llvm-project/clang/test/OpenMP/teams_distribute_firstpriva...

3794 lines
262 KiB
C++

// 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 -DCHECK -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - -Wno-openmp-mapping | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK1
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s -Wno-openmp-mapping
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - -Wno-openmp-mapping | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK2
// RUN: %clang_cc1 -DCHECK -verify -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - -Wno-openmp-mapping | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK3
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s -Wno-openmp-mapping
// RUN: %clang_cc1 -DCHECK -fopenmp -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - -Wno-openmp-mapping | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK4
// RUN: %clang_cc1 -DCHECK -verify -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - -Wno-openmp-mapping | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -DCHECK -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s -Wno-openmp-mapping
// RUN: %clang_cc1 -DCHECK -fopenmp-simd -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - -Wno-openmp-mapping | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -DCHECK -verify -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-llvm %s -o - -Wno-openmp-mapping | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -DCHECK -fopenmp-simd -x c++ -std=c++11 -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -emit-pch -o %t %s -Wno-openmp-mapping
// RUN: %clang_cc1 -DCHECK -fopenmp-simd -x c++ -triple i386-unknown-unknown -fopenmp-targets=i386-pc-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - -Wno-openmp-mapping | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - -Wno-openmp-mapping | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK9
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s -Wno-openmp-mapping
// RUN: %clang_cc1 -DLAMBDA -fopenmp -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - -Wno-openmp-mapping | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK10
// RUN: %clang_cc1 -DLAMBDA -verify -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-llvm %s -o - -Wno-openmp-mapping | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -DLAMBDA -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -emit-pch -o %t %s -Wno-openmp-mapping
// RUN: %clang_cc1 -DLAMBDA -fopenmp-simd -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -fopenmp-targets=powerpc64le-ibm-linux-gnu -std=c++11 -include-pch %t -verify %s -emit-llvm -o - -Wno-openmp-mapping | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
struct St {
int a, b;
St() : a(0), b(0) {}
St(const St &st) : a(st.a + st.b), b(0) {}
~St() {}
};
volatile int g = 1212;
volatile int &g1 = g;
template <class T>
struct S {
T f;
S(T a) : f(a + g) {}
S() : f(g) {}
S(const S &s, St t = St()) : f(s.f + t.a) {}
operator T() { return T(); }
~S() {}
};
template <typename T>
T tmain() {
S<T> test;
T t_var = T();
T vec[] = {1, 2};
S<T> s_arr[] = {1, 2};
S<T> &var = test;
#pragma omp target
#pragma omp teams distribute firstprivate(t_var, vec, s_arr, var)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
}
return T();
}
S<float> test;
int t_var = 333;
int vec[] = {1, 2};
S<float> s_arr[] = {1, 2};
S<float> var(3);
int main() {
static int sivar;
#ifdef LAMBDA
[&]() {
#pragma omp target
#pragma omp teams distribute firstprivate(g, g1, sivar)
for (int i = 0; i < 2; ++i) {
// Skip global and bound tid vars
// skip loop vars
g = 1;
g1 = 1;
sivar = 2;
[&]() {
g = 2;
g1 = 2;
sivar = 4;
}();
}
}();
return 0;
#else
#pragma omp target
#pragma omp teams distribute firstprivate(t_var, vec, s_arr, var, sivar)
for (int i = 0; i < 2; ++i) {
vec[i] = t_var;
s_arr[i] = var;
sivar += i;
}
return tmain<int>();
#endif
}
// Skip global and bound tid vars
// Skip temp vars for loop
// param copy
// T_VAR and SIVAR
// preparation vars
// firstprivate vec(vec): copy from *_addr into priv1 and then from priv1 into priv2
// firstprivate(s_arr)
// firstprivate(var)
// Skip global and bound tid vars
// Skip temp vars for loop
// param copy
// T_VAR and preparation variables
// firstprivate vec(vec): copy from *_addr into priv1 and then from priv1 into priv2
// firstprivate(s_arr)
// firstprivate(var)
#endif
// CHECK1-LABEL: define {{[^@]+}}@__cxx_global_var_init
// CHECK1-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) @test)
// CHECK1-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @test to i8*), i8* @__dso_handle) #[[ATTR2:[0-9]+]]
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: call void @_ZN1SIfEC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: call void @_ZN1SIfED2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR2]]
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: [[TMP0:%.*]] = load volatile i32, i32* @g, align 4
// CHECK1-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to float
// CHECK1-NEXT: store float [[CONV]], float* [[F]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@__cxx_global_var_init.1
// CHECK1-SAME: () #[[ATTR0]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i64 0, i64 0), float 1.000000e+00)
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i64 0, i64 1), float 2.000000e+00)
// CHECK1-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* @__cxx_global_array_dtor, i8* null, i8* @__dso_handle) #[[ATTR2]]
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK1-NEXT: call void @_ZN1SIfEC2Ef(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], float [[TMP0]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@__cxx_global_array_dtor
// CHECK1-SAME: (i8* [[TMP0:%.*]]) #[[ATTR0]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1: arraydestroy.body:
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ getelementptr inbounds ([[STRUCT_S:%.*]], %struct.S* getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0), i64 2), [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0)
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1: arraydestroy.done1:
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK1-NEXT: [[TMP1:%.*]] = load volatile i32, i32* @g, align 4
// CHECK1-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP1]] to float
// CHECK1-NEXT: [[ADD:%.*]] = fadd float [[TMP0]], [[CONV]]
// CHECK1-NEXT: store float [[ADD]], float* [[F]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@__cxx_global_var_init.2
// CHECK1-SAME: () #[[ATTR0]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) @var, float 3.000000e+00)
// CHECK1-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @var to i8*), i8* @__dso_handle) #[[ATTR2]]
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@main
// CHECK1-SAME: () #[[ATTR3:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[T_VAR_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[SIVAR_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [5 x i8*], align 8
// CHECK1-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [5 x i8*], align 8
// CHECK1-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [5 x i8*], align 8
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
// CHECK1-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK1-NEXT: [[TMP0:%.*]] = load i32, i32* @t_var, align 4
// CHECK1-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_CASTED]] to i32*
// CHECK1-NEXT: store i32 [[TMP0]], i32* [[CONV]], align 4
// CHECK1-NEXT: [[TMP1:%.*]] = load i64, i64* [[T_VAR_CASTED]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load i32, i32* @_ZZ4mainE5sivar, align 4
// CHECK1-NEXT: [[CONV1:%.*]] = bitcast i64* [[SIVAR_CASTED]] to i32*
// CHECK1-NEXT: store i32 [[TMP2]], i32* [[CONV1]], align 4
// CHECK1-NEXT: [[TMP3:%.*]] = load i64, i64* [[SIVAR_CASTED]], align 8
// CHECK1-NEXT: [[TMP4:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8** [[TMP4]] to i64*
// CHECK1-NEXT: store i64 [[TMP1]], i64* [[TMP5]], align 8
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT: [[TMP7:%.*]] = bitcast i8** [[TMP6]] to i64*
// CHECK1-NEXT: store i64 [[TMP1]], i64* [[TMP7]], align 8
// CHECK1-NEXT: [[TMP8:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
// CHECK1-NEXT: store i8* null, i8** [[TMP8]], align 8
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK1-NEXT: [[TMP10:%.*]] = bitcast i8** [[TMP9]] to [2 x i32]**
// CHECK1-NEXT: store [2 x i32]* @vec, [2 x i32]** [[TMP10]], align 8
// CHECK1-NEXT: [[TMP11:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK1-NEXT: [[TMP12:%.*]] = bitcast i8** [[TMP11]] to [2 x i32]**
// CHECK1-NEXT: store [2 x i32]* @vec, [2 x i32]** [[TMP12]], align 8
// CHECK1-NEXT: [[TMP13:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
// CHECK1-NEXT: store i8* null, i8** [[TMP13]], align 8
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK1-NEXT: [[TMP15:%.*]] = bitcast i8** [[TMP14]] to [2 x %struct.S]**
// CHECK1-NEXT: store [2 x %struct.S]* @s_arr, [2 x %struct.S]** [[TMP15]], align 8
// CHECK1-NEXT: [[TMP16:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast i8** [[TMP16]] to [2 x %struct.S]**
// CHECK1-NEXT: store [2 x %struct.S]* @s_arr, [2 x %struct.S]** [[TMP17]], align 8
// CHECK1-NEXT: [[TMP18:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 2
// CHECK1-NEXT: store i8* null, i8** [[TMP18]], align 8
// CHECK1-NEXT: [[TMP19:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast i8** [[TMP19]] to %struct.S**
// CHECK1-NEXT: store %struct.S* @var, %struct.S** [[TMP20]], align 8
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK1-NEXT: [[TMP22:%.*]] = bitcast i8** [[TMP21]] to %struct.S**
// CHECK1-NEXT: store %struct.S* @var, %struct.S** [[TMP22]], align 8
// CHECK1-NEXT: [[TMP23:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 3
// CHECK1-NEXT: store i8* null, i8** [[TMP23]], align 8
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 4
// CHECK1-NEXT: [[TMP25:%.*]] = bitcast i8** [[TMP24]] to i64*
// CHECK1-NEXT: store i64 [[TMP3]], i64* [[TMP25]], align 8
// CHECK1-NEXT: [[TMP26:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 4
// CHECK1-NEXT: [[TMP27:%.*]] = bitcast i8** [[TMP26]] to i64*
// CHECK1-NEXT: store i64 [[TMP3]], i64* [[TMP27]], align 8
// CHECK1-NEXT: [[TMP28:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 4
// CHECK1-NEXT: store i8* null, i8** [[TMP28]], align 8
// CHECK1-NEXT: [[TMP29:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT: [[TMP30:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT: call void @__kmpc_push_target_tripcount_mapper(%struct.ident_t* @[[GLOB2:[0-9]+]], i64 -1, i64 2)
// CHECK1-NEXT: [[TMP31:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94.region_id, i32 5, i8** [[TMP29]], i8** [[TMP30]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @.offload_sizes, i32 0, i32 0), i64* getelementptr inbounds ([5 x i64], [5 x i64]* @.offload_maptypes, i32 0, i32 0), i8** null, i8** null, i32 0, i32 0)
// CHECK1-NEXT: [[TMP32:%.*]] = icmp ne i32 [[TMP31]], 0
// CHECK1-NEXT: br i1 [[TMP32]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK1: omp_offload.failed:
// CHECK1-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94(i64 [[TMP1]], [2 x i32]* @vec, [2 x %struct.S]* @s_arr, %struct.S* @var, i64 [[TMP3]]) #[[ATTR2]]
// CHECK1-NEXT: br label [[OMP_OFFLOAD_CONT]]
// CHECK1: omp_offload.cont:
// CHECK1-NEXT: [[CALL:%.*]] = call signext i32 @_Z5tmainIiET_v()
// CHECK1-NEXT: ret i32 [[CALL]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94
// CHECK1-SAME: (i64 [[T_VAR:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR:%.*]], i64 [[SIVAR:%.*]]) #[[ATTR4:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[T_VAR_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK1-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S]*, align 8
// CHECK1-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[SIVAR_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[T_VAR_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[SIVAR_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT: store i64 [[T_VAR]], i64* [[T_VAR_ADDR]], align 8
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: store [2 x %struct.S]* [[S_ARR]], [2 x %struct.S]** [[S_ARR_ADDR]], align 8
// CHECK1-NEXT: store %struct.S* [[VAR]], %struct.S** [[VAR_ADDR]], align 8
// CHECK1-NEXT: store i64 [[SIVAR]], i64* [[SIVAR_ADDR]], align 8
// CHECK1-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK1-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[S_ARR_ADDR]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct.S*, %struct.S** [[VAR_ADDR]], align 8
// CHECK1-NEXT: [[CONV1:%.*]] = bitcast i64* [[SIVAR_ADDR]] to i32*
// CHECK1-NEXT: [[TMP3:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK1-NEXT: [[CONV2:%.*]] = bitcast i64* [[T_VAR_CASTED]] to i32*
// CHECK1-NEXT: store i32 [[TMP3]], i32* [[CONV2]], align 4
// CHECK1-NEXT: [[TMP4:%.*]] = load i64, i64* [[T_VAR_CASTED]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = load i32, i32* [[CONV1]], align 8
// CHECK1-NEXT: [[CONV3:%.*]] = bitcast i64* [[SIVAR_CASTED]] to i32*
// CHECK1-NEXT: store i32 [[TMP5]], i32* [[CONV3]], align 4
// CHECK1-NEXT: [[TMP6:%.*]] = load i64, i64* [[SIVAR_CASTED]], align 8
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB2]], i32 5, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [2 x i32]*, i64, [2 x %struct.S]*, %struct.S*, i64)* @.omp_outlined. to void (i32*, i32*, ...)*), [2 x i32]* [[TMP0]], i64 [[TMP4]], [2 x %struct.S]* [[TMP1]], %struct.S* [[TMP2]], i64 [[TMP6]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], i64 [[T_VAR:%.*]], [2 x %struct.S]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR:%.*]], i64 [[SIVAR:%.*]]) #[[ATTR4]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK1-NEXT: [[T_VAR_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S]*, align 8
// CHECK1-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[SIVAR_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[VEC2:%.*]] = alloca [2 x i32], align 4
// CHECK1-NEXT: [[S_ARR3:%.*]] = alloca [2 x %struct.S], align 4
// CHECK1-NEXT: [[AGG_TMP:%.*]] = alloca [[STRUCT_ST:%.*]], align 4
// CHECK1-NEXT: [[VAR5:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK1-NEXT: [[AGG_TMP6:%.*]] = alloca [[STRUCT_ST]], align 4
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: store i64 [[T_VAR]], i64* [[T_VAR_ADDR]], align 8
// CHECK1-NEXT: store [2 x %struct.S]* [[S_ARR]], [2 x %struct.S]** [[S_ARR_ADDR]], align 8
// CHECK1-NEXT: store %struct.S* [[VAR]], %struct.S** [[VAR_ADDR]], align 8
// CHECK1-NEXT: store i64 [[SIVAR]], i64* [[SIVAR_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK1-NEXT: [[TMP1:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[S_ARR_ADDR]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct.S*, %struct.S** [[VAR_ADDR]], align 8
// CHECK1-NEXT: [[CONV1:%.*]] = bitcast i64* [[SIVAR_ADDR]] to i32*
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast [2 x i32]* [[VEC2]] to i8*
// CHECK1-NEXT: [[TMP4:%.*]] = bitcast [2 x i32]* [[TMP0]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP3]], i8* align 4 [[TMP4]], i64 8, i1 false)
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR3]], i32 0, i32 0
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast [2 x %struct.S]* [[TMP1]] to %struct.S*
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 2
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP6]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE4:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK1: omp.arraycpy.body:
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP5]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK1-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]])
// CHECK1-NEXT: call void @_ZN1SIfEC1ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], %struct.St* [[AGG_TMP]])
// CHECK1-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR2]]
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE4]], label [[OMP_ARRAYCPY_BODY]]
// CHECK1: omp.arraycpy.done4:
// CHECK1-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]])
// CHECK1-NEXT: call void @_ZN1SIfEC1ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[VAR5]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP2]], %struct.St* [[AGG_TMP6]])
// CHECK1-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]]) #[[ATTR2]]
// CHECK1-NEXT: [[TMP7:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP8:%.*]] = load i32, i32* [[TMP7]], align 4
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP8]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK1-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP9]], 1
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK1: cond.true:
// CHECK1-NEXT: br label [[COND_END:%.*]]
// CHECK1: cond.false:
// CHECK1-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK1-NEXT: br label [[COND_END]]
// CHECK1: cond.end:
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP10]], [[COND_FALSE]] ]
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK1-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK1-NEXT: store i32 [[TMP11]], i32* [[DOTOMP_IV]], align 4
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK1: omp.inner.for.cond:
// CHECK1-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK1-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK1-NEXT: [[CMP7:%.*]] = icmp sle i32 [[TMP12]], [[TMP13]]
// CHECK1-NEXT: br i1 [[CMP7]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK1: omp.inner.for.cond.cleanup:
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
// CHECK1: omp.inner.for.body:
// CHECK1-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP14]], 1
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK1-NEXT: [[TMP15:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK1-NEXT: [[TMP16:%.*]] = load i32, i32* [[I]], align 4
// CHECK1-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP16]] to i64
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC2]], i64 0, i64 [[IDXPROM]]
// CHECK1-NEXT: store i32 [[TMP15]], i32* [[ARRAYIDX]], align 4
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[I]], align 4
// CHECK1-NEXT: [[IDXPROM8:%.*]] = sext i32 [[TMP17]] to i64
// CHECK1-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR3]], i64 0, i64 [[IDXPROM8]]
// CHECK1-NEXT: [[TMP18:%.*]] = bitcast %struct.S* [[ARRAYIDX9]] to i8*
// CHECK1-NEXT: [[TMP19:%.*]] = bitcast %struct.S* [[VAR5]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP18]], i8* align 4 [[TMP19]], i64 4, i1 false)
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[I]], align 4
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[CONV1]], align 8
// CHECK1-NEXT: [[ADD10:%.*]] = add nsw i32 [[TMP21]], [[TMP20]]
// CHECK1-NEXT: store i32 [[ADD10]], i32* [[CONV1]], align 8
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK1: omp.body.continue:
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK1: omp.inner.for.inc:
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK1-NEXT: [[ADD11:%.*]] = add nsw i32 [[TMP22]], 1
// CHECK1-NEXT: store i32 [[ADD11]], i32* [[DOTOMP_IV]], align 4
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK1: omp.inner.for.end:
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
// CHECK1: omp.loop.exit:
// CHECK1-NEXT: [[TMP23:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[TMP23]], align 4
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP24]])
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR5]]) #[[ATTR2]]
// CHECK1-NEXT: [[ARRAY_BEGIN12:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR3]], i32 0, i32 0
// CHECK1-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN12]], i64 2
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1: arraydestroy.body:
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP25]], [[OMP_LOOP_EXIT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN12]]
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE13:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1: arraydestroy.done13:
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2StC1Ev
// CHECK1-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 8
// CHECK1-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 8
// CHECK1-NEXT: call void @_ZN2StC2Ev(%struct.St* nonnull align 4 dereferenceable(8) [[THIS1]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC1ERKS0_2St
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[S_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store %struct.S* [[S]], %struct.S** [[S_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.S*, %struct.S** [[S_ADDR]], align 8
// CHECK1-NEXT: call void @_ZN1SIfEC2ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP0]], %struct.St* [[T]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2StD1Ev
// CHECK1-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 8
// CHECK1-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 8
// CHECK1-NEXT: call void @_ZN2StD2Ev(%struct.St* nonnull align 4 dereferenceable(8) [[THIS1]]) #[[ATTR2]]
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z5tmainIiET_v
// CHECK1-SAME: () #[[ATTR6:[0-9]+]] comdat {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK1-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK1-NEXT: [[S_ARR:%.*]] = alloca [2 x %struct.S.0], align 4
// CHECK1-NEXT: [[VAR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[T_VAR_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [4 x i8*], align 8
// CHECK1-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [4 x i8*], align 8
// CHECK1-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [4 x i8*], align 8
// CHECK1-NEXT: [[_TMP1:%.*]] = alloca i32, align 4
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]])
// CHECK1-NEXT: store i32 0, i32* [[T_VAR]], align 4
// CHECK1-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const._Z5tmainIiET_v.vec to i8*), i64 8, i1 false)
// CHECK1-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i64 0, i64 0
