maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/OpenMP/target_parallel_reduction_t...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

1003 lines
77 KiB
C++
Raw Normal View History

[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=50 -x c++ -triple x86_64-unknown-linux -emit-llvm %s -fexceptions -fcxx-exceptions -o - | FileCheck %s --check-prefix=CHECK1
[OPENMP50]Codegen for reduction clauses with 'task' modifier. Summary: Added codegen for reduction clause with task modifier. ``` #pragma omp ... reduction(task, +: a) { #pragma omp ... in_reduction(+: a) } ``` is translated into something like this: ``` #pragma omp ... reduction(+:a) { struct red_input_t { void *reduce_shar; void *reduce_orig; size_t reduce_size; void *reduce_init; void *reduce_fini; void *reduce_comb; unsigned flags; } r_var; r_var.reduce_shar = &a; r_var.reduce_orig = &original a; r_var.reduce_size = sizeof(a); r_var.reduce_init = [](void* l,void*){return *(int*)l=0;}; r_var.reduce_fini = nullptr; r_var.reduce_comb = [](void* l,void* r){return *(int*)l += *(int)r;}; void *tg = __kmpc_taskred_modifier_init(<loc_addr>,<gtid>, <flag - 0 for parallel, 1 for worksharing>, <1 - number of reduction elements>, &r_var); { #pragma omp ... in_reduction(+: a) firstprivate(tg) ... } __kmpc_task_reduction_modifier_fini(<loc_addr>,<gtid>, <flag - 0 for parallel, 1 for worksharing>); } ``` Reviewers: jdoerfert Subscribers: yaxunl, guansong, jfb, cfe-commits, caomhin Tags: #clang Differential Revision: https://reviews.llvm.org/D79034
2020-04-24 21:56:29 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c++ -std=c++11 -triple x86_64-unknown-linux -fexceptions -fcxx-exceptions -emit-pch -o %t %s
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c++ -triple x86_64-unknown-linux -fexceptions -fcxx-exceptions -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK2
[OPENMP50]Codegen for reduction clauses with 'task' modifier. Summary: Added codegen for reduction clause with task modifier. ``` #pragma omp ... reduction(task, +: a) { #pragma omp ... in_reduction(+: a) } ``` is translated into something like this: ``` #pragma omp ... reduction(+:a) { struct red_input_t { void *reduce_shar; void *reduce_orig; size_t reduce_size; void *reduce_init; void *reduce_fini; void *reduce_comb; unsigned flags; } r_var; r_var.reduce_shar = &a; r_var.reduce_orig = &original a; r_var.reduce_size = sizeof(a); r_var.reduce_init = [](void* l,void*){return *(int*)l=0;}; r_var.reduce_fini = nullptr; r_var.reduce_comb = [](void* l,void* r){return *(int*)l += *(int)r;}; void *tg = __kmpc_taskred_modifier_init(<loc_addr>,<gtid>, <flag - 0 for parallel, 1 for worksharing>, <1 - number of reduction elements>, &r_var); { #pragma omp ... in_reduction(+: a) firstprivate(tg) ... } __kmpc_task_reduction_modifier_fini(<loc_addr>,<gtid>, <flag - 0 for parallel, 1 for worksharing>); } ``` Reviewers: jdoerfert Subscribers: yaxunl, guansong, jfb, cfe-commits, caomhin Tags: #clang Differential Revision: https://reviews.llvm.org/D79034
2020-04-24 21:56:29 +08:00
[OpenMP][NFC] Remove SIMD check lines for non-simd tests If a test does not contain an " simd" but -fopenmp-simd RUN lines we can just check that we do not create __kmpc|__tgt calls. Reviewed By: ABataev Differential Revision: https://reviews.llvm.org/D101973
2021-05-19 10:52:53 +08:00
// RUN: %clang_cc1 -triple x86_64-unknown-linux -verify -fopenmp-simd -fopenmp-version=50 -x c++ -emit-llvm %s -fexceptions -fcxx-exceptions -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
[OPENMP50]Codegen for reduction clauses with 'task' modifier. Summary: Added codegen for reduction clause with task modifier. ``` #pragma omp ... reduction(task, +: a) { #pragma omp ... in_reduction(+: a) } ``` is translated into something like this: ``` #pragma omp ... reduction(+:a) { struct red_input_t { void *reduce_shar; void *reduce_orig; size_t reduce_size; void *reduce_init; void *reduce_fini; void *reduce_comb; unsigned flags; } r_var; r_var.reduce_shar = &a; r_var.reduce_orig = &original a; r_var.reduce_size = sizeof(a); r_var.reduce_init = [](void* l,void*){return *(int*)l=0;}; r_var.reduce_fini = nullptr; r_var.reduce_comb = [](void* l,void* r){return *(int*)l += *(int)r;}; void *tg = __kmpc_taskred_modifier_init(<loc_addr>,<gtid>, <flag - 0 for parallel, 1 for worksharing>, <1 - number of reduction elements>, &r_var); { #pragma omp ... in_reduction(+: a) firstprivate(tg) ... } __kmpc_task_reduction_modifier_fini(<loc_addr>,<gtid>, <flag - 0 for parallel, 1 for worksharing>); } ``` Reviewers: jdoerfert Subscribers: yaxunl, guansong, jfb, cfe-commits, caomhin Tags: #clang Differential Revision: https://reviews.llvm.org/D79034
2020-04-24 21:56:29 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
[OpenMP][NFC] Remove SIMD check lines for non-simd tests If a test does not contain an " simd" but -fopenmp-simd RUN lines we can just check that we do not create __kmpc|__tgt calls. Reviewed By: ABataev Differential Revision: https://reviews.llvm.org/D101973
2021-05-19 10:52:53 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -debug-info-kind=limited -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
[OPENMP50]Codegen for reduction clauses with 'task' modifier. Summary: Added codegen for reduction clause with task modifier. ``` #pragma omp ... reduction(task, +: a) { #pragma omp ... in_reduction(+: a) } ``` is translated into something like this: ``` #pragma omp ... reduction(+:a) { struct red_input_t { void *reduce_shar; void *reduce_orig; size_t reduce_size; void *reduce_init; void *reduce_fini; void *reduce_comb; unsigned flags; } r_var; r_var.reduce_shar = &a; r_var.reduce_orig = &original a; r_var.reduce_size = sizeof(a); r_var.reduce_init = [](void* l,void*){return *(int*)l=0;}; r_var.reduce_fini = nullptr; r_var.reduce_comb = [](void* l,void* r){return *(int*)l += *(int)r;}; void *tg = __kmpc_taskred_modifier_init(<loc_addr>,<gtid>, <flag - 0 for parallel, 1 for worksharing>, <1 - number of reduction elements>, &r_var); { #pragma omp ... in_reduction(+: a) firstprivate(tg) ... } __kmpc_task_reduction_modifier_fini(<loc_addr>,<gtid>, <flag - 0 for parallel, 1 for worksharing>); } ``` Reviewers: jdoerfert Subscribers: yaxunl, guansong, jfb, cfe-commits, caomhin Tags: #clang Differential Revision: https://reviews.llvm.org/D79034
2020-04-24 21:56:29 +08:00
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
int main(int argc, char **argv) {
#pragma omp target parallel reduction(task, +: argc, argv[0:10][0:argc])
{
#pragma omp task in_reduction(+: argc, argv[0:10][0:argc])
;
}
}
// Init firstprivate copy of argc
// Init firstprivate copy of argv[0:10][0:argc]
// Register task reduction.
