied.done..i:
// CHECK1-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK1-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK1:       .untied.jmp..i:
// CHECK1-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK1-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK1-NEXT:    [[TMP14:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !52
// CHECK1-NEXT:    [[TMP15:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !52
// CHECK1-NEXT:    [[TMP16:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP14]], i8* [[TMP15]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__7_EXIT:%.*]]
// CHECK1:       .untied.jmp.1.i:
// CHECK1-NEXT:    store i32 1, i32* @a, align 4
// CHECK1-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK1-NEXT:    br label [[CLEANUP_I]]
// CHECK1:       cleanup.i:
// CHECK1-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__7_EXIT]]
// CHECK1:       .omp_outlined..7.exit:
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..10
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.9* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.8*, align 8
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.9*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.9* [[TMP1]], %struct.kmp_task_t_with_privates.9** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.9*, %struct.kmp_task_t_with_privates.9** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_9:%.*]], %struct.kmp_task_t_with_privates.9* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.8*
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.9* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META53:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META56:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META58:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META60:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !62
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !62
// CHECK1-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !62
// CHECK1-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !62
// CHECK1-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !62
// CHECK1-NEXT:    store %struct.anon.8* [[TMP8]], %struct.anon.8** [[__CONTEXT_ADDR_I]], align 8, !noalias !62
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.anon.8*, %struct.anon.8** [[__CONTEXT_ADDR_I]], align 8, !noalias !62
// CHECK1-NEXT:    store i32 2, i32* @a, align 4
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..12
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.11* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.10*, align 8
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.11*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.11* [[TMP1]], %struct.kmp_task_t_with_privates.11** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.11*, %struct.kmp_task_t_with_privates.11** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_11:%.*]], %struct.kmp_task_t_with_privates.11* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.10*
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.11* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META63:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META66:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META68:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META70:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !72
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !72
// CHECK1-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !72
// CHECK1-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !72
// CHECK1-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !72
// CHECK1-NEXT:    store %struct.anon.10* [[TMP8]], %struct.anon.10** [[__CONTEXT_ADDR_I]], align 8, !noalias !72
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.anon.10*, %struct.anon.10** [[__CONTEXT_ADDR_I]], align 8, !noalias !72
// CHECK1-NEXT:    store i32 2, i32* @a, align 4
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..14
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.13* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.12*, align 8
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.13*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.13* [[TMP1]], %struct.kmp_task_t_with_privates.13** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.13*, %struct.kmp_task_t_with_privates.13** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_13:%.*]], %struct.kmp_task_t_with_privates.13* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.12*
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.13* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META73:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META76:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META78:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META80:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !82
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !82
// CHECK1-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !82
// CHECK1-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !82
// CHECK1-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !82
// CHECK1-NEXT:    store %struct.anon.12* [[TMP8]], %struct.anon.12** [[__CONTEXT_ADDR_I]], align 8, !noalias !82
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.anon.12*, %struct.anon.12** [[__CONTEXT_ADDR_I]], align 8, !noalias !82
// CHECK1-NEXT:    store i32 3, i32* @a, align 4
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..16
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.15* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.14*, align 8
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.15*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.15* [[TMP1]], %struct.kmp_task_t_with_privates.15** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.15*, %struct.kmp_task_t_with_privates.15** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_15:%.*]], %struct.kmp_task_t_with_privates.15* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.14*
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.15* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META83:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META86:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META88:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META90:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !92
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !92
// CHECK1-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !92
// CHECK1-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !92
// CHECK1-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !92
// CHECK1-NEXT:    store %struct.anon.14* [[TMP8]], %struct.anon.14** [[__CONTEXT_ADDR_I]], align 8, !noalias !92
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.anon.14*, %struct.anon.14** [[__CONTEXT_ADDR_I]], align 8, !noalias !92
// CHECK1-NEXT:    store i32 4, i32* @a, align 4
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_14:%.*]], %struct.anon.14* [[TMP10]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP12:%.*]] = load i32*, i32** [[TMP11]], align 8
// CHECK1-NEXT:    store i32 5, i32* [[TMP12]], align 128
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_privates_map.
// CHECK1-SAME: (%struct..kmp_privates.t* noalias [[TMP0:%.*]], i32** noalias [[TMP1:%.*]]) #[[ATTR7:[0-9]+]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t*, align 8
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i32**, align 8
// CHECK1-NEXT:    store %struct..kmp_privates.t* [[TMP0]], %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK1-NEXT:    store i32** [[TMP1]], i32*** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load %struct..kmp_privates.t*, %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP2]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP4:%.*]] = load i32**, i32*** [[DOTADDR1]], align 8
// CHECK1-NEXT:    store i32* [[TMP3]], i32** [[TMP4]], align 8
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..19
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.18* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.17*, align 8
// CHECK1-NEXT:    [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.18*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.18* [[TMP1]], %struct.kmp_task_t_with_privates.18** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.18*, %struct.kmp_task_t_with_privates.18** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18:%.*]], %struct.kmp_task_t_with_privates.18* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 128
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.17*
// CHECK1-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18]], %struct.kmp_task_t_with_privates.18* [[TMP3]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP10:%.*]] = bitcast %struct..kmp_privates.t* [[TMP9]] to i8*
// CHECK1-NEXT:    [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates.18* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META93:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META96:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META98:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META100:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !102
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !102
// CHECK1-NEXT:    store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !102
// CHECK1-NEXT:    store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t*, i32**)* @.omp_task_privates_map. to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !102
// CHECK1-NEXT:    store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !102
// CHECK1-NEXT:    store %struct.anon.17* [[TMP8]], %struct.anon.17** [[__CONTEXT_ADDR_I]], align 8, !noalias !102
// CHECK1-NEXT:    [[TMP12:%.*]] = load %struct.anon.17*, %struct.anon.17** [[__CONTEXT_ADDR_I]], align 8, !noalias !102
// CHECK1-NEXT:    [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !102
// CHECK1-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !102
// CHECK1-NEXT:    [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i32**)*
// CHECK1-NEXT:    call void [[TMP15]](i8* [[TMP14]], i32** [[DOTFIRSTPRIV_PTR_ADDR_I]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP16:%.*]] = load i32*, i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !102
// CHECK1-NEXT:    store i32 4, i32* [[TMP16]], align 128
// CHECK1-NEXT:    store i32 4, i32* @a, align 4
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SD1Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] 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 @_ZN1SD2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_privates_map..20
// CHECK1-SAME: (%struct..kmp_privates.t.20* noalias [[TMP0:%.*]], i32** noalias [[TMP1:%.*]], %struct.S** noalias [[TMP2:%.*]], %struct.S*** noalias [[TMP3:%.*]]) #[[ATTR7]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t.20*, align 8
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca i32**, align 8
// CHECK1-NEXT:    [[DOTADDR2:%.*]] = alloca %struct.S**, align 8
// CHECK1-NEXT:    [[DOTADDR3:%.*]] = alloca %struct.S***, align 8
// CHECK1-NEXT:    store %struct..kmp_privates.t.20* [[TMP0]], %struct..kmp_privates.t.20** [[DOTADDR]], align 8
// CHECK1-NEXT:    store i32** [[TMP1]], i32*** [[DOTADDR1]], align 8
// CHECK1-NEXT:    store %struct.S** [[TMP2]], %struct.S*** [[DOTADDR2]], align 8
// CHECK1-NEXT:    store %struct.S*** [[TMP3]], %struct.S**** [[DOTADDR3]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = load %struct..kmp_privates.t.20*, %struct..kmp_privates.t.20** [[DOTADDR]], align 8
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20:%.*]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP6:%.*]] = load i32**, i32*** [[DOTADDR1]], align 8
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP8:%.*]] = load %struct.S***, %struct.S**** [[DOTADDR3]], align 8
// CHECK1-NEXT:    store %struct.S** [[TMP7]], %struct.S*** [[TMP8]], align 8
// CHECK1-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 3
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.S**, %struct.S*** [[DOTADDR2]], align 8
// CHECK1-NEXT:    store %struct.S* [[TMP9]], %struct.S** [[TMP10]], align 8
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..21
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.19* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.16*, align 8
// CHECK1-NEXT:    [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTLOCAL_PTR_ADDR_I:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT:    [[DOTLOCAL_PTR_ADDR1_I:%.*]] = alloca %struct.S**, align 8
// CHECK1-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[REF_TMP_I:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.19*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.19* [[TMP1]], %struct.kmp_task_t_with_privates.19** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.19*, %struct.kmp_task_t_with_privates.19** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19:%.*]], %struct.kmp_task_t_with_privates.19* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 128
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.16*
// CHECK1-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19]], %struct.kmp_task_t_with_privates.19* [[TMP3]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP10:%.*]] = bitcast %struct..kmp_privates.t.20* [[TMP9]] to i8*
// CHECK1-NEXT:    [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates.19* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META103:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META106:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META108:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META110:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t.20*, i32**, %struct.S**, %struct.S***)* @.omp_task_privates_map..20 to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    store %struct.anon.16* [[TMP8]], %struct.anon.16** [[__CONTEXT_ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP12:%.*]] = load %struct.anon.16*, %struct.anon.16** [[__CONTEXT_ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i32**, %struct.S**, %struct.S***)*
// CHECK1-NEXT:    call void [[TMP15]](i8* [[TMP14]], i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], %struct.S** [[DOTLOCAL_PTR_ADDR_I]], %struct.S*** [[DOTLOCAL_PTR_ADDR1_I]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP16:%.*]] = load i32*, i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP17:%.*]] = load %struct.S*, %struct.S** [[DOTLOCAL_PTR_ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP18:%.*]] = load %struct.S**, %struct.S*** [[DOTLOCAL_PTR_ADDR1_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP18]], align 8
// CHECK1-NEXT:    [[TMP20:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP21:%.*]] = load i32, i32* [[TMP20]], align 4
// CHECK1-NEXT:    switch i32 [[TMP21]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK1-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK1-NEXT:    i32 1, label [[DOTUNTIED_JMP_2_I:%.*]]
// CHECK1-NEXT:    i32 2, label [[DOTUNTIED_JMP_3_I:%.*]]
// CHECK1-NEXT:    i32 3, label [[DOTUNTIED_JMP_5_I:%.*]]
// CHECK1-NEXT:    i32 4, label [[DOTUNTIED_JMP_7_I:%.*]]
// CHECK1-NEXT:    i32 5, label [[DOTUNTIED_JMP_10_I:%.*]]
// CHECK1-NEXT:    ]
// CHECK1:       .untied.done..i:
// CHECK1-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK1-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK1:       .untied.jmp..i:
// CHECK1-NEXT:    [[TMP22:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    store i32 1, i32* [[TMP22]], align 4
// CHECK1-NEXT:    [[TMP23:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[TMP24:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP25:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP23]], i8* [[TMP24]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT:%.*]]
// CHECK1:       .untied.jmp.2.i:
// CHECK1-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TMP17]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP26:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[DOTS2__VOID_ADDR_I:%.*]] = call i8* @__kmpc_alloc(i32 [[TMP26]], i64 4, i8* inttoptr (i64 7 to i8*)) #[[ATTR4]]
// CHECK1-NEXT:    [[DOTS2__ADDR_I:%.*]] = bitcast i8* [[DOTS2__VOID_ADDR_I]] to %struct.S*
// CHECK1-NEXT:    store %struct.S* [[DOTS2__ADDR_I]], %struct.S** [[TMP18]], align 8
// CHECK1-NEXT:    [[TMP27:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    store i32 2, i32* [[TMP27]], align 4
// CHECK1-NEXT:    [[TMP28:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[TMP29:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP30:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP28]], i8* [[TMP29]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK1:       .untied.jmp.3.i:
// CHECK1-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TMP19]]) #[[ATTR4]]
// CHECK1-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 0
// CHECK1-NEXT:    store i32 0, i32* [[A_I]], align 4
// CHECK1-NEXT:    [[TMP31:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[TMP32:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP31]], i32 1, i64 256, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.18*)* @.omp_task_entry..19 to i32 (i32, i8*)*)) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP33:%.*]] = bitcast i8* [[TMP32]] to %struct.kmp_task_t_with_privates.18*
// CHECK1-NEXT:    [[TMP34:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18:%.*]], %struct.kmp_task_t_with_privates.18* [[TMP33]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP35:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18]], %struct.kmp_task_t_with_privates.18* [[TMP33]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP36:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP35]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP37:%.*]] = load i32, i32* [[TMP16]], align 128
// CHECK1-NEXT:    store i32 [[TMP37]], i32* [[TMP36]], align 128
// CHECK1-NEXT:    [[TMP38:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[TMP39:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP38]], i8* [[TMP32]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP40:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    store i32 3, i32* [[TMP40]], align 4
// CHECK1-NEXT:    [[TMP41:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[TMP42:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP43:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP41]], i8* [[TMP42]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK1:       .untied.jmp.5.i:
// CHECK1-NEXT:    [[TMP44:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[TMP45:%.*]] = call i32 @__kmpc_omp_taskyield(%struct.ident_t* @[[GLOB1]], i32 [[TMP44]], i32 0) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP46:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    store i32 4, i32* [[TMP46]], align 4
// CHECK1-NEXT:    [[TMP47:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[TMP48:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP49:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP47]], i8* [[TMP48]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK1:       .untied.jmp.7.i:
// CHECK1-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP_I]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP50:%.*]] = bitcast %struct.S* [[TMP17]] to i8*
// CHECK1-NEXT:    [[TMP51:%.*]] = bitcast %struct.S* [[REF_TMP_I]] to i8*
// CHECK1-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP50]], i8* align 4 [[TMP51]], i64 4, i1 false) #[[ATTR4]]
// CHECK1-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP_I]]) #[[ATTR4]]
// CHECK1-NEXT:    [[A9_I:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 0
// CHECK1-NEXT:    store i32 10, i32* [[A9_I]], align 4
// CHECK1-NEXT:    [[TMP52:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[TMP53:%.*]] = call i32 @__kmpc_omp_taskwait(%struct.ident_t* @[[GLOB1]], i32 [[TMP52]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP54:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    store i32 5, i32* [[TMP54]], align 4
// CHECK1-NEXT:    [[TMP55:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[TMP56:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK1-NEXT:    [[TMP57:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP55]], i8* [[TMP56]]) #[[ATTR4]]
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK1:       .untied.jmp.10.i:
// CHECK1-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TMP19]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP58:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK1-NEXT:    [[TMP59:%.*]] = bitcast %struct.S* [[TMP19]] to i8*
// CHECK1-NEXT:    call void @__kmpc_free(i32 [[TMP58]], i8* [[TMP59]], i8* inttoptr (i64 7 to i8*)) #[[ATTR4]]
// CHECK1-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TMP17]]) #[[ATTR4]]
// CHECK1-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK1-NEXT:    br label [[CLEANUP_I]]
// CHECK1:       cleanup.i:
// CHECK1-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK1-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK1:       .omp_outlined..17.exit:
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SC2Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] 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:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT:    store i32 0, i32* [[A]], align 4
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SD2Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] 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 {{[^@]+}}@__cxx_global_var_init
// CHECK1-SAME: () #[[ATTR7]] section "__TEXT,__StaticInit,regular,pure_instructions" {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    call void @_ZN2S1C1Ev(%struct.S1* nonnull align 4 dereferenceable(4) @s1)
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2S1C1Ev
// CHECK1-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK1-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    call void @_ZN2S1C2Ev(%struct.S1* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2S1C2Ev
// CHECK1-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK1-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    call void @_ZN2S18taskinitEv(%struct.S1* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2S18taskinitEv
// CHECK1-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR8:[0-9]+]] align 2 {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK1-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON_21:%.*]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK1-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK1-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_21]], %struct.anon.21* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK1-NEXT:    store %struct.S1* [[THIS1]], %struct.S1** [[TMP1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 1, i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.22*)* @.omp_task_entry..23 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP3:%.*]] = bitcast i8* [[TMP2]] to %struct.kmp_task_t_with_privates.22*
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_22:%.*]], %struct.kmp_task_t_with_privates.22* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP6:%.*]] = load i8*, i8** [[TMP5]], align 8
// CHECK1-NEXT:    [[TMP7:%.*]] = bitcast %struct.anon.21* [[AGG_CAPTURED]] to i8*
// CHECK1-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP6]], i8* align 8 [[TMP7]], i64 8, i1 false)
// CHECK1-NEXT:    [[TMP8:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP2]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..23
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.22* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.21*, align 8
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.22*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.22* [[TMP1]], %struct.kmp_task_t_with_privates.22** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.22*, %struct.kmp_task_t_with_privates.22** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_22:%.*]], %struct.kmp_task_t_with_privates.22* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.21*
// CHECK1-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.22* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META113:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META116:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META118:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META120:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !122
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !122
// CHECK1-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !122
// CHECK1-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !122
// CHECK1-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !122
// CHECK1-NEXT:    store %struct.anon.21* [[TMP8]], %struct.anon.21** [[__CONTEXT_ADDR_I]], align 8, !noalias !122
// CHECK1-NEXT:    [[TMP10:%.*]] = load %struct.anon.21*, %struct.anon.21** [[__CONTEXT_ADDR_I]], align 8, !noalias !122
// CHECK1-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_21:%.*]], %struct.anon.21* [[TMP10]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP12:%.*]] = load %struct.S1*, %struct.S1** [[TMP11]], align 8
// CHECK1-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], %struct.S1* [[TMP12]], i32 0, i32 0
// CHECK1-NEXT:    store i32 0, i32* [[A_I]], align 4
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z4xxxxv
// CHECK1-SAME: () #[[ATTR8]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    call void @_Z6foobarIvEvv()
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z6foobarIvEvv
// CHECK1-SAME: () #[[ATTR8]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[A:%.*]] = alloca float, 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*, float*)* @.omp_outlined..24 to void (i32*, i32*, ...)*), float* [[A]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..24
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], float* nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR9:[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:    [[A_ADDR:%.*]] = alloca float*, align 8
// CHECK1-NEXT:    [[B:%.*]] = alloca double, align 8
// CHECK1-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON_23:%.*]], 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 float* [[A]], float** [[A_ADDR]], align 8
// CHECK1-NEXT:    [[TMP0:%.*]] = load float*, float** [[A_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:    [[TMP3:%.*]] = call i32 @__kmpc_single(%struct.ident_t* @[[GLOB1]], i32 [[TMP2]])
// CHECK1-NEXT:    [[TMP4:%.*]] = icmp ne i32 [[TMP3]], 0
// CHECK1-NEXT:    br i1 [[TMP4]], label [[OMP_IF_THEN:%.*]], label [[OMP_IF_END:%.*]]
// CHECK1:       omp_if.then:
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_23]], %struct.anon.23* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK1-NEXT:    store float* [[TMP0]], float** [[TMP5]], align 8
// CHECK1-NEXT:    [[TMP6:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP2]], i32 1, i64 48, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.24*)* @.omp_task_entry..27 to i32 (i32, i8*)*))
// CHECK1-NEXT:    [[TMP7:%.*]] = bitcast i8* [[TMP6]] to %struct.kmp_task_t_with_privates.24*
// CHECK1-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_24:%.*]], %struct.kmp_task_t_with_privates.24* [[TMP7]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP8]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
// CHECK1-NEXT:    [[TMP11:%.*]] = bitcast %struct.anon.23* [[AGG_CAPTURED]] to i8*
// CHECK1-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP10]], i8* align 8 [[TMP11]], i64 8, i1 false)
// CHECK1-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_24]], %struct.kmp_task_t_with_privates.24* [[TMP7]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_25:%.*]], %struct..kmp_privates.t.25* [[TMP12]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP14:%.*]] = load double, double* [[B]], align 8
// CHECK1-NEXT:    store double [[TMP14]], double* [[TMP13]], align 8
// CHECK1-NEXT:    [[TMP15:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP2]], i8* [[TMP6]])
// CHECK1-NEXT:    call void @__kmpc_end_single(%struct.ident_t* @[[GLOB1]], i32 [[TMP2]])
// CHECK1-NEXT:    br label [[OMP_IF_END]]
// CHECK1:       omp_if.end:
// CHECK1-NEXT:    call void @__kmpc_barrier(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP2]])
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_privates_map..26
// CHECK1-SAME: (%struct..kmp_privates.t.25* noalias [[TMP0:%.*]], double** noalias [[TMP1:%.*]]) #[[ATTR7]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t.25*, align 8
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca double**, align 8
// CHECK1-NEXT:    store %struct..kmp_privates.t.25* [[TMP0]], %struct..kmp_privates.t.25** [[DOTADDR]], align 8