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], i32 signext 1)
// CHECK1-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYINIT_BEGIN]], i64 1
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], i32 signext 2)
// CHECK1-NEXT: store %struct.S.0* [[TEST]], %struct.S.0** [[VAR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR]], align 8
// CHECK1-NEXT: store %struct.S.0* [[TMP1]], %struct.S.0** [[TMP]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load i32, i32* [[T_VAR]], align 4
// CHECK1-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_CASTED]] to i32*
// CHECK1-NEXT: store i32 [[TMP2]], i32* [[CONV]], align 4
// CHECK1-NEXT: [[TMP3:%.*]] = load i64, i64* [[T_VAR_CASTED]], align 8
// CHECK1-NEXT: [[TMP4:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 8
// CHECK1-NEXT: [[TMP6:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 8
// CHECK1-NEXT: [[TMP7:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8** [[TMP7]] to i64*
// CHECK1-NEXT: store i64 [[TMP3]], i64* [[TMP8]], align 8
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT: [[TMP10:%.*]] = bitcast i8** [[TMP9]] to i64*
// CHECK1-NEXT: store i64 [[TMP3]], i64* [[TMP10]], align 8
// CHECK1-NEXT: [[TMP11:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
// CHECK1-NEXT: store i8* null, i8** [[TMP11]], align 8
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK1-NEXT: [[TMP13:%.*]] = bitcast i8** [[TMP12]] to [2 x i32]**
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP13]], align 8
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK1-NEXT: [[TMP15:%.*]] = bitcast i8** [[TMP14]] to [2 x i32]**
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP15]], align 8
// CHECK1-NEXT: [[TMP16:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
// CHECK1-NEXT: store i8* null, i8** [[TMP16]], align 8
// CHECK1-NEXT: [[TMP17:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK1-NEXT: [[TMP18:%.*]] = bitcast i8** [[TMP17]] to [2 x %struct.S.0]**
// CHECK1-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[TMP18]], align 8
// CHECK1-NEXT: [[TMP19:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast i8** [[TMP19]] to [2 x %struct.S.0]**
// CHECK1-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[TMP20]], align 8
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 2
// CHECK1-NEXT: store i8* null, i8** [[TMP21]], align 8
// CHECK1-NEXT: [[TMP22:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK1-NEXT: [[TMP23:%.*]] = bitcast i8** [[TMP22]] to %struct.S.0**
// CHECK1-NEXT: store %struct.S.0* [[TMP5]], %struct.S.0** [[TMP23]], align 8
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK1-NEXT: [[TMP25:%.*]] = bitcast i8** [[TMP24]] to %struct.S.0**
// CHECK1-NEXT: store %struct.S.0* [[TMP6]], %struct.S.0** [[TMP25]], align 8
// CHECK1-NEXT: [[TMP26:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 3
// CHECK1-NEXT: store i8* null, i8** [[TMP26]], align 8
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK1-NEXT: [[TMP28:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK1-NEXT: call void @__kmpc_push_target_tripcount_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i64 2)
// CHECK1-NEXT: [[TMP29:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56.region_id, i32 4, i8** [[TMP27]], i8** [[TMP28]], i64* getelementptr inbounds ([4 x i64], [4 x i64]* @.offload_sizes.4, i32 0, i32 0), i64* getelementptr inbounds ([4 x i64], [4 x i64]* @.offload_maptypes.5, i32 0, i32 0), i8** null, i8** null, i32 0, i32 0)
// CHECK1-NEXT: [[TMP30:%.*]] = icmp ne i32 [[TMP29]], 0
// CHECK1-NEXT: br i1 [[TMP30]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK1: omp_offload.failed:
// CHECK1-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56(i64 [[TMP3]], [2 x i32]* [[VEC]], [2 x %struct.S.0]* [[S_ARR]], %struct.S.0* [[TMP4]]) #[[ATTR2]]
// CHECK1-NEXT: br label [[OMP_OFFLOAD_CONT]]
// CHECK1: omp_offload.cont:
// CHECK1-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK1-NEXT: [[TMP31:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i64 2
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1: arraydestroy.body:
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP31]], [[OMP_OFFLOAD_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE2:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1: arraydestroy.done2:
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR2]]
// CHECK1-NEXT: [[TMP32:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK1-NEXT: ret i32 [[TMP32]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2StC2Ev
// CHECK1-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 8
// CHECK1-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: store i32 0, i32* [[A]], align 4
// CHECK1-NEXT: [[B:%.*]] = getelementptr inbounds [[STRUCT_ST]], %struct.St* [[THIS1]], i32 0, i32 1
// CHECK1-NEXT: store i32 0, i32* [[B]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC2ERKS0_2St
// CHECK1-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[S_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store %struct.S* [[S]], %struct.S** [[S_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.S*, %struct.S** [[S_ADDR]], align 8
// CHECK1-NEXT: [[F2:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP0]], i32 0, i32 0
// CHECK1-NEXT: [[TMP1:%.*]] = load float, float* [[F2]], align 4
// CHECK1-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[T]], i32 0, i32 0
// CHECK1-NEXT: [[TMP2:%.*]] = load i32, i32* [[A]], align 4
// CHECK1-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP2]] to float
// CHECK1-NEXT: [[ADD:%.*]] = fadd float [[TMP1]], [[CONV]]
// CHECK1-NEXT: store float [[ADD]], float* [[F]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2StD2Ev
// CHECK1-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 8
// CHECK1-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 8
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ev
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: call void @_ZN1SIiEC2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ei
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 signext [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK1-NEXT: call void @_ZN1SIiEC2Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]], i32 signext [[TMP0]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56
// CHECK1-SAME: (i64 [[T_VAR:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S.0]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[VAR:%.*]]) #[[ATTR4]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[T_VAR_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK1-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S.0]*, align 8
// CHECK1-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[T_VAR_CASTED:%.*]] = alloca i64, align 8
// CHECK1-NEXT: store i64 [[T_VAR]], i64* [[T_VAR_ADDR]], align 8
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
// CHECK1-NEXT: store %struct.S.0* [[VAR]], %struct.S.0** [[VAR_ADDR]], align 8
// CHECK1-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK1-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load [2 x %struct.S.0]*, [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR_ADDR]], align 8
// CHECK1-NEXT: store %struct.S.0* [[TMP2]], %struct.S.0** [[TMP]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK1-NEXT: [[CONV1:%.*]] = bitcast i64* [[T_VAR_CASTED]] to i32*
// CHECK1-NEXT: store i32 [[TMP3]], i32* [[CONV1]], align 4
// CHECK1-NEXT: [[TMP4:%.*]] = load i64, i64* [[T_VAR_CASTED]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 8
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB2]], i32 4, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [2 x i32]*, i64, [2 x %struct.S.0]*, %struct.S.0*)* @.omp_outlined..3 to void (i32*, i32*, ...)*), [2 x i32]* [[TMP0]], i64 [[TMP4]], [2 x %struct.S.0]* [[TMP1]], %struct.S.0* [[TMP5]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..3
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], i64 [[T_VAR:%.*]], [2 x %struct.S.0]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[VAR:%.*]]) #[[ATTR4]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK1-NEXT: [[T_VAR_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S.0]*, align 8
// CHECK1-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[_TMP1:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[VEC2:%.*]] = alloca [2 x i32], align 4
// CHECK1-NEXT: [[S_ARR3:%.*]] = alloca [2 x %struct.S.0], align 4
// CHECK1-NEXT: [[AGG_TMP:%.*]] = alloca [[STRUCT_ST:%.*]], align 4
// CHECK1-NEXT: [[VAR5:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK1-NEXT: [[AGG_TMP6:%.*]] = alloca [[STRUCT_ST]], align 4
// CHECK1-NEXT: [[_TMP7:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: store i64 [[T_VAR]], i64* [[T_VAR_ADDR]], align 8
// CHECK1-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
// CHECK1-NEXT: store %struct.S.0* [[VAR]], %struct.S.0** [[VAR_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK1-NEXT: [[TMP1:%.*]] = load [2 x %struct.S.0]*, [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR_ADDR]], align 8
// CHECK1-NEXT: store %struct.S.0* [[TMP2]], %struct.S.0** [[TMP]], align 8
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast [2 x i32]* [[VEC2]] to i8*
// CHECK1-NEXT: [[TMP4:%.*]] = bitcast [2 x i32]* [[TMP0]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP3]], i8* align 4 [[TMP4]], i64 8, i1 false)
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i32 0, i32 0
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast [2 x %struct.S.0]* [[TMP1]] to %struct.S.0*
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i64 2
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S.0* [[ARRAY_BEGIN]], [[TMP6]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE4:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK1: omp.arraycpy.body:
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP5]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S.0* [ [[ARRAY_BEGIN]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK1-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]])
// CHECK1-NEXT: call void @_ZN1SIiEC1ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S.0* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], %struct.St* [[AGG_TMP]])
// CHECK1-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR2]]
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S.0* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE4]], label [[OMP_ARRAYCPY_BODY]]
// CHECK1: omp.arraycpy.done4:
// CHECK1-NEXT: [[TMP7:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 8
// CHECK1-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]])
// CHECK1-NEXT: call void @_ZN1SIiEC1ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR5]], %struct.S.0* nonnull align 4 dereferenceable(4) [[TMP7]], %struct.St* [[AGG_TMP6]])
// CHECK1-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]]) #[[ATTR2]]
// CHECK1-NEXT: store %struct.S.0* [[VAR5]], %struct.S.0** [[_TMP7]], align 8
// CHECK1-NEXT: [[TMP8:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP9]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK1-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP10]], 1
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK1: cond.true:
// CHECK1-NEXT: br label [[COND_END:%.*]]
// CHECK1: cond.false:
// CHECK1-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK1-NEXT: br label [[COND_END]]
// CHECK1: cond.end:
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP11]], [[COND_FALSE]] ]
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK1-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK1-NEXT: store i32 [[TMP12]], i32* [[DOTOMP_IV]], align 4
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK1: omp.inner.for.cond:
// CHECK1-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK1-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK1-NEXT: [[CMP8:%.*]] = icmp sle i32 [[TMP13]], [[TMP14]]
// CHECK1-NEXT: br i1 [[CMP8]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK1: omp.inner.for.cond.cleanup:
// CHECK1-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
// CHECK1: omp.inner.for.body:
// CHECK1-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP15]], 1
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK1-NEXT: [[TMP16:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK1-NEXT: [[TMP17:%.*]] = load i32, i32* [[I]], align 4
// CHECK1-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP17]] to i64
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC2]], i64 0, i64 [[IDXPROM]]
// CHECK1-NEXT: store i32 [[TMP16]], i32* [[ARRAYIDX]], align 4
// CHECK1-NEXT: [[TMP18:%.*]] = load %struct.S.0*, %struct.S.0** [[_TMP7]], align 8
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[I]], align 4
// CHECK1-NEXT: [[IDXPROM9:%.*]] = sext i32 [[TMP19]] to i64
// CHECK1-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i64 0, i64 [[IDXPROM9]]
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast %struct.S.0* [[ARRAYIDX10]] to i8*
// CHECK1-NEXT: [[TMP21:%.*]] = bitcast %struct.S.0* [[TMP18]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP20]], i8* align 4 [[TMP21]], i64 4, i1 false)
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK1: omp.body.continue:
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK1: omp.inner.for.inc:
// CHECK1-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK1-NEXT: [[ADD11:%.*]] = add nsw i32 [[TMP22]], 1
// CHECK1-NEXT: store i32 [[ADD11]], i32* [[DOTOMP_IV]], align 4
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK1: omp.inner.for.end:
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
// CHECK1: omp.loop.exit:
// CHECK1-NEXT: [[TMP23:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP24:%.*]] = load i32, i32* [[TMP23]], align 4
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP24]])
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR5]]) #[[ATTR2]]
// CHECK1-NEXT: [[ARRAY_BEGIN12:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i32 0, i32 0
// CHECK1-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN12]], i64 2
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1: arraydestroy.body:
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP25]], [[OMP_LOOP_EXIT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN12]]
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE13:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1: arraydestroy.done13:
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC1ERKS0_2St
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[S_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store %struct.S.0* [[S]], %struct.S.0** [[S_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.S.0*, %struct.S.0** [[S_ADDR]], align 8
// CHECK1-NEXT: call void @_ZN1SIiEC2ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]], %struct.S.0* nonnull align 4 dereferenceable(4) [[TMP0]], %struct.St* [[T]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiED1Ev
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: call void @_ZN1SIiED2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR2]]
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ev
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: [[TMP0:%.*]] = load volatile i32, i32* @g, align 4
// CHECK1-NEXT: store i32 [[TMP0]], i32* [[F]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ei
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 signext [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK1-NEXT: [[TMP1:%.*]] = load volatile i32, i32* @g, align 4
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP0]], [[TMP1]]
// CHECK1-NEXT: store i32 [[ADD]], i32* [[F]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC2ERKS0_2St
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[S_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store %struct.S.0* [[S]], %struct.S.0** [[S_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: [[TMP0:%.*]] = load %struct.S.0*, %struct.S.0** [[S_ADDR]], align 8
// CHECK1-NEXT: [[F2:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[TMP0]], i32 0, i32 0
// CHECK1-NEXT: [[TMP1:%.*]] = load i32, i32* [[F2]], align 4
// CHECK1-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[T]], i32 0, i32 0
// CHECK1-NEXT: [[TMP2:%.*]] = load i32, i32* [[A]], align 4
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP1]], [[TMP2]]
// CHECK1-NEXT: store i32 [[ADD]], i32* [[F]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiED2Ev
// CHECK1-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_GLOBAL__sub_I_teams_distribute_firstprivate_codegen.cpp
// CHECK1-SAME: () #[[ATTR0]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: call void @__cxx_global_var_init()
// CHECK1-NEXT: call void @__cxx_global_var_init.1()
// CHECK1-NEXT: call void @__cxx_global_var_init.2()
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
// CHECK1-SAME: () #[[ATTR0]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: call void @__tgt_register_requires(i64 1)
// CHECK1-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@__cxx_global_var_init
// CHECK2-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) @test)
// CHECK2-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @test to i8*), i8* @__dso_handle) #[[ATTR2:[0-9]+]]
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: call void @_ZN1SIfEC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: call void @_ZN1SIfED2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR2]]
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: [[TMP0:%.*]] = load volatile i32, i32* @g, align 4
// CHECK2-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to float
// CHECK2-NEXT: store float [[CONV]], float* [[F]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@__cxx_global_var_init.1
// CHECK2-SAME: () #[[ATTR0]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i64 0, i64 0), float 1.000000e+00)
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i64 0, i64 1), float 2.000000e+00)
// CHECK2-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* @__cxx_global_array_dtor, i8* null, i8* @__dso_handle) #[[ATTR2]]
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK2-NEXT: call void @_ZN1SIfEC2Ef(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], float [[TMP0]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@__cxx_global_array_dtor
// CHECK2-SAME: (i8* [[TMP0:%.*]]) #[[ATTR0]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2: arraydestroy.body:
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ getelementptr inbounds ([[STRUCT_S:%.*]], %struct.S* getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0), i64 2), [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0)
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2: arraydestroy.done1:
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK2-NEXT: [[TMP1:%.*]] = load volatile i32, i32* @g, align 4
// CHECK2-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP1]] to float
// CHECK2-NEXT: [[ADD:%.*]] = fadd float [[TMP0]], [[CONV]]
// CHECK2-NEXT: store float [[ADD]], float* [[F]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@__cxx_global_var_init.2
// CHECK2-SAME: () #[[ATTR0]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) @var, float 3.000000e+00)
// CHECK2-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @var to i8*), i8* @__dso_handle) #[[ATTR2]]
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@main
// CHECK2-SAME: () #[[ATTR3:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[T_VAR_CASTED:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[SIVAR_CASTED:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [5 x i8*], align 8
// CHECK2-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [5 x i8*], align 8
// CHECK2-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [5 x i8*], align 8
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
// CHECK2-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* @t_var, align 4
// CHECK2-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_CASTED]] to i32*
// CHECK2-NEXT: store i32 [[TMP0]], i32* [[CONV]], align 4
// CHECK2-NEXT: [[TMP1:%.*]] = load i64, i64* [[T_VAR_CASTED]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* @_ZZ4mainE5sivar, align 4
// CHECK2-NEXT: [[CONV1:%.*]] = bitcast i64* [[SIVAR_CASTED]] to i32*
// CHECK2-NEXT: store i32 [[TMP2]], i32* [[CONV1]], align 4
// CHECK2-NEXT: [[TMP3:%.*]] = load i64, i64* [[SIVAR_CASTED]], align 8
// CHECK2-NEXT: [[TMP4:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8** [[TMP4]] to i64*
// CHECK2-NEXT: store i64 [[TMP1]], i64* [[TMP5]], align 8
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK2-NEXT: [[TMP7:%.*]] = bitcast i8** [[TMP6]] to i64*
// CHECK2-NEXT: store i64 [[TMP1]], i64* [[TMP7]], align 8
// CHECK2-NEXT: [[TMP8:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
// CHECK2-NEXT: store i8* null, i8** [[TMP8]], align 8
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK2-NEXT: [[TMP10:%.*]] = bitcast i8** [[TMP9]] to [2 x i32]**
// CHECK2-NEXT: store [2 x i32]* @vec, [2 x i32]** [[TMP10]], align 8
// CHECK2-NEXT: [[TMP11:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK2-NEXT: [[TMP12:%.*]] = bitcast i8** [[TMP11]] to [2 x i32]**
// CHECK2-NEXT: store [2 x i32]* @vec, [2 x i32]** [[TMP12]], align 8
// CHECK2-NEXT: [[TMP13:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
// CHECK2-NEXT: store i8* null, i8** [[TMP13]], align 8
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK2-NEXT: [[TMP15:%.*]] = bitcast i8** [[TMP14]] to [2 x %struct.S]**
// CHECK2-NEXT: store [2 x %struct.S]* @s_arr, [2 x %struct.S]** [[TMP15]], align 8
// CHECK2-NEXT: [[TMP16:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast i8** [[TMP16]] to [2 x %struct.S]**
// CHECK2-NEXT: store [2 x %struct.S]* @s_arr, [2 x %struct.S]** [[TMP17]], align 8
// CHECK2-NEXT: [[TMP18:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 2
// CHECK2-NEXT: store i8* null, i8** [[TMP18]], align 8