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
[OPENMP50]Codegen for reduction clauses with 'task' modifier. Summary: Added codegen for reduction clause with task modifier. ``` #pragma omp ... reduction(task, +: a) { #pragma omp ... in_reduction(+: a) } ``` is translated into something like this: ``` #pragma omp ... reduction(+:a) { struct red_input_t { void *reduce_shar; void *reduce_orig; size_t reduce_size; void *reduce_init; void *reduce_fini; void *reduce_comb; unsigned flags; } r_var; r_var.reduce_shar = &a; r_var.reduce_orig = &original a; r_var.reduce_size = sizeof(a); r_var.reduce_init = [](void* l,void*){return *(int*)l=0;}; r_var.reduce_fini = nullptr; r_var.reduce_comb = [](void* l,void* r){return *(int*)l += *(int)r;}; void *tg = __kmpc_taskred_modifier_init(<loc_addr>,<gtid>, <flag - 0 for parallel, 1 for worksharing>, <1 - number of reduction elements>, &r_var); { #pragma omp ... in_reduction(+: a) firstprivate(tg) ... } __kmpc_task_reduction_modifier_fini(<loc_addr>,<gtid>, <flag - 0 for parallel, 1 for worksharing>); } ``` Reviewers: jdoerfert Subscribers: yaxunl, guansong, jfb, cfe-commits, caomhin Tags: #clang Differential Revision: https://reviews.llvm.org/D79034
2020-04-24 21:56:29 +08:00
#endif
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-LABEL: define {{[^@]+}}@main
// CHECK1-SAME: (i32 [[ARGC:%.*]], i8** [[ARGV:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[ARGC_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[ARGV_ADDR:%.*]] = alloca i8**, align 8
// CHECK1-NEXT: store i32 [[ARGC]], i32* [[ARGC_ADDR]], align 4
// CHECK1-NEXT: store i8** [[ARGV]], i8*** [[ARGV_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK1-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l14(i32* [[ARGC_ADDR]], i8** [[TMP0]]) #[[ATTR5:[0-9]+]]
// CHECK1-NEXT: ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l14
// CHECK1-SAME: (i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i8** [[ARGV:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[ARGC_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[ARGV_ADDR:%.*]] = alloca i8**, align 8
// CHECK1-NEXT: store i32* [[ARGC]], i32** [[ARGC_ADDR]], align 8
// CHECK1-NEXT: store i8** [[ARGV]], i8*** [[ARGV_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i32*, i32** [[ARGC_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*, i8**)* @.omp_outlined. to void (i32*, i32*, ...)*), i32* [[TMP0]], i8** [[TMP1]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i8** [[ARGV:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[ARGC_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[ARGV_ADDR:%.*]] = alloca i8**, align 8
// CHECK1-NEXT: [[ARGC1:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[TMP:%.*]] = alloca i8**, align 8
// CHECK1-NEXT: [[_TMP5:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[DOTRD_INPUT_:%.*]] = alloca [2 x %struct.kmp_taskred_input_t], align 8
// CHECK1-NEXT: [[DOTTASK_RED_:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 8
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [3 x i8*], align 8
// CHECK1-NEXT: [[ATOMIC_TEMP:%.*]] = alloca i8, align 1
// CHECK1-NEXT: [[_TMP24:%.*]] = alloca i8, align 1
// 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 i32* [[ARGC]], i32** [[ARGC_ADDR]], align 8
// CHECK1-NEXT: store i8** [[ARGV]], i8*** [[ARGV_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i32*, i32** [[ARGC_ADDR]], align 8
// CHECK1-NEXT: store i32 0, i32* [[ARGC1]], align 4
// CHECK1-NEXT: [[TMP1:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8*, i8** [[TMP1]], i64 0
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[ARRAYIDX]], align 8
// CHECK1-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i8, i8* [[TMP2]], i64 0
// CHECK1-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK1-NEXT: [[TMP4:%.*]] = sext i32 [[TMP3]] to i64
// CHECK1-NEXT: [[LB_ADD_LEN:%.*]] = add nsw i64 -1, [[TMP4]]
// CHECK1-NEXT: [[TMP5:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK1-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i8*, i8** [[TMP5]], i64 9
// CHECK1-NEXT: [[TMP6:%.*]] = load i8*, i8** [[ARRAYIDX3]], align 8
// CHECK1-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i8, i8* [[TMP6]], i64 [[LB_ADD_LEN]]
// CHECK1-NEXT: [[TMP7:%.*]] = ptrtoint i8* [[ARRAYIDX4]] to i64
// CHECK1-NEXT: [[TMP8:%.*]] = ptrtoint i8* [[ARRAYIDX2]] to i64
// CHECK1-NEXT: [[TMP9:%.*]] = sub i64 [[TMP7]], [[TMP8]]
// CHECK1-NEXT: [[TMP10:%.*]] = sdiv exact i64 [[TMP9]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK1-NEXT: [[TMP11:%.*]] = add nuw i64 [[TMP10]], 1
// CHECK1-NEXT: [[TMP12:%.*]] = mul nuw i64 [[TMP11]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK1-NEXT: [[TMP13:%.*]] = call i8* @llvm.stacksave()
// CHECK1-NEXT: store i8* [[TMP13]], i8** [[SAVED_STACK]], align 8
// CHECK1-NEXT: [[VLA:%.*]] = alloca i8, i64 [[TMP11]], align 16
// CHECK1-NEXT: store i64 [[TMP11]], i64* [[__VLA_EXPR0]], align 8
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr i8, i8* [[VLA]], i64 [[TMP11]]
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i8* [[VLA]], [[TMP14]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
// CHECK1: omp.arrayinit.body:
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i8* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
// CHECK1-NEXT: store i8 0, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP14]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
// CHECK1: omp.arrayinit.done:
// CHECK1-NEXT: [[TMP15:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK1-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
// CHECK1-NEXT: [[TMP17:%.*]] = ptrtoint i8* [[TMP16]] to i64
// CHECK1-NEXT: [[TMP18:%.*]] = ptrtoint i8* [[ARRAYIDX2]] to i64
// CHECK1-NEXT: [[TMP19:%.*]] = sub i64 [[TMP17]], [[TMP18]]
// CHECK1-NEXT: [[TMP20:%.*]] = sdiv exact i64 [[TMP19]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr i8, i8* [[VLA]], i64 [[TMP20]]
// CHECK1-NEXT: store i8** [[_TMP5]], i8*** [[TMP]], align 8
// CHECK1-NEXT: store i8* [[TMP21]], i8** [[_TMP5]], align 8
// CHECK1-NEXT: [[DOTRD_INPUT_GEP_:%.*]] = getelementptr inbounds [2 x %struct.kmp_taskred_input_t], [2 x %struct.kmp_taskred_input_t]* [[DOTRD_INPUT_]], i64 0, i64 0