// CHECK1-NEXT:    store double** [[TMP1]], double*** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load %struct..kmp_privates.t.25*, %struct..kmp_privates.t.25** [[DOTADDR]], align 8
// CHECK1-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_25:%.*]], %struct..kmp_privates.t.25* [[TMP2]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP4:%.*]] = load double**, double*** [[DOTADDR1]], align 8
// CHECK1-NEXT:    store double* [[TMP3]], double** [[TMP4]], align 8
// CHECK1-NEXT:    ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry..27
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.24* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.23*, align 8
// CHECK1-NEXT:    [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca double*, align 8
// CHECK1-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.24*, align 8
// CHECK1-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    store %struct.kmp_task_t_with_privates.24* [[TMP1]], %struct.kmp_task_t_with_privates.24** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.24*, %struct.kmp_task_t_with_privates.24** [[DOTADDR1]], align 8
// CHECK1-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_24:%.*]], %struct.kmp_task_t_with_privates.24* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.23*
// CHECK1-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_24]], %struct.kmp_task_t_with_privates.24* [[TMP3]], i32 0, i32 1
// CHECK1-NEXT:    [[TMP10:%.*]] = bitcast %struct..kmp_privates.t.25* [[TMP9]] to i8*
// CHECK1-NEXT:    [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates.24* [[TMP3]] to i8*
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META123:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META126:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META128:![0-9]+]])
// CHECK1-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META130:![0-9]+]])
// CHECK1-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !132
// CHECK1-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !132
// CHECK1-NEXT:    store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !132
// CHECK1-NEXT:    store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t.25*, double**)* @.omp_task_privates_map..26 to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !132
// CHECK1-NEXT:    store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !132
// CHECK1-NEXT:    store %struct.anon.23* [[TMP8]], %struct.anon.23** [[__CONTEXT_ADDR_I]], align 8, !noalias !132
// CHECK1-NEXT:    [[TMP12:%.*]] = load %struct.anon.23*, %struct.anon.23** [[__CONTEXT_ADDR_I]], align 8, !noalias !132
// CHECK1-NEXT:    [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !132
// CHECK1-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !132
// CHECK1-NEXT:    [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, double**)*
// CHECK1-NEXT:    call void [[TMP15]](i8* [[TMP14]], double** [[DOTFIRSTPRIV_PTR_ADDR_I]]) #[[ATTR4]]
// CHECK1-NEXT:    [[TMP16:%.*]] = load double*, double** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !132
// CHECK1-NEXT:    [[TMP17:%.*]] = load double, double* [[TMP16]], align 8
// CHECK1-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [[STRUCT_ANON_23:%.*]], %struct.anon.23* [[TMP12]], i32 0, i32 0
// CHECK1-NEXT:    [[TMP19:%.*]] = load float*, float** [[TMP18]], align 8
// CHECK1-NEXT:    [[TMP20:%.*]] = load float, float* [[TMP19]], align 4
// CHECK1-NEXT:    [[CONV_I:%.*]] = fpext float [[TMP20]] to double
// CHECK1-NEXT:    [[ADD_I:%.*]] = fadd double [[CONV_I]], [[TMP17]]
// CHECK1-NEXT:    [[CONV1_I:%.*]] = fptrunc double [[ADD_I]] to float
// CHECK1-NEXT:    store float [[CONV1_I]], float* [[TMP19]], align 4
// CHECK1-NEXT:    ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@_GLOBAL__sub_I_task_codegen.cpp
// CHECK1-SAME: () #[[ATTR7]] section "__TEXT,__StaticInit,regular,pure_instructions" {
// CHECK1-NEXT:  entry:
// CHECK1-NEXT:    call void @__cxx_global_var_init()
// 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:    [[B:%.*]] = alloca i8, align 1
// CHECK2-NEXT:    [[S:%.*]] = alloca [2 x %struct.S], align 4
// CHECK2-NEXT:    [[SAVED_STACK:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK2-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 8
// CHECK2-NEXT:    [[AGG_CAPTURED1:%.*]] = alloca [[STRUCT_ANON_0:%.*]], align 8
// CHECK2-NEXT:    [[DOTDEP_ARR_ADDR:%.*]] = alloca [4 x %struct.kmp_depend_info], align 8
// CHECK2-NEXT:    [[DEP_COUNTER_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT:    [[AGG_CAPTURED3:%.*]] = alloca [[STRUCT_ANON_2:%.*]], align 1
// CHECK2-NEXT:    [[AGG_CAPTURED4:%.*]] = alloca [[STRUCT_ANON_4:%.*]], align 1
// CHECK2-NEXT:    [[DOTDEP_ARR_ADDR5:%.*]] = alloca [2 x %struct.kmp_depend_info], align 8
// CHECK2-NEXT:    [[DEP_COUNTER_ADDR11:%.*]] = alloca i64, align 8
// CHECK2-NEXT:    [[AGG_CAPTURED12:%.*]] = alloca [[STRUCT_ANON_6:%.*]], align 1
// CHECK2-NEXT:    [[DOTDEP_ARR_ADDR13:%.*]] = alloca [2 x %struct.kmp_depend_info], align 8
// CHECK2-NEXT:    [[DEP_COUNTER_ADDR19:%.*]] = alloca i64, align 8
// CHECK2-NEXT:    [[AGG_CAPTURED20:%.*]] = alloca [[STRUCT_ANON_8:%.*]], align 1
// CHECK2-NEXT:    [[DOTDEP_ARR_ADDR21:%.*]] = alloca [3 x %struct.kmp_depend_info], align 8
// CHECK2-NEXT:    [[DEP_COUNTER_ADDR27:%.*]] = alloca i64, align 8
// CHECK2-NEXT:    [[AGG_CAPTURED28:%.*]] = alloca [[STRUCT_ANON_10:%.*]], align 1
// CHECK2-NEXT:    [[FLAG:%.*]] = alloca i8, align 1
// CHECK2-NEXT:    [[AGG_CAPTURED29:%.*]] = alloca [[STRUCT_ANON_12:%.*]], align 1
// CHECK2-NEXT:    [[C:%.*]] = alloca i32, align 128
// CHECK2-NEXT:    [[AGG_CAPTURED30:%.*]] = alloca [[STRUCT_ANON_14:%.*]], align 8
// CHECK2-NEXT:    [[AGG_CAPTURED31:%.*]] = alloca [[STRUCT_ANON_16:%.*]], align 1
// CHECK2-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK2-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// CHECK2-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], 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 @_ZN1SC1Ev(%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:    [[TMP1:%.*]] = load i32, i32* @a, align 4
// CHECK2-NEXT:    [[TMP2:%.*]] = zext i32 [[TMP1]] to i64
// CHECK2-NEXT:    [[TMP3:%.*]] = call i8* @llvm.stacksave()
// CHECK2-NEXT:    store i8* [[TMP3]], i8** [[SAVED_STACK]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = mul nuw i64 10, [[TMP2]]
// CHECK2-NEXT:    [[VLA:%.*]] = alloca i32, i64 [[TMP4]], align 16
// CHECK2-NEXT:    store i64 [[TMP2]], i64* [[__VLA_EXPR0]], align 8
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK2-NEXT:    store i8* [[B]], i8** [[TMP5]], align 8
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 1
// CHECK2-NEXT:    store [2 x %struct.S]* [[S]], [2 x %struct.S]** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8, i8* [[B]], align 1
// CHECK2-NEXT:    [[CONV:%.*]] = sext i8 [[TMP7]] to i32
// CHECK2-NEXT:    [[TMP8:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 33, i64 40, i64 16, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast i8* [[TMP8]] to %struct.kmp_task_t_with_privates*
// CHECK2-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP9]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP10]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP12:%.*]] = load i8*, i8** [[TMP11]], align 8
// CHECK2-NEXT:    [[TMP13:%.*]] = bitcast %struct.anon* [[AGG_CAPTURED]] to i8*
// CHECK2-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP12]], i8* align 8 [[TMP13]], i64 16, i1 false)
// CHECK2-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP10]], i32 0, i32 4
// CHECK2-NEXT:    [[TMP15:%.*]] = bitcast %union.kmp_cmplrdata_t* [[TMP14]] to i32*
// CHECK2-NEXT:    store i32 [[CONV]], i32* [[TMP15]], align 8
// CHECK2-NEXT:    [[TMP16:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP8]])
// CHECK2-NEXT:    [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[AGG_CAPTURED1]], i32 0, i32 0
// CHECK2-NEXT:    store [2 x %struct.S]* [[S]], [2 x %struct.S]** [[TMP17]], align 8
// CHECK2-NEXT:    [[TMP18:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 1, i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.1*)* @.omp_task_entry..2 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP19:%.*]] = bitcast i8* [[TMP18]] to %struct.kmp_task_t_with_privates.1*
// CHECK2-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_1:%.*]], %struct.kmp_task_t_with_privates.1* [[TMP19]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP20]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
// CHECK2-NEXT:    [[TMP23:%.*]] = bitcast %struct.anon.0* [[AGG_CAPTURED1]] to i8*
// CHECK2-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP22]], i8* align 8 [[TMP23]], i64 8, i1 false)
// CHECK2-NEXT:    [[TMP24:%.*]] = getelementptr inbounds [4 x %struct.kmp_depend_info], [4 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR]], i64 0, i64 0
// CHECK2-NEXT:    [[TMP25:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO:%.*]], %struct.kmp_depend_info* [[TMP24]], i64 0
// CHECK2-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP25]], i32 0, i32 0
// CHECK2-NEXT:    store i64 ptrtoint (i32* @a to i64), i64* [[TMP26]], align 8
// CHECK2-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP25]], i32 0, i32 1
// CHECK2-NEXT:    store i64 4, i64* [[TMP27]], align 8
// CHECK2-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP25]], i32 0, i32 2
// CHECK2-NEXT:    store i8 1, i8* [[TMP28]], align 8
// CHECK2-NEXT:    [[TMP29:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i64 1
// CHECK2-NEXT:    [[TMP30:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP29]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP31:%.*]] = ptrtoint i8* [[B]] to i64
// CHECK2-NEXT:    store i64 [[TMP31]], i64* [[TMP30]], align 8
// CHECK2-NEXT:    [[TMP32:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP29]], i32 0, i32 1
// CHECK2-NEXT:    store i64 1, i64* [[TMP32]], align 8
// CHECK2-NEXT:    [[TMP33:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP29]], i32 0, i32 2
// CHECK2-NEXT:    store i8 1, i8* [[TMP33]], align 8
// CHECK2-NEXT:    [[TMP34:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i64 2
// CHECK2-NEXT:    [[TMP35:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP34]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP36:%.*]] = ptrtoint [2 x %struct.S]* [[S]] to i64
// CHECK2-NEXT:    store i64 [[TMP36]], i64* [[TMP35]], align 8
// CHECK2-NEXT:    [[TMP37:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP34]], i32 0, i32 1
// CHECK2-NEXT:    store i64 8, i64* [[TMP37]], align 8
// CHECK2-NEXT:    [[TMP38:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP34]], i32 0, i32 2
// CHECK2-NEXT:    store i8 1, i8* [[TMP38]], align 8
// CHECK2-NEXT:    [[TMP39:%.*]] = mul nsw i64 0, [[TMP2]]
// CHECK2-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP39]]
// CHECK2-NEXT:    [[TMP40:%.*]] = mul nsw i64 9, [[TMP2]]
// CHECK2-NEXT:    [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP40]]
// CHECK2-NEXT:    [[TMP41:%.*]] = getelementptr i32, i32* [[ARRAYIDX2]], i32 1
// CHECK2-NEXT:    [[TMP42:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
// CHECK2-NEXT:    [[TMP43:%.*]] = ptrtoint i32* [[TMP41]] to i64
// CHECK2-NEXT:    [[TMP44:%.*]] = sub nuw i64 [[TMP43]], [[TMP42]]
// CHECK2-NEXT:    [[TMP45:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i64 3
// CHECK2-NEXT:    [[TMP46:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP45]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP47:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
// CHECK2-NEXT:    store i64 [[TMP47]], i64* [[TMP46]], align 8
// CHECK2-NEXT:    [[TMP48:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP45]], i32 0, i32 1
// CHECK2-NEXT:    store i64 [[TMP44]], i64* [[TMP48]], align 8
// CHECK2-NEXT:    [[TMP49:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP45]], i32 0, i32 2
// CHECK2-NEXT:    store i8 1, i8* [[TMP49]], align 8
// CHECK2-NEXT:    store i64 4, i64* [[DEP_COUNTER_ADDR]], align 8
// CHECK2-NEXT:    [[TMP50:%.*]] = bitcast %struct.kmp_depend_info* [[TMP24]] to i8*
// CHECK2-NEXT:    [[TMP51:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP18]], i32 4, i8* [[TMP50]], i32 0, i8* null)
// CHECK2-NEXT:    [[TMP52:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.3*)* @.omp_task_entry..4 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP53:%.*]] = bitcast i8* [[TMP52]] to %struct.kmp_task_t_with_privates.3*
// CHECK2-NEXT:    [[TMP54:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_3:%.*]], %struct.kmp_task_t_with_privates.3* [[TMP53]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP55:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP54]], i32 0, i32 2
// CHECK2-NEXT:    store i32 0, i32* [[TMP55]], align 8
// CHECK2-NEXT:    [[TMP56:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP52]])
// CHECK2-NEXT:    [[TMP57:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.5*)* @.omp_task_entry..6 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP58:%.*]] = bitcast i8* [[TMP57]] to %struct.kmp_task_t_with_privates.5*
// CHECK2-NEXT:    [[TMP59:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_5:%.*]], %struct.kmp_task_t_with_privates.5* [[TMP58]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP60:%.*]] = getelementptr inbounds [2 x %struct.kmp_depend_info], [2 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR5]], i64 0, i64 0
// CHECK2-NEXT:    [[ARRAYIDX6:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 0
// CHECK2-NEXT:    [[TMP61:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP60]], i64 0
// CHECK2-NEXT:    [[TMP62:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP61]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP63:%.*]] = ptrtoint %struct.S* [[ARRAYIDX6]] to i64
// CHECK2-NEXT:    store i64 [[TMP63]], i64* [[TMP62]], align 8
// CHECK2-NEXT:    [[TMP64:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP61]], i32 0, i32 1
// CHECK2-NEXT:    store i64 4, i64* [[TMP64]], align 8
// CHECK2-NEXT:    [[TMP65:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP61]], i32 0, i32 2
// CHECK2-NEXT:    store i8 3, i8* [[TMP65]], align 8
// CHECK2-NEXT:    [[TMP66:%.*]] = load i8, i8* [[B]], align 1
// CHECK2-NEXT:    [[TMP67:%.*]] = sext i8 [[TMP66]] to i64
// CHECK2-NEXT:    [[TMP68:%.*]] = mul nsw i64 4, [[TMP2]]
// CHECK2-NEXT:    [[ARRAYIDX7:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP68]]
// CHECK2-NEXT:    [[ARRAYIDX8:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX7]], i64 [[TMP67]]
// CHECK2-NEXT:    [[TMP69:%.*]] = load i8, i8* [[B]], align 1
// CHECK2-NEXT:    [[TMP70:%.*]] = sext i8 [[TMP69]] to i64
// CHECK2-NEXT:    [[TMP71:%.*]] = mul nsw i64 9, [[TMP2]]
// CHECK2-NEXT:    [[ARRAYIDX9:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP71]]
// CHECK2-NEXT:    [[ARRAYIDX10:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX9]], i64 [[TMP70]]
// CHECK2-NEXT:    [[TMP72:%.*]] = getelementptr i32, i32* [[ARRAYIDX10]], i32 1
// CHECK2-NEXT:    [[TMP73:%.*]] = ptrtoint i32* [[ARRAYIDX8]] to i64
// CHECK2-NEXT:    [[TMP74:%.*]] = ptrtoint i32* [[TMP72]] to i64
// CHECK2-NEXT:    [[TMP75:%.*]] = sub nuw i64 [[TMP74]], [[TMP73]]
// CHECK2-NEXT:    [[TMP76:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP60]], i64 1
// CHECK2-NEXT:    [[TMP77:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP76]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP78:%.*]] = ptrtoint i32* [[ARRAYIDX8]] to i64
// CHECK2-NEXT:    store i64 [[TMP78]], i64* [[TMP77]], align 8
// CHECK2-NEXT:    [[TMP79:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP76]], i32 0, i32 1
// CHECK2-NEXT:    store i64 [[TMP75]], i64* [[TMP79]], align 8
// CHECK2-NEXT:    [[TMP80:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP76]], i32 0, i32 2
// CHECK2-NEXT:    store i8 3, i8* [[TMP80]], align 8
// CHECK2-NEXT:    store i64 2, i64* [[DEP_COUNTER_ADDR11]], align 8
// CHECK2-NEXT:    [[TMP81:%.*]] = bitcast %struct.kmp_depend_info* [[TMP60]] to i8*
// CHECK2-NEXT:    [[TMP82:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP59]], i32 0, i32 2
// CHECK2-NEXT:    store i32 0, i32* [[TMP82]], align 8
// CHECK2-NEXT:    [[TMP83:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP57]], i32 2, i8* [[TMP81]], i32 0, i8* null)
// CHECK2-NEXT:    [[TMP84:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.7*)* @.omp_task_entry..8 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP85:%.*]] = bitcast i8* [[TMP84]] to %struct.kmp_task_t_with_privates.7*
// CHECK2-NEXT:    [[TMP86:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_7:%.*]], %struct.kmp_task_t_with_privates.7* [[TMP85]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP87:%.*]] = getelementptr inbounds [2 x %struct.kmp_depend_info], [2 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR13]], i64 0, i64 0
// CHECK2-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 0
// CHECK2-NEXT:    [[TMP88:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP87]], i64 0
// CHECK2-NEXT:    [[TMP89:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP88]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP90:%.*]] = ptrtoint %struct.S* [[ARRAYIDX14]] to i64
// CHECK2-NEXT:    store i64 [[TMP90]], i64* [[TMP89]], align 8
// CHECK2-NEXT:    [[TMP91:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP88]], i32 0, i32 1
// CHECK2-NEXT:    store i64 4, i64* [[TMP91]], align 8
// CHECK2-NEXT:    [[TMP92:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP88]], i32 0, i32 2
// CHECK2-NEXT:    store i8 4, i8* [[TMP92]], align 8
// CHECK2-NEXT:    [[TMP93:%.*]] = load i8, i8* [[B]], align 1
// CHECK2-NEXT:    [[TMP94:%.*]] = sext i8 [[TMP93]] to i64
// CHECK2-NEXT:    [[TMP95:%.*]] = mul nsw i64 4, [[TMP2]]
// CHECK2-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP95]]
// CHECK2-NEXT:    [[ARRAYIDX16:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX15]], i64 [[TMP94]]
// CHECK2-NEXT:    [[TMP96:%.*]] = load i8, i8* [[B]], align 1
// CHECK2-NEXT:    [[TMP97:%.*]] = sext i8 [[TMP96]] to i64
// CHECK2-NEXT:    [[TMP98:%.*]] = mul nsw i64 9, [[TMP2]]
// CHECK2-NEXT:    [[ARRAYIDX17:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP98]]
// CHECK2-NEXT:    [[ARRAYIDX18:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX17]], i64 [[TMP97]]
// CHECK2-NEXT:    [[TMP99:%.*]] = getelementptr i32, i32* [[ARRAYIDX18]], i32 1
// CHECK2-NEXT:    [[TMP100:%.*]] = ptrtoint i32* [[ARRAYIDX16]] to i64
// CHECK2-NEXT:    [[TMP101:%.*]] = ptrtoint i32* [[TMP99]] to i64
// CHECK2-NEXT:    [[TMP102:%.*]] = sub nuw i64 [[TMP101]], [[TMP100]]
// CHECK2-NEXT:    [[TMP103:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP87]], i64 1
// CHECK2-NEXT:    [[TMP104:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP103]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP105:%.*]] = ptrtoint i32* [[ARRAYIDX16]] to i64
// CHECK2-NEXT:    store i64 [[TMP105]], i64* [[TMP104]], align 8
// CHECK2-NEXT:    [[TMP106:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP103]], i32 0, i32 1
// CHECK2-NEXT:    store i64 [[TMP102]], i64* [[TMP106]], align 8
// CHECK2-NEXT:    [[TMP107:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP103]], i32 0, i32 2
// CHECK2-NEXT:    store i8 4, i8* [[TMP107]], align 8
// CHECK2-NEXT:    store i64 2, i64* [[DEP_COUNTER_ADDR19]], align 8
// CHECK2-NEXT:    [[TMP108:%.*]] = bitcast %struct.kmp_depend_info* [[TMP87]] to i8*
// CHECK2-NEXT:    [[TMP109:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP86]], i32 0, i32 2
// CHECK2-NEXT:    store i32 0, i32* [[TMP109]], align 8
// CHECK2-NEXT:    [[TMP110:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP84]], i32 2, i8* [[TMP108]], i32 0, i8* null)
// CHECK2-NEXT:    [[TMP111:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 3, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.9*)* @.omp_task_entry..10 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP112:%.*]] = bitcast i8* [[TMP111]] to %struct.kmp_task_t_with_privates.9*
// CHECK2-NEXT:    [[TMP113:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_9:%.*]], %struct.kmp_task_t_with_privates.9* [[TMP112]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP114:%.*]] = getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR21]], i64 0, i64 0
// CHECK2-NEXT:    [[TMP115:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i64 0
// CHECK2-NEXT:    [[TMP116:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP115]], i32 0, i32 0
// CHECK2-NEXT:    store i64 ptrtoint (i32* @a to i64), i64* [[TMP116]], align 8
// CHECK2-NEXT:    [[TMP117:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP115]], i32 0, i32 1
// CHECK2-NEXT:    store i64 4, i64* [[TMP117]], align 8
// CHECK2-NEXT:    [[TMP118:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP115]], i32 0, i32 2
// CHECK2-NEXT:    store i8 3, i8* [[TMP118]], align 8
// CHECK2-NEXT:    [[ARRAYIDX22:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 1
// CHECK2-NEXT:    [[TMP119:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i64 1
// CHECK2-NEXT:    [[TMP120:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP119]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP121:%.*]] = ptrtoint %struct.S* [[ARRAYIDX22]] to i64
// CHECK2-NEXT:    store i64 [[TMP121]], i64* [[TMP120]], align 8
// CHECK2-NEXT:    [[TMP122:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP119]], i32 0, i32 1
// CHECK2-NEXT:    store i64 4, i64* [[TMP122]], align 8
// CHECK2-NEXT:    [[TMP123:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP119]], i32 0, i32 2
// CHECK2-NEXT:    store i8 3, i8* [[TMP123]], align 8
// CHECK2-NEXT:    [[TMP124:%.*]] = mul nsw i64 0, [[TMP2]]
// CHECK2-NEXT:    [[ARRAYIDX23:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP124]]
// CHECK2-NEXT:    [[ARRAYIDX24:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX23]], i64 3
// CHECK2-NEXT:    [[TMP125:%.*]] = load i32, i32* @a, align 4
// CHECK2-NEXT:    [[TMP126:%.*]] = sext i32 [[TMP125]] to i64
// CHECK2-NEXT:    [[LEN_SUB_1:%.*]] = sub nsw i64 [[TMP126]], 1
// CHECK2-NEXT:    [[TMP127:%.*]] = load i32, i32* @a, align 4
// CHECK2-NEXT:    [[TMP128:%.*]] = sext i32 [[TMP127]] to i64
// CHECK2-NEXT:    [[LB_ADD_LEN:%.*]] = add nsw i64 -1, [[TMP128]]
// CHECK2-NEXT:    [[TMP129:%.*]] = mul nsw i64 [[LB_ADD_LEN]], [[TMP2]]
// CHECK2-NEXT:    [[ARRAYIDX25:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP129]]
// CHECK2-NEXT:    [[ARRAYIDX26:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX25]], i64 [[LEN_SUB_1]]
// CHECK2-NEXT:    [[TMP130:%.*]] = getelementptr i32, i32* [[ARRAYIDX26]], i32 1
// CHECK2-NEXT:    [[TMP131:%.*]] = ptrtoint i32* [[ARRAYIDX24]] to i64
// CHECK2-NEXT:    [[TMP132:%.*]] = ptrtoint i32* [[TMP130]] to i64
// CHECK2-NEXT:    [[TMP133:%.*]] = sub nuw i64 [[TMP132]], [[TMP131]]
// CHECK2-NEXT:    [[TMP134:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i64 2
// CHECK2-NEXT:    [[TMP135:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP134]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP136:%.*]] = ptrtoint i32* [[ARRAYIDX24]] to i64
// CHECK2-NEXT:    store i64 [[TMP136]], i64* [[TMP135]], align 8
// CHECK2-NEXT:    [[TMP137:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP134]], i32 0, i32 1
// CHECK2-NEXT:    store i64 [[TMP133]], i64* [[TMP137]], align 8
// CHECK2-NEXT:    [[TMP138:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP134]], i32 0, i32 2
// CHECK2-NEXT:    store i8 3, i8* [[TMP138]], align 8
// CHECK2-NEXT:    store i64 3, i64* [[DEP_COUNTER_ADDR27]], align 8
// CHECK2-NEXT:    [[TMP139:%.*]] = bitcast %struct.kmp_depend_info* [[TMP114]] to i8*
// CHECK2-NEXT:    [[TMP140:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP111]], i32 3, i8* [[TMP139]], i32 0, i8* null)
// CHECK2-NEXT:    [[TMP141:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 3, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.11*)* @.omp_task_entry..12 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP142:%.*]] = bitcast i8* [[TMP141]] to %struct.kmp_task_t_with_privates.11*
// CHECK2-NEXT:    [[TMP143:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_11:%.*]], %struct.kmp_task_t_with_privates.11* [[TMP142]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP144:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP141]])
// CHECK2-NEXT:    store i8 0, i8* [[FLAG]], align 1
// CHECK2-NEXT:    [[TMP145:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 1, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.13*)* @.omp_task_entry..14 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP146:%.*]] = bitcast i8* [[TMP145]] to %struct.kmp_task_t_with_privates.13*
// CHECK2-NEXT:    [[TMP147:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_13:%.*]], %struct.kmp_task_t_with_privates.13* [[TMP146]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP148:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP145]])
// CHECK2-NEXT:    [[TMP149:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[AGG_CAPTURED30]], i32 0, i32 0
// CHECK2-NEXT:    store i32* [[C]], i32** [[TMP149]], align 8
// CHECK2-NEXT:    [[TMP150:%.*]] = load i8, i8* [[B]], align 1
// CHECK2-NEXT:    [[TOBOOL:%.*]] = icmp ne i8 [[TMP150]], 0
// CHECK2-NEXT:    [[TMP151:%.*]] = select i1 [[TOBOOL]], i32 2, i32 0
// CHECK2-NEXT:    [[TMP152:%.*]] = or i32 [[TMP151]], 1
// CHECK2-NEXT:    [[TMP153:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 [[TMP152]], i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.15*)* @.omp_task_entry..16 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP154:%.*]] = bitcast i8* [[TMP153]] to %struct.kmp_task_t_with_privates.15*
// CHECK2-NEXT:    [[TMP155:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_15:%.*]], %struct.kmp_task_t_with_privates.15* [[TMP154]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP156:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP155]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP157:%.*]] = load i8*, i8** [[TMP156]], align 8
// CHECK2-NEXT:    [[TMP158:%.*]] = bitcast %struct.anon.14* [[AGG_CAPTURED30]] to i8*
// CHECK2-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP157]], i8* align 8 [[TMP158]], i64 8, i1 false)
// CHECK2-NEXT:    [[TMP159:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP153]])
// CHECK2-NEXT:    [[TMP160:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 0, i64 256, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.19*)* @.omp_task_entry..21 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP161:%.*]] = bitcast i8* [[TMP160]] to %struct.kmp_task_t_with_privates.19*
// CHECK2-NEXT:    [[TMP162:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19:%.*]], %struct.kmp_task_t_with_privates.19* [[TMP161]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP163:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19]], %struct.kmp_task_t_with_privates.19* [[TMP161]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP164:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20:%.*]], %struct..kmp_privates.t.20* [[TMP163]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP165:%.*]] = load i32, i32* [[C]], align 128
// CHECK2-NEXT:    store i32 [[TMP165]], i32* [[TMP164]], align 128
// CHECK2-NEXT:    [[TMP166:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP162]], i32 0, i32 2
// CHECK2-NEXT:    store i32 0, i32* [[TMP166]], align 16
// CHECK2-NEXT:    [[TMP167:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP160]])
// CHECK2-NEXT:    [[TMP168:%.*]] = load i32, i32* @a, align 4
// CHECK2-NEXT:    store i32 [[TMP168]], i32* [[RETVAL]], align 4
// CHECK2-NEXT:    [[TMP169:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
// CHECK2-NEXT:    call void @llvm.stackrestore(i8* [[TMP169]])
// CHECK2-NEXT:    [[ARRAY_BEGIN32:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP170:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN32]], i64 2
// CHECK2-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2:       arraydestroy.body:
// CHECK2-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP170]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK2-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK2-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4:[0-9]+]]
// CHECK2-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN32]]
// CHECK2-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE33:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2:       arraydestroy.done33:
// CHECK2-NEXT:    [[TMP171:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK2-NEXT:    ret i32 [[TMP171]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SC1Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] 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 @_ZN1SC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry.