// CHECK2-NEXT: [[TMP19:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast i8** [[TMP19]] to %struct.S**
// CHECK2-NEXT: store %struct.S* @var, %struct.S** [[TMP20]], align 8
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK2-NEXT: [[TMP22:%.*]] = bitcast i8** [[TMP21]] to %struct.S**
// CHECK2-NEXT: store %struct.S* @var, %struct.S** [[TMP22]], align 8
// CHECK2-NEXT: [[TMP23:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 3
// CHECK2-NEXT: store i8* null, i8** [[TMP23]], align 8
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 4
// CHECK2-NEXT: [[TMP25:%.*]] = bitcast i8** [[TMP24]] to i64*
// CHECK2-NEXT: store i64 [[TMP3]], i64* [[TMP25]], align 8
// CHECK2-NEXT: [[TMP26:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 4
// CHECK2-NEXT: [[TMP27:%.*]] = bitcast i8** [[TMP26]] to i64*
// CHECK2-NEXT: store i64 [[TMP3]], i64* [[TMP27]], align 8
// CHECK2-NEXT: [[TMP28:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 4
// CHECK2-NEXT: store i8* null, i8** [[TMP28]], align 8
// CHECK2-NEXT: [[TMP29:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK2-NEXT: [[TMP30:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK2-NEXT: call void @__kmpc_push_target_tripcount_mapper(%struct.ident_t* @[[GLOB2:[0-9]+]], i64 -1, i64 2)
// CHECK2-NEXT: [[TMP31:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94.region_id, i32 5, i8** [[TMP29]], i8** [[TMP30]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @.offload_sizes, i32 0, i32 0), i64* getelementptr inbounds ([5 x i64], [5 x i64]* @.offload_maptypes, i32 0, i32 0), i8** null, i8** null, i32 0, i32 0)
// CHECK2-NEXT: [[TMP32:%.*]] = icmp ne i32 [[TMP31]], 0
// CHECK2-NEXT: br i1 [[TMP32]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK2: omp_offload.failed:
// CHECK2-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94(i64 [[TMP1]], [2 x i32]* @vec, [2 x %struct.S]* @s_arr, %struct.S* @var, i64 [[TMP3]]) #[[ATTR2]]
// CHECK2-NEXT: br label [[OMP_OFFLOAD_CONT]]
// CHECK2: omp_offload.cont:
// CHECK2-NEXT: [[CALL:%.*]] = call signext i32 @_Z5tmainIiET_v()
// CHECK2-NEXT: ret i32 [[CALL]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94
// CHECK2-SAME: (i64 [[T_VAR:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR:%.*]], i64 [[SIVAR:%.*]]) #[[ATTR4:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[T_VAR_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK2-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S]*, align 8
// CHECK2-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[SIVAR_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[T_VAR_CASTED:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[SIVAR_CASTED:%.*]] = alloca i64, align 8
// CHECK2-NEXT: store i64 [[T_VAR]], i64* [[T_VAR_ADDR]], align 8
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: store [2 x %struct.S]* [[S_ARR]], [2 x %struct.S]** [[S_ARR_ADDR]], align 8
// CHECK2-NEXT: store %struct.S* [[VAR]], %struct.S** [[VAR_ADDR]], align 8
// CHECK2-NEXT: store i64 [[SIVAR]], i64* [[SIVAR_ADDR]], align 8
// CHECK2-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK2-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: [[TMP1:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[S_ARR_ADDR]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct.S*, %struct.S** [[VAR_ADDR]], align 8
// CHECK2-NEXT: [[CONV1:%.*]] = bitcast i64* [[SIVAR_ADDR]] to i32*
// CHECK2-NEXT: [[TMP3:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK2-NEXT: [[CONV2:%.*]] = bitcast i64* [[T_VAR_CASTED]] to i32*
// CHECK2-NEXT: store i32 [[TMP3]], i32* [[CONV2]], align 4
// CHECK2-NEXT: [[TMP4:%.*]] = load i64, i64* [[T_VAR_CASTED]], align 8
// CHECK2-NEXT: [[TMP5:%.*]] = load i32, i32* [[CONV1]], align 8
// CHECK2-NEXT: [[CONV3:%.*]] = bitcast i64* [[SIVAR_CASTED]] to i32*
// CHECK2-NEXT: store i32 [[TMP5]], i32* [[CONV3]], align 4
// CHECK2-NEXT: [[TMP6:%.*]] = load i64, i64* [[SIVAR_CASTED]], align 8
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB2]], i32 5, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [2 x i32]*, i64, [2 x %struct.S]*, %struct.S*, i64)* @.omp_outlined. to void (i32*, i32*, ...)*), [2 x i32]* [[TMP0]], i64 [[TMP4]], [2 x %struct.S]* [[TMP1]], %struct.S* [[TMP2]], i64 [[TMP6]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], i64 [[T_VAR:%.*]], [2 x %struct.S]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR:%.*]], i64 [[SIVAR:%.*]]) #[[ATTR4]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK2-NEXT: [[T_VAR_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S]*, align 8
// CHECK2-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[SIVAR_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[VEC2:%.*]] = alloca [2 x i32], align 4
// CHECK2-NEXT: [[S_ARR3:%.*]] = alloca [2 x %struct.S], align 4
// CHECK2-NEXT: [[AGG_TMP:%.*]] = alloca [[STRUCT_ST:%.*]], align 4
// CHECK2-NEXT: [[VAR5:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK2-NEXT: [[AGG_TMP6:%.*]] = alloca [[STRUCT_ST]], align 4
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: store i64 [[T_VAR]], i64* [[T_VAR_ADDR]], align 8
// CHECK2-NEXT: store [2 x %struct.S]* [[S_ARR]], [2 x %struct.S]** [[S_ARR_ADDR]], align 8
// CHECK2-NEXT: store %struct.S* [[VAR]], %struct.S** [[VAR_ADDR]], align 8
// CHECK2-NEXT: store i64 [[SIVAR]], i64* [[SIVAR_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK2-NEXT: [[TMP1:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[S_ARR_ADDR]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct.S*, %struct.S** [[VAR_ADDR]], align 8
// CHECK2-NEXT: [[CONV1:%.*]] = bitcast i64* [[SIVAR_ADDR]] to i32*
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast [2 x i32]* [[VEC2]] to i8*
// CHECK2-NEXT: [[TMP4:%.*]] = bitcast [2 x i32]* [[TMP0]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP3]], i8* align 4 [[TMP4]], i64 8, i1 false)
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR3]], i32 0, i32 0
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast [2 x %struct.S]* [[TMP1]] to %struct.S*
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 2
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP6]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE4:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK2: omp.arraycpy.body:
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP5]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK2-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]])
// CHECK2-NEXT: call void @_ZN1SIfEC1ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], %struct.St* [[AGG_TMP]])
// CHECK2-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR2]]
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE4]], label [[OMP_ARRAYCPY_BODY]]
// CHECK2: omp.arraycpy.done4:
// CHECK2-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]])
// CHECK2-NEXT: call void @_ZN1SIfEC1ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[VAR5]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP2]], %struct.St* [[AGG_TMP6]])
// CHECK2-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]]) #[[ATTR2]]
// CHECK2-NEXT: [[TMP7:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP8:%.*]] = load i32, i32* [[TMP7]], align 4
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP8]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK2-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP9]], 1
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK2: cond.true:
// CHECK2-NEXT: br label [[COND_END:%.*]]
// CHECK2: cond.false:
// CHECK2-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK2-NEXT: br label [[COND_END]]
// CHECK2: cond.end:
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP10]], [[COND_FALSE]] ]
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK2-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK2-NEXT: store i32 [[TMP11]], i32* [[DOTOMP_IV]], align 4
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK2: omp.inner.for.cond:
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK2-NEXT: [[CMP7:%.*]] = icmp sle i32 [[TMP12]], [[TMP13]]
// CHECK2-NEXT: br i1 [[CMP7]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK2: omp.inner.for.cond.cleanup:
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
// CHECK2: omp.inner.for.body:
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP14]], 1
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK2-NEXT: [[TMP15:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[I]], align 4
// CHECK2-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP16]] to i64
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC2]], i64 0, i64 [[IDXPROM]]
// CHECK2-NEXT: store i32 [[TMP15]], i32* [[ARRAYIDX]], align 4
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[I]], align 4
// CHECK2-NEXT: [[IDXPROM8:%.*]] = sext i32 [[TMP17]] to i64
// CHECK2-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR3]], i64 0, i64 [[IDXPROM8]]
// CHECK2-NEXT: [[TMP18:%.*]] = bitcast %struct.S* [[ARRAYIDX9]] to i8*
// CHECK2-NEXT: [[TMP19:%.*]] = bitcast %struct.S* [[VAR5]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP18]], i8* align 4 [[TMP19]], i64 4, i1 false)
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[I]], align 4
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[CONV1]], align 8
// CHECK2-NEXT: [[ADD10:%.*]] = add nsw i32 [[TMP21]], [[TMP20]]
// CHECK2-NEXT: store i32 [[ADD10]], i32* [[CONV1]], align 8
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK2: omp.body.continue:
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK2: omp.inner.for.inc:
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK2-NEXT: [[ADD11:%.*]] = add nsw i32 [[TMP22]], 1
// CHECK2-NEXT: store i32 [[ADD11]], i32* [[DOTOMP_IV]], align 4
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK2: omp.inner.for.end:
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
// CHECK2: omp.loop.exit:
// CHECK2-NEXT: [[TMP23:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[TMP23]], align 4
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP24]])
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR5]]) #[[ATTR2]]
// CHECK2-NEXT: [[ARRAY_BEGIN12:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR3]], i32 0, i32 0
// CHECK2-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN12]], i64 2
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2: arraydestroy.body:
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP25]], [[OMP_LOOP_EXIT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN12]]
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE13:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2: arraydestroy.done13:
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2StC1Ev
// CHECK2-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 8
// CHECK2-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 8
// CHECK2-NEXT: call void @_ZN2StC2Ev(%struct.St* nonnull align 4 dereferenceable(8) [[THIS1]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC1ERKS0_2St
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[S_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store %struct.S* [[S]], %struct.S** [[S_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.S*, %struct.S** [[S_ADDR]], align 8
// CHECK2-NEXT: call void @_ZN1SIfEC2ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP0]], %struct.St* [[T]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2StD1Ev
// CHECK2-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 8
// CHECK2-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 8
// CHECK2-NEXT: call void @_ZN2StD2Ev(%struct.St* nonnull align 4 dereferenceable(8) [[THIS1]]) #[[ATTR2]]
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z5tmainIiET_v
// CHECK2-SAME: () #[[ATTR6:[0-9]+]] comdat {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK2-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK2-NEXT: [[S_ARR:%.*]] = alloca [2 x %struct.S.0], align 4
// CHECK2-NEXT: [[VAR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[T_VAR_CASTED:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [4 x i8*], align 8
// CHECK2-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [4 x i8*], align 8
// CHECK2-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [4 x i8*], align 8
// CHECK2-NEXT: [[_TMP1:%.*]] = alloca i32, align 4
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]])
// CHECK2-NEXT: store i32 0, i32* [[T_VAR]], align 4
// CHECK2-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const._Z5tmainIiET_v.vec to i8*), i64 8, i1 false)
// CHECK2-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i64 0, i64 0
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], i32 signext 1)
// CHECK2-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYINIT_BEGIN]], i64 1
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], i32 signext 2)
// CHECK2-NEXT: store %struct.S.0* [[TEST]], %struct.S.0** [[VAR]], align 8
// CHECK2-NEXT: [[TMP1:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR]], align 8
// CHECK2-NEXT: store %struct.S.0* [[TMP1]], %struct.S.0** [[TMP]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* [[T_VAR]], align 4
// CHECK2-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_CASTED]] to i32*
// CHECK2-NEXT: store i32 [[TMP2]], i32* [[CONV]], align 4
// CHECK2-NEXT: [[TMP3:%.*]] = load i64, i64* [[T_VAR_CASTED]], align 8
// CHECK2-NEXT: [[TMP4:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 8
// CHECK2-NEXT: [[TMP5:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 8
// CHECK2-NEXT: [[TMP6:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 8
// CHECK2-NEXT: [[TMP7:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8** [[TMP7]] to i64*
// CHECK2-NEXT: store i64 [[TMP3]], i64* [[TMP8]], align 8
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK2-NEXT: [[TMP10:%.*]] = bitcast i8** [[TMP9]] to i64*
// CHECK2-NEXT: store i64 [[TMP3]], i64* [[TMP10]], align 8
// CHECK2-NEXT: [[TMP11:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 0
// CHECK2-NEXT: store i8* null, i8** [[TMP11]], align 8
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK2-NEXT: [[TMP13:%.*]] = bitcast i8** [[TMP12]] to [2 x i32]**
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP13]], align 8
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK2-NEXT: [[TMP15:%.*]] = bitcast i8** [[TMP14]] to [2 x i32]**
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP15]], align 8
// CHECK2-NEXT: [[TMP16:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 1
// CHECK2-NEXT: store i8* null, i8** [[TMP16]], align 8
// CHECK2-NEXT: [[TMP17:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK2-NEXT: [[TMP18:%.*]] = bitcast i8** [[TMP17]] to [2 x %struct.S.0]**
// CHECK2-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[TMP18]], align 8
// CHECK2-NEXT: [[TMP19:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast i8** [[TMP19]] to [2 x %struct.S.0]**
// CHECK2-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[TMP20]], align 8
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 2
// CHECK2-NEXT: store i8* null, i8** [[TMP21]], align 8
// CHECK2-NEXT: [[TMP22:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK2-NEXT: [[TMP23:%.*]] = bitcast i8** [[TMP22]] to %struct.S.0**
// CHECK2-NEXT: store %struct.S.0* [[TMP5]], %struct.S.0** [[TMP23]], align 8
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK2-NEXT: [[TMP25:%.*]] = bitcast i8** [[TMP24]] to %struct.S.0**
// CHECK2-NEXT: store %struct.S.0* [[TMP6]], %struct.S.0** [[TMP25]], align 8
// CHECK2-NEXT: [[TMP26:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i64 0, i64 3
// CHECK2-NEXT: store i8* null, i8** [[TMP26]], align 8
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK2-NEXT: [[TMP28:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK2-NEXT: call void @__kmpc_push_target_tripcount_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i64 2)
// CHECK2-NEXT: [[TMP29:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56.region_id, i32 4, i8** [[TMP27]], i8** [[TMP28]], i64* getelementptr inbounds ([4 x i64], [4 x i64]* @.offload_sizes.4, i32 0, i32 0), i64* getelementptr inbounds ([4 x i64], [4 x i64]* @.offload_maptypes.5, i32 0, i32 0), i8** null, i8** null, i32 0, i32 0)
// CHECK2-NEXT: [[TMP30:%.*]] = icmp ne i32 [[TMP29]], 0
// CHECK2-NEXT: br i1 [[TMP30]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK2: omp_offload.failed:
// CHECK2-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56(i64 [[TMP3]], [2 x i32]* [[VEC]], [2 x %struct.S.0]* [[S_ARR]], %struct.S.0* [[TMP4]]) #[[ATTR2]]
// CHECK2-NEXT: br label [[OMP_OFFLOAD_CONT]]
// CHECK2: omp_offload.cont:
// CHECK2-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK2-NEXT: [[TMP31:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i64 2
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2: arraydestroy.body:
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP31]], [[OMP_OFFLOAD_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE2:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2: arraydestroy.done2:
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR2]]
// CHECK2-NEXT: [[TMP32:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK2-NEXT: ret i32 [[TMP32]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2StC2Ev
// CHECK2-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 8
// CHECK2-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: store i32 0, i32* [[A]], align 4
// CHECK2-NEXT: [[B:%.*]] = getelementptr inbounds [[STRUCT_ST]], %struct.St* [[THIS1]], i32 0, i32 1
// CHECK2-NEXT: store i32 0, i32* [[B]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC2ERKS0_2St
// CHECK2-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[S_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store %struct.S* [[S]], %struct.S** [[S_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.S*, %struct.S** [[S_ADDR]], align 8
// CHECK2-NEXT: [[F2:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP0]], i32 0, i32 0
// CHECK2-NEXT: [[TMP1:%.*]] = load float, float* [[F2]], align 4
// CHECK2-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[T]], i32 0, i32 0
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* [[A]], align 4
// CHECK2-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP2]] to float
// CHECK2-NEXT: [[ADD:%.*]] = fadd float [[TMP1]], [[CONV]]
// CHECK2-NEXT: store float [[ADD]], float* [[F]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2StD2Ev
// CHECK2-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 8
// CHECK2-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 8
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ev
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: call void @_ZN1SIiEC2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ei
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 signext [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK2-NEXT: call void @_ZN1SIiEC2Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]], i32 signext [[TMP0]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56
// CHECK2-SAME: (i64 [[T_VAR:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S.0]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[VAR:%.*]]) #[[ATTR4]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[T_VAR_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK2-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S.0]*, align 8
// CHECK2-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[T_VAR_CASTED:%.*]] = alloca i64, align 8
// CHECK2-NEXT: store i64 [[T_VAR]], i64* [[T_VAR_ADDR]], align 8
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
// CHECK2-NEXT: store %struct.S.0* [[VAR]], %struct.S.0** [[VAR_ADDR]], align 8
// CHECK2-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK2-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: [[TMP1:%.*]] = load [2 x %struct.S.0]*, [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR_ADDR]], align 8
// CHECK2-NEXT: store %struct.S.0* [[TMP2]], %struct.S.0** [[TMP]], align 8
// CHECK2-NEXT: [[TMP3:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK2-NEXT: [[CONV1:%.*]] = bitcast i64* [[T_VAR_CASTED]] to i32*
// CHECK2-NEXT: store i32 [[TMP3]], i32* [[CONV1]], align 4
// CHECK2-NEXT: [[TMP4:%.*]] = load i64, i64* [[T_VAR_CASTED]], align 8
// CHECK2-NEXT: [[TMP5:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 8
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB2]], i32 4, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [2 x i32]*, i64, [2 x %struct.S.0]*, %struct.S.0*)* @.omp_outlined..3 to void (i32*, i32*, ...)*), [2 x i32]* [[TMP0]], i64 [[TMP4]], [2 x %struct.S.0]* [[TMP1]], %struct.S.0* [[TMP5]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..3
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], i64 [[T_VAR:%.*]], [2 x %struct.S.0]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[VAR:%.*]]) #[[ATTR4]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK2-NEXT: [[T_VAR_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S.0]*, align 8
// CHECK2-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[_TMP1:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[VEC2:%.*]] = alloca [2 x i32], align 4
// CHECK2-NEXT: [[S_ARR3:%.*]] = alloca [2 x %struct.S.0], align 4
// CHECK2-NEXT: [[AGG_TMP:%.*]] = alloca [[STRUCT_ST:%.*]], align 4
// CHECK2-NEXT: [[VAR5:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK2-NEXT: [[AGG_TMP6:%.*]] = alloca [[STRUCT_ST]], align 4
// CHECK2-NEXT: [[_TMP7:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: store i64 [[T_VAR]], i64* [[T_VAR_ADDR]], align 8
// CHECK2-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
// CHECK2-NEXT: store %struct.S.0* [[VAR]], %struct.S.0** [[VAR_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: [[CONV:%.*]] = bitcast i64* [[T_VAR_ADDR]] to i32*
// CHECK2-NEXT: [[TMP1:%.*]] = load [2 x %struct.S.0]*, [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR_ADDR]], align 8
// CHECK2-NEXT: store %struct.S.0* [[TMP2]], %struct.S.0** [[TMP]], align 8
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast [2 x i32]* [[VEC2]] to i8*