// CHECK1-NEXT: [[TMP22:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T:%.*]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 0
// CHECK1-NEXT: [[TMP23:%.*]] = bitcast i32* [[ARGC1]] to i8*
// CHECK1-NEXT: store i8* [[TMP23]], i8** [[TMP22]], align 8
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 1
// CHECK1-NEXT: [[TMP25:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK1-NEXT: store i8* [[TMP25]], i8** [[TMP24]], align 8
// CHECK1-NEXT: [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 2
// CHECK1-NEXT: store i64 4, i64* [[TMP26]], align 8
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 3
// CHECK1-NEXT: store i8* bitcast (void (i8*, i8*)* @.red_init. to i8*), i8** [[TMP27]], align 8
// CHECK1-NEXT: [[TMP28:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 4
// CHECK1-NEXT: store i8* null, i8** [[TMP28]], align 8
// CHECK1-NEXT: [[TMP29:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 5
// CHECK1-NEXT: store i8* bitcast (void (i8*, i8*)* @.red_comb. to i8*), i8** [[TMP29]], align 8
// CHECK1-NEXT: [[TMP30:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 6
// CHECK1-NEXT: [[TMP31:%.*]] = bitcast i32* [[TMP30]] to i8*
// CHECK1-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[TMP31]], i8 0, i64 4, i1 false)
// CHECK1-NEXT: [[DOTRD_INPUT_GEP_6:%.*]] = getelementptr inbounds [2 x %struct.kmp_taskred_input_t], [2 x %struct.kmp_taskred_input_t]* [[DOTRD_INPUT_]], i64 0, i64 1
// CHECK1-NEXT: [[TMP32:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 0
// CHECK1-NEXT: [[TMP33:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK1-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds i8*, i8** [[TMP33]], i64 0
// CHECK1-NEXT: [[TMP34:%.*]] = load i8*, i8** [[ARRAYIDX7]], align 8
// CHECK1-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i8, i8* [[TMP34]], i64 0
// CHECK1-NEXT: [[TMP35:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK1-NEXT: [[TMP36:%.*]] = sext i32 [[TMP35]] to i64
// CHECK1-NEXT: [[LB_ADD_LEN9:%.*]] = add nsw i64 -1, [[TMP36]]
// CHECK1-NEXT: [[TMP37:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK1-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds i8*, i8** [[TMP37]], i64 9
// CHECK1-NEXT: [[TMP38:%.*]] = load i8*, i8** [[ARRAYIDX10]], align 8
// CHECK1-NEXT: [[ARRAYIDX11:%.*]] = getelementptr inbounds i8, i8* [[TMP38]], i64 [[LB_ADD_LEN9]]
// CHECK1-NEXT: store i8* [[VLA]], i8** [[TMP32]], align 8
// CHECK1-NEXT: [[TMP39:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 1
// CHECK1-NEXT: store i8* [[ARRAYIDX8]], i8** [[TMP39]], align 8
// CHECK1-NEXT: [[TMP40:%.*]] = ptrtoint i8* [[ARRAYIDX11]] to i64
// CHECK1-NEXT: [[TMP41:%.*]] = ptrtoint i8* [[ARRAYIDX8]] to i64
// CHECK1-NEXT: [[TMP42:%.*]] = sub i64 [[TMP40]], [[TMP41]]
// CHECK1-NEXT: [[TMP43:%.*]] = sdiv exact i64 [[TMP42]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK1-NEXT: [[TMP44:%.*]] = add nuw i64 [[TMP43]], 1
// CHECK1-NEXT: [[TMP45:%.*]] = mul nuw i64 [[TMP44]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK1-NEXT: [[TMP46:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 2
// CHECK1-NEXT: store i64 [[TMP45]], i64* [[TMP46]], align 8
// CHECK1-NEXT: [[TMP47:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 3
// CHECK1-NEXT: store i8* bitcast (void (i8*, i8*)* @.red_init..1 to i8*), i8** [[TMP47]], align 8
// CHECK1-NEXT: [[TMP48:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 4
// CHECK1-NEXT: store i8* null, i8** [[TMP48]], align 8
// CHECK1-NEXT: [[TMP49:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 5
// CHECK1-NEXT: store i8* bitcast (void (i8*, i8*)* @.red_comb..2 to i8*), i8** [[TMP49]], align 8
// CHECK1-NEXT: [[TMP50:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 6
// CHECK1-NEXT: store i32 1, i32* [[TMP50]], align 8
// CHECK1-NEXT: [[TMP51:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP52:%.*]] = load i32, i32* [[TMP51]], align 4
// CHECK1-NEXT: [[TMP53:%.*]] = bitcast [2 x %struct.kmp_taskred_input_t]* [[DOTRD_INPUT_]] to i8*
// CHECK1-NEXT: [[TMP54:%.*]] = call i8* @__kmpc_taskred_modifier_init(%struct.ident_t* @[[GLOB1]], i32 [[TMP52]], i32 0, i32 2, i8* [[TMP53]])
// CHECK1-NEXT: store i8* [[TMP54]], i8** [[DOTTASK_RED_]], align 8
// CHECK1-NEXT: [[TMP55:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK1-NEXT: store i8** [[DOTTASK_RED_]], i8*** [[TMP55]], align 8
// CHECK1-NEXT: [[TMP56:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 1
// CHECK1-NEXT: store i32* [[ARGC1]], i32** [[TMP56]], align 8
// CHECK1-NEXT: [[TMP57:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 2
// CHECK1-NEXT: [[TMP58:%.*]] = load i8**, i8*** [[TMP]], align 8
// CHECK1-NEXT: store i8** [[TMP58]], i8*** [[TMP57]], align 8
// CHECK1-NEXT: [[TMP59:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP60:%.*]] = load i32, i32* [[TMP59]], align 4
// CHECK1-NEXT: [[TMP61:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP60]], i32 1, i64 48, i64 24, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*))
// CHECK1-NEXT: [[TMP62:%.*]] = bitcast i8* [[TMP61]] to %struct.kmp_task_t_with_privates*
// CHECK1-NEXT: [[TMP63:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP62]], i32 0, i32 0
// CHECK1-NEXT: [[TMP64:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP63]], i32 0, i32 0
// CHECK1-NEXT: [[TMP65:%.*]] = load i8*, i8** [[TMP64]], align 8
// CHECK1-NEXT: [[TMP66:%.*]] = bitcast %struct.anon* [[AGG_CAPTURED]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP65]], i8* align 8 [[TMP66]], i64 24, i1 false)
// CHECK1-NEXT: [[TMP67:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES]], %struct.kmp_task_t_with_privates* [[TMP62]], i32 0, i32 1
// CHECK1-NEXT: [[TMP68:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP67]], i32 0, i32 0
// CHECK1-NEXT: [[TMP69:%.*]] = load i8*, i8** [[DOTTASK_RED_]], align 8
// CHECK1-NEXT: store i8* [[TMP69]], i8** [[TMP68]], align 8
// CHECK1-NEXT: [[TMP70:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP71:%.*]] = load i32, i32* [[TMP70]], align 4
// CHECK1-NEXT: [[TMP72:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP71]], i8* [[TMP61]])
// CHECK1-NEXT: [[TMP73:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP74:%.*]] = load i32, i32* [[TMP73]], align 4