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates* noalias [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon*, align 8
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates* [[TMP1]], %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates*, %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon*
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META3:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META6:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META8:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META10:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !12
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT:    store %struct.anon* [[TMP8]], %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT:    store i32 15, i32* @a, align 4
// CHECK2-NEXT:    [[TMP11:%.*]] = load i32, i32* @a, align 4
// CHECK2-NEXT:    [[CONV_I:%.*]] = trunc i32 [[TMP11]] to i8
// CHECK2-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [[STRUCT_ANON:%.*]], %struct.anon* [[TMP10]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
// CHECK2-NEXT:    store i8 [[CONV_I]], i8* [[TMP13]], align 1
// CHECK2-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP10]], i32 0, i32 1
// CHECK2-NEXT:    [[TMP15:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[TMP14]], align 8
// CHECK2-NEXT:    [[ARRAYIDX_I:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP15]], i64 0, i64 0
// CHECK2-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAYIDX_I]], i32 0, i32 0
// CHECK2-NEXT:    store i32 10, i32* [[A_I]], align 4
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..2
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.1* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.0*, align 8
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.1*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.1* [[TMP1]], %struct.kmp_task_t_with_privates.1** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.1*, %struct.kmp_task_t_with_privates.1** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_1:%.*]], %struct.kmp_task_t_with_privates.1* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.0*
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.1* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META13:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META16:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META18:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META20:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !22
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !22
// CHECK2-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !22
// CHECK2-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !22
// CHECK2-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !22
// CHECK2-NEXT:    store %struct.anon.0* [[TMP8]], %struct.anon.0** [[__CONTEXT_ADDR_I]], align 8, !noalias !22
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.anon.0*, %struct.anon.0** [[__CONTEXT_ADDR_I]], align 8, !noalias !22
// CHECK2-NEXT:    store i32 15, i32* @a, align 4
// CHECK2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_0:%.*]], %struct.anon.0* [[TMP10]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP12:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[TMP11]], align 8
// CHECK2-NEXT:    [[ARRAYIDX_I:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP12]], i64 0, i64 1
// CHECK2-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAYIDX_I]], i32 0, i32 0
// CHECK2-NEXT:    store i32 10, i32* [[A_I]], align 4
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..4
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.3* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.2*, align 8
// CHECK2-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.3*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.3* [[TMP1]], %struct.kmp_task_t_with_privates.3** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.3*, %struct.kmp_task_t_with_privates.3** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_3:%.*]], %struct.kmp_task_t_with_privates.3* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.2*
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.3* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META23:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META26:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META28:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META30:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !32
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK2-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !32
// CHECK2-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !32
// CHECK2-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !32
// CHECK2-NEXT:    store %struct.anon.2* [[TMP8]], %struct.anon.2** [[__CONTEXT_ADDR_I]], align 8, !noalias !32
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.anon.2*, %struct.anon.2** [[__CONTEXT_ADDR_I]], align 8, !noalias !32
// CHECK2-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK2-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK2-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK2-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK2-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK2-NEXT:    ]
// CHECK2:       .untied.done..i:
// CHECK2-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK2-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK2:       .untied.jmp..i:
// CHECK2-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK2-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK2-NEXT:    [[TMP14:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !32
// CHECK2-NEXT:    [[TMP15:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !32
// CHECK2-NEXT:    [[TMP16:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP14]], i8* [[TMP15]]) #[[ATTR4]]
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__3_EXIT:%.*]]
// CHECK2:       .untied.jmp.1.i:
// CHECK2-NEXT:    [[TMP17:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !32
// CHECK2-NEXT:    call void @__kmpc_critical(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], [8 x i32]* @.gomp_critical_user_.var) #[[ATTR4]]
// CHECK2-NEXT:    store i32 1, i32* @a, align 4
// CHECK2-NEXT:    call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB1]], i32 [[TMP17]], [8 x i32]* @.gomp_critical_user_.var) #[[ATTR4]]
// CHECK2-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK2-NEXT:    br label [[CLEANUP_I]]
// CHECK2:       cleanup.i:
// CHECK2-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__3_EXIT]]
// CHECK2:       .omp_outlined..3.exit:
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..6
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.5* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.4*, align 8
// CHECK2-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.5*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.5* [[TMP1]], %struct.kmp_task_t_with_privates.5** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.5*, %struct.kmp_task_t_with_privates.5** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_5:%.*]], %struct.kmp_task_t_with_privates.5* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.4*
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.5* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META33:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META36:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META38:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META40:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !42
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK2-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !42
// CHECK2-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !42
// CHECK2-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !42
// CHECK2-NEXT:    store %struct.anon.4* [[TMP8]], %struct.anon.4** [[__CONTEXT_ADDR_I]], align 8, !noalias !42
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.anon.4*, %struct.anon.4** [[__CONTEXT_ADDR_I]], align 8, !noalias !42
// CHECK2-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK2-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK2-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK2-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK2-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK2-NEXT:    ]
// CHECK2:       .untied.done..i:
// CHECK2-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK2-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK2:       .untied.jmp..i:
// CHECK2-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK2-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK2-NEXT:    [[TMP14:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !42
// CHECK2-NEXT:    [[TMP15:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !42
// CHECK2-NEXT:    [[TMP16:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP14]], i8* [[TMP15]]) #[[ATTR4]]
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__5_EXIT:%.*]]
// CHECK2:       .untied.jmp.1.i:
// CHECK2-NEXT:    store i32 1, i32* @a, align 4
// CHECK2-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK2-NEXT:    br label [[CLEANUP_I]]
// CHECK2:       cleanup.i:
// CHECK2-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__5_EXIT]]
// CHECK2:       .omp_outlined..5.exit:
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..8
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.7* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.6*, align 8
// CHECK2-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.7*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.7* [[TMP1]], %struct.kmp_task_t_with_privates.7** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.7*, %struct.kmp_task_t_with_privates.7** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_7:%.*]], %struct.kmp_task_t_with_privates.7* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.6*
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.7* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META43:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META46:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META48:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META50:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !52
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK2-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !52
// CHECK2-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !52
// CHECK2-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !52
// CHECK2-NEXT:    store %struct.anon.6* [[TMP8]], %struct.anon.6** [[__CONTEXT_ADDR_I]], align 8, !noalias !52
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.anon.6*, %struct.anon.6** [[__CONTEXT_ADDR_I]], align 8, !noalias !52
// CHECK2-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK2-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK2-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK2-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK2-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK2-NEXT:    ]
// CHECK2:       .untied.done..i:
// CHECK2-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK2-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK2:       .untied.jmp..i:
// CHECK2-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK2-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK2-NEXT:    [[TMP14:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !52
// CHECK2-NEXT:    [[TMP15:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !52
// CHECK2-NEXT:    [[TMP16:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP14]], i8* [[TMP15]]) #[[ATTR4]]
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__7_EXIT:%.*]]
// CHECK2:       .untied.jmp.1.i:
// CHECK2-NEXT:    store i32 1, i32* @a, align 4
// CHECK2-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK2-NEXT:    br label [[CLEANUP_I]]
// CHECK2:       cleanup.i:
// CHECK2-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__7_EXIT]]
// CHECK2:       .omp_outlined..7.exit:
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..10
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.9* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.8*, align 8
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.9*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.9* [[TMP1]], %struct.kmp_task_t_with_privates.9** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.9*, %struct.kmp_task_t_with_privates.9** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_9:%.*]], %struct.kmp_task_t_with_privates.9* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.8*
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.9* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META53:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META56:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META58:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META60:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !62
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !62
// CHECK2-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !62
// CHECK2-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !62
// CHECK2-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !62
// CHECK2-NEXT:    store %struct.anon.8* [[TMP8]], %struct.anon.8** [[__CONTEXT_ADDR_I]], align 8, !noalias !62
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.anon.8*, %struct.anon.8** [[__CONTEXT_ADDR_I]], align 8, !noalias !62
// CHECK2-NEXT:    store i32 2, i32* @a, align 4
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..12
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.11* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.10*, align 8
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.11*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.11* [[TMP1]], %struct.kmp_task_t_with_privates.11** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.11*, %struct.kmp_task_t_with_privates.11** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_11:%.*]], %struct.kmp_task_t_with_privates.11* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.10*
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.11* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META63:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META66:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META68:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META70:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !72
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !72
// CHECK2-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !72
// CHECK2-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !72
// CHECK2-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !72
// CHECK2-NEXT:    store %struct.anon.10* [[TMP8]], %struct.anon.10** [[__CONTEXT_ADDR_I]], align 8, !noalias !72
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.anon.10*, %struct.anon.10** [[__CONTEXT_ADDR_I]], align 8, !noalias !72
// CHECK2-NEXT:    store i32 2, i32* @a, align 4
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..14
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.13* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.12*, align 8
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.13*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.13* [[TMP1]], %struct.kmp_task_t_with_privates.13** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.13*, %struct.kmp_task_t_with_privates.13** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_13:%.*]], %struct.kmp_task_t_with_privates.13* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.12*
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.13* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META73:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META76:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META78:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META80:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !82
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !82
// CHECK2-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !82
// CHECK2-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !82
// CHECK2-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !82
// CHECK2-NEXT:    store %struct.anon.12* [[TMP8]], %struct.anon.12** [[__CONTEXT_ADDR_I]], align 8, !noalias !82
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.anon.12*, %struct.anon.12** [[__CONTEXT_ADDR_I]], align 8, !noalias !82
// CHECK2-NEXT:    store i32 3, i32* @a, align 4
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..16
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.15* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.14*, align 8
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.15*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.15* [[TMP1]], %struct.kmp_task_t_with_privates.15** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.15*, %struct.kmp_task_t_with_privates.15** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_15:%.*]], %struct.kmp_task_t_with_privates.15* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.14*
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.15* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META83:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META86:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META88:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META90:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !92
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !92
// CHECK2-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !92
// CHECK2-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !92
// CHECK2-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !92
// CHECK2-NEXT:    store %struct.anon.14* [[TMP8]], %struct.anon.14** [[__CONTEXT_ADDR_I]], align 8, !noalias !92
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.anon.14*, %struct.anon.14** [[__CONTEXT_ADDR_I]], align 8, !noalias !92
// CHECK2-NEXT:    store i32 4, i32* @a, align 4
// CHECK2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_14:%.*]], %struct.anon.14* [[TMP10]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP12:%.*]] = load i32*, i32** [[TMP11]], align 8
// CHECK2-NEXT:    store i32 5, i32* [[TMP12]], align 128
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_privates_map.
// CHECK2-SAME: (%struct..kmp_privates.t* noalias [[TMP0:%.*]], i32** noalias [[TMP1:%.*]]) #[[ATTR7:[0-9]+]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t*, align 8
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca i32**, align 8
// CHECK2-NEXT:    store %struct..kmp_privates.t* [[TMP0]], %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK2-NEXT:    store i32** [[TMP1]], i32*** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load %struct..kmp_privates.t*, %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP2]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP4:%.*]] = load i32**, i32*** [[DOTADDR1]], align 8
// CHECK2-NEXT:    store i32* [[TMP3]], i32** [[TMP4]], align 8
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..19
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.18* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.17*, align 8
// CHECK2-NEXT:    [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.18*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.18* [[TMP1]], %struct.kmp_task_t_with_privates.18** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.18*, %struct.kmp_task_t_with_privates.18** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18:%.*]], %struct.kmp_task_t_with_privates.18* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 128
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.17*
// CHECK2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18]], %struct.kmp_task_t_with_privates.18* [[TMP3]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP10:%.*]] = bitcast %struct..kmp_privates.t* [[TMP9]] to i8*
// CHECK2-NEXT:    [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates.18* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META93:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META96:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META98:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META100:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !102
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !102
// CHECK2-NEXT:    store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !102
// CHECK2-NEXT:    store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t*, i32**)* @.omp_task_privates_map. to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !102
// CHECK2-NEXT:    store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !102
// CHECK2-NEXT:    store %struct.anon.17* [[TMP8]], %struct.anon.17** [[__CONTEXT_ADDR_I]], align 8, !noalias !102
// CHECK2-NEXT:    [[TMP12:%.*]] = load %struct.anon.17*, %struct.anon.17** [[__CONTEXT_ADDR_I]], align 8, !noalias !102
// CHECK2-NEXT:    [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !102
// CHECK2-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !102
// CHECK2-NEXT:    [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i32**)*
// CHECK2-NEXT:    call void [[TMP15]](i8* [[TMP14]], i32** [[DOTFIRSTPRIV_PTR_ADDR_I]]) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP16:%.*]] = load i32*, i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !102
// CHECK2-NEXT:    store i32 4, i32* [[TMP16]], align 128
// CHECK2-NEXT:    store i32 4, i32* @a, align 4
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SD1Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] 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 @_ZN1SD2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_privates_map..20
// CHECK2-SAME: (%struct..kmp_privates.t.20* noalias [[TMP0:%.*]], i32** noalias [[TMP1:%.*]], %struct.S** noalias [[TMP2:%.*]], %struct.S*** noalias [[TMP3:%.*]]) #[[ATTR7]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t.20*, align 8
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca i32**, align 8
// CHECK2-NEXT:    [[DOTADDR2:%.*]] = alloca %struct.S**, align 8
// CHECK2-NEXT:    [[DOTADDR3:%.*]] = alloca %struct.S***, align 8
// CHECK2-NEXT:    store %struct..kmp_privates.t.20* [[TMP0]], %struct..kmp_privates.t.20** [[DOTADDR]], align 8
// CHECK2-NEXT:    store i32** [[TMP1]], i32*** [[DOTADDR1]], align 8
// CHECK2-NEXT:    store %struct.S** [[TMP2]], %struct.S*** [[DOTADDR2]], align 8
// CHECK2-NEXT:    store %struct.S*** [[TMP3]], %struct.S**** [[DOTADDR3]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = load %struct..kmp_privates.t.20*, %struct..kmp_privates.t.20** [[DOTADDR]], align 8
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20:%.*]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP6:%.*]] = load i32**, i32*** [[DOTADDR1]], align 8
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP7:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP8:%.*]] = load %struct.S***, %struct.S**** [[DOTADDR3]], align 8
// CHECK2-NEXT:    store %struct.S** [[TMP7]], %struct.S*** [[TMP8]], align 8
// CHECK2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 3
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.S**, %struct.S*** [[DOTADDR2]], align 8
// CHECK2-NEXT:    store %struct.S* [[TMP9]], %struct.S** [[TMP10]], align 8
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..21
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.19* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.16*, align 8
// CHECK2-NEXT:    [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTLOCAL_PTR_ADDR_I:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT:    [[DOTLOCAL_PTR_ADDR1_I:%.*]] = alloca %struct.S**, align 8
// CHECK2-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[REF_TMP_I:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.19*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.19* [[TMP1]], %struct.kmp_task_t_with_privates.19** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.19*, %struct.kmp_task_t_with_privates.19** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19:%.*]], %struct.kmp_task_t_with_privates.19* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 128
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.16*
// CHECK2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19]], %struct.kmp_task_t_with_privates.19* [[TMP3]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP10:%.*]] = bitcast %struct..kmp_privates.t.20* [[TMP9]] to i8*
// CHECK2-NEXT:    [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates.19* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META103:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META106:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META108:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META110:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t.20*, i32**, %struct.S**, %struct.S***)* @.omp_task_privates_map..20 to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    store %struct.anon.16* [[TMP8]], %struct.anon.16** [[__CONTEXT_ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP12:%.*]] = load %struct.anon.16*, %struct.anon.16** [[__CONTEXT_ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i32**, %struct.S**, %struct.S***)*
// CHECK2-NEXT:    call void [[TMP15]](i8* [[TMP14]], i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], %struct.S** [[DOTLOCAL_PTR_ADDR_I]], %struct.S*** [[DOTLOCAL_PTR_ADDR1_I]]) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP16:%.*]] = load i32*, i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP17:%.*]] = load %struct.S*, %struct.S** [[DOTLOCAL_PTR_ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP18:%.*]] = load %struct.S**, %struct.S*** [[DOTLOCAL_PTR_ADDR1_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP19:%.*]] = load %struct.S*, %struct.S** [[TMP18]], align 8
// CHECK2-NEXT:    [[TMP20:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP21:%.*]] = load i32, i32* [[TMP20]], align 4
// CHECK2-NEXT:    switch i32 [[TMP21]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK2-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK2-NEXT:    i32 1, label [[DOTUNTIED_JMP_2_I:%.*]]
// CHECK2-NEXT:    i32 2, label [[DOTUNTIED_JMP_3_I:%.*]]
// CHECK2-NEXT:    i32 3, label [[DOTUNTIED_JMP_5_I:%.*]]
// CHECK2-NEXT:    i32 4, label [[DOTUNTIED_JMP_7_I:%.*]]
// CHECK2-NEXT:    i32 5, label [[DOTUNTIED_JMP_10_I:%.*]]
// CHECK2-NEXT:    ]
// CHECK2:       .untied.done..i:
// CHECK2-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK2-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK2:       .untied.jmp..i:
// CHECK2-NEXT:    [[TMP22:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    store i32 1, i32* [[TMP22]], align 4
// CHECK2-NEXT:    [[TMP23:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[TMP24:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP25:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP23]], i8* [[TMP24]]) #[[ATTR4]]
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT:%.*]]
// CHECK2:       .untied.jmp.2.i:
// CHECK2-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TMP17]]) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP26:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[DOTS2__VOID_ADDR_I:%.*]] = call i8* @__kmpc_alloc(i32 [[TMP26]], i64 4, i8* inttoptr (i64 7 to i8*)) #[[ATTR4]]
// CHECK2-NEXT:    [[DOTS2__ADDR_I:%.*]] = bitcast i8* [[DOTS2__VOID_ADDR_I]] to %struct.S*
// CHECK2-NEXT:    store %struct.S* [[DOTS2__ADDR_I]], %struct.S** [[TMP18]], align 8
// CHECK2-NEXT:    [[TMP27:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    store i32 2, i32* [[TMP27]], align 4
// CHECK2-NEXT:    [[TMP28:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[TMP29:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP30:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP28]], i8* [[TMP29]]) #[[ATTR4]]
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK2:       .untied.jmp.3.i:
// CHECK2-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TMP19]]) #[[ATTR4]]
// CHECK2-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 0
// CHECK2-NEXT:    store i32 0, i32* [[A_I]], align 4
// CHECK2-NEXT:    [[TMP31:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[TMP32:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP31]], i32 1, i64 256, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.18*)* @.omp_task_entry..19 to i32 (i32, i8*)*)) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP33:%.*]] = bitcast i8* [[TMP32]] to %struct.kmp_task_t_with_privates.18*
// CHECK2-NEXT:    [[TMP34:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18:%.*]], %struct.kmp_task_t_with_privates.18* [[TMP33]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP35:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18]], %struct.kmp_task_t_with_privates.18* [[TMP33]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP36:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP35]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP37:%.*]] = load i32, i32* [[TMP16]], align 128
// CHECK2-NEXT:    store i32 [[TMP37]], i32* [[TMP36]], align 128
// CHECK2-NEXT:    [[TMP38:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[TMP39:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP38]], i8* [[TMP32]]) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP40:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    store i32 3, i32* [[TMP40]], align 4
// CHECK2-NEXT:    [[TMP41:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[TMP42:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP43:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP41]], i8* [[TMP42]]) #[[ATTR4]]
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK2:       .untied.jmp.5.i:
// CHECK2-NEXT:    [[TMP44:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[TMP45:%.*]] = call i32 @__kmpc_omp_taskyield(%struct.ident_t* @[[GLOB1]], i32 [[TMP44]], i32 0) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP46:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    store i32 4, i32* [[TMP46]], align 4