// CHECK2-NEXT: [[TMP4:%.*]] = bitcast [2 x i32]* [[TMP0]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP3]], i8* align 4 [[TMP4]], i64 8, i1 false)
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i32 0, i32 0
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast [2 x %struct.S.0]* [[TMP1]] to %struct.S.0*
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i64 2
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S.0* [[ARRAY_BEGIN]], [[TMP6]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE4:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK2: omp.arraycpy.body:
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP5]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S.0* [ [[ARRAY_BEGIN]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK2-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]])
// CHECK2-NEXT: call void @_ZN1SIiEC1ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S.0* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], %struct.St* [[AGG_TMP]])
// CHECK2-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR2]]
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S.0* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE4]], label [[OMP_ARRAYCPY_BODY]]
// CHECK2: omp.arraycpy.done4:
// CHECK2-NEXT: [[TMP7:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 8
// CHECK2-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]])
// CHECK2-NEXT: call void @_ZN1SIiEC1ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR5]], %struct.S.0* nonnull align 4 dereferenceable(4) [[TMP7]], %struct.St* [[AGG_TMP6]])
// CHECK2-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]]) #[[ATTR2]]
// CHECK2-NEXT: store %struct.S.0* [[VAR5]], %struct.S.0** [[_TMP7]], align 8
// CHECK2-NEXT: [[TMP8:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP9]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK2-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP10]], 1
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK2: cond.true:
// CHECK2-NEXT: br label [[COND_END:%.*]]
// CHECK2: cond.false:
// CHECK2-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK2-NEXT: br label [[COND_END]]
// CHECK2: cond.end:
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP11]], [[COND_FALSE]] ]
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK2-NEXT: store i32 [[TMP12]], i32* [[DOTOMP_IV]], align 4
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK2: omp.inner.for.cond:
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK2-NEXT: [[CMP8:%.*]] = icmp sle i32 [[TMP13]], [[TMP14]]
// CHECK2-NEXT: br i1 [[CMP8]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK2: omp.inner.for.cond.cleanup:
// CHECK2-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
// CHECK2: omp.inner.for.body:
// CHECK2-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP15]], 1
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK2-NEXT: [[TMP16:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK2-NEXT: [[TMP17:%.*]] = load i32, i32* [[I]], align 4
// CHECK2-NEXT: [[IDXPROM:%.*]] = sext i32 [[TMP17]] to i64
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC2]], i64 0, i64 [[IDXPROM]]
// CHECK2-NEXT: store i32 [[TMP16]], i32* [[ARRAYIDX]], align 4
// CHECK2-NEXT: [[TMP18:%.*]] = load %struct.S.0*, %struct.S.0** [[_TMP7]], align 8
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[I]], align 4
// CHECK2-NEXT: [[IDXPROM9:%.*]] = sext i32 [[TMP19]] to i64
// CHECK2-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i64 0, i64 [[IDXPROM9]]
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast %struct.S.0* [[ARRAYIDX10]] to i8*
// CHECK2-NEXT: [[TMP21:%.*]] = bitcast %struct.S.0* [[TMP18]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP20]], i8* align 4 [[TMP21]], i64 4, i1 false)
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK2: omp.body.continue:
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK2: omp.inner.for.inc:
// CHECK2-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK2-NEXT: [[ADD11:%.*]] = add nsw i32 [[TMP22]], 1
// CHECK2-NEXT: store i32 [[ADD11]], i32* [[DOTOMP_IV]], align 4
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK2: omp.inner.for.end:
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
// CHECK2: omp.loop.exit:
// CHECK2-NEXT: [[TMP23:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP24:%.*]] = load i32, i32* [[TMP23]], align 4
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP24]])
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR5]]) #[[ATTR2]]
// CHECK2-NEXT: [[ARRAY_BEGIN12:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i32 0, i32 0
// CHECK2-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN12]], i64 2
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2: arraydestroy.body:
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP25]], [[OMP_LOOP_EXIT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN12]]
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE13:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2: arraydestroy.done13:
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC1ERKS0_2St
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[S_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store %struct.S.0* [[S]], %struct.S.0** [[S_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.S.0*, %struct.S.0** [[S_ADDR]], align 8
// CHECK2-NEXT: call void @_ZN1SIiEC2ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]], %struct.S.0* nonnull align 4 dereferenceable(4) [[TMP0]], %struct.St* [[T]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiED1Ev
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: call void @_ZN1SIiED2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR2]]
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ev
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: [[TMP0:%.*]] = load volatile i32, i32* @g, align 4
// CHECK2-NEXT: store i32 [[TMP0]], i32* [[F]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ei
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 signext [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK2-NEXT: [[TMP1:%.*]] = load volatile i32, i32* @g, align 4
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP0]], [[TMP1]]
// CHECK2-NEXT: store i32 [[ADD]], i32* [[F]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC2ERKS0_2St
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[S_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store %struct.S.0* [[S]], %struct.S.0** [[S_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: [[TMP0:%.*]] = load %struct.S.0*, %struct.S.0** [[S_ADDR]], align 8
// CHECK2-NEXT: [[F2:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[TMP0]], i32 0, i32 0
// CHECK2-NEXT: [[TMP1:%.*]] = load i32, i32* [[F2]], align 4
// CHECK2-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[T]], i32 0, i32 0
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* [[A]], align 4
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP1]], [[TMP2]]
// CHECK2-NEXT: store i32 [[ADD]], i32* [[F]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiED2Ev
// CHECK2-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_GLOBAL__sub_I_teams_distribute_firstprivate_codegen.cpp
// CHECK2-SAME: () #[[ATTR0]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: call void @__cxx_global_var_init()
// CHECK2-NEXT: call void @__cxx_global_var_init.1()
// CHECK2-NEXT: call void @__cxx_global_var_init.2()
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
// CHECK2-SAME: () #[[ATTR0]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: call void @__tgt_register_requires(i64 1)
// CHECK2-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__cxx_global_var_init
// CHECK3-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) @test)
// CHECK3-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @test to i8*), i8* @__dso_handle) #[[ATTR2:[0-9]+]]
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: call void @_ZN1SIfEC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: call void @_ZN1SIfED2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR2]]
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT: [[TMP0:%.*]] = load volatile i32, i32* @g, align 4
// CHECK3-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to float
// CHECK3-NEXT: store float [[CONV]], float* [[F]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__cxx_global_var_init.1
// CHECK3-SAME: () #[[ATTR0]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0), float 1.000000e+00)
// CHECK3-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 1), float 2.000000e+00)
// CHECK3-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* @__cxx_global_array_dtor, i8* null, i8* @__dso_handle) #[[ATTR2]]
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK3-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK3-NEXT: call void @_ZN1SIfEC2Ef(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], float [[TMP0]])
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__cxx_global_array_dtor
// CHECK3-SAME: (i8* [[TMP0:%.*]]) #[[ATTR0]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 4
// CHECK3-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 4
// CHECK3-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK3: arraydestroy.body:
// CHECK3-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ getelementptr inbounds ([[STRUCT_S:%.*]], %struct.S* getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0), i32 2), [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK3-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i32 -1
// CHECK3-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK3-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0)
// CHECK3-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK3: arraydestroy.done1:
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK3-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load volatile i32, i32* @g, align 4
// CHECK3-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP1]] to float
// CHECK3-NEXT: [[ADD:%.*]] = fadd float [[TMP0]], [[CONV]]
// CHECK3-NEXT: store float [[ADD]], float* [[F]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__cxx_global_var_init.2
// CHECK3-SAME: () #[[ATTR0]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) @var, float 3.000000e+00)
// CHECK3-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @var to i8*), i8* @__dso_handle) #[[ATTR2]]
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@main
// CHECK3-SAME: () #[[ATTR3:[0-9]+]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[T_VAR_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[SIVAR_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [5 x i8*], align 4
// CHECK3-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [5 x i8*], align 4
// CHECK3-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [5 x i8*], align 4
// CHECK3-NEXT: [[TMP:%.*]] = alloca i32, align 4
// CHECK3-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load i32, i32* @t_var, align 4
// CHECK3-NEXT: store i32 [[TMP0]], i32* [[T_VAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load i32, i32* [[T_VAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP2:%.*]] = load i32, i32* @_ZZ4mainE5sivar, align 4
// CHECK3-NEXT: store i32 [[TMP2]], i32* [[SIVAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP3:%.*]] = load i32, i32* [[SIVAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP4:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT: [[TMP5:%.*]] = bitcast i8** [[TMP4]] to i32*
// CHECK3-NEXT: store i32 [[TMP1]], i32* [[TMP5]], align 4
// CHECK3-NEXT: [[TMP6:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT: [[TMP7:%.*]] = bitcast i8** [[TMP6]] to i32*
// CHECK3-NEXT: store i32 [[TMP1]], i32* [[TMP7]], align 4
// CHECK3-NEXT: [[TMP8:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 0
// CHECK3-NEXT: store i8* null, i8** [[TMP8]], align 4
// CHECK3-NEXT: [[TMP9:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK3-NEXT: [[TMP10:%.*]] = bitcast i8** [[TMP9]] to [2 x i32]**
// CHECK3-NEXT: store [2 x i32]* @vec, [2 x i32]** [[TMP10]], align 4
// CHECK3-NEXT: [[TMP11:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK3-NEXT: [[TMP12:%.*]] = bitcast i8** [[TMP11]] to [2 x i32]**
// CHECK3-NEXT: store [2 x i32]* @vec, [2 x i32]** [[TMP12]], align 4
// CHECK3-NEXT: [[TMP13:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 1
// CHECK3-NEXT: store i8* null, i8** [[TMP13]], align 4
// CHECK3-NEXT: [[TMP14:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK3-NEXT: [[TMP15:%.*]] = bitcast i8** [[TMP14]] to [2 x %struct.S]**
// CHECK3-NEXT: store [2 x %struct.S]* @s_arr, [2 x %struct.S]** [[TMP15]], align 4
// CHECK3-NEXT: [[TMP16:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK3-NEXT: [[TMP17:%.*]] = bitcast i8** [[TMP16]] to [2 x %struct.S]**
// CHECK3-NEXT: store [2 x %struct.S]* @s_arr, [2 x %struct.S]** [[TMP17]], align 4
// CHECK3-NEXT: [[TMP18:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 2
// CHECK3-NEXT: store i8* null, i8** [[TMP18]], align 4
// CHECK3-NEXT: [[TMP19:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK3-NEXT: [[TMP20:%.*]] = bitcast i8** [[TMP19]] to %struct.S**
// CHECK3-NEXT: store %struct.S* @var, %struct.S** [[TMP20]], align 4
// CHECK3-NEXT: [[TMP21:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK3-NEXT: [[TMP22:%.*]] = bitcast i8** [[TMP21]] to %struct.S**
// CHECK3-NEXT: store %struct.S* @var, %struct.S** [[TMP22]], align 4
// CHECK3-NEXT: [[TMP23:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 3
// CHECK3-NEXT: store i8* null, i8** [[TMP23]], align 4
// CHECK3-NEXT: [[TMP24:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 4
// CHECK3-NEXT: [[TMP25:%.*]] = bitcast i8** [[TMP24]] to i32*
// CHECK3-NEXT: store i32 [[TMP3]], i32* [[TMP25]], align 4
// CHECK3-NEXT: [[TMP26:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 4
// CHECK3-NEXT: [[TMP27:%.*]] = bitcast i8** [[TMP26]] to i32*
// CHECK3-NEXT: store i32 [[TMP3]], i32* [[TMP27]], align 4
// CHECK3-NEXT: [[TMP28:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 4
// CHECK3-NEXT: store i8* null, i8** [[TMP28]], align 4
// CHECK3-NEXT: [[TMP29:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT: [[TMP30:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT: call void @__kmpc_push_target_tripcount_mapper(%struct.ident_t* @[[GLOB2:[0-9]+]], i64 -1, i64 2)
// CHECK3-NEXT: [[TMP31:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94.region_id, i32 5, i8** [[TMP29]], i8** [[TMP30]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @.offload_sizes, i32 0, i32 0), i64* getelementptr inbounds ([5 x i64], [5 x i64]* @.offload_maptypes, i32 0, i32 0), i8** null, i8** null, i32 0, i32 0)
// CHECK3-NEXT: [[TMP32:%.*]] = icmp ne i32 [[TMP31]], 0
// CHECK3-NEXT: br i1 [[TMP32]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK3: omp_offload.failed:
// CHECK3-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94(i32 [[TMP1]], [2 x i32]* @vec, [2 x %struct.S]* @s_arr, %struct.S* @var, i32 [[TMP3]]) #[[ATTR2]]
// CHECK3-NEXT: br label [[OMP_OFFLOAD_CONT]]
// CHECK3: omp_offload.cont:
// CHECK3-NEXT: [[CALL:%.*]] = call i32 @_Z5tmainIiET_v()
// CHECK3-NEXT: ret i32 [[CALL]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94
// CHECK3-SAME: (i32 [[T_VAR:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR:%.*]], i32 [[SIVAR:%.*]]) #[[ATTR4:[0-9]+]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[T_VAR_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 4
// CHECK3-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S]*, align 4
// CHECK3-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: [[SIVAR_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[T_VAR_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[SIVAR_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT: store i32 [[T_VAR]], i32* [[T_VAR_ADDR]], align 4
// CHECK3-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 4
// CHECK3-NEXT: store [2 x %struct.S]* [[S_ARR]], [2 x %struct.S]** [[S_ARR_ADDR]], align 4
// CHECK3-NEXT: store %struct.S* [[VAR]], %struct.S** [[VAR_ADDR]], align 4
// CHECK3-NEXT: store i32 [[SIVAR]], i32* [[SIVAR_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[S_ARR_ADDR]], align 4
// CHECK3-NEXT: [[TMP2:%.*]] = load %struct.S*, %struct.S** [[VAR_ADDR]], align 4
// CHECK3-NEXT: [[TMP3:%.*]] = load i32, i32* [[T_VAR_ADDR]], align 4
// CHECK3-NEXT: store i32 [[TMP3]], i32* [[T_VAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP4:%.*]] = load i32, i32* [[T_VAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP5:%.*]] = load i32, i32* [[SIVAR_ADDR]], align 4
// CHECK3-NEXT: store i32 [[TMP5]], i32* [[SIVAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP6:%.*]] = load i32, i32* [[SIVAR_CASTED]], align 4
// CHECK3-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB2]], i32 5, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [2 x i32]*, i32, [2 x %struct.S]*, %struct.S*, i32)* @.omp_outlined. to void (i32*, i32*, ...)*), [2 x i32]* [[TMP0]], i32 [[TMP4]], [2 x %struct.S]* [[TMP1]], %struct.S* [[TMP2]], i32 [[TMP6]])
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], i32 [[T_VAR:%.*]], [2 x %struct.S]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR:%.*]], i32 [[SIVAR:%.*]]) #[[ATTR4]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 4
// CHECK3-NEXT: [[T_VAR_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S]*, align 4
// CHECK3-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: [[SIVAR_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[TMP:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[VEC1:%.*]] = alloca [2 x i32], align 4
// CHECK3-NEXT: [[S_ARR2:%.*]] = alloca [2 x %struct.S], align 4
// CHECK3-NEXT: [[AGG_TMP:%.*]] = alloca [[STRUCT_ST:%.*]], align 4
// CHECK3-NEXT: [[VAR4:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK3-NEXT: [[AGG_TMP5:%.*]] = alloca [[STRUCT_ST]], align 4
// CHECK3-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK3-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 4
// CHECK3-NEXT: store i32 [[T_VAR]], i32* [[T_VAR_ADDR]], align 4
// CHECK3-NEXT: store [2 x %struct.S]* [[S_ARR]], [2 x %struct.S]** [[S_ARR_ADDR]], align 4
// CHECK3-NEXT: store %struct.S* [[VAR]], %struct.S** [[VAR_ADDR]], align 4
// CHECK3-NEXT: store i32 [[SIVAR]], i32* [[SIVAR_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[S_ARR_ADDR]], align 4
// CHECK3-NEXT: [[TMP2:%.*]] = load %struct.S*, %struct.S** [[VAR_ADDR]], align 4
// CHECK3-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK3-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
// CHECK3-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK3-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK3-NEXT: [[TMP3:%.*]] = bitcast [2 x i32]* [[VEC1]] to i8*
// CHECK3-NEXT: [[TMP4:%.*]] = bitcast [2 x i32]* [[TMP0]] to i8*
// CHECK3-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP3]], i8* align 4 [[TMP4]], i32 8, i1 false)
// CHECK3-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR2]], i32 0, i32 0
// CHECK3-NEXT: [[TMP5:%.*]] = bitcast [2 x %struct.S]* [[TMP1]] to %struct.S*
// CHECK3-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i32 2
// CHECK3-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP6]]
// CHECK3-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE3:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK3: omp.arraycpy.body:
// CHECK3-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP5]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK3-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK3-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]])
// CHECK3-NEXT: call void @_ZN1SIfEC1ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], %struct.St* [[AGG_TMP]])
// CHECK3-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR2]]
// CHECK3-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK3-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK3-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
// CHECK3-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE3]], label [[OMP_ARRAYCPY_BODY]]
// CHECK3: omp.arraycpy.done3:
// CHECK3-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP5]])
// CHECK3-NEXT: call void @_ZN1SIfEC1ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[VAR4]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP2]], %struct.St* [[AGG_TMP5]])
// CHECK3-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP5]]) #[[ATTR2]]
// CHECK3-NEXT: [[TMP7:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: [[TMP8:%.*]] = load i32, i32* [[TMP7]], align 4
// CHECK3-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP8]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK3-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK3-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP9]], 1
// CHECK3-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK3: cond.true:
// CHECK3-NEXT: br label [[COND_END:%.*]]
// CHECK3: cond.false:
// CHECK3-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK3-NEXT: br label [[COND_END]]
// CHECK3: cond.end:
// CHECK3-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP10]], [[COND_FALSE]] ]
// CHECK3-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK3-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK3-NEXT: store i32 [[TMP11]], i32* [[DOTOMP_IV]], align 4
// CHECK3-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK3: omp.inner.for.cond:
// CHECK3-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK3-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK3-NEXT: [[CMP6:%.*]] = icmp sle i32 [[TMP12]], [[TMP13]]
// CHECK3-NEXT: br i1 [[CMP6]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK3: omp.inner.for.cond.cleanup:
// CHECK3-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
// CHECK3: omp.inner.for.body:
// CHECK3-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK3-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP14]], 1