// CHECK1-NEXT: call void @__kmpc_task_reduction_modifier_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP74]], i32 0)
// CHECK1-NEXT: [[TMP75:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
// CHECK1-NEXT: [[TMP76:%.*]] = bitcast i32* [[ARGC1]] to i8*
// CHECK1-NEXT: store i8* [[TMP76]], i8** [[TMP75]], align 8
// CHECK1-NEXT: [[TMP77:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
// CHECK1-NEXT: store i8* [[VLA]], i8** [[TMP77]], align 8
// CHECK1-NEXT: [[TMP78:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
// CHECK1-NEXT: [[TMP79:%.*]] = inttoptr i64 [[TMP11]] to i8*
// CHECK1-NEXT: store i8* [[TMP79]], i8** [[TMP78]], align 8
// CHECK1-NEXT: [[TMP80:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP81:%.*]] = load i32, i32* [[TMP80]], align 4
// CHECK1-NEXT: [[TMP82:%.*]] = bitcast [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
// CHECK1-NEXT: [[TMP83:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP81]], i32 2, i64 24, i8* [[TMP82]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
// CHECK1-NEXT: switch i32 [[TMP83]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
// CHECK1-NEXT: ]
// CHECK1: .omp.reduction.case1:
// CHECK1-NEXT: [[TMP84:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK1-NEXT: [[TMP85:%.*]] = load i32, i32* [[ARGC1]], align 4
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP84]], [[TMP85]]
// CHECK1-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
// CHECK1-NEXT: [[TMP86:%.*]] = getelementptr i8, i8* [[ARRAYIDX2]], i64 [[TMP11]]
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i8* [[ARRAYIDX2]], [[TMP86]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE18:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK1: omp.arraycpy.body:
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i8* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST12:%.*]] = phi i8* [ [[ARRAYIDX2]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT16:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK1-NEXT: [[TMP87:%.*]] = load i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST12]], align 1
// CHECK1-NEXT: [[CONV:%.*]] = sext i8 [[TMP87]] to i32
// CHECK1-NEXT: [[TMP88:%.*]] = load i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 1
// CHECK1-NEXT: [[CONV13:%.*]] = sext i8 [[TMP88]] to i32
// CHECK1-NEXT: [[ADD14:%.*]] = add nsw i32 [[CONV]], [[CONV13]]
// CHECK1-NEXT: [[CONV15:%.*]] = trunc i32 [[ADD14]] to i8
// CHECK1-NEXT: store i8 [[CONV15]], i8* [[OMP_ARRAYCPY_DESTELEMENTPAST12]], align 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT16]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST12]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE17:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT16]], [[TMP86]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE17]], label [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_BODY]]
// CHECK1: omp.arraycpy.done18:
// CHECK1-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP81]], [8 x i32]* @.gomp_critical_user_.reduction.var)
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK1: .omp.reduction.case2:
// CHECK1-NEXT: [[TMP89:%.*]] = load i32, i32* [[ARGC1]], align 4
// CHECK1-NEXT: [[TMP90:%.*]] = atomicrmw add i32* [[TMP0]], i32 [[TMP89]] monotonic, align 4
// CHECK1-NEXT: [[TMP91:%.*]] = getelementptr i8, i8* [[ARRAYIDX2]], i64 [[TMP11]]
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY19:%.*]] = icmp eq i8* [[ARRAYIDX2]], [[TMP91]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY19]], label [[OMP_ARRAYCPY_DONE32:%.*]], label [[OMP_ARRAYCPY_BODY20:%.*]]
// CHECK1: omp.arraycpy.body20:
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST21:%.*]] = phi i8* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT30:%.*]], [[ATOMIC_EXIT:%.*]] ]
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST22:%.*]] = phi i8* [ [[ARRAYIDX2]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT29:%.*]], [[ATOMIC_EXIT]] ]
// CHECK1-NEXT: [[TMP92:%.*]] = load i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST21]], align 1
// CHECK1-NEXT: [[CONV23:%.*]] = sext i8 [[TMP92]] to i32
// CHECK1-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST22]] monotonic, align 1
// CHECK1-NEXT: br label [[ATOMIC_CONT:%.*]]
// CHECK1: atomic_cont:
// CHECK1-NEXT: [[TMP93:%.*]] = phi i8 [ [[ATOMIC_LOAD]], [[OMP_ARRAYCPY_BODY20]] ], [ [[TMP98:%.*]], [[ATOMIC_CONT]] ]
// CHECK1-NEXT: store i8 [[TMP93]], i8* [[_TMP24]], align 1
// CHECK1-NEXT: [[TMP94:%.*]] = load i8, i8* [[_TMP24]], align 1
// CHECK1-NEXT: [[CONV25:%.*]] = sext i8 [[TMP94]] to i32
// CHECK1-NEXT: [[TMP95:%.*]] = load i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST21]], align 1
// CHECK1-NEXT: [[CONV26:%.*]] = sext i8 [[TMP95]] to i32
// CHECK1-NEXT: [[ADD27:%.*]] = add nsw i32 [[CONV25]], [[CONV26]]
// CHECK1-NEXT: [[CONV28:%.*]] = trunc i32 [[ADD27]] to i8
// CHECK1-NEXT: store i8 [[CONV28]], i8* [[ATOMIC_TEMP]], align 1
// CHECK1-NEXT: [[TMP96:%.*]] = load i8, i8* [[ATOMIC_TEMP]], align 1
// CHECK1-NEXT: [[TMP97:%.*]] = cmpxchg i8* [[OMP_ARRAYCPY_DESTELEMENTPAST22]], i8 [[TMP93]], i8 [[TMP96]] monotonic monotonic, align 1
// CHECK1-NEXT: [[TMP98]] = extractvalue { i8, i1 } [[TMP97]], 0
// CHECK1-NEXT: [[TMP99:%.*]] = extractvalue { i8, i1 } [[TMP97]], 1
// CHECK1-NEXT: br i1 [[TMP99]], label [[ATOMIC_EXIT]], label [[ATOMIC_CONT]]
// CHECK1: atomic_exit:
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT29]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST22]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT30]] = getelementptr i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST21]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE31:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT29]], [[TMP91]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE31]], label [[OMP_ARRAYCPY_DONE32]], label [[OMP_ARRAYCPY_BODY20]]
// CHECK1: omp.arraycpy.done32:
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK1: .omp.reduction.default:
// CHECK1-NEXT: [[TMP100:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
// CHECK1-NEXT: call void @llvm.stackrestore(i8* [[TMP100]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.red_init.