// CHECK2-NEXT:    [[TMP47:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[TMP48:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP49:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP47]], i8* [[TMP48]]) #[[ATTR4]]
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK2:       .untied.jmp.7.i:
// CHECK2-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP_I]]) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP50:%.*]] = bitcast %struct.S* [[TMP17]] to i8*
// CHECK2-NEXT:    [[TMP51:%.*]] = bitcast %struct.S* [[REF_TMP_I]] to i8*
// CHECK2-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP50]], i8* align 4 [[TMP51]], i64 4, i1 false) #[[ATTR4]]
// CHECK2-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP_I]]) #[[ATTR4]]
// CHECK2-NEXT:    [[A9_I:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP19]], i32 0, i32 0
// CHECK2-NEXT:    store i32 10, i32* [[A9_I]], align 4
// CHECK2-NEXT:    [[TMP52:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[TMP53:%.*]] = call i32 @__kmpc_omp_taskwait(%struct.ident_t* @[[GLOB1]], i32 [[TMP52]]) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP54:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    store i32 5, i32* [[TMP54]], align 4
// CHECK2-NEXT:    [[TMP55:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[TMP56:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK2-NEXT:    [[TMP57:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP55]], i8* [[TMP56]]) #[[ATTR4]]
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK2:       .untied.jmp.10.i:
// CHECK2-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TMP19]]) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP58:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK2-NEXT:    [[TMP59:%.*]] = bitcast %struct.S* [[TMP19]] to i8*
// CHECK2-NEXT:    call void @__kmpc_free(i32 [[TMP58]], i8* [[TMP59]], i8* inttoptr (i64 7 to i8*)) #[[ATTR4]]
// CHECK2-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[TMP17]]) #[[ATTR4]]
// CHECK2-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK2-NEXT:    br label [[CLEANUP_I]]
// CHECK2:       cleanup.i:
// CHECK2-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK2-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK2:       .omp_outlined..17.exit:
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SC2Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] 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:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT:    store i32 0, i32* [[A]], align 4
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SD2Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] 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 {{[^@]+}}@__cxx_global_var_init
// CHECK2-SAME: () #[[ATTR7]] section "__TEXT,__StaticInit,regular,pure_instructions" {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    call void @_ZN2S1C1Ev(%struct.S1* nonnull align 4 dereferenceable(4) @s1)
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2S1C1Ev
// CHECK2-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK2-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    call void @_ZN2S1C2Ev(%struct.S1* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2S1C2Ev
// CHECK2-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK2-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    call void @_ZN2S18taskinitEv(%struct.S1* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2S18taskinitEv
// CHECK2-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR8:[0-9]+]] align 2 {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK2-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON_21:%.*]], align 8
// CHECK2-NEXT:    [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]])
// CHECK2-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK2-NEXT:    [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_ANON_21]], %struct.anon.21* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK2-NEXT:    store %struct.S1* [[THIS1]], %struct.S1** [[TMP1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 1, i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.22*)* @.omp_task_entry..23 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP3:%.*]] = bitcast i8* [[TMP2]] to %struct.kmp_task_t_with_privates.22*
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_22:%.*]], %struct.kmp_task_t_with_privates.22* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP6:%.*]] = load i8*, i8** [[TMP5]], align 8
// CHECK2-NEXT:    [[TMP7:%.*]] = bitcast %struct.anon.21* [[AGG_CAPTURED]] to i8*
// CHECK2-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP6]], i8* align 8 [[TMP7]], i64 8, i1 false)
// CHECK2-NEXT:    [[TMP8:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP2]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..23
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.22* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.21*, align 8
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.22*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.22* [[TMP1]], %struct.kmp_task_t_with_privates.22** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.22*, %struct.kmp_task_t_with_privates.22** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_22:%.*]], %struct.kmp_task_t_with_privates.22* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.21*
// CHECK2-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.22* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META113:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META116:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META118:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META120:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !122
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !122
// CHECK2-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !122
// CHECK2-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !122
// CHECK2-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !122
// CHECK2-NEXT:    store %struct.anon.21* [[TMP8]], %struct.anon.21** [[__CONTEXT_ADDR_I]], align 8, !noalias !122
// CHECK2-NEXT:    [[TMP10:%.*]] = load %struct.anon.21*, %struct.anon.21** [[__CONTEXT_ADDR_I]], align 8, !noalias !122
// CHECK2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_21:%.*]], %struct.anon.21* [[TMP10]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP12:%.*]] = load %struct.S1*, %struct.S1** [[TMP11]], align 8
// CHECK2-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], %struct.S1* [[TMP12]], i32 0, i32 0
// CHECK2-NEXT:    store i32 0, i32* [[A_I]], align 4
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z4xxxxv
// CHECK2-SAME: () #[[ATTR8]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    call void @_Z6foobarIvEvv()
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z6foobarIvEvv
// CHECK2-SAME: () #[[ATTR8]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[A:%.*]] = alloca float, 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*, float*)* @.omp_outlined..24 to void (i32*, i32*, ...)*), float* [[A]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..24
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], float* nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR9:[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:    [[A_ADDR:%.*]] = alloca float*, align 8
// CHECK2-NEXT:    [[B:%.*]] = alloca double, align 8
// CHECK2-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON_23:%.*]], 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 float* [[A]], float** [[A_ADDR]], align 8
// CHECK2-NEXT:    [[TMP0:%.*]] = load float*, float** [[A_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:    [[TMP3:%.*]] = call i32 @__kmpc_single(%struct.ident_t* @[[GLOB1]], i32 [[TMP2]])
// CHECK2-NEXT:    [[TMP4:%.*]] = icmp ne i32 [[TMP3]], 0
// CHECK2-NEXT:    br i1 [[TMP4]], label [[OMP_IF_THEN:%.*]], label [[OMP_IF_END:%.*]]
// CHECK2:       omp_if.then:
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON_23]], %struct.anon.23* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK2-NEXT:    store float* [[TMP0]], float** [[TMP5]], align 8
// CHECK2-NEXT:    [[TMP6:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP2]], i32 1, i64 48, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.24*)* @.omp_task_entry..27 to i32 (i32, i8*)*))
// CHECK2-NEXT:    [[TMP7:%.*]] = bitcast i8* [[TMP6]] to %struct.kmp_task_t_with_privates.24*
// CHECK2-NEXT:    [[TMP8:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_24:%.*]], %struct.kmp_task_t_with_privates.24* [[TMP7]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP8]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
// CHECK2-NEXT:    [[TMP11:%.*]] = bitcast %struct.anon.23* [[AGG_CAPTURED]] to i8*
// CHECK2-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP10]], i8* align 8 [[TMP11]], i64 8, i1 false)
// CHECK2-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_24]], %struct.kmp_task_t_with_privates.24* [[TMP7]], i32 0, i32 1
// CHECK2-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_25:%.*]], %struct..kmp_privates.t.25* [[TMP12]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP14:%.*]] = load double, double* [[B]], align 8
// CHECK2-NEXT:    store double [[TMP14]], double* [[TMP13]], align 8
// CHECK2-NEXT:    [[TMP15:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP2]], i8* [[TMP6]])
// CHECK2-NEXT:    call void @__kmpc_end_single(%struct.ident_t* @[[GLOB1]], i32 [[TMP2]])
// CHECK2-NEXT:    br label [[OMP_IF_END]]
// CHECK2:       omp_if.end:
// CHECK2-NEXT:    call void @__kmpc_barrier(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP2]])
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_privates_map..26
// CHECK2-SAME: (%struct..kmp_privates.t.25* noalias [[TMP0:%.*]], double** noalias [[TMP1:%.*]]) #[[ATTR7]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t.25*, align 8
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca double**, align 8
// CHECK2-NEXT:    store %struct..kmp_privates.t.25* [[TMP0]], %struct..kmp_privates.t.25** [[DOTADDR]], align 8
// CHECK2-NEXT:    store double** [[TMP1]], double*** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load %struct..kmp_privates.t.25*, %struct..kmp_privates.t.25** [[DOTADDR]], align 8
// CHECK2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_25:%.*]], %struct..kmp_privates.t.25* [[TMP2]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP4:%.*]] = load double**, double*** [[DOTADDR1]], align 8
// CHECK2-NEXT:    store double* [[TMP3]], double** [[TMP4]], align 8
// CHECK2-NEXT:    ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry..27
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.24* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.23*, align 8
// CHECK2-NEXT:    [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca double*, align 8
// CHECK2-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.24*, align 8
// CHECK2-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    store %struct.kmp_task_t_with_privates.24* [[TMP1]], %struct.kmp_task_t_with_privates.24** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.24*, %struct.kmp_task_t_with_privates.24** [[DOTADDR1]], align 8
// CHECK2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_24:%.*]], %struct.kmp_task_t_with_privates.24* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.23*
// CHECK2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_24]], %struct.kmp_task_t_with_privates.24* [[TMP3]], i32 0, i32 1
// CHECK2-NEXT:    [[TMP10:%.*]] = bitcast %struct..kmp_privates.t.25* [[TMP9]] to i8*
// CHECK2-NEXT:    [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates.24* [[TMP3]] to i8*
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META123:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META126:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META128:![0-9]+]])
// CHECK2-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META130:![0-9]+]])
// CHECK2-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !132
// CHECK2-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !132
// CHECK2-NEXT:    store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !132
// CHECK2-NEXT:    store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t.25*, double**)* @.omp_task_privates_map..26 to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !132
// CHECK2-NEXT:    store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !132
// CHECK2-NEXT:    store %struct.anon.23* [[TMP8]], %struct.anon.23** [[__CONTEXT_ADDR_I]], align 8, !noalias !132
// CHECK2-NEXT:    [[TMP12:%.*]] = load %struct.anon.23*, %struct.anon.23** [[__CONTEXT_ADDR_I]], align 8, !noalias !132
// CHECK2-NEXT:    [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !132
// CHECK2-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !132
// CHECK2-NEXT:    [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, double**)*
// CHECK2-NEXT:    call void [[TMP15]](i8* [[TMP14]], double** [[DOTFIRSTPRIV_PTR_ADDR_I]]) #[[ATTR4]]
// CHECK2-NEXT:    [[TMP16:%.*]] = load double*, double** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !132
// CHECK2-NEXT:    [[TMP17:%.*]] = load double, double* [[TMP16]], align 8
// CHECK2-NEXT:    [[TMP18:%.*]] = getelementptr inbounds [[STRUCT_ANON_23:%.*]], %struct.anon.23* [[TMP12]], i32 0, i32 0
// CHECK2-NEXT:    [[TMP19:%.*]] = load float*, float** [[TMP18]], align 8
// CHECK2-NEXT:    [[TMP20:%.*]] = load float, float* [[TMP19]], align 4
// CHECK2-NEXT:    [[CONV_I:%.*]] = fpext float [[TMP20]] to double
// CHECK2-NEXT:    [[ADD_I:%.*]] = fadd double [[CONV_I]], [[TMP17]]
// CHECK2-NEXT:    [[CONV1_I:%.*]] = fptrunc double [[ADD_I]] to float
// CHECK2-NEXT:    store float [[CONV1_I]], float* [[TMP19]], align 4
// CHECK2-NEXT:    ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@_GLOBAL__sub_I_task_codegen.cpp
// CHECK2-SAME: () #[[ATTR7]] section "__TEXT,__StaticInit,regular,pure_instructions" {
// CHECK2-NEXT:  entry:
// CHECK2-NEXT:    call void @__cxx_global_var_init()
// 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:    [[B:%.*]] = alloca i8, align 1
// CHECK3-NEXT:    [[S:%.*]] = alloca [2 x %struct.S], align 4
// CHECK3-NEXT:    [[SAVED_STACK:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK3-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 8
// CHECK3-NEXT:    [[AGG_CAPTURED2:%.*]] = alloca [[STRUCT_ANON_0:%.*]], align 8
// CHECK3-NEXT:    [[DOTDEP_ARR_ADDR:%.*]] = alloca [4 x %struct.kmp_depend_info], align 8
// CHECK3-NEXT:    [[DEP_COUNTER_ADDR:%.*]] = alloca i64, align 8
// CHECK3-NEXT:    [[AGG_CAPTURED6:%.*]] = alloca [[STRUCT_ANON_2:%.*]], align 1
// CHECK3-NEXT:    [[AGG_CAPTURED9:%.*]] = alloca [[STRUCT_ANON_4:%.*]], align 1
// CHECK3-NEXT:    [[DOTDEP_ARR_ADDR11:%.*]] = alloca [2 x %struct.kmp_depend_info], align 8
// CHECK3-NEXT:    [[DEP_COUNTER_ADDR17:%.*]] = alloca i64, align 8
// CHECK3-NEXT:    [[AGG_CAPTURED19:%.*]] = alloca [[STRUCT_ANON_6:%.*]], align 1
// CHECK3-NEXT:    [[DOTDEP_ARR_ADDR21:%.*]] = alloca [2 x %struct.kmp_depend_info], align 8
// CHECK3-NEXT:    [[DEP_COUNTER_ADDR27:%.*]] = alloca i64, align 8
// CHECK3-NEXT:    [[AGG_CAPTURED29:%.*]] = alloca [[STRUCT_ANON_8:%.*]], align 1
// CHECK3-NEXT:    [[DOTDEP_ARR_ADDR31:%.*]] = alloca [3 x %struct.kmp_depend_info], align 8
// CHECK3-NEXT:    [[DEP_COUNTER_ADDR37:%.*]] = alloca i64, align 8
// CHECK3-NEXT:    [[AGG_CAPTURED39:%.*]] = alloca [[STRUCT_ANON_10:%.*]], align 1
// CHECK3-NEXT:    [[FLAG:%.*]] = alloca i8, align 1
// CHECK3-NEXT:    [[AGG_CAPTURED42:%.*]] = alloca [[STRUCT_ANON_12:%.*]], align 1
// CHECK3-NEXT:    [[C:%.*]] = alloca i32, align 128
// CHECK3-NEXT:    [[AGG_CAPTURED45:%.*]] = alloca [[STRUCT_ANON_14:%.*]], align 8
// CHECK3-NEXT:    [[AGG_CAPTURED48:%.*]] = alloca [[STRUCT_ANON_16:%.*]], align 1
// CHECK3-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// CHECK3-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i32 0, i32 0
// CHECK3-NEXT:    [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 2
// CHECK3-NEXT:    br label [[ARRAYCTOR_LOOP:%.*]]
// CHECK3:       arrayctor.loop:
// CHECK3-NEXT:    [[ARRAYCTOR_CUR:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
// CHECK3-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
// CHECK3-NEXT:    [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYCTOR_CUR]], i64 1
// CHECK3-NEXT:    [[ARRAYCTOR_DONE:%.*]] = icmp eq %struct.S* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
// CHECK3-NEXT:    br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
// CHECK3:       arrayctor.cont:
// CHECK3-NEXT:    [[TMP0:%.*]] = load i32, i32* @a, align 4
// CHECK3-NEXT:    [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
// CHECK3-NEXT:    [[TMP2:%.*]] = call i8* @llvm.stacksave()
// CHECK3-NEXT:    store i8* [[TMP2]], i8** [[SAVED_STACK]], align 8
// CHECK3-NEXT:    [[TMP3:%.*]] = mul nuw i64 10, [[TMP1]]
// CHECK3-NEXT:    [[VLA:%.*]] = alloca i32, i64 [[TMP3]], align 16
// CHECK3-NEXT:    store i64 [[TMP1]], i64* [[__VLA_EXPR0]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK3-NEXT:    store i8* [[B]], i8** [[TMP4]], align 8
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 1
// CHECK3-NEXT:    store [2 x %struct.S]* [[S]], [2 x %struct.S]** [[TMP5]], align 8
// CHECK3-NEXT:    [[TMP6:%.*]] = load i8, i8* [[B]], align 1
// CHECK3-NEXT:    [[CONV:%.*]] = sext i8 [[TMP6]] to i32
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3:[0-9]+]])
// CHECK3-NEXT:    [[TMP7:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[OMP_GLOBAL_THREAD_NUM]], i32 33, i64 40, i64 16, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.kmp_task_t_with_privates*
// CHECK3-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP8]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP9]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP11:%.*]] = load i8*, i8** [[TMP10]], align 8
// CHECK3-NEXT:    [[TMP12:%.*]] = bitcast %struct.anon* [[AGG_CAPTURED]] to i8*
// CHECK3-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP11]], i8* align 8 [[TMP12]], i64 16, i1 false)
// CHECK3-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP9]], i32 0, i32 4
// CHECK3-NEXT:    [[TMP14:%.*]] = bitcast %union.kmp_cmplrdata_t* [[TMP13]] to i32*
// CHECK3-NEXT:    store i32 [[CONV]], i32* [[TMP14]], align 8
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3]])
// CHECK3-NEXT:    [[TMP15:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM1]], i8* [[TMP7]])
// CHECK3-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[AGG_CAPTURED2]], i32 0, i32 0
// CHECK3-NEXT:    store [2 x %struct.S]* [[S]], [2 x %struct.S]** [[TMP16]], align 8
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM3:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB5:[0-9]+]])
// CHECK3-NEXT:    [[TMP17:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM3]], i32 1, i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.1*)* @.omp_task_entry..2 to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP18:%.*]] = bitcast i8* [[TMP17]] to %struct.kmp_task_t_with_privates.1*
// CHECK3-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_1:%.*]], %struct.kmp_task_t_with_privates.1* [[TMP18]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP19]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP21:%.*]] = load i8*, i8** [[TMP20]], align 8
// CHECK3-NEXT:    [[TMP22:%.*]] = bitcast %struct.anon.0* [[AGG_CAPTURED2]] to i8*
// CHECK3-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP21]], i8* align 8 [[TMP22]], i64 8, i1 false)
// CHECK3-NEXT:    [[TMP23:%.*]] = getelementptr inbounds [4 x %struct.kmp_depend_info], [4 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR]], i64 0, i64 0
// CHECK3-NEXT:    [[TMP24:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO:%.*]], %struct.kmp_depend_info* [[TMP23]], i64 0
// CHECK3-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i32 0, i32 0
// CHECK3-NEXT:    store i64 ptrtoint (i32* @a to i64), i64* [[TMP25]], align 8
// CHECK3-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i32 0, i32 1
// CHECK3-NEXT:    store i64 4, i64* [[TMP26]], align 8
// CHECK3-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i32 0, i32 2
// CHECK3-NEXT:    store i8 1, i8* [[TMP27]], align 8
// CHECK3-NEXT:    [[TMP28:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP23]], i64 1
// CHECK3-NEXT:    [[TMP29:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP28]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP30:%.*]] = ptrtoint i8* [[B]] to i64
// CHECK3-NEXT:    store i64 [[TMP30]], i64* [[TMP29]], align 8
// CHECK3-NEXT:    [[TMP31:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP28]], i32 0, i32 1
// CHECK3-NEXT:    store i64 1, i64* [[TMP31]], align 8
// CHECK3-NEXT:    [[TMP32:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP28]], i32 0, i32 2
// CHECK3-NEXT:    store i8 1, i8* [[TMP32]], align 8
// CHECK3-NEXT:    [[TMP33:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP23]], i64 2
// CHECK3-NEXT:    [[TMP34:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP33]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP35:%.*]] = ptrtoint [2 x %struct.S]* [[S]] to i64
// CHECK3-NEXT:    store i64 [[TMP35]], i64* [[TMP34]], align 8
// CHECK3-NEXT:    [[TMP36:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP33]], i32 0, i32 1
// CHECK3-NEXT:    store i64 8, i64* [[TMP36]], align 8
// CHECK3-NEXT:    [[TMP37:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP33]], i32 0, i32 2
// CHECK3-NEXT:    store i8 1, i8* [[TMP37]], align 8
// CHECK3-NEXT:    [[TMP38:%.*]] = mul nsw i64 0, [[TMP1]]
// CHECK3-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP38]]
// CHECK3-NEXT:    [[TMP39:%.*]] = mul nsw i64 9, [[TMP1]]
// CHECK3-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP39]]
// CHECK3-NEXT:    [[TMP40:%.*]] = getelementptr i32, i32* [[ARRAYIDX4]], i32 1
// CHECK3-NEXT:    [[TMP41:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
// CHECK3-NEXT:    [[TMP42:%.*]] = ptrtoint i32* [[TMP40]] to i64
// CHECK3-NEXT:    [[TMP43:%.*]] = sub nuw i64 [[TMP42]], [[TMP41]]
// CHECK3-NEXT:    [[TMP44:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP23]], i64 3
// CHECK3-NEXT:    [[TMP45:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP44]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP46:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
// CHECK3-NEXT:    store i64 [[TMP46]], i64* [[TMP45]], align 8
// CHECK3-NEXT:    [[TMP47:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP44]], i32 0, i32 1
// CHECK3-NEXT:    store i64 [[TMP43]], i64* [[TMP47]], align 8
// CHECK3-NEXT:    [[TMP48:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP44]], i32 0, i32 2
// CHECK3-NEXT:    store i8 1, i8* [[TMP48]], align 8
// CHECK3-NEXT:    store i64 4, i64* [[DEP_COUNTER_ADDR]], align 8
// CHECK3-NEXT:    [[TMP49:%.*]] = bitcast %struct.kmp_depend_info* [[TMP23]] to i8*
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM5:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB5]])
// CHECK3-NEXT:    [[TMP50:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM5]], i8* [[TMP17]], i32 4, i8* [[TMP49]], i32 0, i8* null)
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM7:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB7:[0-9]+]])
// CHECK3-NEXT:    [[TMP51:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM7]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.3*)* @.omp_task_entry..4 to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP52:%.*]] = bitcast i8* [[TMP51]] to %struct.kmp_task_t_with_privates.3*
// CHECK3-NEXT:    [[TMP53:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_3:%.*]], %struct.kmp_task_t_with_privates.3* [[TMP52]], i32 0, i32 0
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM8:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB7]])
// CHECK3-NEXT:    [[TMP54:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP53]], i32 0, i32 2
// CHECK3-NEXT:    store i32 0, i32* [[TMP54]], align 8
// CHECK3-NEXT:    [[TMP55:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM8]], i8* [[TMP51]])
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM10:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB9:[0-9]+]])
// CHECK3-NEXT:    [[TMP56:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM10]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.5*)* @.omp_task_entry..6 to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP57:%.*]] = bitcast i8* [[TMP56]] to %struct.kmp_task_t_with_privates.5*
// CHECK3-NEXT:    [[TMP58:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_5:%.*]], %struct.kmp_task_t_with_privates.5* [[TMP57]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP59:%.*]] = getelementptr inbounds [2 x %struct.kmp_depend_info], [2 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR11]], i64 0, i64 0
// CHECK3-NEXT:    [[ARRAYIDX12:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 0
// CHECK3-NEXT:    [[TMP60:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP59]], i64 0
// CHECK3-NEXT:    [[TMP61:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP60]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP62:%.*]] = ptrtoint %struct.S* [[ARRAYIDX12]] to i64
// CHECK3-NEXT:    store i64 [[TMP62]], i64* [[TMP61]], align 8
// CHECK3-NEXT:    [[TMP63:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP60]], i32 0, i32 1
// CHECK3-NEXT:    store i64 4, i64* [[TMP63]], align 8
// CHECK3-NEXT:    [[TMP64:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP60]], i32 0, i32 2
// CHECK3-NEXT:    store i8 3, i8* [[TMP64]], align 8
// CHECK3-NEXT:    [[TMP65:%.*]] = load i8, i8* [[B]], align 1
// CHECK3-NEXT:    [[TMP66:%.*]] = sext i8 [[TMP65]] to i64
// CHECK3-NEXT:    [[TMP67:%.*]] = mul nsw i64 4, [[TMP1]]
// CHECK3-NEXT:    [[ARRAYIDX13:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP67]]
// CHECK3-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX13]], i64 [[TMP66]]
// CHECK3-NEXT:    [[TMP68:%.*]] = load i8, i8* [[B]], align 1
// CHECK3-NEXT:    [[TMP69:%.*]] = sext i8 [[TMP68]] to i64
// CHECK3-NEXT:    [[TMP70:%.*]] = mul nsw i64 9, [[TMP1]]
// CHECK3-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP70]]
// CHECK3-NEXT:    [[ARRAYIDX16:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX15]], i64 [[TMP69]]
// CHECK3-NEXT:    [[TMP71:%.*]] = getelementptr i32, i32* [[ARRAYIDX16]], i32 1
// CHECK3-NEXT:    [[TMP72:%.*]] = ptrtoint i32* [[ARRAYIDX14]] to i64
// CHECK3-NEXT:    [[TMP73:%.*]] = ptrtoint i32* [[TMP71]] to i64
// CHECK3-NEXT:    [[TMP74:%.*]] = sub nuw i64 [[TMP73]], [[TMP72]]
// CHECK3-NEXT:    [[TMP75:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP59]], i64 1
// CHECK3-NEXT:    [[TMP76:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP75]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP77:%.*]] = ptrtoint i32* [[ARRAYIDX14]] to i64
// CHECK3-NEXT:    store i64 [[TMP77]], i64* [[TMP76]], align 8
// CHECK3-NEXT:    [[TMP78:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP75]], i32 0, i32 1
// CHECK3-NEXT:    store i64 [[TMP74]], i64* [[TMP78]], align 8
// CHECK3-NEXT:    [[TMP79:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP75]], i32 0, i32 2
// CHECK3-NEXT:    store i8 3, i8* [[TMP79]], align 8
// CHECK3-NEXT:    store i64 2, i64* [[DEP_COUNTER_ADDR17]], align 8
// CHECK3-NEXT:    [[TMP80:%.*]] = bitcast %struct.kmp_depend_info* [[TMP59]] to i8*
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM18:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB9]])
// CHECK3-NEXT:    [[TMP81:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP58]], i32 0, i32 2
// CHECK3-NEXT:    store i32 0, i32* [[TMP81]], align 8
// CHECK3-NEXT:    [[TMP82:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM18]], i8* [[TMP56]], i32 2, i8* [[TMP80]], i32 0, i8* null)
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM20:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB11:[0-9]+]])
// CHECK3-NEXT:    [[TMP83:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM20]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.7*)* @.omp_task_entry..8 to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP84:%.*]] = bitcast i8* [[TMP83]] to %struct.kmp_task_t_with_privates.7*
// CHECK3-NEXT:    [[TMP85:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_7:%.*]], %struct.kmp_task_t_with_privates.7* [[TMP84]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP86:%.*]] = getelementptr inbounds [2 x %struct.kmp_depend_info], [2 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR21]], i64 0, i64 0
// CHECK3-NEXT:    [[ARRAYIDX22:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 0
// CHECK3-NEXT:    [[TMP87:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP86]], i64 0
// CHECK3-NEXT:    [[TMP88:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP87]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP89:%.*]] = ptrtoint %struct.S* [[ARRAYIDX22]] to i64
// CHECK3-NEXT:    store i64 [[TMP89]], i64* [[TMP88]], align 8
// CHECK3-NEXT:    [[TMP90:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP87]], i32 0, i32 1
// CHECK3-NEXT:    store i64 4, i64* [[TMP90]], align 8
// CHECK3-NEXT:    [[TMP91:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP87]], i32 0, i32 2
// CHECK3-NEXT:    store i8 4, i8* [[TMP91]], align 8
// CHECK3-NEXT:    [[TMP92:%.*]] = load i8, i8* [[B]], align 1
// CHECK3-NEXT:    [[TMP93:%.*]] = sext i8 [[TMP92]] to i64
// CHECK3-NEXT:    [[TMP94:%.*]] = mul nsw i64 4, [[TMP1]]
// CHECK3-NEXT:    [[ARRAYIDX23:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP94]]
// CHECK3-NEXT:    [[ARRAYIDX24:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX23]], i64 [[TMP93]]
// CHECK3-NEXT:    [[TMP95:%.*]] = load i8, i8* [[B]], align 1
// CHECK3-NEXT:    [[TMP96:%.*]] = sext i8 [[TMP95]] to i64
// CHECK3-NEXT:    [[TMP97:%.*]] = mul nsw i64 9, [[TMP1]]
// CHECK3-NEXT:    [[ARRAYIDX25:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP97]]
// CHECK3-NEXT:    [[ARRAYIDX26:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX25]], i64 [[TMP96]]
// CHECK3-NEXT:    [[TMP98:%.*]] = getelementptr i32, i32* [[ARRAYIDX26]], i32 1
// CHECK3-NEXT:    [[TMP99:%.*]] = ptrtoint i32* [[ARRAYIDX24]] to i64