// CHECK3-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK3-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK3-NEXT: [[TMP15:%.*]] = load i32, i32* [[T_VAR_ADDR]], align 4
// CHECK3-NEXT: [[TMP16:%.*]] = load i32, i32* [[I]], align 4
// CHECK3-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC1]], i32 0, i32 [[TMP16]]
// CHECK3-NEXT: store i32 [[TMP15]], i32* [[ARRAYIDX]], align 4
// CHECK3-NEXT: [[TMP17:%.*]] = load i32, i32* [[I]], align 4
// CHECK3-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR2]], i32 0, i32 [[TMP17]]
// CHECK3-NEXT: [[TMP18:%.*]] = bitcast %struct.S* [[ARRAYIDX7]] to i8*
// CHECK3-NEXT: [[TMP19:%.*]] = bitcast %struct.S* [[VAR4]] to i8*
// CHECK3-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP18]], i8* align 4 [[TMP19]], i32 4, i1 false)
// CHECK3-NEXT: [[TMP20:%.*]] = load i32, i32* [[I]], align 4
// CHECK3-NEXT: [[TMP21:%.*]] = load i32, i32* [[SIVAR_ADDR]], align 4
// CHECK3-NEXT: [[ADD8:%.*]] = add nsw i32 [[TMP21]], [[TMP20]]
// CHECK3-NEXT: store i32 [[ADD8]], i32* [[SIVAR_ADDR]], align 4
// CHECK3-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK3: omp.body.continue:
// CHECK3-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK3: omp.inner.for.inc:
// CHECK3-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK3-NEXT: [[ADD9:%.*]] = add nsw i32 [[TMP22]], 1
// CHECK3-NEXT: store i32 [[ADD9]], i32* [[DOTOMP_IV]], align 4
// CHECK3-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK3: omp.inner.for.end:
// CHECK3-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
// CHECK3: omp.loop.exit:
// CHECK3-NEXT: [[TMP23:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: [[TMP24:%.*]] = load i32, i32* [[TMP23]], align 4
// CHECK3-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP24]])
// CHECK3-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR4]]) #[[ATTR2]]
// CHECK3-NEXT: [[ARRAY_BEGIN10:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR2]], i32 0, i32 0
// CHECK3-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN10]], i32 2
// CHECK3-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK3: arraydestroy.body:
// CHECK3-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP25]], [[OMP_LOOP_EXIT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK3-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i32 -1
// CHECK3-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK3-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN10]]
// CHECK3-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE11:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK3: arraydestroy.done11:
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2StC1Ev
// CHECK3-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 4
// CHECK3-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 4
// CHECK3-NEXT: call void @_ZN2StC2Ev(%struct.St* nonnull align 4 dereferenceable(8) [[THIS1]])
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIfEC1ERKS0_2St
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: [[S_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: store %struct.S* [[S]], %struct.S** [[S_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load %struct.S*, %struct.S** [[S_ADDR]], align 4
// CHECK3-NEXT: call void @_ZN1SIfEC2ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP0]], %struct.St* [[T]])
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2StD1Ev
// CHECK3-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 4
// CHECK3-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 4
// CHECK3-NEXT: call void @_ZN2StD2Ev(%struct.St* nonnull align 4 dereferenceable(8) [[THIS1]]) #[[ATTR2]]
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z5tmainIiET_v
// CHECK3-SAME: () #[[ATTR6:[0-9]+]] comdat {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK3-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK3-NEXT: [[S_ARR:%.*]] = alloca [2 x %struct.S.0], align 4
// CHECK3-NEXT: [[VAR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[T_VAR_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [4 x i8*], align 4
// CHECK3-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [4 x i8*], align 4
// CHECK3-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [4 x i8*], align 4
// CHECK3-NEXT: [[_TMP1:%.*]] = alloca i32, align 4
// CHECK3-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]])
// CHECK3-NEXT: store i32 0, i32* [[T_VAR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK3-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const._Z5tmainIiET_v.vec to i8*), i32 8, i1 false)
// CHECK3-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK3-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], i32 1)
// CHECK3-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYINIT_BEGIN]], i32 1
// CHECK3-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], i32 2)
// CHECK3-NEXT: store %struct.S.0* [[TEST]], %struct.S.0** [[VAR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR]], align 4
// CHECK3-NEXT: store %struct.S.0* [[TMP1]], %struct.S.0** [[TMP]], align 4
// CHECK3-NEXT: [[TMP2:%.*]] = load i32, i32* [[T_VAR]], align 4
// CHECK3-NEXT: store i32 [[TMP2]], i32* [[T_VAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP3:%.*]] = load i32, i32* [[T_VAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP4:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 4
// CHECK3-NEXT: [[TMP5:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 4
// CHECK3-NEXT: [[TMP6:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 4
// CHECK3-NEXT: [[TMP7:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT: [[TMP8:%.*]] = bitcast i8** [[TMP7]] to i32*
// CHECK3-NEXT: store i32 [[TMP3]], i32* [[TMP8]], align 4
// CHECK3-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT: [[TMP10:%.*]] = bitcast i8** [[TMP9]] to i32*
// CHECK3-NEXT: store i32 [[TMP3]], i32* [[TMP10]], align 4
// CHECK3-NEXT: [[TMP11:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 0
// CHECK3-NEXT: store i8* null, i8** [[TMP11]], align 4
// CHECK3-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK3-NEXT: [[TMP13:%.*]] = bitcast i8** [[TMP12]] to [2 x i32]**
// CHECK3-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP13]], align 4
// CHECK3-NEXT: [[TMP14:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK3-NEXT: [[TMP15:%.*]] = bitcast i8** [[TMP14]] to [2 x i32]**
// CHECK3-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP15]], align 4
// CHECK3-NEXT: [[TMP16:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 1
// CHECK3-NEXT: store i8* null, i8** [[TMP16]], align 4
// CHECK3-NEXT: [[TMP17:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK3-NEXT: [[TMP18:%.*]] = bitcast i8** [[TMP17]] to [2 x %struct.S.0]**
// CHECK3-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[TMP18]], align 4
// CHECK3-NEXT: [[TMP19:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK3-NEXT: [[TMP20:%.*]] = bitcast i8** [[TMP19]] to [2 x %struct.S.0]**
// CHECK3-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[TMP20]], align 4
// CHECK3-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 2
// CHECK3-NEXT: store i8* null, i8** [[TMP21]], align 4
// CHECK3-NEXT: [[TMP22:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK3-NEXT: [[TMP23:%.*]] = bitcast i8** [[TMP22]] to %struct.S.0**
// CHECK3-NEXT: store %struct.S.0* [[TMP5]], %struct.S.0** [[TMP23]], align 4
// CHECK3-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK3-NEXT: [[TMP25:%.*]] = bitcast i8** [[TMP24]] to %struct.S.0**
// CHECK3-NEXT: store %struct.S.0* [[TMP6]], %struct.S.0** [[TMP25]], align 4
// CHECK3-NEXT: [[TMP26:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 3
// CHECK3-NEXT: store i8* null, i8** [[TMP26]], align 4
// CHECK3-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK3-NEXT: [[TMP28:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK3-NEXT: call void @__kmpc_push_target_tripcount_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i64 2)
// CHECK3-NEXT: [[TMP29:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56.region_id, i32 4, i8** [[TMP27]], i8** [[TMP28]], i64* getelementptr inbounds ([4 x i64], [4 x i64]* @.offload_sizes.4, i32 0, i32 0), i64* getelementptr inbounds ([4 x i64], [4 x i64]* @.offload_maptypes.5, i32 0, i32 0), i8** null, i8** null, i32 0, i32 0)
// CHECK3-NEXT: [[TMP30:%.*]] = icmp ne i32 [[TMP29]], 0
// CHECK3-NEXT: br i1 [[TMP30]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK3: omp_offload.failed:
// CHECK3-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56(i32 [[TMP3]], [2 x i32]* [[VEC]], [2 x %struct.S.0]* [[S_ARR]], %struct.S.0* [[TMP4]]) #[[ATTR2]]
// CHECK3-NEXT: br label [[OMP_OFFLOAD_CONT]]
// CHECK3: omp_offload.cont:
// CHECK3-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK3-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK3-NEXT: [[TMP31:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i32 2
// CHECK3-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK3: arraydestroy.body:
// CHECK3-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP31]], [[OMP_OFFLOAD_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK3-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i32 -1
// CHECK3-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK3-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK3-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE2:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK3: arraydestroy.done2:
// CHECK3-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR2]]
// CHECK3-NEXT: [[TMP32:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK3-NEXT: ret i32 [[TMP32]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2StC2Ev
// CHECK3-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 4
// CHECK3-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT: store i32 0, i32* [[A]], align 4
// CHECK3-NEXT: [[B:%.*]] = getelementptr inbounds [[STRUCT_ST]], %struct.St* [[THIS1]], i32 0, i32 1
// CHECK3-NEXT: store i32 0, i32* [[B]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIfEC2ERKS0_2St
// CHECK3-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: [[S_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK3-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: store %struct.S* [[S]], %struct.S** [[S_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT: [[TMP0:%.*]] = load %struct.S*, %struct.S** [[S_ADDR]], align 4
// CHECK3-NEXT: [[F2:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP0]], i32 0, i32 0
// CHECK3-NEXT: [[TMP1:%.*]] = load float, float* [[F2]], align 4
// CHECK3-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[T]], i32 0, i32 0
// CHECK3-NEXT: [[TMP2:%.*]] = load i32, i32* [[A]], align 4
// CHECK3-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP2]] to float
// CHECK3-NEXT: [[ADD:%.*]] = fadd float [[TMP1]], [[CONV]]
// CHECK3-NEXT: store float [[ADD]], float* [[F]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN2StD2Ev
// CHECK3-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 4
// CHECK3-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ev
// CHECK3-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: call void @_ZN1SIiEC2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ei
// CHECK3-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK3-NEXT: call void @_ZN1SIiEC2Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]], i32 [[TMP0]])
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56
// CHECK3-SAME: (i32 [[T_VAR:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S.0]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[VAR:%.*]]) #[[ATTR4]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[T_VAR_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 4
// CHECK3-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S.0]*, align 4
// CHECK3-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[T_VAR_CASTED:%.*]] = alloca i32, align 4
// CHECK3-NEXT: store i32 [[T_VAR]], i32* [[T_VAR_ADDR]], align 4
// CHECK3-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 4
// CHECK3-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[S_ARR_ADDR]], align 4
// CHECK3-NEXT: store %struct.S.0* [[VAR]], %struct.S.0** [[VAR_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load [2 x %struct.S.0]*, [2 x %struct.S.0]** [[S_ARR_ADDR]], align 4
// CHECK3-NEXT: [[TMP2:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR_ADDR]], align 4
// CHECK3-NEXT: store %struct.S.0* [[TMP2]], %struct.S.0** [[TMP]], align 4
// CHECK3-NEXT: [[TMP3:%.*]] = load i32, i32* [[T_VAR_ADDR]], align 4
// CHECK3-NEXT: store i32 [[TMP3]], i32* [[T_VAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP4:%.*]] = load i32, i32* [[T_VAR_CASTED]], align 4
// CHECK3-NEXT: [[TMP5:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 4
// CHECK3-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB2]], i32 4, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [2 x i32]*, i32, [2 x %struct.S.0]*, %struct.S.0*)* @.omp_outlined..3 to void (i32*, i32*, ...)*), [2 x i32]* [[TMP0]], i32 [[TMP4]], [2 x %struct.S.0]* [[TMP1]], %struct.S.0* [[TMP5]])
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_outlined..3
// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], i32 [[T_VAR:%.*]], [2 x %struct.S.0]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[VAR:%.*]]) #[[ATTR4]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 4
// CHECK3-NEXT: [[T_VAR_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S.0]*, align 4
// CHECK3-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[_TMP1:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[VEC2:%.*]] = alloca [2 x i32], align 4
// CHECK3-NEXT: [[S_ARR3:%.*]] = alloca [2 x %struct.S.0], align 4
// CHECK3-NEXT: [[AGG_TMP:%.*]] = alloca [[STRUCT_ST:%.*]], align 4
// CHECK3-NEXT: [[VAR5:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK3-NEXT: [[AGG_TMP6:%.*]] = alloca [[STRUCT_ST]], align 4
// CHECK3-NEXT: [[_TMP7:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK3-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK3-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 4
// CHECK3-NEXT: store i32 [[T_VAR]], i32* [[T_VAR_ADDR]], align 4
// CHECK3-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[S_ARR_ADDR]], align 4
// CHECK3-NEXT: store %struct.S.0* [[VAR]], %struct.S.0** [[VAR_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load [2 x %struct.S.0]*, [2 x %struct.S.0]** [[S_ARR_ADDR]], align 4
// CHECK3-NEXT: [[TMP2:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR_ADDR]], align 4
// CHECK3-NEXT: store %struct.S.0* [[TMP2]], %struct.S.0** [[TMP]], align 4
// CHECK3-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK3-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
// CHECK3-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK3-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK3-NEXT: [[TMP3:%.*]] = bitcast [2 x i32]* [[VEC2]] to i8*
// CHECK3-NEXT: [[TMP4:%.*]] = bitcast [2 x i32]* [[TMP0]] to i8*
// CHECK3-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP3]], i8* align 4 [[TMP4]], i32 8, i1 false)
// CHECK3-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i32 0, i32 0
// CHECK3-NEXT: [[TMP5:%.*]] = bitcast [2 x %struct.S.0]* [[TMP1]] to %struct.S.0*
// CHECK3-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i32 2
// CHECK3-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S.0* [[ARRAY_BEGIN]], [[TMP6]]
// CHECK3-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE4:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK3: omp.arraycpy.body:
// CHECK3-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP5]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK3-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S.0* [ [[ARRAY_BEGIN]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK3-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]])
// CHECK3-NEXT: call void @_ZN1SIiEC1ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S.0* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], %struct.St* [[AGG_TMP]])
// CHECK3-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR2]]
// CHECK3-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK3-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK3-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S.0* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
// CHECK3-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE4]], label [[OMP_ARRAYCPY_BODY]]
// CHECK3: omp.arraycpy.done4:
// CHECK3-NEXT: [[TMP7:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 4
// CHECK3-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]])
// CHECK3-NEXT: call void @_ZN1SIiEC1ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR5]], %struct.S.0* nonnull align 4 dereferenceable(4) [[TMP7]], %struct.St* [[AGG_TMP6]])
// CHECK3-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]]) #[[ATTR2]]
// CHECK3-NEXT: store %struct.S.0* [[VAR5]], %struct.S.0** [[_TMP7]], align 4
// CHECK3-NEXT: [[TMP8:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
// CHECK3-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP9]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK3-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK3-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP10]], 1
// CHECK3-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK3: cond.true:
// CHECK3-NEXT: br label [[COND_END:%.*]]
// CHECK3: cond.false:
// CHECK3-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK3-NEXT: br label [[COND_END]]
// CHECK3: cond.end:
// CHECK3-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP11]], [[COND_FALSE]] ]
// CHECK3-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK3-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK3-NEXT: store i32 [[TMP12]], i32* [[DOTOMP_IV]], align 4
// CHECK3-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK3: omp.inner.for.cond:
// CHECK3-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK3-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK3-NEXT: [[CMP8:%.*]] = icmp sle i32 [[TMP13]], [[TMP14]]
// CHECK3-NEXT: br i1 [[CMP8]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK3: omp.inner.for.cond.cleanup:
// CHECK3-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
// CHECK3: omp.inner.for.body:
// CHECK3-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK3-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP15]], 1
// CHECK3-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK3-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK3-NEXT: [[TMP16:%.*]] = load i32, i32* [[T_VAR_ADDR]], align 4
// CHECK3-NEXT: [[TMP17:%.*]] = load i32, i32* [[I]], align 4
// CHECK3-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC2]], i32 0, i32 [[TMP17]]
// CHECK3-NEXT: store i32 [[TMP16]], i32* [[ARRAYIDX]], align 4
// CHECK3-NEXT: [[TMP18:%.*]] = load %struct.S.0*, %struct.S.0** [[_TMP7]], align 4
// CHECK3-NEXT: [[TMP19:%.*]] = load i32, i32* [[I]], align 4
// CHECK3-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i32 0, i32 [[TMP19]]
// CHECK3-NEXT: [[TMP20:%.*]] = bitcast %struct.S.0* [[ARRAYIDX9]] to i8*
// CHECK3-NEXT: [[TMP21:%.*]] = bitcast %struct.S.0* [[TMP18]] to i8*
// CHECK3-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP20]], i8* align 4 [[TMP21]], i32 4, i1 false)
// CHECK3-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK3: omp.body.continue:
// CHECK3-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK3: omp.inner.for.inc:
// CHECK3-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK3-NEXT: [[ADD10:%.*]] = add nsw i32 [[TMP22]], 1
// CHECK3-NEXT: store i32 [[ADD10]], i32* [[DOTOMP_IV]], align 4
// CHECK3-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK3: omp.inner.for.end:
// CHECK3-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
// CHECK3: omp.loop.exit:
// CHECK3-NEXT: [[TMP23:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: [[TMP24:%.*]] = load i32, i32* [[TMP23]], align 4
// CHECK3-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP24]])
// CHECK3-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR5]]) #[[ATTR2]]
// CHECK3-NEXT: [[ARRAY_BEGIN11:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i32 0, i32 0
// CHECK3-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN11]], i32 2
// CHECK3-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK3: arraydestroy.body:
// CHECK3-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP25]], [[OMP_LOOP_EXIT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK3-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i32 -1
// CHECK3-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK3-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN11]]
// CHECK3-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE12:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK3: arraydestroy.done12:
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIiEC1ERKS0_2St
// CHECK3-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[S_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: store %struct.S.0* [[S]], %struct.S.0** [[S_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = load %struct.S.0*, %struct.S.0** [[S_ADDR]], align 4
// CHECK3-NEXT: call void @_ZN1SIiEC2ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]], %struct.S.0* nonnull align 4 dereferenceable(4) [[TMP0]], %struct.St* [[T]])
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIiED1Ev
// CHECK3-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: call void @_ZN1SIiED2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR2]]
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ev
// CHECK3-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT: [[TMP0:%.*]] = load volatile i32, i32* @g, align 4
// CHECK3-NEXT: store i32 [[TMP0]], i32* [[F]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ei
// CHECK3-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load volatile i32, i32* @g, align 4
// CHECK3-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP0]], [[TMP1]]