// CHECK1-SAME: (i8* noalias [[TMP0:%.*]], i8* noalias [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to i32*
// CHECK1-NEXT: store i32 0, i32* [[TMP3]], align 8
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.red_comb.
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to i32*
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to i32*
// CHECK1-NEXT: [[TMP6:%.*]] = load i32, i32* [[TMP3]], align 8
// CHECK1-NEXT: [[TMP7:%.*]] = load i32, i32* [[TMP5]], align 8
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP6]], [[TMP7]]
// CHECK1-NEXT: store i32 [[ADD]], i32* [[TMP3]], align 8
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.red_init..1
// CHECK1-SAME: (i8* noalias [[TMP0:%.*]], i8* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = load i64, i64* @{{reduction_size[.].+[.]}}, align 8
// CHECK1-NEXT: [[TMP4:%.*]] = getelementptr i8, i8* [[TMP2]], i64 [[TMP3]]
// CHECK1-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i8* [[TMP2]], [[TMP4]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
// CHECK1: omp.arrayinit.body:
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i8* [ [[TMP2]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
// CHECK1-NEXT: store i8 0, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP4]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
// CHECK1: omp.arrayinit.done:
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.red_comb..2
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load i64, i64* @{{reduction_size[.].+[.]}}, align 8
// CHECK1-NEXT: [[TMP3:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr i8, i8* [[TMP3]], i64 [[TMP2]]
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i8* [[TMP3]], [[TMP5]]
// 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 i8* [ [[TMP4]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i8* [ [[TMP3]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK1-NEXT: [[TMP6:%.*]] = load i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK1-NEXT: [[CONV:%.*]] = sext i8 [[TMP6]] to i32
// CHECK1-NEXT: [[TMP7:%.*]] = load i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 1
// CHECK1-NEXT: [[CONV2:%.*]] = sext i8 [[TMP7]] to i32
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[CONV]], [[CONV2]]
// CHECK1-NEXT: [[CONV3:%.*]] = trunc i32 [[ADD]] to i8
// CHECK1-NEXT: store i8 [[CONV3]], i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP5]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE4]], label [[OMP_ARRAYCPY_BODY]]
// CHECK1: omp.arraycpy.done4:
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_privates_map.
// CHECK1-SAME: (%struct..kmp_privates.t* noalias [[TMP0:%.*]], i8*** noalias [[TMP1:%.*]]) #[[ATTR6:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t*, align 8
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8***, align 8
// CHECK1-NEXT: store %struct..kmp_privates.t* [[TMP0]], %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK1-NEXT: store i8*** [[TMP1]], i8**** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct..kmp_privates.t*, %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP2]], i32 0, i32 0
// CHECK1-NEXT: [[TMP4:%.*]] = load i8***, i8**** [[DOTADDR1]], align 8
// CHECK1-NEXT: store i8** [[TMP3]], i8*** [[TMP4]], align 8
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_task_entry.
// CHECK1-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK1-NEXT: [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon*, align 8
// CHECK1-NEXT: [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i8**, align 8
// CHECK1-NEXT: [[TMP_I:%.*]] = alloca i8**, align 8
// CHECK1-NEXT: [[TMP4_I:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates*, align 8
// CHECK1-NEXT: store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK1-NEXT: store %struct.kmp_task_t_with_privates* [[TMP1]], %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK1-NEXT: [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates*, %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP3]], i32 0, i32 0
// CHECK1-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon*
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES]], %struct.kmp_task_t_with_privates* [[TMP3]], i32 0, i32 1
// CHECK1-NEXT: [[TMP10:%.*]] = bitcast %struct..kmp_privates.t* [[TMP9]] to i8*
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates* [[TMP3]] to i8*
[OpenMP] Add Module metadata for OpenMP compilation This patch adds a module level metadata flag indicating that the module was compiled with the `-fopenmp` flag. This will make it easier for passes like OpenMPOpt to determine if it should be run. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D102361
2021-06-25 02:39:12 +08:00
// CHECK1-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META3:![0-9]+]])
// CHECK1-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META6:![0-9]+]])
// CHECK1-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META8:![0-9]+]])
// CHECK1-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META10:![0-9]+]])
// CHECK1-NEXT: store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !12
// CHECK1-NEXT: store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT: store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT: store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t*, i8***)* @.omp_task_privates_map. to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT: store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT: store %struct.anon* [[TMP8]], %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT: [[TMP12:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT: [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !12
// CHECK1-NEXT: [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !12
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i8***)*
// CHECK1-NEXT: call void [[TMP15]](i8* [[TMP14]], i8*** [[DOTFIRSTPRIV_PTR_ADDR_I]]) #[[ATTR5]]
[OpenMP] Add Module metadata for OpenMP compilation This patch adds a module level metadata flag indicating that the module was compiled with the `-fopenmp` flag. This will make it easier for passes like OpenMPOpt to determine if it should be run. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D102361
2021-06-25 02:39:12 +08:00
// CHECK1-NEXT: [[TMP16:%.*]] = load i8**, i8*** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !12
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_ANON:%.*]], %struct.anon* [[TMP12]], i32 0, i32 1
// CHECK1-NEXT: [[TMP18:%.*]] = load i32*, i32** [[TMP17]], align 8
// CHECK1-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP16]], align 8
[OpenMP] Add Module metadata for OpenMP compilation This patch adds a module level metadata flag indicating that the module was compiled with the `-fopenmp` flag. This will make it easier for passes like OpenMPOpt to determine if it should be run. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D102361