// CHECK3-NEXT:    [[TMP100:%.*]] = ptrtoint i32* [[TMP98]] to i64
// CHECK3-NEXT:    [[TMP101:%.*]] = sub nuw i64 [[TMP100]], [[TMP99]]
// CHECK3-NEXT:    [[TMP102:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP86]], i64 1
// CHECK3-NEXT:    [[TMP103:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP102]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP104:%.*]] = ptrtoint i32* [[ARRAYIDX24]] to i64
// CHECK3-NEXT:    store i64 [[TMP104]], i64* [[TMP103]], align 8
// CHECK3-NEXT:    [[TMP105:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP102]], i32 0, i32 1
// CHECK3-NEXT:    store i64 [[TMP101]], i64* [[TMP105]], align 8
// CHECK3-NEXT:    [[TMP106:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP102]], i32 0, i32 2
// CHECK3-NEXT:    store i8 4, i8* [[TMP106]], align 8
// CHECK3-NEXT:    store i64 2, i64* [[DEP_COUNTER_ADDR27]], align 8
// CHECK3-NEXT:    [[TMP107:%.*]] = bitcast %struct.kmp_depend_info* [[TMP86]] to i8*
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM28:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB11]])
// CHECK3-NEXT:    [[TMP108:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP85]], i32 0, i32 2
// CHECK3-NEXT:    store i32 0, i32* [[TMP108]], align 8
// CHECK3-NEXT:    [[TMP109:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM28]], i8* [[TMP83]], i32 2, i8* [[TMP107]], i32 0, i8* null)
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM30:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB13:[0-9]+]])
// CHECK3-NEXT:    [[TMP110:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM30]], i32 3, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.9*)* @.omp_task_entry..10 to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP111:%.*]] = bitcast i8* [[TMP110]] to %struct.kmp_task_t_with_privates.9*
// CHECK3-NEXT:    [[TMP112:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_9:%.*]], %struct.kmp_task_t_with_privates.9* [[TMP111]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP113:%.*]] = getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR31]], i64 0, i64 0
// CHECK3-NEXT:    [[TMP114:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP113]], i64 0
// CHECK3-NEXT:    [[TMP115:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i32 0, i32 0
// CHECK3-NEXT:    store i64 ptrtoint (i32* @a to i64), i64* [[TMP115]], align 8
// CHECK3-NEXT:    [[TMP116:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i32 0, i32 1
// CHECK3-NEXT:    store i64 4, i64* [[TMP116]], align 8
// CHECK3-NEXT:    [[TMP117:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i32 0, i32 2
// CHECK3-NEXT:    store i8 3, i8* [[TMP117]], align 8
// CHECK3-NEXT:    [[ARRAYIDX32:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 1
// CHECK3-NEXT:    [[TMP118:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP113]], i64 1
// CHECK3-NEXT:    [[TMP119:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP118]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP120:%.*]] = ptrtoint %struct.S* [[ARRAYIDX32]] to i64
// CHECK3-NEXT:    store i64 [[TMP120]], i64* [[TMP119]], align 8
// CHECK3-NEXT:    [[TMP121:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP118]], i32 0, i32 1
// CHECK3-NEXT:    store i64 4, i64* [[TMP121]], align 8
// CHECK3-NEXT:    [[TMP122:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP118]], i32 0, i32 2
// CHECK3-NEXT:    store i8 3, i8* [[TMP122]], align 8
// CHECK3-NEXT:    [[TMP123:%.*]] = mul nsw i64 0, [[TMP1]]
// CHECK3-NEXT:    [[ARRAYIDX33:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP123]]
// CHECK3-NEXT:    [[ARRAYIDX34:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX33]], i64 3
// CHECK3-NEXT:    [[TMP124:%.*]] = load i32, i32* @a, align 4
// CHECK3-NEXT:    [[TMP125:%.*]] = sext i32 [[TMP124]] to i64
// CHECK3-NEXT:    [[LEN_SUB_1:%.*]] = sub nsw i64 [[TMP125]], 1
// CHECK3-NEXT:    [[TMP126:%.*]] = load i32, i32* @a, align 4
// CHECK3-NEXT:    [[TMP127:%.*]] = sext i32 [[TMP126]] to i64
// CHECK3-NEXT:    [[LB_ADD_LEN:%.*]] = add nsw i64 -1, [[TMP127]]
// CHECK3-NEXT:    [[TMP128:%.*]] = mul nsw i64 [[LB_ADD_LEN]], [[TMP1]]
// CHECK3-NEXT:    [[ARRAYIDX35:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP128]]
// CHECK3-NEXT:    [[ARRAYIDX36:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX35]], i64 [[LEN_SUB_1]]
// CHECK3-NEXT:    [[TMP129:%.*]] = getelementptr i32, i32* [[ARRAYIDX36]], i32 1
// CHECK3-NEXT:    [[TMP130:%.*]] = ptrtoint i32* [[ARRAYIDX34]] to i64
// CHECK3-NEXT:    [[TMP131:%.*]] = ptrtoint i32* [[TMP129]] to i64
// CHECK3-NEXT:    [[TMP132:%.*]] = sub nuw i64 [[TMP131]], [[TMP130]]
// CHECK3-NEXT:    [[TMP133:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP113]], i64 2
// CHECK3-NEXT:    [[TMP134:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP133]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP135:%.*]] = ptrtoint i32* [[ARRAYIDX34]] to i64
// CHECK3-NEXT:    store i64 [[TMP135]], i64* [[TMP134]], align 8
// CHECK3-NEXT:    [[TMP136:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP133]], i32 0, i32 1
// CHECK3-NEXT:    store i64 [[TMP132]], i64* [[TMP136]], align 8
// CHECK3-NEXT:    [[TMP137:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP133]], i32 0, i32 2
// CHECK3-NEXT:    store i8 3, i8* [[TMP137]], align 8
// CHECK3-NEXT:    store i64 3, i64* [[DEP_COUNTER_ADDR37]], align 8
// CHECK3-NEXT:    [[TMP138:%.*]] = bitcast %struct.kmp_depend_info* [[TMP113]] to i8*
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM38:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB13]])
// CHECK3-NEXT:    [[TMP139:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM38]], i8* [[TMP110]], i32 3, i8* [[TMP138]], i32 0, i8* null)
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM40:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB15:[0-9]+]])
// CHECK3-NEXT:    [[TMP140:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM40]], i32 3, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.11*)* @.omp_task_entry..12 to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP141:%.*]] = bitcast i8* [[TMP140]] to %struct.kmp_task_t_with_privates.11*
// CHECK3-NEXT:    [[TMP142:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_11:%.*]], %struct.kmp_task_t_with_privates.11* [[TMP141]], i32 0, i32 0
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM41:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB15]])
// CHECK3-NEXT:    [[TMP143:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM41]], i8* [[TMP140]])
// CHECK3-NEXT:    store i8 0, i8* [[FLAG]], align 1
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM43:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB17:[0-9]+]])
// CHECK3-NEXT:    [[TMP144:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM43]], i32 1, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.13*)* @.omp_task_entry..14 to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP145:%.*]] = bitcast i8* [[TMP144]] to %struct.kmp_task_t_with_privates.13*
// CHECK3-NEXT:    [[TMP146:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_13:%.*]], %struct.kmp_task_t_with_privates.13* [[TMP145]], i32 0, i32 0
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM44:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB17]])
// CHECK3-NEXT:    [[TMP147:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM44]], i8* [[TMP144]])
// CHECK3-NEXT:    [[TMP148:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[AGG_CAPTURED45]], i32 0, i32 0
// CHECK3-NEXT:    store i32* [[C]], i32** [[TMP148]], align 8
// CHECK3-NEXT:    [[TMP149:%.*]] = load i8, i8* [[B]], align 1
// CHECK3-NEXT:    [[TOBOOL:%.*]] = icmp ne i8 [[TMP149]], 0
// CHECK3-NEXT:    [[TMP150:%.*]] = select i1 [[TOBOOL]], i32 2, i32 0
// CHECK3-NEXT:    [[TMP151:%.*]] = or i32 [[TMP150]], 1
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM46:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB19:[0-9]+]])
// CHECK3-NEXT:    [[TMP152:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM46]], i32 [[TMP151]], i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.15*)* @.omp_task_entry..16 to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP153:%.*]] = bitcast i8* [[TMP152]] to %struct.kmp_task_t_with_privates.15*
// CHECK3-NEXT:    [[TMP154:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_15:%.*]], %struct.kmp_task_t_with_privates.15* [[TMP153]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP155:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP154]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP156:%.*]] = load i8*, i8** [[TMP155]], align 8
// CHECK3-NEXT:    [[TMP157:%.*]] = bitcast %struct.anon.14* [[AGG_CAPTURED45]] to i8*
// CHECK3-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP156]], i8* align 8 [[TMP157]], i64 8, i1 false)
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM47:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB19]])
// CHECK3-NEXT:    [[TMP158:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM47]], i8* [[TMP152]])
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM49:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21:[0-9]+]])
// CHECK3-NEXT:    [[TMP159:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM49]], i32 0, i64 256, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.19*)* @.omp_task_entry..21 to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP160:%.*]] = bitcast i8* [[TMP159]] to %struct.kmp_task_t_with_privates.19*
// CHECK3-NEXT:    [[TMP161:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19:%.*]], %struct.kmp_task_t_with_privates.19* [[TMP160]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP162:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19]], %struct.kmp_task_t_with_privates.19* [[TMP160]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP163:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20:%.*]], %struct..kmp_privates.t.20* [[TMP162]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP164:%.*]] = load i32, i32* [[C]], align 128
// CHECK3-NEXT:    store i32 [[TMP164]], i32* [[TMP163]], align 128
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM50:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21]])
// CHECK3-NEXT:    [[TMP165:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP161]], i32 0, i32 2
// CHECK3-NEXT:    store i32 0, i32* [[TMP165]], align 16
// CHECK3-NEXT:    [[TMP166:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM50]], i8* [[TMP159]])
// CHECK3-NEXT:    [[TMP167:%.*]] = load i32, i32* @a, align 4
// CHECK3-NEXT:    store i32 [[TMP167]], i32* [[RETVAL]], align 4
// CHECK3-NEXT:    [[TMP168:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
// CHECK3-NEXT:    call void @llvm.stackrestore(i8* [[TMP168]])
// CHECK3-NEXT:    [[ARRAY_BEGIN51:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP169:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN51]], i64 2
// CHECK3-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK3:       arraydestroy.body:
// CHECK3-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP169]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK3-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK3-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4:[0-9]+]]
// CHECK3-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN51]]
// CHECK3-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE52:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK3:       arraydestroy.done52:
// CHECK3-NEXT:    [[TMP170:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK3-NEXT:    ret i32 [[TMP170]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SC1Ev
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK3-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    call void @_ZN1SC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry.
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates* noalias [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon*, align 8
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates* [[TMP1]], %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates*, %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon*
// CHECK3-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META3:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META6:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META8:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META10:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !12
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !12
// CHECK3-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !12
// CHECK3-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !12
// CHECK3-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !12
// CHECK3-NEXT:    store %struct.anon* [[TMP8]], %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK3-NEXT:    store i32 15, i32* @a, align 4
// CHECK3-NEXT:    [[TMP11:%.*]] = load i32, i32* @a, align 4
// CHECK3-NEXT:    [[CONV_I:%.*]] = trunc i32 [[TMP11]] to i8
// CHECK3-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [[STRUCT_ANON:%.*]], %struct.anon* [[TMP10]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
// CHECK3-NEXT:    store i8 [[CONV_I]], i8* [[TMP13]], align 1
// CHECK3-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP10]], i32 0, i32 1
// CHECK3-NEXT:    [[TMP15:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[TMP14]], align 8
// CHECK3-NEXT:    [[ARRAYIDX_I:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP15]], i64 0, i64 0
// CHECK3-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAYIDX_I]], i32 0, i32 0
// CHECK3-NEXT:    store i32 10, i32* [[A_I]], align 4
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..2
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.1* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.0*, align 8
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.1*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.1* [[TMP1]], %struct.kmp_task_t_with_privates.1** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.1*, %struct.kmp_task_t_with_privates.1** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_1:%.*]], %struct.kmp_task_t_with_privates.1* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.0*
// CHECK3-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.1* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META13:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META16:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META18:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META20:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !22
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !22
// CHECK3-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !22
// CHECK3-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !22
// CHECK3-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !22
// CHECK3-NEXT:    store %struct.anon.0* [[TMP8]], %struct.anon.0** [[__CONTEXT_ADDR_I]], align 8, !noalias !22
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.anon.0*, %struct.anon.0** [[__CONTEXT_ADDR_I]], align 8, !noalias !22
// CHECK3-NEXT:    store i32 15, i32* @a, align 4
// CHECK3-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_0:%.*]], %struct.anon.0* [[TMP10]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP12:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[TMP11]], align 8
// CHECK3-NEXT:    [[ARRAYIDX_I:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP12]], i64 0, i64 1
// CHECK3-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAYIDX_I]], i32 0, i32 0
// CHECK3-NEXT:    store i32 10, i32* [[A_I]], align 4
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..4
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.3* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.2*, align 8
// CHECK3-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.3*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.3* [[TMP1]], %struct.kmp_task_t_with_privates.3** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.3*, %struct.kmp_task_t_with_privates.3** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_3:%.*]], %struct.kmp_task_t_with_privates.3* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.2*
// CHECK3-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.3* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META23:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META26:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META28:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META30:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !32
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK3-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !32
// CHECK3-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !32
// CHECK3-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !32
// CHECK3-NEXT:    store %struct.anon.2* [[TMP8]], %struct.anon.2** [[__CONTEXT_ADDR_I]], align 8, !noalias !32
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.anon.2*, %struct.anon.2** [[__CONTEXT_ADDR_I]], align 8, !noalias !32
// CHECK3-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK3-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK3-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK3-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK3-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK3-NEXT:    ]
// CHECK3:       .untied.done..i:
// CHECK3-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK3-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK3:       .untied.jmp..i:
// CHECK3-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK3-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB7]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !32
// CHECK3-NEXT:    [[TMP15:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM_I]], i8* [[TMP14]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__3_EXIT:%.*]]
// CHECK3:       .untied.jmp.1.i:
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM2_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR4]]
// CHECK3-NEXT:    call void @__kmpc_critical(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM2_I]], [8 x i32]* @.gomp_critical_user_.var) #[[ATTR4]]
// CHECK3-NEXT:    store i32 1, i32* @a, align 4
// CHECK3-NEXT:    call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM2_I]], [8 x i32]* @.gomp_critical_user_.var) #[[ATTR4]]
// CHECK3-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK3-NEXT:    br label [[CLEANUP_I]]
// CHECK3:       cleanup.i:
// CHECK3-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__3_EXIT]]
// CHECK3:       .omp_outlined..3.exit:
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..6
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.5* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.4*, align 8
// CHECK3-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.5*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.5* [[TMP1]], %struct.kmp_task_t_with_privates.5** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.5*, %struct.kmp_task_t_with_privates.5** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_5:%.*]], %struct.kmp_task_t_with_privates.5* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.4*
// CHECK3-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.5* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META33:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META36:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META38:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META40:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !42
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK3-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !42
// CHECK3-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !42
// CHECK3-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !42
// CHECK3-NEXT:    store %struct.anon.4* [[TMP8]], %struct.anon.4** [[__CONTEXT_ADDR_I]], align 8, !noalias !42
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.anon.4*, %struct.anon.4** [[__CONTEXT_ADDR_I]], align 8, !noalias !42
// CHECK3-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK3-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK3-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK3-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK3-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK3-NEXT:    ]
// CHECK3:       .untied.done..i:
// CHECK3-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK3-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK3:       .untied.jmp..i:
// CHECK3-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK3-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB9]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !42
// CHECK3-NEXT:    [[TMP15:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM_I]], i8* [[TMP14]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__5_EXIT:%.*]]
// CHECK3:       .untied.jmp.1.i:
// CHECK3-NEXT:    store i32 1, i32* @a, align 4
// CHECK3-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK3-NEXT:    br label [[CLEANUP_I]]
// CHECK3:       cleanup.i:
// CHECK3-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__5_EXIT]]
// CHECK3:       .omp_outlined..5.exit:
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..8
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.7* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.6*, align 8
// CHECK3-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.7*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.7* [[TMP1]], %struct.kmp_task_t_with_privates.7** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.7*, %struct.kmp_task_t_with_privates.7** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_7:%.*]], %struct.kmp_task_t_with_privates.7* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.6*
// CHECK3-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.7* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META43:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META46:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META48:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META50:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !52
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK3-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !52
// CHECK3-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !52
// CHECK3-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !52
// CHECK3-NEXT:    store %struct.anon.6* [[TMP8]], %struct.anon.6** [[__CONTEXT_ADDR_I]], align 8, !noalias !52
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.anon.6*, %struct.anon.6** [[__CONTEXT_ADDR_I]], align 8, !noalias !52
// CHECK3-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK3-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK3-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK3-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK3-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK3-NEXT:    ]
// CHECK3:       .untied.done..i:
// CHECK3-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK3-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK3:       .untied.jmp..i:
// CHECK3-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK3-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB11]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !52
// CHECK3-NEXT:    [[TMP15:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM_I]], i8* [[TMP14]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__7_EXIT:%.*]]
// CHECK3:       .untied.jmp.1.i:
// CHECK3-NEXT:    store i32 1, i32* @a, align 4
// CHECK3-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK3-NEXT:    br label [[CLEANUP_I]]
// CHECK3:       cleanup.i:
// CHECK3-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__7_EXIT]]
// CHECK3:       .omp_outlined..7.exit:
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..10
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.9* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.8*, align 8
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.9*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.9* [[TMP1]], %struct.kmp_task_t_with_privates.9** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.9*, %struct.kmp_task_t_with_privates.9** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_9:%.*]], %struct.kmp_task_t_with_privates.9* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.8*
// CHECK3-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.9* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META53:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META56:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META58:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META60:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !62
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !62
// CHECK3-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !62
// CHECK3-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !62
// CHECK3-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !62
// CHECK3-NEXT:    store %struct.anon.8* [[TMP8]], %struct.anon.8** [[__CONTEXT_ADDR_I]], align 8, !noalias !62
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.anon.8*, %struct.anon.8** [[__CONTEXT_ADDR_I]], align 8, !noalias !62
// CHECK3-NEXT:    store i32 2, i32* @a, align 4
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..12
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.11* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.10*, align 8
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.11*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.11* [[TMP1]], %struct.kmp_task_t_with_privates.11** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.11*, %struct.kmp_task_t_with_privates.11** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_11:%.*]], %struct.kmp_task_t_with_privates.11* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.10*
// CHECK3-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.11* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META63:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META66:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META68:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META70:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !72
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !72
// CHECK3-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !72
// CHECK3-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !72
// CHECK3-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !72
// CHECK3-NEXT:    store %struct.anon.10* [[TMP8]], %struct.anon.10** [[__CONTEXT_ADDR_I]], align 8, !noalias !72
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.anon.10*, %struct.anon.10** [[__CONTEXT_ADDR_I]], align 8, !noalias !72
// CHECK3-NEXT:    store i32 2, i32* @a, align 4
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..14
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.13* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.12*, align 8
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.13*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.13* [[TMP1]], %struct.kmp_task_t_with_privates.13** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.13*, %struct.kmp_task_t_with_privates.13** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_13:%.*]], %struct.kmp_task_t_with_privates.13* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.12*
// CHECK3-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.13* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META73:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META76:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META78:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META80:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !82
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !82
// CHECK3-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !82
// CHECK3-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !82
// CHECK3-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !82
// CHECK3-NEXT:    store %struct.anon.12* [[TMP8]], %struct.anon.12** [[__CONTEXT_ADDR_I]], align 8, !noalias !82
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.anon.12*, %struct.anon.12** [[__CONTEXT_ADDR_I]], align 8, !noalias !82
// CHECK3-NEXT:    store i32 3, i32* @a, align 4
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..16
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.15* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.14*, align 8
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.15*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.15* [[TMP1]], %struct.kmp_task_t_with_privates.15** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.15*, %struct.kmp_task_t_with_privates.15** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_15:%.*]], %struct.kmp_task_t_with_privates.15* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.14*
// CHECK3-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.15* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META83:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META86:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META88:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META90:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !92
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !92
// CHECK3-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !92
// CHECK3-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !92
// CHECK3-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !92
// CHECK3-NEXT:    store %struct.anon.14* [[TMP8]], %struct.anon.14** [[__CONTEXT_ADDR_I]], align 8, !noalias !92
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.anon.14*, %struct.anon.14** [[__CONTEXT_ADDR_I]], align 8, !noalias !92
// CHECK3-NEXT:    store i32 4, i32* @a, align 4
// CHECK3-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_14:%.*]], %struct.anon.14* [[TMP10]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP12:%.*]] = load i32*, i32** [[TMP11]], align 8
// CHECK3-NEXT:    store i32 5, i32* [[TMP12]], align 128
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_privates_map.