// CHECK3-NEXT: store i32 [[ADD]], i32* [[F]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIiEC2ERKS0_2St
// CHECK3-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: [[S_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: store %struct.S.0* [[S]], %struct.S.0** [[S_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK3-NEXT: [[TMP0:%.*]] = load %struct.S.0*, %struct.S.0** [[S_ADDR]], align 4
// CHECK3-NEXT: [[F2:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[TMP0]], i32 0, i32 0
// CHECK3-NEXT: [[TMP1:%.*]] = load i32, i32* [[F2]], align 4
// CHECK3-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[T]], i32 0, i32 0
// CHECK3-NEXT: [[TMP2:%.*]] = load i32, i32* [[A]], align 4
// CHECK3-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP1]], [[TMP2]]
// CHECK3-NEXT: store i32 [[ADD]], i32* [[F]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_ZN1SIiED2Ev
// CHECK3-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK3-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_GLOBAL__sub_I_teams_distribute_firstprivate_codegen.cpp
// CHECK3-SAME: () #[[ATTR0]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: call void @__cxx_global_var_init()
// CHECK3-NEXT: call void @__cxx_global_var_init.1()
// CHECK3-NEXT: call void @__cxx_global_var_init.2()
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
// CHECK3-SAME: () #[[ATTR0]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: call void @__tgt_register_requires(i64 1)
// CHECK3-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@__cxx_global_var_init
// CHECK4-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) @test)
// CHECK4-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @test to i8*), i8* @__dso_handle) #[[ATTR2:[0-9]+]]
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: call void @_ZN1SIfEC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: call void @_ZN1SIfED2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR2]]
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK4-NEXT: [[TMP0:%.*]] = load volatile i32, i32* @g, align 4
// CHECK4-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to float
// CHECK4-NEXT: store float [[CONV]], float* [[F]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@__cxx_global_var_init.1
// CHECK4-SAME: () #[[ATTR0]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0), float 1.000000e+00)
// CHECK4-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 1), float 2.000000e+00)
// CHECK4-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* @__cxx_global_array_dtor, i8* null, i8* @__dso_handle) #[[ATTR2]]
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK4-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK4-NEXT: call void @_ZN1SIfEC2Ef(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], float [[TMP0]])
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@__cxx_global_array_dtor
// CHECK4-SAME: (i8* [[TMP0:%.*]]) #[[ATTR0]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 4
// CHECK4-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 4
// CHECK4-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK4: arraydestroy.body:
// CHECK4-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ getelementptr inbounds ([[STRUCT_S:%.*]], %struct.S* getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0), i32 2), [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK4-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i32 -1
// CHECK4-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK4-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0)
// CHECK4-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK4: arraydestroy.done1:
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK4-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK4-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK4-NEXT: [[TMP1:%.*]] = load volatile i32, i32* @g, align 4
// CHECK4-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP1]] to float
// CHECK4-NEXT: [[ADD:%.*]] = fadd float [[TMP0]], [[CONV]]
// CHECK4-NEXT: store float [[ADD]], float* [[F]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@__cxx_global_var_init.2
// CHECK4-SAME: () #[[ATTR0]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) @var, float 3.000000e+00)
// CHECK4-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @var to i8*), i8* @__dso_handle) #[[ATTR2]]
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@main
// CHECK4-SAME: () #[[ATTR3:[0-9]+]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[T_VAR_CASTED:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[SIVAR_CASTED:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [5 x i8*], align 4
// CHECK4-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [5 x i8*], align 4
// CHECK4-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [5 x i8*], align 4
// CHECK4-NEXT: [[TMP:%.*]] = alloca i32, align 4
// CHECK4-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = load i32, i32* @t_var, align 4
// CHECK4-NEXT: store i32 [[TMP0]], i32* [[T_VAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP1:%.*]] = load i32, i32* [[T_VAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP2:%.*]] = load i32, i32* @_ZZ4mainE5sivar, align 4
// CHECK4-NEXT: store i32 [[TMP2]], i32* [[SIVAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP3:%.*]] = load i32, i32* [[SIVAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP4:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK4-NEXT: [[TMP5:%.*]] = bitcast i8** [[TMP4]] to i32*
// CHECK4-NEXT: store i32 [[TMP1]], i32* [[TMP5]], align 4
// CHECK4-NEXT: [[TMP6:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK4-NEXT: [[TMP7:%.*]] = bitcast i8** [[TMP6]] to i32*
// CHECK4-NEXT: store i32 [[TMP1]], i32* [[TMP7]], align 4
// CHECK4-NEXT: [[TMP8:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 0
// CHECK4-NEXT: store i8* null, i8** [[TMP8]], align 4
// CHECK4-NEXT: [[TMP9:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK4-NEXT: [[TMP10:%.*]] = bitcast i8** [[TMP9]] to [2 x i32]**
// CHECK4-NEXT: store [2 x i32]* @vec, [2 x i32]** [[TMP10]], align 4
// CHECK4-NEXT: [[TMP11:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK4-NEXT: [[TMP12:%.*]] = bitcast i8** [[TMP11]] to [2 x i32]**
// CHECK4-NEXT: store [2 x i32]* @vec, [2 x i32]** [[TMP12]], align 4
// CHECK4-NEXT: [[TMP13:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 1
// CHECK4-NEXT: store i8* null, i8** [[TMP13]], align 4
// CHECK4-NEXT: [[TMP14:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK4-NEXT: [[TMP15:%.*]] = bitcast i8** [[TMP14]] to [2 x %struct.S]**
// CHECK4-NEXT: store [2 x %struct.S]* @s_arr, [2 x %struct.S]** [[TMP15]], align 4
// CHECK4-NEXT: [[TMP16:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK4-NEXT: [[TMP17:%.*]] = bitcast i8** [[TMP16]] to [2 x %struct.S]**
// CHECK4-NEXT: store [2 x %struct.S]* @s_arr, [2 x %struct.S]** [[TMP17]], align 4
// CHECK4-NEXT: [[TMP18:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 2
// CHECK4-NEXT: store i8* null, i8** [[TMP18]], align 4
// CHECK4-NEXT: [[TMP19:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK4-NEXT: [[TMP20:%.*]] = bitcast i8** [[TMP19]] to %struct.S**
// CHECK4-NEXT: store %struct.S* @var, %struct.S** [[TMP20]], align 4
// CHECK4-NEXT: [[TMP21:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK4-NEXT: [[TMP22:%.*]] = bitcast i8** [[TMP21]] to %struct.S**
// CHECK4-NEXT: store %struct.S* @var, %struct.S** [[TMP22]], align 4
// CHECK4-NEXT: [[TMP23:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 3
// CHECK4-NEXT: store i8* null, i8** [[TMP23]], align 4
// CHECK4-NEXT: [[TMP24:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 4
// CHECK4-NEXT: [[TMP25:%.*]] = bitcast i8** [[TMP24]] to i32*
// CHECK4-NEXT: store i32 [[TMP3]], i32* [[TMP25]], align 4
// CHECK4-NEXT: [[TMP26:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 4
// CHECK4-NEXT: [[TMP27:%.*]] = bitcast i8** [[TMP26]] to i32*
// CHECK4-NEXT: store i32 [[TMP3]], i32* [[TMP27]], align 4
// CHECK4-NEXT: [[TMP28:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 4
// CHECK4-NEXT: store i8* null, i8** [[TMP28]], align 4
// CHECK4-NEXT: [[TMP29:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK4-NEXT: [[TMP30:%.*]] = getelementptr inbounds [5 x i8*], [5 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK4-NEXT: call void @__kmpc_push_target_tripcount_mapper(%struct.ident_t* @[[GLOB2:[0-9]+]], i64 -1, i64 2)
// CHECK4-NEXT: [[TMP31:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94.region_id, i32 5, i8** [[TMP29]], i8** [[TMP30]], i64* getelementptr inbounds ([5 x i64], [5 x i64]* @.offload_sizes, i32 0, i32 0), i64* getelementptr inbounds ([5 x i64], [5 x i64]* @.offload_maptypes, i32 0, i32 0), i8** null, i8** null, i32 0, i32 0)
// CHECK4-NEXT: [[TMP32:%.*]] = icmp ne i32 [[TMP31]], 0
// CHECK4-NEXT: br i1 [[TMP32]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK4: omp_offload.failed:
// CHECK4-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94(i32 [[TMP1]], [2 x i32]* @vec, [2 x %struct.S]* @s_arr, %struct.S* @var, i32 [[TMP3]]) #[[ATTR2]]
// CHECK4-NEXT: br label [[OMP_OFFLOAD_CONT]]
// CHECK4: omp_offload.cont:
// CHECK4-NEXT: [[CALL:%.*]] = call i32 @_Z5tmainIiET_v()
// CHECK4-NEXT: ret i32 [[CALL]]
//
//
// CHECK4-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l94
// CHECK4-SAME: (i32 [[T_VAR:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR:%.*]], i32 [[SIVAR:%.*]]) #[[ATTR4:[0-9]+]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[T_VAR_ADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 4
// CHECK4-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S]*, align 4
// CHECK4-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: [[SIVAR_ADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[T_VAR_CASTED:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[SIVAR_CASTED:%.*]] = alloca i32, align 4
// CHECK4-NEXT: store i32 [[T_VAR]], i32* [[T_VAR_ADDR]], align 4
// CHECK4-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 4
// CHECK4-NEXT: store [2 x %struct.S]* [[S_ARR]], [2 x %struct.S]** [[S_ARR_ADDR]], align 4
// CHECK4-NEXT: store %struct.S* [[VAR]], %struct.S** [[VAR_ADDR]], align 4
// CHECK4-NEXT: store i32 [[SIVAR]], i32* [[SIVAR_ADDR]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 4
// CHECK4-NEXT: [[TMP1:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[S_ARR_ADDR]], align 4
// CHECK4-NEXT: [[TMP2:%.*]] = load %struct.S*, %struct.S** [[VAR_ADDR]], align 4
// CHECK4-NEXT: [[TMP3:%.*]] = load i32, i32* [[T_VAR_ADDR]], align 4
// CHECK4-NEXT: store i32 [[TMP3]], i32* [[T_VAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP4:%.*]] = load i32, i32* [[T_VAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP5:%.*]] = load i32, i32* [[SIVAR_ADDR]], align 4
// CHECK4-NEXT: store i32 [[TMP5]], i32* [[SIVAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP6:%.*]] = load i32, i32* [[SIVAR_CASTED]], align 4
// CHECK4-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB2]], i32 5, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [2 x i32]*, i32, [2 x %struct.S]*, %struct.S*, i32)* @.omp_outlined. to void (i32*, i32*, ...)*), [2 x i32]* [[TMP0]], i32 [[TMP4]], [2 x %struct.S]* [[TMP1]], %struct.S* [[TMP2]], i32 [[TMP6]])
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK4-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], i32 [[T_VAR:%.*]], [2 x %struct.S]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[VAR:%.*]], i32 [[SIVAR:%.*]]) #[[ATTR4]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK4-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK4-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 4
// CHECK4-NEXT: [[T_VAR_ADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S]*, align 4
// CHECK4-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: [[SIVAR_ADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[TMP:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[VEC1:%.*]] = alloca [2 x i32], align 4
// CHECK4-NEXT: [[S_ARR2:%.*]] = alloca [2 x %struct.S], align 4
// CHECK4-NEXT: [[AGG_TMP:%.*]] = alloca [[STRUCT_ST:%.*]], align 4
// CHECK4-NEXT: [[VAR4:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK4-NEXT: [[AGG_TMP5:%.*]] = alloca [[STRUCT_ST]], align 4
// CHECK4-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK4-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK4-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK4-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 4
// CHECK4-NEXT: store i32 [[T_VAR]], i32* [[T_VAR_ADDR]], align 4
// CHECK4-NEXT: store [2 x %struct.S]* [[S_ARR]], [2 x %struct.S]** [[S_ARR_ADDR]], align 4
// CHECK4-NEXT: store %struct.S* [[VAR]], %struct.S** [[VAR_ADDR]], align 4
// CHECK4-NEXT: store i32 [[SIVAR]], i32* [[SIVAR_ADDR]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 4
// CHECK4-NEXT: [[TMP1:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[S_ARR_ADDR]], align 4
// CHECK4-NEXT: [[TMP2:%.*]] = load %struct.S*, %struct.S** [[VAR_ADDR]], align 4
// CHECK4-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK4-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
// CHECK4-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK4-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK4-NEXT: [[TMP3:%.*]] = bitcast [2 x i32]* [[VEC1]] to i8*
// CHECK4-NEXT: [[TMP4:%.*]] = bitcast [2 x i32]* [[TMP0]] to i8*
// CHECK4-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP3]], i8* align 4 [[TMP4]], i32 8, i1 false)
// CHECK4-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR2]], i32 0, i32 0
// CHECK4-NEXT: [[TMP5:%.*]] = bitcast [2 x %struct.S]* [[TMP1]] to %struct.S*
// CHECK4-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i32 2
// CHECK4-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S* [[ARRAY_BEGIN]], [[TMP6]]
// CHECK4-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE3:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK4: omp.arraycpy.body:
// CHECK4-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP5]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK4-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S* [ [[ARRAY_BEGIN]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK4-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]])
// CHECK4-NEXT: call void @_ZN1SIfEC1ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], %struct.St* [[AGG_TMP]])
// CHECK4-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR2]]
// CHECK4-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK4-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S]], %struct.S* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK4-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
// CHECK4-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE3]], label [[OMP_ARRAYCPY_BODY]]
// CHECK4: omp.arraycpy.done3:
// CHECK4-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP5]])
// CHECK4-NEXT: call void @_ZN1SIfEC1ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[VAR4]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP2]], %struct.St* [[AGG_TMP5]])
// CHECK4-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP5]]) #[[ATTR2]]
// CHECK4-NEXT: [[TMP7:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK4-NEXT: [[TMP8:%.*]] = load i32, i32* [[TMP7]], align 4
// CHECK4-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP8]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK4-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK4-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP9]], 1
// CHECK4-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK4: cond.true:
// CHECK4-NEXT: br label [[COND_END:%.*]]
// CHECK4: cond.false:
// CHECK4-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK4-NEXT: br label [[COND_END]]
// CHECK4: cond.end:
// CHECK4-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP10]], [[COND_FALSE]] ]
// CHECK4-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK4-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK4-NEXT: store i32 [[TMP11]], i32* [[DOTOMP_IV]], align 4
// CHECK4-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK4: omp.inner.for.cond:
// CHECK4-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK4-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK4-NEXT: [[CMP6:%.*]] = icmp sle i32 [[TMP12]], [[TMP13]]
// CHECK4-NEXT: br i1 [[CMP6]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK4: omp.inner.for.cond.cleanup:
// CHECK4-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
// CHECK4: omp.inner.for.body:
// CHECK4-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK4-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP14]], 1
// CHECK4-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK4-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK4-NEXT: [[TMP15:%.*]] = load i32, i32* [[T_VAR_ADDR]], align 4
// CHECK4-NEXT: [[TMP16:%.*]] = load i32, i32* [[I]], align 4
// CHECK4-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC1]], i32 0, i32 [[TMP16]]
// CHECK4-NEXT: store i32 [[TMP15]], i32* [[ARRAYIDX]], align 4
// CHECK4-NEXT: [[TMP17:%.*]] = load i32, i32* [[I]], align 4
// CHECK4-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR2]], i32 0, i32 [[TMP17]]
// CHECK4-NEXT: [[TMP18:%.*]] = bitcast %struct.S* [[ARRAYIDX7]] to i8*
// CHECK4-NEXT: [[TMP19:%.*]] = bitcast %struct.S* [[VAR4]] to i8*
// CHECK4-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP18]], i8* align 4 [[TMP19]], i32 4, i1 false)
// CHECK4-NEXT: [[TMP20:%.*]] = load i32, i32* [[I]], align 4
// CHECK4-NEXT: [[TMP21:%.*]] = load i32, i32* [[SIVAR_ADDR]], align 4
// CHECK4-NEXT: [[ADD8:%.*]] = add nsw i32 [[TMP21]], [[TMP20]]
// CHECK4-NEXT: store i32 [[ADD8]], i32* [[SIVAR_ADDR]], align 4
// CHECK4-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK4: omp.body.continue:
// CHECK4-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK4: omp.inner.for.inc:
// CHECK4-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK4-NEXT: [[ADD9:%.*]] = add nsw i32 [[TMP22]], 1
// CHECK4-NEXT: store i32 [[ADD9]], i32* [[DOTOMP_IV]], align 4
// CHECK4-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK4: omp.inner.for.end:
// CHECK4-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
// CHECK4: omp.loop.exit:
// CHECK4-NEXT: [[TMP23:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK4-NEXT: [[TMP24:%.*]] = load i32, i32* [[TMP23]], align 4
// CHECK4-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP24]])
// CHECK4-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[VAR4]]) #[[ATTR2]]
// CHECK4-NEXT: [[ARRAY_BEGIN10:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR2]], i32 0, i32 0
// CHECK4-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN10]], i32 2
// CHECK4-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK4: arraydestroy.body:
// CHECK4-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP25]], [[OMP_LOOP_EXIT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK4-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i32 -1
// CHECK4-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK4-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN10]]
// CHECK4-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE11:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK4: arraydestroy.done11:
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN2StC1Ev
// CHECK4-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 4
// CHECK4-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 4
// CHECK4-NEXT: call void @_ZN2StC2Ev(%struct.St* nonnull align 4 dereferenceable(8) [[THIS1]])
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIfEC1ERKS0_2St
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: [[S_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: store %struct.S* [[S]], %struct.S** [[S_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = load %struct.S*, %struct.S** [[S_ADDR]], align 4
// CHECK4-NEXT: call void @_ZN1SIfEC2ERKS0_2St(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], %struct.S* nonnull align 4 dereferenceable(4) [[TMP0]], %struct.St* [[T]])
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN2StD1Ev
// CHECK4-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 4
// CHECK4-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 4
// CHECK4-NEXT: call void @_ZN2StD2Ev(%struct.St* nonnull align 4 dereferenceable(8) [[THIS1]]) #[[ATTR2]]
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_Z5tmainIiET_v
// CHECK4-SAME: () #[[ATTR6:[0-9]+]] comdat {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK4-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK4-NEXT: [[S_ARR:%.*]] = alloca [2 x %struct.S.0], align 4
// CHECK4-NEXT: [[VAR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[T_VAR_CASTED:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOFFLOAD_BASEPTRS:%.*]] = alloca [4 x i8*], align 4
// CHECK4-NEXT: [[DOTOFFLOAD_PTRS:%.*]] = alloca [4 x i8*], align 4
// CHECK4-NEXT: [[DOTOFFLOAD_MAPPERS:%.*]] = alloca [4 x i8*], align 4
// CHECK4-NEXT: [[_TMP1:%.*]] = alloca i32, align 4
// CHECK4-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]])
// CHECK4-NEXT: store i32 0, i32* [[T_VAR]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK4-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const._Z5tmainIiET_v.vec to i8*), i32 8, i1 false)
// CHECK4-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK4-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], i32 1)
// CHECK4-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYINIT_BEGIN]], i32 1
// CHECK4-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], i32 2)
// CHECK4-NEXT: store %struct.S.0* [[TEST]], %struct.S.0** [[VAR]], align 4
// CHECK4-NEXT: [[TMP1:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR]], align 4
// CHECK4-NEXT: store %struct.S.0* [[TMP1]], %struct.S.0** [[TMP]], align 4
// CHECK4-NEXT: [[TMP2:%.*]] = load i32, i32* [[T_VAR]], align 4