2021-06-25 02:39:12 +08:00
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !12
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TMP21:%.*]] = bitcast i32* [[TMP18]] to i8*
// CHECK1-NEXT: [[TMP22:%.*]] = call i8* @__kmpc_task_reduction_get_th_data(i32 [[TMP20]], i8* [[TMP19]], i8* [[TMP21]]) #[[ATTR5]]
// CHECK1-NEXT: [[CONV_I:%.*]] = bitcast i8* [[TMP22]] to i32*
// CHECK1-NEXT: [[TMP23:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP12]], i32 0, i32 2
// CHECK1-NEXT: [[TMP24:%.*]] = load i8**, i8*** [[TMP23]], align 8
// CHECK1-NEXT: [[TMP25:%.*]] = load i8*, i8** [[TMP24]], align 8
// CHECK1-NEXT: [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP12]], i32 0, i32 1
// CHECK1-NEXT: [[TMP27:%.*]] = load i32*, i32** [[TMP26]], align 8
// CHECK1-NEXT: [[TMP28:%.*]] = load i32, i32* [[TMP27]], align 4
// CHECK1-NEXT: [[TMP29:%.*]] = sext i32 [[TMP28]] to i64
// CHECK1-NEXT: [[LB_ADD_LEN_I:%.*]] = add nsw i64 -1, [[TMP29]]
// CHECK1-NEXT: [[TMP30:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP12]], i32 0, i32 2
// CHECK1-NEXT: [[TMP31:%.*]] = load i8**, i8*** [[TMP30]], align 8
// CHECK1-NEXT: [[ARRAYIDX2_I:%.*]] = getelementptr inbounds i8*, i8** [[TMP31]], i64 9
// CHECK1-NEXT: [[TMP32:%.*]] = load i8*, i8** [[ARRAYIDX2_I]], align 8
// CHECK1-NEXT: [[ARRAYIDX3_I:%.*]] = getelementptr inbounds i8, i8* [[TMP32]], i64 [[LB_ADD_LEN_I]]
// CHECK1-NEXT: [[TMP33:%.*]] = ptrtoint i8* [[ARRAYIDX3_I]] to i64
// CHECK1-NEXT: [[TMP34:%.*]] = ptrtoint i8* [[TMP25]] to i64
// CHECK1-NEXT: [[TMP35:%.*]] = sub i64 [[TMP33]], [[TMP34]]
// CHECK1-NEXT: [[TMP36:%.*]] = sdiv exact i64 [[TMP35]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK1-NEXT: [[TMP37:%.*]] = add nuw i64 [[TMP36]], 1
// CHECK1-NEXT: [[TMP38:%.*]] = mul nuw i64 [[TMP37]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK1-NEXT: store i64 [[TMP37]], i64* @{{reduction_size[.].+[.]}}, align 8
// CHECK1-NEXT: [[TMP39:%.*]] = load i8*, i8** [[TMP16]], align 8
// CHECK1-NEXT: [[TMP40:%.*]] = call i8* @__kmpc_task_reduction_get_th_data(i32 [[TMP20]], i8* [[TMP39]], i8* [[TMP25]]) #[[ATTR5]]
// CHECK1-NEXT: [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP12]], i32 0, i32 2
// CHECK1-NEXT: [[TMP42:%.*]] = load i8**, i8*** [[TMP41]], align 8
// CHECK1-NEXT: [[TMP43:%.*]] = load i8*, i8** [[TMP42]], align 8
// CHECK1-NEXT: [[TMP44:%.*]] = ptrtoint i8* [[TMP43]] to i64
// CHECK1-NEXT: [[TMP45:%.*]] = ptrtoint i8* [[TMP25]] to i64
// CHECK1-NEXT: [[TMP46:%.*]] = sub i64 [[TMP44]], [[TMP45]]
// CHECK1-NEXT: [[TMP47:%.*]] = sdiv exact i64 [[TMP46]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK1-NEXT: [[TMP48:%.*]] = getelementptr i8, i8* [[TMP40]], i64 [[TMP47]]
[OpenMP] Add Module metadata for OpenMP compilation This patch adds a module level metadata flag indicating that the module was compiled with the `-fopenmp` flag. This will make it easier for passes like OpenMPOpt to determine if it should be run. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D102361
2021-06-25 02:39:12 +08:00
// CHECK1-NEXT: store i8** [[TMP4_I]], i8*** [[TMP_I]], align 8, !noalias !12
// CHECK1-NEXT: store i8* [[TMP48]], i8** [[TMP4_I]], align 8, !noalias !12
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
// CHECK1-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [3 x i8*]*
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [3 x i8*]*
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP5]], i64 0, i64 0
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 0
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP5]], i64 0, i64 1
// CHECK1-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
// CHECK1-NEXT: [[TMP14:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 1
// CHECK1-NEXT: [[TMP15:%.*]] = load i8*, i8** [[TMP14]], align 8
// CHECK1-NEXT: [[TMP16:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 2
// CHECK1-NEXT: [[TMP17:%.*]] = load i8*, i8** [[TMP16]], align 8
// CHECK1-NEXT: [[TMP18:%.*]] = ptrtoint i8* [[TMP17]] to i64
// CHECK1-NEXT: [[TMP19:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK1-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP8]], align 4
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP19]], [[TMP20]]
// CHECK1-NEXT: store i32 [[ADD]], i32* [[TMP11]], align 4
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr i8, i8* [[TMP15]], i64 [[TMP18]]
// CHECK1-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i8* [[TMP15]], [[TMP21]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE5:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK1: omp.arraycpy.body:
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i8* [ [[TMP13]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK1-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i8* [ [[TMP15]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK1-NEXT: [[TMP22:%.*]] = load i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK1-NEXT: [[CONV:%.*]] = sext i8 [[TMP22]] to i32
// CHECK1-NEXT: [[TMP23:%.*]] = load i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 1
// CHECK1-NEXT: [[CONV2:%.*]] = sext i8 [[TMP23]] to i32
// CHECK1-NEXT: [[ADD3:%.*]] = add nsw i32 [[CONV]], [[CONV2]]
// CHECK1-NEXT: [[CONV4:%.*]] = trunc i32 [[ADD3]] to i8
// CHECK1-NEXT: store i8 [[CONV4]], i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK1-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP21]]
// CHECK1-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE5]], label [[OMP_ARRAYCPY_BODY]]
// CHECK1: omp.arraycpy.done5:
// CHECK1-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@main
// CHECK2-SAME: (i32 [[ARGC:%.*]], i8** [[ARGV:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[ARGC_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[ARGV_ADDR:%.*]] = alloca i8**, align 8
// CHECK2-NEXT: store i32 [[ARGC]], i32* [[ARGC_ADDR]], align 4
// CHECK2-NEXT: store i8** [[ARGV]], i8*** [[ARGV_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK2-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l14(i32* [[ARGC_ADDR]], i8** [[TMP0]]) #[[ATTR5:[0-9]+]]
// CHECK2-NEXT: ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l14
// CHECK2-SAME: (i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i8** [[ARGV:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[ARGC_ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[ARGV_ADDR:%.*]] = alloca i8**, align 8
// CHECK2-NEXT: store i32* [[ARGC]], i32** [[ARGC_ADDR]], align 8
// CHECK2-NEXT: store i8** [[ARGV]], i8*** [[ARGV_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load i32*, i32** [[ARGC_ADDR]], align 8
// CHECK2-NEXT: [[TMP1:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*, i8**)* @.omp_outlined. to void (i32*, i32*, ...)*), i32* [[TMP0]], i8** [[TMP1]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined.
// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i8** [[ARGV:%.*]]) #[[ATTR1]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[ARGC_ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[ARGV_ADDR:%.*]] = alloca i8**, align 8
// CHECK2-NEXT: [[ARGC1:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[SAVED_STACK:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[TMP:%.*]] = alloca i8**, align 8
// CHECK2-NEXT: [[_TMP5:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[DOTRD_INPUT_:%.*]] = alloca [2 x %struct.kmp_taskred_input_t], align 8
// CHECK2-NEXT: [[DOTTASK_RED_:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 8
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [3 x i8*], align 8
// CHECK2-NEXT: [[ATOMIC_TEMP:%.*]] = alloca i8, align 1
// CHECK2-NEXT: [[_TMP24:%.*]] = alloca i8, align 1
// 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 i32* [[ARGC]], i32** [[ARGC_ADDR]], align 8
// CHECK2-NEXT: store i8** [[ARGV]], i8*** [[ARGV_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load i32*, i32** [[ARGC_ADDR]], align 8
// CHECK2-NEXT: store i32 0, i32* [[ARGC1]], align 4
// CHECK2-NEXT: [[TMP1:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8*, i8** [[TMP1]], i64 0
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[ARRAYIDX]], align 8
// CHECK2-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i8, i8* [[TMP2]], i64 0
// CHECK2-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK2-NEXT: [[TMP4:%.*]] = sext i32 [[TMP3]] to i64
// CHECK2-NEXT: [[LB_ADD_LEN:%.*]] = add nsw i64 -1, [[TMP4]]
// CHECK2-NEXT: [[TMP5:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK2-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i8*, i8** [[TMP5]], i64 9
// CHECK2-NEXT: [[TMP6:%.*]] = load i8*, i8** [[ARRAYIDX3]], align 8
// CHECK2-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i8, i8* [[TMP6]], i64 [[LB_ADD_LEN]]
// CHECK2-NEXT: [[TMP7:%.*]] = ptrtoint i8* [[ARRAYIDX4]] to i64
// CHECK2-NEXT: [[TMP8:%.*]] = ptrtoint i8* [[ARRAYIDX2]] to i64
// CHECK2-NEXT: [[TMP9:%.*]] = sub i64 [[TMP7]], [[TMP8]]
// CHECK2-NEXT: [[TMP10:%.*]] = sdiv exact i64 [[TMP9]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK2-NEXT: [[TMP11:%.*]] = add nuw i64 [[TMP10]], 1
// CHECK2-NEXT: [[TMP12:%.*]] = mul nuw i64 [[TMP11]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK2-NEXT: [[TMP13:%.*]] = call i8* @llvm.stacksave()
// CHECK2-NEXT: store i8* [[TMP13]], i8** [[SAVED_STACK]], align 8
// CHECK2-NEXT: [[VLA:%.*]] = alloca i8, i64 [[TMP11]], align 16
// CHECK2-NEXT: store i64 [[TMP11]], i64* [[__VLA_EXPR0]], align 8
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr i8, i8* [[VLA]], i64 [[TMP11]]
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i8* [[VLA]], [[TMP14]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
// CHECK2: omp.arrayinit.body:
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i8* [ [[VLA]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
// CHECK2-NEXT: store i8 0, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP14]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
// CHECK2: omp.arrayinit.done:
// CHECK2-NEXT: [[TMP15:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK2-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
// CHECK2-NEXT: [[TMP17:%.*]] = ptrtoint i8* [[TMP16]] to i64
// CHECK2-NEXT: [[TMP18:%.*]] = ptrtoint i8* [[ARRAYIDX2]] to i64
// CHECK2-NEXT: [[TMP19:%.*]] = sub i64 [[TMP17]], [[TMP18]]
// CHECK2-NEXT: [[TMP20:%.*]] = sdiv exact i64 [[TMP19]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr i8, i8* [[VLA]], i64 [[TMP20]]
// CHECK2-NEXT: store i8** [[_TMP5]], i8*** [[TMP]], align 8
// CHECK2-NEXT: store i8* [[TMP21]], i8** [[_TMP5]], align 8
// CHECK2-NEXT: [[DOTRD_INPUT_GEP_:%.*]] = getelementptr inbounds [2 x %struct.kmp_taskred_input_t], [2 x %struct.kmp_taskred_input_t]* [[DOTRD_INPUT_]], i64 0, i64 0
// CHECK2-NEXT: [[TMP22:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T:%.*]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 0
// CHECK2-NEXT: [[TMP23:%.*]] = bitcast i32* [[ARGC1]] to i8*
// CHECK2-NEXT: store i8* [[TMP23]], i8** [[TMP22]], align 8
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 1
// CHECK2-NEXT: [[TMP25:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK2-NEXT: store i8* [[TMP25]], i8** [[TMP24]], align 8
// CHECK2-NEXT: [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 2
// CHECK2-NEXT: store i64 4, i64* [[TMP26]], align 8
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 3
// CHECK2-NEXT: store i8* bitcast (void (i8*, i8*)* @.red_init. to i8*), i8** [[TMP27]], align 8
// CHECK2-NEXT: [[TMP28:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 4
// CHECK2-NEXT: store i8* null, i8** [[TMP28]], align 8
// CHECK2-NEXT: [[TMP29:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 5
// CHECK2-NEXT: store i8* bitcast (void (i8*, i8*)* @.red_comb. to i8*), i8** [[TMP29]], align 8
// CHECK2-NEXT: [[TMP30:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_]], i32 0, i32 6
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast i32* [[TMP30]] to i8*
// CHECK2-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[TMP31]], i8 0, i64 4, i1 false)
// CHECK2-NEXT: [[DOTRD_INPUT_GEP_6:%.*]] = getelementptr inbounds [2 x %struct.kmp_taskred_input_t], [2 x %struct.kmp_taskred_input_t]* [[DOTRD_INPUT_]], i64 0, i64 1
// CHECK2-NEXT: [[TMP32:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 0
// CHECK2-NEXT: [[TMP33:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK2-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds i8*, i8** [[TMP33]], i64 0
// CHECK2-NEXT: [[TMP34:%.*]] = load i8*, i8** [[ARRAYIDX7]], align 8
// CHECK2-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds i8, i8* [[TMP34]], i64 0
// CHECK2-NEXT: [[TMP35:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK2-NEXT: [[TMP36:%.*]] = sext i32 [[TMP35]] to i64
// CHECK2-NEXT: [[LB_ADD_LEN9:%.*]] = add nsw i64 -1, [[TMP36]]
// CHECK2-NEXT: [[TMP37:%.*]] = load i8**, i8*** [[ARGV_ADDR]], align 8
// CHECK2-NEXT: [[ARRAYIDX10:%.*]] = getelementptr inbounds i8*, i8** [[TMP37]], i64 9
// CHECK2-NEXT: [[TMP38:%.*]] = load i8*, i8** [[ARRAYIDX10]], align 8
// CHECK2-NEXT: [[ARRAYIDX11:%.*]] = getelementptr inbounds i8, i8* [[TMP38]], i64 [[LB_ADD_LEN9]]
// CHECK2-NEXT: store i8* [[VLA]], i8** [[TMP32]], align 8
// CHECK2-NEXT: [[TMP39:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 1
// CHECK2-NEXT: store i8* [[ARRAYIDX8]], i8** [[TMP39]], align 8
// CHECK2-NEXT: [[TMP40:%.*]] = ptrtoint i8* [[ARRAYIDX11]] to i64
// CHECK2-NEXT: [[TMP41:%.*]] = ptrtoint i8* [[ARRAYIDX8]] to i64
// CHECK2-NEXT: [[TMP42:%.*]] = sub i64 [[TMP40]], [[TMP41]]
// CHECK2-NEXT: [[TMP43:%.*]] = sdiv exact i64 [[TMP42]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK2-NEXT: [[TMP44:%.*]] = add nuw i64 [[TMP43]], 1