// CHECK3-SAME: (%struct..kmp_privates.t* noalias [[TMP0:%.*]], i32** noalias [[TMP1:%.*]]) #[[ATTR7:[0-9]+]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t*, align 8
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca i32**, align 8
// CHECK3-NEXT:    store %struct..kmp_privates.t* [[TMP0]], %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK3-NEXT:    store i32** [[TMP1]], i32*** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load %struct..kmp_privates.t*, %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK3-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP2]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP4:%.*]] = load i32**, i32*** [[DOTADDR1]], align 8
// CHECK3-NEXT:    store i32* [[TMP3]], i32** [[TMP4]], align 8
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..19
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.18* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.17*, align 8
// CHECK3-NEXT:    [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.18*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.18* [[TMP1]], %struct.kmp_task_t_with_privates.18** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.18*, %struct.kmp_task_t_with_privates.18** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18:%.*]], %struct.kmp_task_t_with_privates.18* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 128
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.17*
// CHECK3-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18]], %struct.kmp_task_t_with_privates.18* [[TMP3]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP10:%.*]] = bitcast %struct..kmp_privates.t* [[TMP9]] to i8*
// CHECK3-NEXT:    [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates.18* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META93:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META96:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META98:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META100:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !102
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !102
// CHECK3-NEXT:    store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !102
// CHECK3-NEXT:    store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t*, i32**)* @.omp_task_privates_map. to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !102
// CHECK3-NEXT:    store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !102
// CHECK3-NEXT:    store %struct.anon.17* [[TMP8]], %struct.anon.17** [[__CONTEXT_ADDR_I]], align 8, !noalias !102
// CHECK3-NEXT:    [[TMP12:%.*]] = load %struct.anon.17*, %struct.anon.17** [[__CONTEXT_ADDR_I]], align 8, !noalias !102
// CHECK3-NEXT:    [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !102
// CHECK3-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !102
// CHECK3-NEXT:    [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i32**)*
// CHECK3-NEXT:    call void [[TMP15]](i8* [[TMP14]], i32** [[DOTFIRSTPRIV_PTR_ADDR_I]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP16:%.*]] = load i32*, i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !102
// CHECK3-NEXT:    store i32 4, i32* [[TMP16]], align 128
// CHECK3-NEXT:    store i32 4, i32* @a, align 4
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SD1Ev
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK3-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    call void @_ZN1SD2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_privates_map..20
// CHECK3-SAME: (%struct..kmp_privates.t.20* noalias [[TMP0:%.*]], i32** noalias [[TMP1:%.*]], %struct.S** noalias [[TMP2:%.*]], %struct.S** noalias [[TMP3:%.*]]) #[[ATTR7]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t.20*, align 8
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca i32**, align 8
// CHECK3-NEXT:    [[DOTADDR2:%.*]] = alloca %struct.S**, align 8
// CHECK3-NEXT:    [[DOTADDR3:%.*]] = alloca %struct.S**, align 8
// CHECK3-NEXT:    store %struct..kmp_privates.t.20* [[TMP0]], %struct..kmp_privates.t.20** [[DOTADDR]], align 8
// CHECK3-NEXT:    store i32** [[TMP1]], i32*** [[DOTADDR1]], align 8
// CHECK3-NEXT:    store %struct.S** [[TMP2]], %struct.S*** [[DOTADDR2]], align 8
// CHECK3-NEXT:    store %struct.S** [[TMP3]], %struct.S*** [[DOTADDR3]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = load %struct..kmp_privates.t.20*, %struct..kmp_privates.t.20** [[DOTADDR]], align 8
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20:%.*]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP6:%.*]] = load i32**, i32*** [[DOTADDR1]], align 8
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP7:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 1
// CHECK3-NEXT:    [[TMP8:%.*]] = load %struct.S**, %struct.S*** [[DOTADDR2]], align 8
// CHECK3-NEXT:    store %struct.S* [[TMP7]], %struct.S** [[TMP8]], align 8
// CHECK3-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.S**, %struct.S*** [[DOTADDR3]], align 8
// CHECK3-NEXT:    store %struct.S* [[TMP9]], %struct.S** [[TMP10]], align 8
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..21
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.19* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.16*, align 8
// CHECK3-NEXT:    [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTLOCAL_PTR_ADDR_I:%.*]] = alloca %struct.S*, align 8
// CHECK3-NEXT:    [[DOTLOCAL_PTR_ADDR1_I:%.*]] = alloca %struct.S*, align 8
// CHECK3-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[S1_I:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK3-NEXT:    [[S2_I:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK3-NEXT:    [[REF_TMP_I:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.19*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.19* [[TMP1]], %struct.kmp_task_t_with_privates.19** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.19*, %struct.kmp_task_t_with_privates.19** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19:%.*]], %struct.kmp_task_t_with_privates.19* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 128
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.16*
// CHECK3-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19]], %struct.kmp_task_t_with_privates.19* [[TMP3]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP10:%.*]] = bitcast %struct..kmp_privates.t.20* [[TMP9]] to i8*
// CHECK3-NEXT:    [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates.19* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META103:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META106:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META108:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META110:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t.20*, i32**, %struct.S**, %struct.S**)* @.omp_task_privates_map..20 to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    store %struct.anon.16* [[TMP8]], %struct.anon.16** [[__CONTEXT_ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP12:%.*]] = load %struct.anon.16*, %struct.anon.16** [[__CONTEXT_ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i32**, %struct.S**, %struct.S**)*
// CHECK3-NEXT:    call void [[TMP15]](i8* [[TMP14]], i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], %struct.S** [[DOTLOCAL_PTR_ADDR_I]], %struct.S** [[DOTLOCAL_PTR_ADDR1_I]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP16:%.*]] = load i32*, i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP17:%.*]] = load %struct.S*, %struct.S** [[DOTLOCAL_PTR_ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP18:%.*]] = load %struct.S*, %struct.S** [[DOTLOCAL_PTR_ADDR1_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP19:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP20:%.*]] = load i32, i32* [[TMP19]], align 4
// CHECK3-NEXT:    switch i32 [[TMP20]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK3-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK3-NEXT:    i32 1, label [[DOTUNTIED_JMP_2_I:%.*]]
// CHECK3-NEXT:    i32 2, label [[DOTUNTIED_JMP_6_I:%.*]]
// CHECK3-NEXT:    i32 3, label [[DOTUNTIED_JMP_10_I:%.*]]
// CHECK3-NEXT:    i32 4, label [[DOTUNTIED_JMP_15_I:%.*]]
// CHECK3-NEXT:    ]
// CHECK3:       .untied.done..i:
// CHECK3-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK3-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK3:       .untied.jmp..i:
// CHECK3-NEXT:    [[TMP21:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    store i32 1, i32* [[TMP21]], align 4
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP22:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP23:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM_I]], i8* [[TMP22]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT:%.*]]
// CHECK3:       .untied.jmp.2.i:
// CHECK3-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[S1_I]]) #[[ATTR4]]
// CHECK3-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[S2_I]]) #[[ATTR4]]
// CHECK3-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[S2_I]], i32 0, i32 0
// CHECK3-NEXT:    store i32 0, i32* [[A_I]], align 4, !noalias !112
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM3_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB23:[0-9]+]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP24:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM3_I]], i32 1, i64 256, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.18*)* @.omp_task_entry..19 to i32 (i32, i8*)*)) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP25:%.*]] = bitcast i8* [[TMP24]] to %struct.kmp_task_t_with_privates.18*
// CHECK3-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18:%.*]], %struct.kmp_task_t_with_privates.18* [[TMP25]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18]], %struct.kmp_task_t_with_privates.18* [[TMP25]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP27]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP29:%.*]] = load i32, i32* [[TMP16]], align 128
// CHECK3-NEXT:    store i32 [[TMP29]], i32* [[TMP28]], align 128
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM4_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB23]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP30:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM4_I]], i8* [[TMP24]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP31:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    store i32 2, i32* [[TMP31]], align 4
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM5_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP32:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP33:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM5_I]], i8* [[TMP32]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK3:       .untied.jmp.6.i:
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM8_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP34:%.*]] = call i32 @__kmpc_omp_taskyield(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM8_I]], i32 0) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP35:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    store i32 3, i32* [[TMP35]], align 4
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM9_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP36:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP37:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM9_I]], i8* [[TMP36]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK3:       .untied.jmp.10.i:
// CHECK3-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP_I]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP38:%.*]] = bitcast %struct.S* [[S1_I]] to i8*
// CHECK3-NEXT:    [[TMP39:%.*]] = bitcast %struct.S* [[REF_TMP_I]] to i8*
// CHECK3-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP38]], i8* align 4 [[TMP39]], i64 4, i1 false) #[[ATTR4]], !noalias !112
// CHECK3-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP_I]]) #[[ATTR4]]
// CHECK3-NEXT:    [[A12_I:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[S2_I]], i32 0, i32 0
// CHECK3-NEXT:    store i32 10, i32* [[A12_I]], align 4, !noalias !112
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM13_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP40:%.*]] = call i32 @__kmpc_omp_taskwait(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM13_I]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP41:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    store i32 4, i32* [[TMP41]], align 4
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM14_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21]]) #[[ATTR4]]
// CHECK3-NEXT:    [[TMP42:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK3-NEXT:    [[TMP43:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM14_I]], i8* [[TMP42]]) #[[ATTR4]]
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK3:       .untied.jmp.15.i:
// CHECK3-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[S2_I]]) #[[ATTR4]]
// CHECK3-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[S1_I]]) #[[ATTR4]]
// CHECK3-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK3-NEXT:    br label [[CLEANUP_I]]
// CHECK3:       cleanup.i:
// CHECK3-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK3-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK3:       .omp_outlined..17.exit:
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SC2Ev
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK3-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT:    store i32 0, i32* [[A]], align 4
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SD2Ev
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK3-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__cxx_global_var_init
// CHECK3-SAME: () #[[ATTR7]] section "__TEXT,__StaticInit,regular,pure_instructions" {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    call void @_ZN2S1C1Ev(%struct.S1* nonnull align 4 dereferenceable(4) @s1)
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2S1C1Ev
// CHECK3-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK3-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    call void @_ZN2S1C2Ev(%struct.S1* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2S1C2Ev
// CHECK3-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK3-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    call void @_ZN2S18taskinitEv(%struct.S1* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2S18taskinitEv
// CHECK3-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR8:[0-9]+]] align 2 {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK3-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON_21:%.*]], align 8
// CHECK3-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK3-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [[STRUCT_ANON_21]], %struct.anon.21* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK3-NEXT:    store %struct.S1* [[THIS1]], %struct.S1** [[TMP0]], align 8
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB25:[0-9]+]])
// CHECK3-NEXT:    [[TMP1:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM]], i32 1, i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.22*)* @.omp_task_entry..23 to i32 (i32, i8*)*))
// CHECK3-NEXT:    [[TMP2:%.*]] = bitcast i8* [[TMP1]] to %struct.kmp_task_t_with_privates.22*
// CHECK3-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_22:%.*]], %struct.kmp_task_t_with_privates.22* [[TMP2]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = load i8*, i8** [[TMP4]], align 8
// CHECK3-NEXT:    [[TMP6:%.*]] = bitcast %struct.anon.21* [[AGG_CAPTURED]] to i8*
// CHECK3-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP5]], i8* align 8 [[TMP6]], i64 8, i1 false)
// CHECK3-NEXT:    [[OMP_GLOBAL_THREAD_NUM2:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB25]])
// CHECK3-NEXT:    [[TMP7:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM2]], i8* [[TMP1]])
// CHECK3-NEXT:    ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_task_entry..23
// CHECK3-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.22* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK3-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK3-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK3-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.21*, align 8
// CHECK3-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.22*, align 8
// CHECK3-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    store %struct.kmp_task_t_with_privates.22* [[TMP1]], %struct.kmp_task_t_with_privates.22** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK3-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.22*, %struct.kmp_task_t_with_privates.22** [[DOTADDR1]], align 8
// CHECK3-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_22:%.*]], %struct.kmp_task_t_with_privates.22* [[TMP3]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK3-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.21*
// CHECK3-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.22* [[TMP3]] to i8*
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META113:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META116:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META118:![0-9]+]])
// CHECK3-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META120:![0-9]+]])
// CHECK3-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !122
// CHECK3-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !122
// CHECK3-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !122
// CHECK3-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !122
// CHECK3-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !122
// CHECK3-NEXT:    store %struct.anon.21* [[TMP8]], %struct.anon.21** [[__CONTEXT_ADDR_I]], align 8, !noalias !122
// CHECK3-NEXT:    [[TMP10:%.*]] = load %struct.anon.21*, %struct.anon.21** [[__CONTEXT_ADDR_I]], align 8, !noalias !122
// CHECK3-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_21:%.*]], %struct.anon.21* [[TMP10]], i32 0, i32 0
// CHECK3-NEXT:    [[TMP12:%.*]] = load %struct.S1*, %struct.S1** [[TMP11]], align 8
// CHECK3-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], %struct.S1* [[TMP12]], i32 0, i32 0
// CHECK3-NEXT:    store i32 0, i32* [[A_I]], align 4
// CHECK3-NEXT:    ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@_GLOBAL__sub_I_task_codegen.cpp
// CHECK3-SAME: () #[[ATTR7]] section "__TEXT,__StaticInit,regular,pure_instructions" {
// CHECK3-NEXT:  entry:
// CHECK3-NEXT:    call void @__cxx_global_var_init()
// CHECK3-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@main
// CHECK4-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[RETVAL:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[B:%.*]] = alloca i8, align 1
// CHECK4-NEXT:    [[S:%.*]] = alloca [2 x %struct.S], align 4
// CHECK4-NEXT:    [[SAVED_STACK:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK4-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 8
// CHECK4-NEXT:    [[AGG_CAPTURED2:%.*]] = alloca [[STRUCT_ANON_0:%.*]], align 8
// CHECK4-NEXT:    [[DOTDEP_ARR_ADDR:%.*]] = alloca [4 x %struct.kmp_depend_info], align 8
// CHECK4-NEXT:    [[DEP_COUNTER_ADDR:%.*]] = alloca i64, align 8
// CHECK4-NEXT:    [[AGG_CAPTURED6:%.*]] = alloca [[STRUCT_ANON_2:%.*]], align 1
// CHECK4-NEXT:    [[AGG_CAPTURED9:%.*]] = alloca [[STRUCT_ANON_4:%.*]], align 1
// CHECK4-NEXT:    [[DOTDEP_ARR_ADDR11:%.*]] = alloca [2 x %struct.kmp_depend_info], align 8
// CHECK4-NEXT:    [[DEP_COUNTER_ADDR17:%.*]] = alloca i64, align 8
// CHECK4-NEXT:    [[AGG_CAPTURED19:%.*]] = alloca [[STRUCT_ANON_6:%.*]], align 1
// CHECK4-NEXT:    [[DOTDEP_ARR_ADDR21:%.*]] = alloca [2 x %struct.kmp_depend_info], align 8
// CHECK4-NEXT:    [[DEP_COUNTER_ADDR27:%.*]] = alloca i64, align 8
// CHECK4-NEXT:    [[AGG_CAPTURED29:%.*]] = alloca [[STRUCT_ANON_8:%.*]], align 1
// CHECK4-NEXT:    [[DOTDEP_ARR_ADDR31:%.*]] = alloca [3 x %struct.kmp_depend_info], align 8
// CHECK4-NEXT:    [[DEP_COUNTER_ADDR37:%.*]] = alloca i64, align 8
// CHECK4-NEXT:    [[AGG_CAPTURED39:%.*]] = alloca [[STRUCT_ANON_10:%.*]], align 1
// CHECK4-NEXT:    [[FLAG:%.*]] = alloca i8, align 1
// CHECK4-NEXT:    [[AGG_CAPTURED42:%.*]] = alloca [[STRUCT_ANON_12:%.*]], align 1
// CHECK4-NEXT:    [[C:%.*]] = alloca i32, align 128
// CHECK4-NEXT:    [[AGG_CAPTURED45:%.*]] = alloca [[STRUCT_ANON_14:%.*]], align 8
// CHECK4-NEXT:    [[AGG_CAPTURED48:%.*]] = alloca [[STRUCT_ANON_16:%.*]], align 1
// CHECK4-NEXT:    store i32 0, i32* [[RETVAL]], align 4
// CHECK4-NEXT:    [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i32 0, i32 0
// CHECK4-NEXT:    [[ARRAYCTOR_END:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAY_BEGIN]], i64 2
// CHECK4-NEXT:    br label [[ARRAYCTOR_LOOP:%.*]]
// CHECK4:       arrayctor.loop:
// CHECK4-NEXT:    [[ARRAYCTOR_CUR:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY:%.*]] ], [ [[ARRAYCTOR_NEXT:%.*]], [[ARRAYCTOR_LOOP]] ]
// CHECK4-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYCTOR_CUR]])
// CHECK4-NEXT:    [[ARRAYCTOR_NEXT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYCTOR_CUR]], i64 1
// CHECK4-NEXT:    [[ARRAYCTOR_DONE:%.*]] = icmp eq %struct.S* [[ARRAYCTOR_NEXT]], [[ARRAYCTOR_END]]
// CHECK4-NEXT:    br i1 [[ARRAYCTOR_DONE]], label [[ARRAYCTOR_CONT:%.*]], label [[ARRAYCTOR_LOOP]]
// CHECK4:       arrayctor.cont:
// CHECK4-NEXT:    [[TMP0:%.*]] = load i32, i32* @a, align 4
// CHECK4-NEXT:    [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
// CHECK4-NEXT:    [[TMP2:%.*]] = call i8* @llvm.stacksave()
// CHECK4-NEXT:    store i8* [[TMP2]], i8** [[SAVED_STACK]], align 8
// CHECK4-NEXT:    [[TMP3:%.*]] = mul nuw i64 10, [[TMP1]]
// CHECK4-NEXT:    [[VLA:%.*]] = alloca i32, i64 [[TMP3]], align 16
// CHECK4-NEXT:    store i64 [[TMP1]], i64* [[__VLA_EXPR0]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK4-NEXT:    store i8* [[B]], i8** [[TMP4]], align 8
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 1
// CHECK4-NEXT:    store [2 x %struct.S]* [[S]], [2 x %struct.S]** [[TMP5]], align 8
// CHECK4-NEXT:    [[TMP6:%.*]] = load i8, i8* [[B]], align 1
// CHECK4-NEXT:    [[CONV:%.*]] = sext i8 [[TMP6]] to i32
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3:[0-9]+]])
// CHECK4-NEXT:    [[TMP7:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[OMP_GLOBAL_THREAD_NUM]], i32 33, i64 40, i64 16, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.kmp_task_t_with_privates*
// CHECK4-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP8]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP10:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP9]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP11:%.*]] = load i8*, i8** [[TMP10]], align 8
// CHECK4-NEXT:    [[TMP12:%.*]] = bitcast %struct.anon* [[AGG_CAPTURED]] to i8*
// CHECK4-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP11]], i8* align 8 [[TMP12]], i64 16, i1 false)
// CHECK4-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP9]], i32 0, i32 4
// CHECK4-NEXT:    [[TMP14:%.*]] = bitcast %union.kmp_cmplrdata_t* [[TMP13]] to i32*
// CHECK4-NEXT:    store i32 [[CONV]], i32* [[TMP14]], align 8
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM1:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3]])
// CHECK4-NEXT:    [[TMP15:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM1]], i8* [[TMP7]])
// CHECK4-NEXT:    [[TMP16:%.*]] = getelementptr inbounds [[STRUCT_ANON_0]], %struct.anon.0* [[AGG_CAPTURED2]], i32 0, i32 0
// CHECK4-NEXT:    store [2 x %struct.S]* [[S]], [2 x %struct.S]** [[TMP16]], align 8
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM3:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB5:[0-9]+]])