// CHECK4-NEXT: store i32 [[TMP2]], i32* [[T_VAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP3:%.*]] = load i32, i32* [[T_VAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP4:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 4
// CHECK4-NEXT: [[TMP5:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 4
// CHECK4-NEXT: [[TMP6:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 4
// CHECK4-NEXT: [[TMP7:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK4-NEXT: [[TMP8:%.*]] = bitcast i8** [[TMP7]] to i32*
// CHECK4-NEXT: store i32 [[TMP3]], i32* [[TMP8]], align 4
// CHECK4-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK4-NEXT: [[TMP10:%.*]] = bitcast i8** [[TMP9]] to i32*
// CHECK4-NEXT: store i32 [[TMP3]], i32* [[TMP10]], align 4
// CHECK4-NEXT: [[TMP11:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 0
// CHECK4-NEXT: store i8* null, i8** [[TMP11]], align 4
// CHECK4-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 1
// CHECK4-NEXT: [[TMP13:%.*]] = bitcast i8** [[TMP12]] to [2 x i32]**
// CHECK4-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP13]], align 4
// CHECK4-NEXT: [[TMP14:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 1
// CHECK4-NEXT: [[TMP15:%.*]] = bitcast i8** [[TMP14]] to [2 x i32]**
// CHECK4-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[TMP15]], align 4
// CHECK4-NEXT: [[TMP16:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 1
// CHECK4-NEXT: store i8* null, i8** [[TMP16]], align 4
// CHECK4-NEXT: [[TMP17:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 2
// CHECK4-NEXT: [[TMP18:%.*]] = bitcast i8** [[TMP17]] to [2 x %struct.S.0]**
// CHECK4-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[TMP18]], align 4
// CHECK4-NEXT: [[TMP19:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 2
// CHECK4-NEXT: [[TMP20:%.*]] = bitcast i8** [[TMP19]] to [2 x %struct.S.0]**
// CHECK4-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[TMP20]], align 4
// CHECK4-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 2
// CHECK4-NEXT: store i8* null, i8** [[TMP21]], align 4
// CHECK4-NEXT: [[TMP22:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 3
// CHECK4-NEXT: [[TMP23:%.*]] = bitcast i8** [[TMP22]] to %struct.S.0**
// CHECK4-NEXT: store %struct.S.0* [[TMP5]], %struct.S.0** [[TMP23]], align 4
// CHECK4-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 3
// CHECK4-NEXT: [[TMP25:%.*]] = bitcast i8** [[TMP24]] to %struct.S.0**
// CHECK4-NEXT: store %struct.S.0* [[TMP6]], %struct.S.0** [[TMP25]], align 4
// CHECK4-NEXT: [[TMP26:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_MAPPERS]], i32 0, i32 3
// CHECK4-NEXT: store i8* null, i8** [[TMP26]], align 4
// CHECK4-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_BASEPTRS]], i32 0, i32 0
// CHECK4-NEXT: [[TMP28:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOFFLOAD_PTRS]], i32 0, i32 0
// CHECK4-NEXT: call void @__kmpc_push_target_tripcount_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i64 2)
// CHECK4-NEXT: [[TMP29:%.*]] = call i32 @__tgt_target_teams_mapper(%struct.ident_t* @[[GLOB2]], i64 -1, i8* @.{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56.region_id, i32 4, i8** [[TMP27]], i8** [[TMP28]], i64* getelementptr inbounds ([4 x i64], [4 x i64]* @.offload_sizes.4, i32 0, i32 0), i64* getelementptr inbounds ([4 x i64], [4 x i64]* @.offload_maptypes.5, i32 0, i32 0), i8** null, i8** null, i32 0, i32 0)
// CHECK4-NEXT: [[TMP30:%.*]] = icmp ne i32 [[TMP29]], 0
// CHECK4-NEXT: br i1 [[TMP30]], label [[OMP_OFFLOAD_FAILED:%.*]], label [[OMP_OFFLOAD_CONT:%.*]]
// CHECK4: omp_offload.failed:
// CHECK4-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56(i32 [[TMP3]], [2 x i32]* [[VEC]], [2 x %struct.S.0]* [[S_ARR]], %struct.S.0* [[TMP4]]) #[[ATTR2]]
// CHECK4-NEXT: br label [[OMP_OFFLOAD_CONT]]
// CHECK4: omp_offload.cont:
// CHECK4-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK4-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
// CHECK4-NEXT: [[TMP31:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i32 2
// CHECK4-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK4: arraydestroy.body:
// CHECK4-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP31]], [[OMP_OFFLOAD_CONT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK4-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i32 -1
// CHECK4-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK4-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK4-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE2:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK4: arraydestroy.done2:
// CHECK4-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR2]]
// CHECK4-NEXT: [[TMP32:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK4-NEXT: ret i32 [[TMP32]]
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN2StC2Ev
// CHECK4-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 4
// CHECK4-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[THIS1]], i32 0, i32 0
// CHECK4-NEXT: store i32 0, i32* [[A]], align 4
// CHECK4-NEXT: [[B:%.*]] = getelementptr inbounds [[STRUCT_ST]], %struct.St* [[THIS1]], i32 0, i32 1
// CHECK4-NEXT: store i32 0, i32* [[B]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIfEC2ERKS0_2St
// CHECK4-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: [[S_ADDR:%.*]] = alloca %struct.S*, align 4
// CHECK4-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: store %struct.S* [[S]], %struct.S** [[S_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK4-NEXT: [[TMP0:%.*]] = load %struct.S*, %struct.S** [[S_ADDR]], align 4
// CHECK4-NEXT: [[F2:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[TMP0]], i32 0, i32 0
// CHECK4-NEXT: [[TMP1:%.*]] = load float, float* [[F2]], align 4
// CHECK4-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[T]], i32 0, i32 0
// CHECK4-NEXT: [[TMP2:%.*]] = load i32, i32* [[A]], align 4
// CHECK4-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP2]] to float
// CHECK4-NEXT: [[ADD:%.*]] = fadd float [[TMP1]], [[CONV]]
// CHECK4-NEXT: store float [[ADD]], float* [[F]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN2StD2Ev
// CHECK4-SAME: (%struct.St* nonnull align 4 dereferenceable(8) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.St*, align 4
// CHECK4-NEXT: store %struct.St* [[THIS]], %struct.St** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.St*, %struct.St** [[THIS_ADDR]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ev
// CHECK4-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: call void @_ZN1SIiEC2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ei
// CHECK4-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK4-NEXT: call void @_ZN1SIiEC2Ei(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]], i32 [[TMP0]])
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z5tmainIiET_v_l56
// CHECK4-SAME: (i32 [[T_VAR:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S.0]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[VAR:%.*]]) #[[ATTR4]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[T_VAR_ADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 4
// CHECK4-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S.0]*, align 4
// CHECK4-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[T_VAR_CASTED:%.*]] = alloca i32, align 4
// CHECK4-NEXT: store i32 [[T_VAR]], i32* [[T_VAR_ADDR]], align 4
// CHECK4-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 4
// CHECK4-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[S_ARR_ADDR]], align 4
// CHECK4-NEXT: store %struct.S.0* [[VAR]], %struct.S.0** [[VAR_ADDR]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 4
// CHECK4-NEXT: [[TMP1:%.*]] = load [2 x %struct.S.0]*, [2 x %struct.S.0]** [[S_ARR_ADDR]], align 4
// CHECK4-NEXT: [[TMP2:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR_ADDR]], align 4
// CHECK4-NEXT: store %struct.S.0* [[TMP2]], %struct.S.0** [[TMP]], align 4
// CHECK4-NEXT: [[TMP3:%.*]] = load i32, i32* [[T_VAR_ADDR]], align 4
// CHECK4-NEXT: store i32 [[TMP3]], i32* [[T_VAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP4:%.*]] = load i32, i32* [[T_VAR_CASTED]], align 4
// CHECK4-NEXT: [[TMP5:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 4
// CHECK4-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB2]], i32 4, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, [2 x i32]*, i32, [2 x %struct.S.0]*, %struct.S.0*)* @.omp_outlined..3 to void (i32*, i32*, ...)*), [2 x i32]* [[TMP0]], i32 [[TMP4]], [2 x %struct.S.0]* [[TMP1]], %struct.S.0* [[TMP5]])
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_outlined..3
// CHECK4-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], [2 x i32]* nonnull align 4 dereferenceable(8) [[VEC:%.*]], i32 [[T_VAR:%.*]], [2 x %struct.S.0]* nonnull align 4 dereferenceable(8) [[S_ARR:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[VAR:%.*]]) #[[ATTR4]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK4-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK4-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 4
// CHECK4-NEXT: [[T_VAR_ADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S.0]*, align 4
// CHECK4-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[TMP:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[_TMP1:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[VEC2:%.*]] = alloca [2 x i32], align 4
// CHECK4-NEXT: [[S_ARR3:%.*]] = alloca [2 x %struct.S.0], align 4
// CHECK4-NEXT: [[AGG_TMP:%.*]] = alloca [[STRUCT_ST:%.*]], align 4
// CHECK4-NEXT: [[VAR5:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK4-NEXT: [[AGG_TMP6:%.*]] = alloca [[STRUCT_ST]], align 4
// CHECK4-NEXT: [[_TMP7:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK4-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK4-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
// CHECK4-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 4
// CHECK4-NEXT: store i32 [[T_VAR]], i32* [[T_VAR_ADDR]], align 4
// CHECK4-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[S_ARR_ADDR]], align 4
// CHECK4-NEXT: store %struct.S.0* [[VAR]], %struct.S.0** [[VAR_ADDR]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 4
// CHECK4-NEXT: [[TMP1:%.*]] = load [2 x %struct.S.0]*, [2 x %struct.S.0]** [[S_ARR_ADDR]], align 4
// CHECK4-NEXT: [[TMP2:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR_ADDR]], align 4
// CHECK4-NEXT: store %struct.S.0* [[TMP2]], %struct.S.0** [[TMP]], align 4
// CHECK4-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK4-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
// CHECK4-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK4-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK4-NEXT: [[TMP3:%.*]] = bitcast [2 x i32]* [[VEC2]] to i8*
// CHECK4-NEXT: [[TMP4:%.*]] = bitcast [2 x i32]* [[TMP0]] to i8*
// CHECK4-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP3]], i8* align 4 [[TMP4]], i32 8, i1 false)
// CHECK4-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i32 0, i32 0
// CHECK4-NEXT: [[TMP5:%.*]] = bitcast [2 x %struct.S.0]* [[TMP1]] to %struct.S.0*
// CHECK4-NEXT: [[TMP6:%.*]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i32 2
// CHECK4-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq %struct.S.0* [[ARRAY_BEGIN]], [[TMP6]]
// CHECK4-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE4:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK4: omp.arraycpy.body:
// CHECK4-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP5]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK4-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi %struct.S.0* [ [[ARRAY_BEGIN]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK4-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]])
// CHECK4-NEXT: call void @_ZN1SIiEC1ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_DESTELEMENTPAST]], %struct.S.0* nonnull align 4 dereferenceable(4) [[OMP_ARRAYCPY_SRCELEMENTPAST]], %struct.St* [[AGG_TMP]])
// CHECK4-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP]]) #[[ATTR2]]
// CHECK4-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK4-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr [[STRUCT_S_0]], %struct.S.0* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK4-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq %struct.S.0* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP6]]
// CHECK4-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE4]], label [[OMP_ARRAYCPY_BODY]]
// CHECK4: omp.arraycpy.done4:
// CHECK4-NEXT: [[TMP7:%.*]] = load %struct.S.0*, %struct.S.0** [[TMP]], align 4
// CHECK4-NEXT: call void @_ZN2StC1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]])
// CHECK4-NEXT: call void @_ZN1SIiEC1ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR5]], %struct.S.0* nonnull align 4 dereferenceable(4) [[TMP7]], %struct.St* [[AGG_TMP6]])
// CHECK4-NEXT: call void @_ZN2StD1Ev(%struct.St* nonnull align 4 dereferenceable(8) [[AGG_TMP6]]) #[[ATTR2]]
// CHECK4-NEXT: store %struct.S.0* [[VAR5]], %struct.S.0** [[_TMP7]], align 4
// CHECK4-NEXT: [[TMP8:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK4-NEXT: [[TMP9:%.*]] = load i32, i32* [[TMP8]], align 4
// CHECK4-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP9]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK4-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK4-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP10]], 1
// CHECK4-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK4: cond.true:
// CHECK4-NEXT: br label [[COND_END:%.*]]
// CHECK4: cond.false:
// CHECK4-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK4-NEXT: br label [[COND_END]]
// CHECK4: cond.end:
// CHECK4-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP11]], [[COND_FALSE]] ]
// CHECK4-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK4-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK4-NEXT: store i32 [[TMP12]], i32* [[DOTOMP_IV]], align 4
// CHECK4-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK4: omp.inner.for.cond:
// CHECK4-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK4-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK4-NEXT: [[CMP8:%.*]] = icmp sle i32 [[TMP13]], [[TMP14]]
// CHECK4-NEXT: br i1 [[CMP8]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_COND_CLEANUP:%.*]]
// CHECK4: omp.inner.for.cond.cleanup:
// CHECK4-NEXT: br label [[OMP_INNER_FOR_END:%.*]]
// CHECK4: omp.inner.for.body:
// CHECK4-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK4-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP15]], 1
// CHECK4-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK4-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK4-NEXT: [[TMP16:%.*]] = load i32, i32* [[T_VAR_ADDR]], align 4
// CHECK4-NEXT: [[TMP17:%.*]] = load i32, i32* [[I]], align 4
// CHECK4-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[VEC2]], i32 0, i32 [[TMP17]]
// CHECK4-NEXT: store i32 [[TMP16]], i32* [[ARRAYIDX]], align 4
// CHECK4-NEXT: [[TMP18:%.*]] = load %struct.S.0*, %struct.S.0** [[_TMP7]], align 4
// CHECK4-NEXT: [[TMP19:%.*]] = load i32, i32* [[I]], align 4
// CHECK4-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i32 0, i32 [[TMP19]]
// CHECK4-NEXT: [[TMP20:%.*]] = bitcast %struct.S.0* [[ARRAYIDX9]] to i8*
// CHECK4-NEXT: [[TMP21:%.*]] = bitcast %struct.S.0* [[TMP18]] to i8*
// CHECK4-NEXT: call void @llvm.memcpy.p0i8.p0i8.i32(i8* align 4 [[TMP20]], i8* align 4 [[TMP21]], i32 4, i1 false)
// CHECK4-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK4: omp.body.continue:
// CHECK4-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK4: omp.inner.for.inc:
// CHECK4-NEXT: [[TMP22:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK4-NEXT: [[ADD10:%.*]] = add nsw i32 [[TMP22]], 1
// CHECK4-NEXT: store i32 [[ADD10]], i32* [[DOTOMP_IV]], align 4
// CHECK4-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK4: omp.inner.for.end:
// CHECK4-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
// CHECK4: omp.loop.exit:
// CHECK4-NEXT: [[TMP23:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK4-NEXT: [[TMP24:%.*]] = load i32, i32* [[TMP23]], align 4
// CHECK4-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP24]])
// CHECK4-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[VAR5]]) #[[ATTR2]]
// CHECK4-NEXT: [[ARRAY_BEGIN11:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR3]], i32 0, i32 0
// CHECK4-NEXT: [[TMP25:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN11]], i32 2
// CHECK4-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK4: arraydestroy.body:
// CHECK4-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP25]], [[OMP_LOOP_EXIT]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK4-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i32 -1
// CHECK4-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK4-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN11]]
// CHECK4-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE12:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK4: arraydestroy.done12:
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIiEC1ERKS0_2St
// CHECK4-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[S_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: store %struct.S.0* [[S]], %struct.S.0** [[S_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = load %struct.S.0*, %struct.S.0** [[S_ADDR]], align 4
// CHECK4-NEXT: call void @_ZN1SIiEC2ERKS0_2St(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]], %struct.S.0* nonnull align 4 dereferenceable(4) [[TMP0]], %struct.St* [[T]])
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIiED1Ev
// CHECK4-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: call void @_ZN1SIiED2Ev(%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR2]]
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ev
// CHECK4-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK4-NEXT: [[TMP0:%.*]] = load volatile i32, i32* @g, align 4
// CHECK4-NEXT: store i32 [[TMP0]], i32* [[F]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ei
// CHECK4-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK4-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK4-NEXT: [[TMP1:%.*]] = load volatile i32, i32* @g, align 4
// CHECK4-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP0]], [[TMP1]]
// CHECK4-NEXT: store i32 [[ADD]], i32* [[F]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIiEC2ERKS0_2St
// CHECK4-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.0* nonnull align 4 dereferenceable(4) [[S:%.*]], %struct.St* [[T:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: [[S_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: store %struct.S.0* [[S]], %struct.S.0** [[S_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK4-NEXT: [[TMP0:%.*]] = load %struct.S.0*, %struct.S.0** [[S_ADDR]], align 4
// CHECK4-NEXT: [[F2:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[TMP0]], i32 0, i32 0
// CHECK4-NEXT: [[TMP1:%.*]] = load i32, i32* [[F2]], align 4
// CHECK4-NEXT: [[A:%.*]] = getelementptr inbounds [[STRUCT_ST:%.*]], %struct.St* [[T]], i32 0, i32 0
// CHECK4-NEXT: [[TMP2:%.*]] = load i32, i32* [[A]], align 4
// CHECK4-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP1]], [[TMP2]]
// CHECK4-NEXT: store i32 [[ADD]], i32* [[F]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_ZN1SIiED2Ev
// CHECK4-SAME: (%struct.S.0* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 4
// CHECK4-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 4
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_GLOBAL__sub_I_teams_distribute_firstprivate_codegen.cpp
// CHECK4-SAME: () #[[ATTR0]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: call void @__cxx_global_var_init()
// CHECK4-NEXT: call void @__cxx_global_var_init.1()
// CHECK4-NEXT: call void @__cxx_global_var_init.2()
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
// CHECK4-SAME: () #[[ATTR0]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: call void @__tgt_register_requires(i64 1)
// CHECK4-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@__cxx_global_var_init
// CHECK9-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) @test)
// CHECK9-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @test to i8*), i8* @__dso_handle) #[[ATTR2:[0-9]+]]
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
// CHECK9-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] comdat align 2 {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK9-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: call void @_ZN1SIfEC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
// CHECK9-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK9-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: call void @_ZN1SIfED2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR2]]
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
// CHECK9-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK9-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK9-NEXT: [[TMP0:%.*]] = load volatile i32, i32* @g, align 4
// CHECK9-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to float
// CHECK9-NEXT: store float [[CONV]], float* [[F]], align 4
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
// CHECK9-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK9-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@__cxx_global_var_init.1
// CHECK9-SAME: () #[[ATTR0]] {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i64 0, i64 0), float 1.000000e+00)
// CHECK9-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i64 0, i64 1), float 2.000000e+00)
// CHECK9-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* @__cxx_global_array_dtor, i8* null, i8* @__dso_handle) #[[ATTR2]]
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
// CHECK9-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK9-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK9-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK9-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK9-NEXT: call void @_ZN1SIfEC2Ef(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], float [[TMP0]])
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@__cxx_global_array_dtor
// CHECK9-SAME: (i8* [[TMP0:%.*]]) #[[ATTR0]] {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK9-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK9-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK9: arraydestroy.body:
// CHECK9-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ getelementptr inbounds ([[STRUCT_S:%.*]], %struct.S* getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0), i64 2), [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK9-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK9-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK9-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0)
// CHECK9-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK9: arraydestroy.done1:
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
// CHECK9-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK9-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK9-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK9-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK9-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK9-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK9-NEXT: [[TMP1:%.*]] = load volatile i32, i32* @g, align 4
// CHECK9-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP1]] to float
// CHECK9-NEXT: [[ADD:%.*]] = fadd float [[TMP0]], [[CONV]]
// CHECK9-NEXT: store float [[ADD]], float* [[F]], align 4
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@__cxx_global_var_init.2
// CHECK9-SAME: () #[[ATTR0]] {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) @var, float 3.000000e+00)
// CHECK9-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @var to i8*), i8* @__dso_handle) #[[ATTR2]]
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@main
// CHECK9-SAME: () #[[ATTR3:[0-9]+]] {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK9-NEXT: [[REF_TMP:%.*]] = alloca [[CLASS_ANON:%.*]], align 1
// CHECK9-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK9-NEXT: call void @"_ZZ4mainENK3$_0clEv"(%class.anon* nonnull align 1 dereferenceable(1) [[REF_TMP]])
// CHECK9-NEXT: ret i32 0
//
//
// CHECK9-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l75
// CHECK9-SAME: (i64 [[G:%.*]], i64 [[SIVAR:%.*]], i64 [[G1:%.*]]) #[[ATTR5:[0-9]+]] {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: [[G_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT: [[SIVAR_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT: [[G1_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT: [[TMP:%.*]] = alloca i32*, align 8
// CHECK9-NEXT: [[G_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT: [[G1_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT: [[SIVAR_CASTED:%.*]] = alloca i64, align 8
// CHECK9-NEXT: store i64 [[G]], i64* [[G_ADDR]], align 8
// CHECK9-NEXT: store i64 [[SIVAR]], i64* [[SIVAR_ADDR]], align 8
// CHECK9-NEXT: store i64 [[G1]], i64* [[G1_ADDR]], align 8
// CHECK9-NEXT: [[CONV:%.*]] = bitcast i64* [[G_ADDR]] to i32*
// CHECK9-NEXT: [[CONV1:%.*]] = bitcast i64* [[SIVAR_ADDR]] to i32*
// CHECK9-NEXT: [[CONV2:%.*]] = bitcast i64* [[G1_ADDR]] to i32*
// CHECK9-NEXT: store i32* [[CONV2]], i32** [[TMP]], align 8
// CHECK9-NEXT: [[TMP0:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK9-NEXT: [[CONV3:%.*]] = bitcast i64* [[G_CASTED]] to i32*
// CHECK9-NEXT: store i32 [[TMP0]], i32* [[CONV3]], align 4
// CHECK9-NEXT: [[TMP1:%.*]] = load i64, i64* [[G_CASTED]], align 8
// CHECK9-NEXT: [[TMP2:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK9-NEXT: [[TMP3:%.*]] = load volatile i32, i32* [[TMP2]], align 4
// CHECK9-NEXT: [[CONV4:%.*]] = bitcast i64* [[G1_CASTED]] to i32*
// CHECK9-NEXT: store i32 [[TMP3]], i32* [[CONV4]], align 4
// CHECK9-NEXT: [[TMP4:%.*]] = load i64, i64* [[G1_CASTED]], align 8
// CHECK9-NEXT: [[TMP5:%.*]] = load i32, i32* [[CONV1]], align 8
// CHECK9-NEXT: [[CONV5:%.*]] = bitcast i64* [[SIVAR_CASTED]] to i32*
// CHECK9-NEXT: store i32 [[TMP5]], i32* [[CONV5]], align 4
// CHECK9-NEXT: [[TMP6:%.*]] = load i64, i64* [[SIVAR_CASTED]], align 8
// CHECK9-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 3, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i64, i64, i64)* @.omp_outlined. to void (i32*, i32*, ...)*), i64 [[TMP1]], i64 [[TMP4]], i64 [[TMP6]])
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK9-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i64 [[G:%.*]], i64 [[G1:%.*]], i64 [[SIVAR:%.*]]) #[[ATTR5]] {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK9-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK9-NEXT: [[G_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT: [[G1_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT: [[SIVAR_ADDR:%.*]] = alloca i64, align 8
// CHECK9-NEXT: [[TMP:%.*]] = alloca i32*, align 8
// CHECK9-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK9-NEXT: [[_TMP3:%.*]] = alloca i32, align 4
// CHECK9-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK9-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK9-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK9-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK9-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK9-NEXT: [[REF_TMP:%.*]] = alloca [[CLASS_ANON_0:%.*]], align 8
// CHECK9-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK9-NEXT: store i64 [[G]], i64* [[G_ADDR]], align 8
// CHECK9-NEXT: store i64 [[G1]], i64* [[G1_ADDR]], align 8
// CHECK9-NEXT: store i64 [[SIVAR]], i64* [[SIVAR_ADDR]], align 8
// CHECK9-NEXT: [[CONV:%.*]] = bitcast i64* [[G_ADDR]] to i32*
// CHECK9-NEXT: [[CONV1:%.*]] = bitcast i64* [[G1_ADDR]] to i32*
// CHECK9-NEXT: [[CONV2:%.*]] = bitcast i64* [[SIVAR_ADDR]] to i32*
// CHECK9-NEXT: store i32* [[CONV1]], i32** [[TMP]], align 8
// CHECK9-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK9-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
// CHECK9-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK9-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK9-NEXT: [[TMP0:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK9-NEXT: [[TMP1:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK9-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP1]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK9-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK9-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP2]], 1
// CHECK9-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK9: cond.true:
// CHECK9-NEXT: br label [[COND_END:%.*]]
// CHECK9: cond.false:
// CHECK9-NEXT: [[TMP3:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK9-NEXT: br label [[COND_END]]
// CHECK9: cond.end:
// CHECK9-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP3]], [[COND_FALSE]] ]
// CHECK9-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK9-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK9-NEXT: store i32 [[TMP4]], i32* [[DOTOMP_IV]], align 4
// CHECK9-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK9: omp.inner.for.cond:
// CHECK9-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK9-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK9-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP5]], [[TMP6]]
// CHECK9-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
// CHECK9: omp.inner.for.body:
// CHECK9-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK9-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP7]], 1
// CHECK9-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK9-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK9-NEXT: store i32 1, i32* [[CONV]], align 8
// CHECK9-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK9-NEXT: store volatile i32 1, i32* [[TMP8]], align 4
// CHECK9-NEXT: store i32 2, i32* [[CONV2]], align 8
// CHECK9-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 0
// CHECK9-NEXT: store i32* [[CONV]], i32** [[TMP9]], align 8
// CHECK9-NEXT: [[TMP10:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 1
// CHECK9-NEXT: [[TMP11:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK9-NEXT: store i32* [[TMP11]], i32** [[TMP10]], align 8
// CHECK9-NEXT: [[TMP12:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 2
// CHECK9-NEXT: store i32* [[CONV2]], i32** [[TMP12]], align 8
// CHECK9-NEXT: call void @"_ZZZ4mainENK3$_0clEvENKUlvE_clEv"(%class.anon.0* nonnull align 8 dereferenceable(24) [[REF_TMP]])
// CHECK9-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK9: omp.body.continue:
// CHECK9-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK9: omp.inner.for.inc:
// CHECK9-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK9-NEXT: [[ADD5:%.*]] = add nsw i32 [[TMP13]], 1
// CHECK9-NEXT: store i32 [[ADD5]], i32* [[DOTOMP_IV]], align 4
// CHECK9-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK9: omp.inner.for.end:
// CHECK9-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
// CHECK9: omp.loop.exit:
// CHECK9-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]])
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@_GLOBAL__sub_I_teams_distribute_firstprivate_codegen.cpp
// CHECK9-SAME: () #[[ATTR0]] {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: call void @__cxx_global_var_init()
// CHECK9-NEXT: call void @__cxx_global_var_init.1()
// CHECK9-NEXT: call void @__cxx_global_var_init.2()
// CHECK9-NEXT: ret void
//
//
// CHECK9-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
// CHECK9-SAME: () #[[ATTR0]] {
// CHECK9-NEXT: entry:
// CHECK9-NEXT: call void @__tgt_register_requires(i64 1)
// CHECK9-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@__cxx_global_var_init
// CHECK10-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* nonnull align 4 dereferenceable(4) @test)
// CHECK10-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @test to i8*), i8* @__dso_handle) #[[ATTR2:[0-9]+]]
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
// CHECK10-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] comdat align 2 {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK10-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: call void @_ZN1SIfEC2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]])
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
// CHECK10-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK10-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: call void @_ZN1SIfED2Ev(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR2]]
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
// CHECK10-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK10-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK10-NEXT: [[TMP0:%.*]] = load volatile i32, i32* @g, align 4
// CHECK10-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to float
// CHECK10-NEXT: store float [[CONV]], float* [[F]], align 4
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
// CHECK10-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK10-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@__cxx_global_var_init.1
// CHECK10-SAME: () #[[ATTR0]] {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i64 0, i64 0), float 1.000000e+00)
// CHECK10-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i64 0, i64 1), float 2.000000e+00)
// CHECK10-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* @__cxx_global_array_dtor, i8* null, i8* @__dso_handle) #[[ATTR2]]
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
// CHECK10-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK10-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK10-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK10-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK10-NEXT: call void @_ZN1SIfEC2Ef(%struct.S* nonnull align 4 dereferenceable(4) [[THIS1]], float [[TMP0]])
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@__cxx_global_array_dtor
// CHECK10-SAME: (i8* [[TMP0:%.*]]) #[[ATTR0]] {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK10-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK10-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK10: arraydestroy.body:
// CHECK10-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ getelementptr inbounds ([[STRUCT_S:%.*]], %struct.S* getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0), i64 2), [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
// CHECK10-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
// CHECK10-NEXT: call void @_ZN1SIfED1Ev(%struct.S* nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR2]]
// CHECK10-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], getelementptr inbounds ([2 x %struct.S], [2 x %struct.S]* @s_arr, i32 0, i32 0)
// CHECK10-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK10: arraydestroy.done1:
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
// CHECK10-SAME: (%struct.S* nonnull align 4 dereferenceable(4) [[THIS:%.*]], float [[A:%.*]]) unnamed_addr #[[ATTR1]] comdat align 2 {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK10-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK10-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK10-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK10-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK10-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK10-NEXT: [[TMP1:%.*]] = load volatile i32, i32* @g, align 4
// CHECK10-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP1]] to float
// CHECK10-NEXT: [[ADD:%.*]] = fadd float [[TMP0]], [[CONV]]
// CHECK10-NEXT: store float [[ADD]], float* [[F]], align 4
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@__cxx_global_var_init.2
// CHECK10-SAME: () #[[ATTR0]] {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* nonnull align 4 dereferenceable(4) @var, float 3.000000e+00)
// CHECK10-NEXT: [[TMP0:%.*]] = call i32 @__cxa_atexit(void (i8*)* bitcast (void (%struct.S*)* @_ZN1SIfED1Ev to void (i8*)*), i8* bitcast (%struct.S* @var to i8*), i8* @__dso_handle) #[[ATTR2]]
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@main
// CHECK10-SAME: () #[[ATTR3:[0-9]+]] {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK10-NEXT: [[REF_TMP:%.*]] = alloca [[CLASS_ANON:%.*]], align 1
// CHECK10-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK10-NEXT: call void @"_ZZ4mainENK3$_0clEv"(%class.anon* nonnull align 1 dereferenceable(1) [[REF_TMP]])
// CHECK10-NEXT: ret i32 0
//
//
// CHECK10-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l75
// CHECK10-SAME: (i64 [[G:%.*]], i64 [[SIVAR:%.*]], i64 [[G1:%.*]]) #[[ATTR5:[0-9]+]] {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: [[G_ADDR:%.*]] = alloca i64, align 8
// CHECK10-NEXT: [[SIVAR_ADDR:%.*]] = alloca i64, align 8
// CHECK10-NEXT: [[G1_ADDR:%.*]] = alloca i64, align 8
// CHECK10-NEXT: [[TMP:%.*]] = alloca i32*, align 8
// CHECK10-NEXT: [[G_CASTED:%.*]] = alloca i64, align 8
// CHECK10-NEXT: [[G1_CASTED:%.*]] = alloca i64, align 8
// CHECK10-NEXT: [[SIVAR_CASTED:%.*]] = alloca i64, align 8
// CHECK10-NEXT: store i64 [[G]], i64* [[G_ADDR]], align 8
// CHECK10-NEXT: store i64 [[SIVAR]], i64* [[SIVAR_ADDR]], align 8
// CHECK10-NEXT: store i64 [[G1]], i64* [[G1_ADDR]], align 8
// CHECK10-NEXT: [[CONV:%.*]] = bitcast i64* [[G_ADDR]] to i32*
// CHECK10-NEXT: [[CONV1:%.*]] = bitcast i64* [[SIVAR_ADDR]] to i32*
// CHECK10-NEXT: [[CONV2:%.*]] = bitcast i64* [[G1_ADDR]] to i32*
// CHECK10-NEXT: store i32* [[CONV2]], i32** [[TMP]], align 8
// CHECK10-NEXT: [[TMP0:%.*]] = load i32, i32* [[CONV]], align 8
// CHECK10-NEXT: [[CONV3:%.*]] = bitcast i64* [[G_CASTED]] to i32*
// CHECK10-NEXT: store i32 [[TMP0]], i32* [[CONV3]], align 4
// CHECK10-NEXT: [[TMP1:%.*]] = load i64, i64* [[G_CASTED]], align 8
// CHECK10-NEXT: [[TMP2:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK10-NEXT: [[TMP3:%.*]] = load volatile i32, i32* [[TMP2]], align 4
// CHECK10-NEXT: [[CONV4:%.*]] = bitcast i64* [[G1_CASTED]] to i32*
// CHECK10-NEXT: store i32 [[TMP3]], i32* [[CONV4]], align 4
// CHECK10-NEXT: [[TMP4:%.*]] = load i64, i64* [[G1_CASTED]], align 8
// CHECK10-NEXT: [[TMP5:%.*]] = load i32, i32* [[CONV1]], align 8
// CHECK10-NEXT: [[CONV5:%.*]] = bitcast i64* [[SIVAR_CASTED]] to i32*
// CHECK10-NEXT: store i32 [[TMP5]], i32* [[CONV5]], align 4
// CHECK10-NEXT: [[TMP6:%.*]] = load i64, i64* [[SIVAR_CASTED]], align 8
// CHECK10-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_teams(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 3, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i64, i64, i64)* @.omp_outlined. to void (i32*, i32*, ...)*), i64 [[TMP1]], i64 [[TMP4]], i64 [[TMP6]])
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK10-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i64 [[G:%.*]], i64 [[G1:%.*]], i64 [[SIVAR:%.*]]) #[[ATTR5]] {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK10-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK10-NEXT: [[G_ADDR:%.*]] = alloca i64, align 8
// CHECK10-NEXT: [[G1_ADDR:%.*]] = alloca i64, align 8
// CHECK10-NEXT: [[SIVAR_ADDR:%.*]] = alloca i64, align 8
// CHECK10-NEXT: [[TMP:%.*]] = alloca i32*, align 8
// CHECK10-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
// CHECK10-NEXT: [[_TMP3:%.*]] = alloca i32, align 4
// CHECK10-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
// CHECK10-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
// CHECK10-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
// CHECK10-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
// CHECK10-NEXT: [[I:%.*]] = alloca i32, align 4
// CHECK10-NEXT: [[REF_TMP:%.*]] = alloca [[CLASS_ANON_0:%.*]], align 8
// CHECK10-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK10-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK10-NEXT: store i64 [[G]], i64* [[G_ADDR]], align 8
// CHECK10-NEXT: store i64 [[G1]], i64* [[G1_ADDR]], align 8
// CHECK10-NEXT: store i64 [[SIVAR]], i64* [[SIVAR_ADDR]], align 8
// CHECK10-NEXT: [[CONV:%.*]] = bitcast i64* [[G_ADDR]] to i32*
// CHECK10-NEXT: [[CONV1:%.*]] = bitcast i64* [[G1_ADDR]] to i32*
// CHECK10-NEXT: [[CONV2:%.*]] = bitcast i64* [[SIVAR_ADDR]] to i32*
// CHECK10-NEXT: store i32* [[CONV1]], i32** [[TMP]], align 8
// CHECK10-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
// CHECK10-NEXT: store i32 1, i32* [[DOTOMP_UB]], align 4
// CHECK10-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
// CHECK10-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
// CHECK10-NEXT: [[TMP0:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK10-NEXT: [[TMP1:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK10-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP1]], i32 92, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
// CHECK10-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK10-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP2]], 1
// CHECK10-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK10: cond.true:
// CHECK10-NEXT: br label [[COND_END:%.*]]
// CHECK10: cond.false:
// CHECK10-NEXT: [[TMP3:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK10-NEXT: br label [[COND_END]]
// CHECK10: cond.end:
// CHECK10-NEXT: [[COND:%.*]] = phi i32 [ 1, [[COND_TRUE]] ], [ [[TMP3]], [[COND_FALSE]] ]
// CHECK10-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
// CHECK10-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
// CHECK10-NEXT: store i32 [[TMP4]], i32* [[DOTOMP_IV]], align 4
// CHECK10-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK10: omp.inner.for.cond:
// CHECK10-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK10-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
// CHECK10-NEXT: [[CMP4:%.*]] = icmp sle i32 [[TMP5]], [[TMP6]]
// CHECK10-NEXT: br i1 [[CMP4]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
// CHECK10: omp.inner.for.body:
// CHECK10-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK10-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP7]], 1
// CHECK10-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
// CHECK10-NEXT: store i32 [[ADD]], i32* [[I]], align 4
// CHECK10-NEXT: store i32 1, i32* [[CONV]], align 8
// CHECK10-NEXT: [[TMP8:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK10-NEXT: store volatile i32 1, i32* [[TMP8]], align 4
// CHECK10-NEXT: store i32 2, i32* [[CONV2]], align 8
// CHECK10-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 0
// CHECK10-NEXT: store i32* [[CONV]], i32** [[TMP9]], align 8
// CHECK10-NEXT: [[TMP10:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 1
// CHECK10-NEXT: [[TMP11:%.*]] = load i32*, i32** [[TMP]], align 8
// CHECK10-NEXT: store i32* [[TMP11]], i32** [[TMP10]], align 8
// CHECK10-NEXT: [[TMP12:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 2
// CHECK10-NEXT: store i32* [[CONV2]], i32** [[TMP12]], align 8
// CHECK10-NEXT: call void @"_ZZZ4mainENK3$_0clEvENKUlvE_clEv"(%class.anon.0* nonnull align 8 dereferenceable(24) [[REF_TMP]])
// CHECK10-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
// CHECK10: omp.body.continue:
// CHECK10-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK10: omp.inner.for.inc:
// CHECK10-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4
// CHECK10-NEXT: [[ADD5:%.*]] = add nsw i32 [[TMP13]], 1
// CHECK10-NEXT: store i32 [[ADD5]], i32* [[DOTOMP_IV]], align 4
// CHECK10-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK10: omp.inner.for.end:
// CHECK10-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
// CHECK10: omp.loop.exit:
// CHECK10-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]])
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@_GLOBAL__sub_I_teams_distribute_firstprivate_codegen.cpp
// CHECK10-SAME: () #[[ATTR0]] {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: call void @__cxx_global_var_init()
// CHECK10-NEXT: call void @__cxx_global_var_init.1()
// CHECK10-NEXT: call void @__cxx_global_var_init.2()
// CHECK10-NEXT: ret void
//
//
// CHECK10-LABEL: define {{[^@]+}}@.omp_offloading.requires_reg
// CHECK10-SAME: () #[[ATTR0]] {
// CHECK10-NEXT: entry:
// CHECK10-NEXT: call void @__tgt_register_requires(i64 1)
// CHECK10-NEXT: ret void
//
//