// CHECK4-NEXT:    [[TMP17:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM3]], i32 1, i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.1*)* @.omp_task_entry..2 to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP18:%.*]] = bitcast i8* [[TMP17]] to %struct.kmp_task_t_with_privates.1*
// CHECK4-NEXT:    [[TMP19:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_1:%.*]], %struct.kmp_task_t_with_privates.1* [[TMP18]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP20:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP19]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP21:%.*]] = load i8*, i8** [[TMP20]], align 8
// CHECK4-NEXT:    [[TMP22:%.*]] = bitcast %struct.anon.0* [[AGG_CAPTURED2]] to i8*
// CHECK4-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP21]], i8* align 8 [[TMP22]], i64 8, i1 false)
// CHECK4-NEXT:    [[TMP23:%.*]] = getelementptr inbounds [4 x %struct.kmp_depend_info], [4 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR]], i64 0, i64 0
// CHECK4-NEXT:    [[TMP24:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO:%.*]], %struct.kmp_depend_info* [[TMP23]], i64 0
// CHECK4-NEXT:    [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i32 0, i32 0
// CHECK4-NEXT:    store i64 ptrtoint (i32* @a to i64), i64* [[TMP25]], align 8
// CHECK4-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i32 0, i32 1
// CHECK4-NEXT:    store i64 4, i64* [[TMP26]], align 8
// CHECK4-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP24]], i32 0, i32 2
// CHECK4-NEXT:    store i8 1, i8* [[TMP27]], align 8
// CHECK4-NEXT:    [[TMP28:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP23]], i64 1
// CHECK4-NEXT:    [[TMP29:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP28]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP30:%.*]] = ptrtoint i8* [[B]] to i64
// CHECK4-NEXT:    store i64 [[TMP30]], i64* [[TMP29]], align 8
// CHECK4-NEXT:    [[TMP31:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP28]], i32 0, i32 1
// CHECK4-NEXT:    store i64 1, i64* [[TMP31]], align 8
// CHECK4-NEXT:    [[TMP32:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP28]], i32 0, i32 2
// CHECK4-NEXT:    store i8 1, i8* [[TMP32]], align 8
// CHECK4-NEXT:    [[TMP33:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP23]], i64 2
// CHECK4-NEXT:    [[TMP34:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP33]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP35:%.*]] = ptrtoint [2 x %struct.S]* [[S]] to i64
// CHECK4-NEXT:    store i64 [[TMP35]], i64* [[TMP34]], align 8
// CHECK4-NEXT:    [[TMP36:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP33]], i32 0, i32 1
// CHECK4-NEXT:    store i64 8, i64* [[TMP36]], align 8
// CHECK4-NEXT:    [[TMP37:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP33]], i32 0, i32 2
// CHECK4-NEXT:    store i8 1, i8* [[TMP37]], align 8
// CHECK4-NEXT:    [[TMP38:%.*]] = mul nsw i64 0, [[TMP1]]
// CHECK4-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP38]]
// CHECK4-NEXT:    [[TMP39:%.*]] = mul nsw i64 9, [[TMP1]]
// CHECK4-NEXT:    [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP39]]
// CHECK4-NEXT:    [[TMP40:%.*]] = getelementptr i32, i32* [[ARRAYIDX4]], i32 1
// CHECK4-NEXT:    [[TMP41:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
// CHECK4-NEXT:    [[TMP42:%.*]] = ptrtoint i32* [[TMP40]] to i64
// CHECK4-NEXT:    [[TMP43:%.*]] = sub nuw i64 [[TMP42]], [[TMP41]]
// CHECK4-NEXT:    [[TMP44:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP23]], i64 3
// CHECK4-NEXT:    [[TMP45:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP44]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP46:%.*]] = ptrtoint i32* [[ARRAYIDX]] to i64
// CHECK4-NEXT:    store i64 [[TMP46]], i64* [[TMP45]], align 8
// CHECK4-NEXT:    [[TMP47:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP44]], i32 0, i32 1
// CHECK4-NEXT:    store i64 [[TMP43]], i64* [[TMP47]], align 8
// CHECK4-NEXT:    [[TMP48:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP44]], i32 0, i32 2
// CHECK4-NEXT:    store i8 1, i8* [[TMP48]], align 8
// CHECK4-NEXT:    store i64 4, i64* [[DEP_COUNTER_ADDR]], align 8
// CHECK4-NEXT:    [[TMP49:%.*]] = bitcast %struct.kmp_depend_info* [[TMP23]] to i8*
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM5:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB5]])
// CHECK4-NEXT:    [[TMP50:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM5]], i8* [[TMP17]], i32 4, i8* [[TMP49]], i32 0, i8* null)
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM7:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB7:[0-9]+]])
// CHECK4-NEXT:    [[TMP51:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM7]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.3*)* @.omp_task_entry..4 to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP52:%.*]] = bitcast i8* [[TMP51]] to %struct.kmp_task_t_with_privates.3*
// CHECK4-NEXT:    [[TMP53:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_3:%.*]], %struct.kmp_task_t_with_privates.3* [[TMP52]], i32 0, i32 0
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM8:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB7]])
// CHECK4-NEXT:    [[TMP54:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP53]], i32 0, i32 2
// CHECK4-NEXT:    store i32 0, i32* [[TMP54]], align 8
// CHECK4-NEXT:    [[TMP55:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM8]], i8* [[TMP51]])
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM10:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB9:[0-9]+]])
// CHECK4-NEXT:    [[TMP56:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM10]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.5*)* @.omp_task_entry..6 to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP57:%.*]] = bitcast i8* [[TMP56]] to %struct.kmp_task_t_with_privates.5*
// CHECK4-NEXT:    [[TMP58:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_5:%.*]], %struct.kmp_task_t_with_privates.5* [[TMP57]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP59:%.*]] = getelementptr inbounds [2 x %struct.kmp_depend_info], [2 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR11]], i64 0, i64 0
// CHECK4-NEXT:    [[ARRAYIDX12:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 0
// CHECK4-NEXT:    [[TMP60:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP59]], i64 0
// CHECK4-NEXT:    [[TMP61:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP60]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP62:%.*]] = ptrtoint %struct.S* [[ARRAYIDX12]] to i64
// CHECK4-NEXT:    store i64 [[TMP62]], i64* [[TMP61]], align 8
// CHECK4-NEXT:    [[TMP63:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP60]], i32 0, i32 1
// CHECK4-NEXT:    store i64 4, i64* [[TMP63]], align 8
// CHECK4-NEXT:    [[TMP64:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP60]], i32 0, i32 2
// CHECK4-NEXT:    store i8 3, i8* [[TMP64]], align 8
// CHECK4-NEXT:    [[TMP65:%.*]] = load i8, i8* [[B]], align 1
// CHECK4-NEXT:    [[TMP66:%.*]] = sext i8 [[TMP65]] to i64
// CHECK4-NEXT:    [[TMP67:%.*]] = mul nsw i64 4, [[TMP1]]
// CHECK4-NEXT:    [[ARRAYIDX13:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP67]]
// CHECK4-NEXT:    [[ARRAYIDX14:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX13]], i64 [[TMP66]]
// CHECK4-NEXT:    [[TMP68:%.*]] = load i8, i8* [[B]], align 1
// CHECK4-NEXT:    [[TMP69:%.*]] = sext i8 [[TMP68]] to i64
// CHECK4-NEXT:    [[TMP70:%.*]] = mul nsw i64 9, [[TMP1]]
// CHECK4-NEXT:    [[ARRAYIDX15:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP70]]
// CHECK4-NEXT:    [[ARRAYIDX16:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX15]], i64 [[TMP69]]
// CHECK4-NEXT:    [[TMP71:%.*]] = getelementptr i32, i32* [[ARRAYIDX16]], i32 1
// CHECK4-NEXT:    [[TMP72:%.*]] = ptrtoint i32* [[ARRAYIDX14]] to i64
// CHECK4-NEXT:    [[TMP73:%.*]] = ptrtoint i32* [[TMP71]] to i64
// CHECK4-NEXT:    [[TMP74:%.*]] = sub nuw i64 [[TMP73]], [[TMP72]]
// CHECK4-NEXT:    [[TMP75:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP59]], i64 1
// CHECK4-NEXT:    [[TMP76:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP75]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP77:%.*]] = ptrtoint i32* [[ARRAYIDX14]] to i64
// CHECK4-NEXT:    store i64 [[TMP77]], i64* [[TMP76]], align 8
// CHECK4-NEXT:    [[TMP78:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP75]], i32 0, i32 1
// CHECK4-NEXT:    store i64 [[TMP74]], i64* [[TMP78]], align 8
// CHECK4-NEXT:    [[TMP79:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP75]], i32 0, i32 2
// CHECK4-NEXT:    store i8 3, i8* [[TMP79]], align 8
// CHECK4-NEXT:    store i64 2, i64* [[DEP_COUNTER_ADDR17]], align 8
// CHECK4-NEXT:    [[TMP80:%.*]] = bitcast %struct.kmp_depend_info* [[TMP59]] to i8*
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM18:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB9]])
// CHECK4-NEXT:    [[TMP81:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP58]], i32 0, i32 2
// CHECK4-NEXT:    store i32 0, i32* [[TMP81]], align 8
// CHECK4-NEXT:    [[TMP82:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM18]], i8* [[TMP56]], i32 2, i8* [[TMP80]], i32 0, i8* null)
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM20:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB11:[0-9]+]])
// CHECK4-NEXT:    [[TMP83:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM20]], i32 0, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.7*)* @.omp_task_entry..8 to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP84:%.*]] = bitcast i8* [[TMP83]] to %struct.kmp_task_t_with_privates.7*
// CHECK4-NEXT:    [[TMP85:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_7:%.*]], %struct.kmp_task_t_with_privates.7* [[TMP84]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP86:%.*]] = getelementptr inbounds [2 x %struct.kmp_depend_info], [2 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR21]], i64 0, i64 0
// CHECK4-NEXT:    [[ARRAYIDX22:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 0
// CHECK4-NEXT:    [[TMP87:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP86]], i64 0
// CHECK4-NEXT:    [[TMP88:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP87]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP89:%.*]] = ptrtoint %struct.S* [[ARRAYIDX22]] to i64
// CHECK4-NEXT:    store i64 [[TMP89]], i64* [[TMP88]], align 8
// CHECK4-NEXT:    [[TMP90:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP87]], i32 0, i32 1
// CHECK4-NEXT:    store i64 4, i64* [[TMP90]], align 8
// CHECK4-NEXT:    [[TMP91:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP87]], i32 0, i32 2
// CHECK4-NEXT:    store i8 4, i8* [[TMP91]], align 8
// CHECK4-NEXT:    [[TMP92:%.*]] = load i8, i8* [[B]], align 1
// CHECK4-NEXT:    [[TMP93:%.*]] = sext i8 [[TMP92]] to i64
// CHECK4-NEXT:    [[TMP94:%.*]] = mul nsw i64 4, [[TMP1]]
// CHECK4-NEXT:    [[ARRAYIDX23:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP94]]
// CHECK4-NEXT:    [[ARRAYIDX24:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX23]], i64 [[TMP93]]
// CHECK4-NEXT:    [[TMP95:%.*]] = load i8, i8* [[B]], align 1
// CHECK4-NEXT:    [[TMP96:%.*]] = sext i8 [[TMP95]] to i64
// CHECK4-NEXT:    [[TMP97:%.*]] = mul nsw i64 9, [[TMP1]]
// CHECK4-NEXT:    [[ARRAYIDX25:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP97]]
// CHECK4-NEXT:    [[ARRAYIDX26:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX25]], i64 [[TMP96]]
// CHECK4-NEXT:    [[TMP98:%.*]] = getelementptr i32, i32* [[ARRAYIDX26]], i32 1
// CHECK4-NEXT:    [[TMP99:%.*]] = ptrtoint i32* [[ARRAYIDX24]] to i64
// CHECK4-NEXT:    [[TMP100:%.*]] = ptrtoint i32* [[TMP98]] to i64
// CHECK4-NEXT:    [[TMP101:%.*]] = sub nuw i64 [[TMP100]], [[TMP99]]
// CHECK4-NEXT:    [[TMP102:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP86]], i64 1
// CHECK4-NEXT:    [[TMP103:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP102]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP104:%.*]] = ptrtoint i32* [[ARRAYIDX24]] to i64
// CHECK4-NEXT:    store i64 [[TMP104]], i64* [[TMP103]], align 8
// CHECK4-NEXT:    [[TMP105:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP102]], i32 0, i32 1
// CHECK4-NEXT:    store i64 [[TMP101]], i64* [[TMP105]], align 8
// CHECK4-NEXT:    [[TMP106:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP102]], i32 0, i32 2
// CHECK4-NEXT:    store i8 4, i8* [[TMP106]], align 8
// CHECK4-NEXT:    store i64 2, i64* [[DEP_COUNTER_ADDR27]], align 8
// CHECK4-NEXT:    [[TMP107:%.*]] = bitcast %struct.kmp_depend_info* [[TMP86]] to i8*
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM28:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB11]])
// CHECK4-NEXT:    [[TMP108:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP85]], i32 0, i32 2
// CHECK4-NEXT:    store i32 0, i32* [[TMP108]], align 8
// CHECK4-NEXT:    [[TMP109:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM28]], i8* [[TMP83]], i32 2, i8* [[TMP107]], i32 0, i8* null)
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM30:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB13:[0-9]+]])
// CHECK4-NEXT:    [[TMP110:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM30]], i32 3, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.9*)* @.omp_task_entry..10 to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP111:%.*]] = bitcast i8* [[TMP110]] to %struct.kmp_task_t_with_privates.9*
// CHECK4-NEXT:    [[TMP112:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_9:%.*]], %struct.kmp_task_t_with_privates.9* [[TMP111]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP113:%.*]] = getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* [[DOTDEP_ARR_ADDR31]], i64 0, i64 0
// CHECK4-NEXT:    [[TMP114:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP113]], i64 0
// CHECK4-NEXT:    [[TMP115:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i32 0, i32 0
// CHECK4-NEXT:    store i64 ptrtoint (i32* @a to i64), i64* [[TMP115]], align 8
// CHECK4-NEXT:    [[TMP116:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i32 0, i32 1
// CHECK4-NEXT:    store i64 4, i64* [[TMP116]], align 8
// CHECK4-NEXT:    [[TMP117:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP114]], i32 0, i32 2
// CHECK4-NEXT:    store i8 3, i8* [[TMP117]], align 8
// CHECK4-NEXT:    [[ARRAYIDX32:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i64 0, i64 1
// CHECK4-NEXT:    [[TMP118:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP113]], i64 1
// CHECK4-NEXT:    [[TMP119:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP118]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP120:%.*]] = ptrtoint %struct.S* [[ARRAYIDX32]] to i64
// CHECK4-NEXT:    store i64 [[TMP120]], i64* [[TMP119]], align 8
// CHECK4-NEXT:    [[TMP121:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP118]], i32 0, i32 1
// CHECK4-NEXT:    store i64 4, i64* [[TMP121]], align 8
// CHECK4-NEXT:    [[TMP122:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP118]], i32 0, i32 2
// CHECK4-NEXT:    store i8 3, i8* [[TMP122]], align 8
// CHECK4-NEXT:    [[TMP123:%.*]] = mul nsw i64 0, [[TMP1]]
// CHECK4-NEXT:    [[ARRAYIDX33:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP123]]
// CHECK4-NEXT:    [[ARRAYIDX34:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX33]], i64 3
// CHECK4-NEXT:    [[TMP124:%.*]] = load i32, i32* @a, align 4
// CHECK4-NEXT:    [[TMP125:%.*]] = sext i32 [[TMP124]] to i64
// CHECK4-NEXT:    [[LEN_SUB_1:%.*]] = sub nsw i64 [[TMP125]], 1
// CHECK4-NEXT:    [[TMP126:%.*]] = load i32, i32* @a, align 4
// CHECK4-NEXT:    [[TMP127:%.*]] = sext i32 [[TMP126]] to i64
// CHECK4-NEXT:    [[LB_ADD_LEN:%.*]] = add nsw i64 -1, [[TMP127]]
// CHECK4-NEXT:    [[TMP128:%.*]] = mul nsw i64 [[LB_ADD_LEN]], [[TMP1]]
// CHECK4-NEXT:    [[ARRAYIDX35:%.*]] = getelementptr inbounds i32, i32* [[VLA]], i64 [[TMP128]]
// CHECK4-NEXT:    [[ARRAYIDX36:%.*]] = getelementptr inbounds i32, i32* [[ARRAYIDX35]], i64 [[LEN_SUB_1]]
// CHECK4-NEXT:    [[TMP129:%.*]] = getelementptr i32, i32* [[ARRAYIDX36]], i32 1
// CHECK4-NEXT:    [[TMP130:%.*]] = ptrtoint i32* [[ARRAYIDX34]] to i64
// CHECK4-NEXT:    [[TMP131:%.*]] = ptrtoint i32* [[TMP129]] to i64
// CHECK4-NEXT:    [[TMP132:%.*]] = sub nuw i64 [[TMP131]], [[TMP130]]
// CHECK4-NEXT:    [[TMP133:%.*]] = getelementptr [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP113]], i64 2
// CHECK4-NEXT:    [[TMP134:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP133]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP135:%.*]] = ptrtoint i32* [[ARRAYIDX34]] to i64
// CHECK4-NEXT:    store i64 [[TMP135]], i64* [[TMP134]], align 8
// CHECK4-NEXT:    [[TMP136:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP133]], i32 0, i32 1
// CHECK4-NEXT:    store i64 [[TMP132]], i64* [[TMP136]], align 8
// CHECK4-NEXT:    [[TMP137:%.*]] = getelementptr inbounds [[STRUCT_KMP_DEPEND_INFO]], %struct.kmp_depend_info* [[TMP133]], i32 0, i32 2
// CHECK4-NEXT:    store i8 3, i8* [[TMP137]], align 8
// CHECK4-NEXT:    store i64 3, i64* [[DEP_COUNTER_ADDR37]], align 8
// CHECK4-NEXT:    [[TMP138:%.*]] = bitcast %struct.kmp_depend_info* [[TMP113]] to i8*
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM38:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB13]])
// CHECK4-NEXT:    [[TMP139:%.*]] = call i32 @__kmpc_omp_task_with_deps(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM38]], i8* [[TMP110]], i32 3, i8* [[TMP138]], i32 0, i8* null)
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM40:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB15:[0-9]+]])
// CHECK4-NEXT:    [[TMP140:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM40]], i32 3, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.11*)* @.omp_task_entry..12 to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP141:%.*]] = bitcast i8* [[TMP140]] to %struct.kmp_task_t_with_privates.11*
// CHECK4-NEXT:    [[TMP142:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_11:%.*]], %struct.kmp_task_t_with_privates.11* [[TMP141]], i32 0, i32 0
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM41:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB15]])
// CHECK4-NEXT:    [[TMP143:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM41]], i8* [[TMP140]])
// CHECK4-NEXT:    store i8 0, i8* [[FLAG]], align 1
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM43:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB17:[0-9]+]])
// CHECK4-NEXT:    [[TMP144:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM43]], i32 1, i64 40, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.13*)* @.omp_task_entry..14 to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP145:%.*]] = bitcast i8* [[TMP144]] to %struct.kmp_task_t_with_privates.13*
// CHECK4-NEXT:    [[TMP146:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_13:%.*]], %struct.kmp_task_t_with_privates.13* [[TMP145]], i32 0, i32 0
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM44:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB17]])
// CHECK4-NEXT:    [[TMP147:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM44]], i8* [[TMP144]])
// CHECK4-NEXT:    [[TMP148:%.*]] = getelementptr inbounds [[STRUCT_ANON_14]], %struct.anon.14* [[AGG_CAPTURED45]], i32 0, i32 0
// CHECK4-NEXT:    store i32* [[C]], i32** [[TMP148]], align 8
// CHECK4-NEXT:    [[TMP149:%.*]] = load i8, i8* [[B]], align 1
// CHECK4-NEXT:    [[TOBOOL:%.*]] = icmp ne i8 [[TMP149]], 0
// CHECK4-NEXT:    [[TMP150:%.*]] = select i1 [[TOBOOL]], i32 2, i32 0
// CHECK4-NEXT:    [[TMP151:%.*]] = or i32 [[TMP150]], 1
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM46:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB19:[0-9]+]])
// CHECK4-NEXT:    [[TMP152:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM46]], i32 [[TMP151]], i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.15*)* @.omp_task_entry..16 to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP153:%.*]] = bitcast i8* [[TMP152]] to %struct.kmp_task_t_with_privates.15*
// CHECK4-NEXT:    [[TMP154:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_15:%.*]], %struct.kmp_task_t_with_privates.15* [[TMP153]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP155:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP154]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP156:%.*]] = load i8*, i8** [[TMP155]], align 8
// CHECK4-NEXT:    [[TMP157:%.*]] = bitcast %struct.anon.14* [[AGG_CAPTURED45]] to i8*
// CHECK4-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP156]], i8* align 8 [[TMP157]], i64 8, i1 false)
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM47:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB19]])
// CHECK4-NEXT:    [[TMP158:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM47]], i8* [[TMP152]])
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM49:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21:[0-9]+]])
// CHECK4-NEXT:    [[TMP159:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM49]], i32 0, i64 256, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.19*)* @.omp_task_entry..21 to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP160:%.*]] = bitcast i8* [[TMP159]] to %struct.kmp_task_t_with_privates.19*
// CHECK4-NEXT:    [[TMP161:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19:%.*]], %struct.kmp_task_t_with_privates.19* [[TMP160]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP162:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19]], %struct.kmp_task_t_with_privates.19* [[TMP160]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP163:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20:%.*]], %struct..kmp_privates.t.20* [[TMP162]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP164:%.*]] = load i32, i32* [[C]], align 128
// CHECK4-NEXT:    store i32 [[TMP164]], i32* [[TMP163]], align 128
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM50:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21]])
// CHECK4-NEXT:    [[TMP165:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP161]], i32 0, i32 2
// CHECK4-NEXT:    store i32 0, i32* [[TMP165]], align 16
// CHECK4-NEXT:    [[TMP166:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM50]], i8* [[TMP159]])
// CHECK4-NEXT:    [[TMP167:%.*]] = load i32, i32* @a, align 4
// CHECK4-NEXT:    store i32 [[TMP167]], i32* [[RETVAL]], align 4
// CHECK4-NEXT:    [[TMP168:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
// CHECK4-NEXT:    call void @llvm.stackrestore(i8* [[TMP168]])
// CHECK4-NEXT:    [[ARRAY_BEGIN51:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP169:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN51]], i64 2
// CHECK4-NEXT:    br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK4:       arraydestroy.body:
// CHECK4-NEXT:    [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP169]], [[ARRAYCTOR_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK4-NEXT:    [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK4-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4:[0-9]+]]
// CHECK4-NEXT:    [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN51]]
// CHECK4-NEXT:    br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE52:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK4:       arraydestroy.done52:
// CHECK4-NEXT:    [[TMP170:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK4-NEXT:    ret i32 [[TMP170]]
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SC1Ev
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] align 2 {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK4-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    call void @_ZN1SC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry.
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates* noalias [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon*, align 8
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates* [[TMP1]], %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates*, %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon*
// CHECK4-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META3:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META6:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META8:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META10:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !12
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !12
// CHECK4-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !12
// CHECK4-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !12
// CHECK4-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !12
// CHECK4-NEXT:    store %struct.anon* [[TMP8]], %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK4-NEXT:    store i32 15, i32* @a, align 4
// CHECK4-NEXT:    [[TMP11:%.*]] = load i32, i32* @a, align 4
// CHECK4-NEXT:    [[CONV_I:%.*]] = trunc i32 [[TMP11]] to i8
// CHECK4-NEXT:    [[TMP12:%.*]] = getelementptr inbounds [[STRUCT_ANON:%.*]], %struct.anon* [[TMP10]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
// CHECK4-NEXT:    store i8 [[CONV_I]], i8* [[TMP13]], align 1
// CHECK4-NEXT:    [[TMP14:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP10]], i32 0, i32 1
// CHECK4-NEXT:    [[TMP15:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[TMP14]], align 8
// CHECK4-NEXT:    [[ARRAYIDX_I:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP15]], i64 0, i64 0
// CHECK4-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAYIDX_I]], i32 0, i32 0
// CHECK4-NEXT:    store i32 10, i32* [[A_I]], align 4
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..2
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.1* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.0*, align 8
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.1*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.1* [[TMP1]], %struct.kmp_task_t_with_privates.1** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.1*, %struct.kmp_task_t_with_privates.1** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_1:%.*]], %struct.kmp_task_t_with_privates.1* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.0*
// CHECK4-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.1* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META13:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META16:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META18:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META20:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !22
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !22
// CHECK4-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !22
// CHECK4-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !22
// CHECK4-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !22
// CHECK4-NEXT:    store %struct.anon.0* [[TMP8]], %struct.anon.0** [[__CONTEXT_ADDR_I]], align 8, !noalias !22
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.anon.0*, %struct.anon.0** [[__CONTEXT_ADDR_I]], align 8, !noalias !22
// CHECK4-NEXT:    store i32 15, i32* @a, align 4
// CHECK4-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_0:%.*]], %struct.anon.0* [[TMP10]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP12:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[TMP11]], align 8
// CHECK4-NEXT:    [[ARRAYIDX_I:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP12]], i64 0, i64 1
// CHECK4-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[ARRAYIDX_I]], i32 0, i32 0
// CHECK4-NEXT:    store i32 10, i32* [[A_I]], align 4
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..4
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.3* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.2*, align 8
// CHECK4-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.3*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.3* [[TMP1]], %struct.kmp_task_t_with_privates.3** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.3*, %struct.kmp_task_t_with_privates.3** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_3:%.*]], %struct.kmp_task_t_with_privates.3* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.2*
// CHECK4-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.3* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META23:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META26:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META28:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META30:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !32
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK4-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !32
// CHECK4-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !32
// CHECK4-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !32
// CHECK4-NEXT:    store %struct.anon.2* [[TMP8]], %struct.anon.2** [[__CONTEXT_ADDR_I]], align 8, !noalias !32
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.anon.2*, %struct.anon.2** [[__CONTEXT_ADDR_I]], align 8, !noalias !32
// CHECK4-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK4-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK4-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK4-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK4-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK4-NEXT:    ]
// CHECK4:       .untied.done..i:
// CHECK4-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK4-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK4:       .untied.jmp..i:
// CHECK4-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !32
// CHECK4-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB7]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !32
// CHECK4-NEXT:    [[TMP15:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM_I]], i8* [[TMP14]]) #[[ATTR4]]
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__3_EXIT:%.*]]
// CHECK4:       .untied.jmp.1.i:
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM2_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR4]]
// CHECK4-NEXT:    call void @__kmpc_critical(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM2_I]], [8 x i32]* @.gomp_critical_user_.var) #[[ATTR4]]
// CHECK4-NEXT:    store i32 1, i32* @a, align 4
// CHECK4-NEXT:    call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM2_I]], [8 x i32]* @.gomp_critical_user_.var) #[[ATTR4]]
// CHECK4-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK4-NEXT:    br label [[CLEANUP_I]]
// CHECK4:       cleanup.i:
// CHECK4-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !32
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__3_EXIT]]
// CHECK4:       .omp_outlined..3.exit:
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..6
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.5* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.4*, align 8
// CHECK4-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.5*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.5* [[TMP1]], %struct.kmp_task_t_with_privates.5** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.5*, %struct.kmp_task_t_with_privates.5** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_5:%.*]], %struct.kmp_task_t_with_privates.5* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.4*
// CHECK4-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.5* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META33:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META36:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META38:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META40:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !42
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK4-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !42
// CHECK4-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !42
// CHECK4-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !42
// CHECK4-NEXT:    store %struct.anon.4* [[TMP8]], %struct.anon.4** [[__CONTEXT_ADDR_I]], align 8, !noalias !42
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.anon.4*, %struct.anon.4** [[__CONTEXT_ADDR_I]], align 8, !noalias !42
// CHECK4-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK4-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK4-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK4-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK4-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK4-NEXT:    ]
// CHECK4:       .untied.done..i:
// CHECK4-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK4-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK4:       .untied.jmp..i:
// CHECK4-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !42
// CHECK4-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB9]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !42
// CHECK4-NEXT:    [[TMP15:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM_I]], i8* [[TMP14]]) #[[ATTR4]]
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__5_EXIT:%.*]]
// CHECK4:       .untied.jmp.1.i:
// CHECK4-NEXT:    store i32 1, i32* @a, align 4
// CHECK4-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK4-NEXT:    br label [[CLEANUP_I]]
// CHECK4:       cleanup.i:
// CHECK4-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !42
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__5_EXIT]]
// CHECK4:       .omp_outlined..5.exit:
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..8
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.7* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.6*, align 8
// CHECK4-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.7*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.7* [[TMP1]], %struct.kmp_task_t_with_privates.7** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.7*, %struct.kmp_task_t_with_privates.7** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_7:%.*]], %struct.kmp_task_t_with_privates.7* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.6*
// CHECK4-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.7* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META43:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META46:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META48:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META50:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !52
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK4-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !52
// CHECK4-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !52
// CHECK4-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !52
// CHECK4-NEXT:    store %struct.anon.6* [[TMP8]], %struct.anon.6** [[__CONTEXT_ADDR_I]], align 8, !noalias !52
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.anon.6*, %struct.anon.6** [[__CONTEXT_ADDR_I]], align 8, !noalias !52
// CHECK4-NEXT:    [[TMP11:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK4-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK4-NEXT:    switch i32 [[TMP12]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK4-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK4-NEXT:    i32 1, label [[DOTUNTIED_JMP_1_I:%.*]]
// CHECK4-NEXT:    ]
// CHECK4:       .untied.done..i:
// CHECK4-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK4-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK4:       .untied.jmp..i:
// CHECK4-NEXT:    [[TMP13:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !52
// CHECK4-NEXT:    store i32 1, i32* [[TMP13]], align 4
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB11]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !52
// CHECK4-NEXT:    [[TMP15:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM_I]], i8* [[TMP14]]) #[[ATTR4]]
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__7_EXIT:%.*]]
// CHECK4:       .untied.jmp.1.i:
// CHECK4-NEXT:    store i32 1, i32* @a, align 4
// CHECK4-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK4-NEXT:    br label [[CLEANUP_I]]
// CHECK4:       cleanup.i:
// CHECK4-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !52
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__7_EXIT]]
// CHECK4:       .omp_outlined..7.exit:
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..10
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.9* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.8*, align 8
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.9*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.9* [[TMP1]], %struct.kmp_task_t_with_privates.9** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.9*, %struct.kmp_task_t_with_privates.9** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_9:%.*]], %struct.kmp_task_t_with_privates.9* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.8*
// CHECK4-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.9* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META53:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META56:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META58:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META60:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !62
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !62
// CHECK4-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !62
// CHECK4-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !62
// CHECK4-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !62
// CHECK4-NEXT:    store %struct.anon.8* [[TMP8]], %struct.anon.8** [[__CONTEXT_ADDR_I]], align 8, !noalias !62
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.anon.8*, %struct.anon.8** [[__CONTEXT_ADDR_I]], align 8, !noalias !62
// CHECK4-NEXT:    store i32 2, i32* @a, align 4
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..12
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.11* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.10*, align 8
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.11*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.11* [[TMP1]], %struct.kmp_task_t_with_privates.11** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.11*, %struct.kmp_task_t_with_privates.11** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_11:%.*]], %struct.kmp_task_t_with_privates.11* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.10*
// CHECK4-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.11* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META63:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META66:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META68:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META70:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !72
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !72
// CHECK4-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !72
// CHECK4-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !72
// CHECK4-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !72
// CHECK4-NEXT:    store %struct.anon.10* [[TMP8]], %struct.anon.10** [[__CONTEXT_ADDR_I]], align 8, !noalias !72
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.anon.10*, %struct.anon.10** [[__CONTEXT_ADDR_I]], align 8, !noalias !72
// CHECK4-NEXT:    store i32 2, i32* @a, align 4
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..14
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.13* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.12*, align 8
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.13*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.13* [[TMP1]], %struct.kmp_task_t_with_privates.13** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.13*, %struct.kmp_task_t_with_privates.13** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_13:%.*]], %struct.kmp_task_t_with_privates.13* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.12*
// CHECK4-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.13* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META73:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META76:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META78:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META80:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !82
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !82
// CHECK4-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !82
// CHECK4-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !82
// CHECK4-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !82
// CHECK4-NEXT:    store %struct.anon.12* [[TMP8]], %struct.anon.12** [[__CONTEXT_ADDR_I]], align 8, !noalias !82
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.anon.12*, %struct.anon.12** [[__CONTEXT_ADDR_I]], align 8, !noalias !82
// CHECK4-NEXT:    store i32 3, i32* @a, align 4
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..16
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.15* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.14*, align 8
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.15*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.15* [[TMP1]], %struct.kmp_task_t_with_privates.15** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.15*, %struct.kmp_task_t_with_privates.15** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_15:%.*]], %struct.kmp_task_t_with_privates.15* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.14*
// CHECK4-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.15* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META83:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META86:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META88:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META90:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !92
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !92
// CHECK4-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !92
// CHECK4-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !92
// CHECK4-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !92
// CHECK4-NEXT:    store %struct.anon.14* [[TMP8]], %struct.anon.14** [[__CONTEXT_ADDR_I]], align 8, !noalias !92
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.anon.14*, %struct.anon.14** [[__CONTEXT_ADDR_I]], align 8, !noalias !92
// CHECK4-NEXT:    store i32 4, i32* @a, align 4
// CHECK4-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_14:%.*]], %struct.anon.14* [[TMP10]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP12:%.*]] = load i32*, i32** [[TMP11]], align 8
// CHECK4-NEXT:    store i32 5, i32* [[TMP12]], align 128
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_privates_map.
// CHECK4-SAME: (%struct..kmp_privates.t* noalias [[TMP0:%.*]], i32** noalias [[TMP1:%.*]]) #[[ATTR7:[0-9]+]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t*, align 8
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca i32**, align 8
// CHECK4-NEXT:    store %struct..kmp_privates.t* [[TMP0]], %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK4-NEXT:    store i32** [[TMP1]], i32*** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load %struct..kmp_privates.t*, %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK4-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP2]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP4:%.*]] = load i32**, i32*** [[DOTADDR1]], align 8
// CHECK4-NEXT:    store i32* [[TMP3]], i32** [[TMP4]], align 8
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..19
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.18* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.17*, align 8
// CHECK4-NEXT:    [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.18*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.18* [[TMP1]], %struct.kmp_task_t_with_privates.18** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.18*, %struct.kmp_task_t_with_privates.18** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18:%.*]], %struct.kmp_task_t_with_privates.18* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 128
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.17*
// CHECK4-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18]], %struct.kmp_task_t_with_privates.18* [[TMP3]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP10:%.*]] = bitcast %struct..kmp_privates.t* [[TMP9]] to i8*
// CHECK4-NEXT:    [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates.18* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META93:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META96:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META98:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META100:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !102
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !102
// CHECK4-NEXT:    store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !102
// CHECK4-NEXT:    store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t*, i32**)* @.omp_task_privates_map. to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !102
// CHECK4-NEXT:    store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !102
// CHECK4-NEXT:    store %struct.anon.17* [[TMP8]], %struct.anon.17** [[__CONTEXT_ADDR_I]], align 8, !noalias !102
// CHECK4-NEXT:    [[TMP12:%.*]] = load %struct.anon.17*, %struct.anon.17** [[__CONTEXT_ADDR_I]], align 8, !noalias !102
// CHECK4-NEXT:    [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !102
// CHECK4-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !102
// CHECK4-NEXT:    [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i32**)*
// CHECK4-NEXT:    call void [[TMP15]](i8* [[TMP14]], i32** [[DOTFIRSTPRIV_PTR_ADDR_I]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP16:%.*]] = load i32*, i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !102
// CHECK4-NEXT:    store i32 4, i32* [[TMP16]], align 128
// CHECK4-NEXT:    store i32 4, i32* @a, align 4
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SD1Ev
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK4-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    call void @_ZN1SD2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_privates_map..20
// CHECK4-SAME: (%struct..kmp_privates.t.20* noalias [[TMP0:%.*]], i32** noalias [[TMP1:%.*]], %struct.S** noalias [[TMP2:%.*]], %struct.S** noalias [[TMP3:%.*]]) #[[ATTR7]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t.20*, align 8
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca i32**, align 8
// CHECK4-NEXT:    [[DOTADDR2:%.*]] = alloca %struct.S**, align 8
// CHECK4-NEXT:    [[DOTADDR3:%.*]] = alloca %struct.S**, align 8
// CHECK4-NEXT:    store %struct..kmp_privates.t.20* [[TMP0]], %struct..kmp_privates.t.20** [[DOTADDR]], align 8
// CHECK4-NEXT:    store i32** [[TMP1]], i32*** [[DOTADDR1]], align 8
// CHECK4-NEXT:    store %struct.S** [[TMP2]], %struct.S*** [[DOTADDR2]], align 8
// CHECK4-NEXT:    store %struct.S** [[TMP3]], %struct.S*** [[DOTADDR3]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = load %struct..kmp_privates.t.20*, %struct..kmp_privates.t.20** [[DOTADDR]], align 8
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20:%.*]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP6:%.*]] = load i32**, i32*** [[DOTADDR1]], align 8
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP7:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 1
// CHECK4-NEXT:    [[TMP8:%.*]] = load %struct.S**, %struct.S*** [[DOTADDR2]], align 8
// CHECK4-NEXT:    store %struct.S* [[TMP7]], %struct.S** [[TMP8]], align 8
// CHECK4-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T_20]], %struct..kmp_privates.t.20* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.S**, %struct.S*** [[DOTADDR3]], align 8
// CHECK4-NEXT:    store %struct.S* [[TMP9]], %struct.S** [[TMP10]], align 8
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..21
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.19* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.16*, align 8
// CHECK4-NEXT:    [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTLOCAL_PTR_ADDR_I:%.*]] = alloca %struct.S*, align 8
// CHECK4-NEXT:    [[DOTLOCAL_PTR_ADDR1_I:%.*]] = alloca %struct.S*, align 8
// CHECK4-NEXT:    [[CLEANUP_DEST_SLOT_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[S1_I:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK4-NEXT:    [[S2_I:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK4-NEXT:    [[REF_TMP_I:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.19*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.19* [[TMP1]], %struct.kmp_task_t_with_privates.19** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.19*, %struct.kmp_task_t_with_privates.19** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19:%.*]], %struct.kmp_task_t_with_privates.19* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 128
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.16*
// CHECK4-NEXT:    [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_19]], %struct.kmp_task_t_with_privates.19* [[TMP3]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP10:%.*]] = bitcast %struct..kmp_privates.t.20* [[TMP9]] to i8*
// CHECK4-NEXT:    [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates.19* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META103:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META106:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META108:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META110:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !112
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t.20*, i32**, %struct.S**, %struct.S**)* @.omp_task_privates_map..20 to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    store %struct.anon.16* [[TMP8]], %struct.anon.16** [[__CONTEXT_ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP12:%.*]] = load %struct.anon.16*, %struct.anon.16** [[__CONTEXT_ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i32**, %struct.S**, %struct.S**)*
// CHECK4-NEXT:    call void [[TMP15]](i8* [[TMP14]], i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], %struct.S** [[DOTLOCAL_PTR_ADDR_I]], %struct.S** [[DOTLOCAL_PTR_ADDR1_I]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP16:%.*]] = load i32*, i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP17:%.*]] = load %struct.S*, %struct.S** [[DOTLOCAL_PTR_ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP18:%.*]] = load %struct.S*, %struct.S** [[DOTLOCAL_PTR_ADDR1_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP19:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP20:%.*]] = load i32, i32* [[TMP19]], align 4
// CHECK4-NEXT:    switch i32 [[TMP20]], label [[DOTUNTIED_DONE__I:%.*]] [
// CHECK4-NEXT:    i32 0, label [[DOTUNTIED_JMP__I:%.*]]
// CHECK4-NEXT:    i32 1, label [[DOTUNTIED_JMP_2_I:%.*]]
// CHECK4-NEXT:    i32 2, label [[DOTUNTIED_JMP_6_I:%.*]]
// CHECK4-NEXT:    i32 3, label [[DOTUNTIED_JMP_10_I:%.*]]
// CHECK4-NEXT:    i32 4, label [[DOTUNTIED_JMP_15_I:%.*]]
// CHECK4-NEXT:    ]
// CHECK4:       .untied.done..i:
// CHECK4-NEXT:    store i32 1, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK4-NEXT:    br label [[CLEANUP_I:%.*]]
// CHECK4:       .untied.jmp..i:
// CHECK4-NEXT:    [[TMP21:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    store i32 1, i32* [[TMP21]], align 4
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP22:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP23:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM_I]], i8* [[TMP22]]) #[[ATTR4]]
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT:%.*]]
// CHECK4:       .untied.jmp.2.i:
// CHECK4-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[S1_I]]) #[[ATTR4]]
// CHECK4-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[S2_I]]) #[[ATTR4]]
// CHECK4-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[S2_I]], i32 0, i32 0
// CHECK4-NEXT:    store i32 0, i32* [[A_I]], align 4, !noalias !112
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM3_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB23:[0-9]+]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP24:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM3_I]], i32 1, i64 256, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.18*)* @.omp_task_entry..19 to i32 (i32, i8*)*)) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP25:%.*]] = bitcast i8* [[TMP24]] to %struct.kmp_task_t_with_privates.18*
// CHECK4-NEXT:    [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18:%.*]], %struct.kmp_task_t_with_privates.18* [[TMP25]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_18]], %struct.kmp_task_t_with_privates.18* [[TMP25]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP28:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP27]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP29:%.*]] = load i32, i32* [[TMP16]], align 128
// CHECK4-NEXT:    store i32 [[TMP29]], i32* [[TMP28]], align 128
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM4_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB23]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP30:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM4_I]], i8* [[TMP24]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP31:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    store i32 2, i32* [[TMP31]], align 4
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM5_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP32:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP33:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM5_I]], i8* [[TMP32]]) #[[ATTR4]]
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK4:       .untied.jmp.6.i:
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM8_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP34:%.*]] = call i32 @__kmpc_omp_taskyield(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM8_I]], i32 0) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP35:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    store i32 3, i32* [[TMP35]], align 4
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM9_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP36:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP37:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM9_I]], i8* [[TMP36]]) #[[ATTR4]]
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK4:       .untied.jmp.10.i:
// CHECK4-NEXT:    call void @_ZN1SC1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP_I]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP38:%.*]] = bitcast %struct.S* [[S1_I]] to i8*
// CHECK4-NEXT:    [[TMP39:%.*]] = bitcast %struct.S* [[REF_TMP_I]] to i8*
// CHECK4-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP38]], i8* align 4 [[TMP39]], i64 4, i1 false) #[[ATTR4]], !noalias !112
// CHECK4-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[REF_TMP_I]]) #[[ATTR4]]
// CHECK4-NEXT:    [[A12_I:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[S2_I]], i32 0, i32 0
// CHECK4-NEXT:    store i32 10, i32* [[A12_I]], align 4, !noalias !112
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM13_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP40:%.*]] = call i32 @__kmpc_omp_taskwait(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM13_I]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP41:%.*]] = load i32*, i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    store i32 4, i32* [[TMP41]], align 4
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM14_I:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB21]]) #[[ATTR4]]
// CHECK4-NEXT:    [[TMP42:%.*]] = load i8*, i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !112
// CHECK4-NEXT:    [[TMP43:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM14_I]], i8* [[TMP42]]) #[[ATTR4]]
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK4:       .untied.jmp.15.i:
// CHECK4-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[S2_I]]) #[[ATTR4]]
// CHECK4-NEXT:    call void @_ZN1SD1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[S1_I]]) #[[ATTR4]]
// CHECK4-NEXT:    store i32 0, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK4-NEXT:    br label [[CLEANUP_I]]
// CHECK4:       cleanup.i:
// CHECK4-NEXT:    [[CLEANUP_DEST_I:%.*]] = load i32, i32* [[CLEANUP_DEST_SLOT_I]], align 4, !noalias !112
// CHECK4-NEXT:    br label [[DOTOMP_OUTLINED__17_EXIT]]
// CHECK4:       .omp_outlined..17.exit:
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SC2Ev
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK4-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[A:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK4-NEXT:    store i32 0, i32* [[A]], align 4
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SD2Ev
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK4-NEXT:    store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@__cxx_global_var_init
// CHECK4-SAME: () #[[ATTR7]] section "__TEXT,__StaticInit,regular,pure_instructions" {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    call void @_ZN2S1C1Ev(%struct.S1* nonnull align 4 dereferenceable(4) @s1)
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN2S1C1Ev
// CHECK4-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK4-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    call void @_ZN2S1C2Ev(%struct.S1* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN2S1C2Ev
// CHECK4-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK4-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    call void @_ZN2S18taskinitEv(%struct.S1* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN2S18taskinitEv
// CHECK4-SAME: (%struct.S1* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR8:[0-9]+]] align 2 {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK4-NEXT:    [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON_21:%.*]], align 8
// CHECK4-NEXT:    store %struct.S1* [[THIS]], %struct.S1** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[THIS1:%.*]] = load %struct.S1*, %struct.S1** [[THIS_ADDR]], align 8
// CHECK4-NEXT:    [[TMP0:%.*]] = getelementptr inbounds [[STRUCT_ANON_21]], %struct.anon.21* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK4-NEXT:    store %struct.S1* [[THIS1]], %struct.S1** [[TMP0]], align 8
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB25:[0-9]+]])
// CHECK4-NEXT:    [[TMP1:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM]], i32 1, i64 40, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.22*)* @.omp_task_entry..23 to i32 (i32, i8*)*))
// CHECK4-NEXT:    [[TMP2:%.*]] = bitcast i8* [[TMP1]] to %struct.kmp_task_t_with_privates.22*
// CHECK4-NEXT:    [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_22:%.*]], %struct.kmp_task_t_with_privates.22* [[TMP2]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = load i8*, i8** [[TMP4]], align 8
// CHECK4-NEXT:    [[TMP6:%.*]] = bitcast %struct.anon.21* [[AGG_CAPTURED]] to i8*
// CHECK4-NEXT:    call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP5]], i8* align 8 [[TMP6]], i64 8, i1 false)
// CHECK4-NEXT:    [[OMP_GLOBAL_THREAD_NUM2:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB25]])
// CHECK4-NEXT:    [[TMP7:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[OMP_GLOBAL_THREAD_NUM2]], i8* [[TMP1]])
// CHECK4-NEXT:    ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_task_entry..23
// CHECK4-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates.22* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK4-NEXT:    [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK4-NEXT:    [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK4-NEXT:    [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon.21*, align 8
// CHECK4-NEXT:    [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT:    [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates.22*, align 8
// CHECK4-NEXT:    store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    store %struct.kmp_task_t_with_privates.22* [[TMP1]], %struct.kmp_task_t_with_privates.22** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK4-NEXT:    [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates.22*, %struct.kmp_task_t_with_privates.22** [[DOTADDR1]], align 8
// CHECK4-NEXT:    [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES_22:%.*]], %struct.kmp_task_t_with_privates.22* [[TMP3]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK4-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT:    [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon.21*
// CHECK4-NEXT:    [[TMP9:%.*]] = bitcast %struct.kmp_task_t_with_privates.22* [[TMP3]] to i8*
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META113:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META116:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META118:![0-9]+]])
// CHECK4-NEXT:    call void @llvm.experimental.noalias.scope.decl(metadata [[META120:![0-9]+]])
// CHECK4-NEXT:    store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !122
// CHECK4-NEXT:    store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !122
// CHECK4-NEXT:    store i8* null, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !122
// CHECK4-NEXT:    store void (i8*, ...)* null, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !122
// CHECK4-NEXT:    store i8* [[TMP9]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !122
// CHECK4-NEXT:    store %struct.anon.21* [[TMP8]], %struct.anon.21** [[__CONTEXT_ADDR_I]], align 8, !noalias !122
// CHECK4-NEXT:    [[TMP10:%.*]] = load %struct.anon.21*, %struct.anon.21** [[__CONTEXT_ADDR_I]], align 8, !noalias !122
// CHECK4-NEXT:    [[TMP11:%.*]] = getelementptr inbounds [[STRUCT_ANON_21:%.*]], %struct.anon.21* [[TMP10]], i32 0, i32 0
// CHECK4-NEXT:    [[TMP12:%.*]] = load %struct.S1*, %struct.S1** [[TMP11]], align 8
// CHECK4-NEXT:    [[A_I:%.*]] = getelementptr inbounds [[STRUCT_S1:%.*]], %struct.S1* [[TMP12]], i32 0, i32 0
// CHECK4-NEXT:    store i32 0, i32* [[A_I]], align 4
// CHECK4-NEXT:    ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@_GLOBAL__sub_I_task_codegen.cpp
// CHECK4-SAME: () #[[ATTR7]] section "__TEXT,__StaticInit,regular,pure_instructions" {
// CHECK4-NEXT:  entry:
// CHECK4-NEXT:    call void @__cxx_global_var_init()
// CHECK4-NEXT:    ret void
//