// CHECK2-NEXT: [[TMP45:%.*]] = mul nuw i64 [[TMP44]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK2-NEXT: [[TMP46:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 2
// CHECK2-NEXT: store i64 [[TMP45]], i64* [[TMP46]], align 8
// CHECK2-NEXT: [[TMP47:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 3
// CHECK2-NEXT: store i8* bitcast (void (i8*, i8*)* @.red_init..1 to i8*), i8** [[TMP47]], align 8
// CHECK2-NEXT: [[TMP48:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 4
// CHECK2-NEXT: store i8* null, i8** [[TMP48]], align 8
// CHECK2-NEXT: [[TMP49:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 5
// CHECK2-NEXT: store i8* bitcast (void (i8*, i8*)* @.red_comb..2 to i8*), i8** [[TMP49]], align 8
// CHECK2-NEXT: [[TMP50:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASKRED_INPUT_T]], %struct.kmp_taskred_input_t* [[DOTRD_INPUT_GEP_6]], i32 0, i32 6
// CHECK2-NEXT: store i32 1, i32* [[TMP50]], align 8
// CHECK2-NEXT: [[TMP51:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP52:%.*]] = load i32, i32* [[TMP51]], align 4
// CHECK2-NEXT: [[TMP53:%.*]] = bitcast [2 x %struct.kmp_taskred_input_t]* [[DOTRD_INPUT_]] to i8*
// CHECK2-NEXT: [[TMP54:%.*]] = call i8* @__kmpc_taskred_modifier_init(%struct.ident_t* @[[GLOB1]], i32 [[TMP52]], i32 0, i32 2, i8* [[TMP53]])
// CHECK2-NEXT: store i8* [[TMP54]], i8** [[DOTTASK_RED_]], align 8
// CHECK2-NEXT: [[TMP55:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 0
// CHECK2-NEXT: store i8** [[DOTTASK_RED_]], i8*** [[TMP55]], align 8
// CHECK2-NEXT: [[TMP56:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 1
// CHECK2-NEXT: store i32* [[ARGC1]], i32** [[TMP56]], align 8
// CHECK2-NEXT: [[TMP57:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[AGG_CAPTURED]], i32 0, i32 2
// CHECK2-NEXT: [[TMP58:%.*]] = load i8**, i8*** [[TMP]], align 8
// CHECK2-NEXT: store i8** [[TMP58]], i8*** [[TMP57]], align 8
// CHECK2-NEXT: [[TMP59:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP60:%.*]] = load i32, i32* [[TMP59]], align 4
// CHECK2-NEXT: [[TMP61:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP60]], i32 1, i64 48, i64 24, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*))
// CHECK2-NEXT: [[TMP62:%.*]] = bitcast i8* [[TMP61]] to %struct.kmp_task_t_with_privates*
// CHECK2-NEXT: [[TMP63:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP62]], i32 0, i32 0
// CHECK2-NEXT: [[TMP64:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP63]], i32 0, i32 0
// CHECK2-NEXT: [[TMP65:%.*]] = load i8*, i8** [[TMP64]], align 8
// CHECK2-NEXT: [[TMP66:%.*]] = bitcast %struct.anon* [[AGG_CAPTURED]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[TMP65]], i8* align 8 [[TMP66]], i64 24, i1 false)
// CHECK2-NEXT: [[TMP67:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES]], %struct.kmp_task_t_with_privates* [[TMP62]], i32 0, i32 1
// CHECK2-NEXT: [[TMP68:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP67]], i32 0, i32 0
// CHECK2-NEXT: [[TMP69:%.*]] = load i8*, i8** [[DOTTASK_RED_]], align 8
// CHECK2-NEXT: store i8* [[TMP69]], i8** [[TMP68]], align 8
// CHECK2-NEXT: [[TMP70:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP71:%.*]] = load i32, i32* [[TMP70]], align 4
// CHECK2-NEXT: [[TMP72:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP71]], i8* [[TMP61]])
// CHECK2-NEXT: [[TMP73:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP74:%.*]] = load i32, i32* [[TMP73]], align 4
// CHECK2-NEXT: call void @__kmpc_task_reduction_modifier_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP74]], i32 0)
// CHECK2-NEXT: [[TMP75:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
// CHECK2-NEXT: [[TMP76:%.*]] = bitcast i32* [[ARGC1]] to i8*
// CHECK2-NEXT: store i8* [[TMP76]], i8** [[TMP75]], align 8
// CHECK2-NEXT: [[TMP77:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
// CHECK2-NEXT: store i8* [[VLA]], i8** [[TMP77]], align 8
// CHECK2-NEXT: [[TMP78:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
// CHECK2-NEXT: [[TMP79:%.*]] = inttoptr i64 [[TMP11]] to i8*
// CHECK2-NEXT: store i8* [[TMP79]], i8** [[TMP78]], align 8
// CHECK2-NEXT: [[TMP80:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP81:%.*]] = load i32, i32* [[TMP80]], align 4
// CHECK2-NEXT: [[TMP82:%.*]] = bitcast [3 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
// CHECK2-NEXT: [[TMP83:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP81]], i32 2, i64 24, i8* [[TMP82]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
// CHECK2-NEXT: switch i32 [[TMP83]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
// CHECK2-NEXT: ]
// CHECK2: .omp.reduction.case1:
// CHECK2-NEXT: [[TMP84:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK2-NEXT: [[TMP85:%.*]] = load i32, i32* [[ARGC1]], align 4
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP84]], [[TMP85]]
// CHECK2-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
// CHECK2-NEXT: [[TMP86:%.*]] = getelementptr i8, i8* [[ARRAYIDX2]], i64 [[TMP11]]
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i8* [[ARRAYIDX2]], [[TMP86]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE18:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK2: omp.arraycpy.body:
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i8* [ [[VLA]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST12:%.*]] = phi i8* [ [[ARRAYIDX2]], [[DOTOMP_REDUCTION_CASE1]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT16:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK2-NEXT: [[TMP87:%.*]] = load i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST12]], align 1
// CHECK2-NEXT: [[CONV:%.*]] = sext i8 [[TMP87]] to i32
// CHECK2-NEXT: [[TMP88:%.*]] = load i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 1
// CHECK2-NEXT: [[CONV13:%.*]] = sext i8 [[TMP88]] to i32
// CHECK2-NEXT: [[ADD14:%.*]] = add nsw i32 [[CONV]], [[CONV13]]
// CHECK2-NEXT: [[CONV15:%.*]] = trunc i32 [[ADD14]] to i8
// CHECK2-NEXT: store i8 [[CONV15]], i8* [[OMP_ARRAYCPY_DESTELEMENTPAST12]], align 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT16]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST12]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE17:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT16]], [[TMP86]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE17]], label [[OMP_ARRAYCPY_DONE18]], label [[OMP_ARRAYCPY_BODY]]
// CHECK2: omp.arraycpy.done18:
// CHECK2-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP81]], [8 x i32]* @.gomp_critical_user_.reduction.var)
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK2: .omp.reduction.case2:
// CHECK2-NEXT: [[TMP89:%.*]] = load i32, i32* [[ARGC1]], align 4
// CHECK2-NEXT: [[TMP90:%.*]] = atomicrmw add i32* [[TMP0]], i32 [[TMP89]] monotonic, align 4
// CHECK2-NEXT: [[TMP91:%.*]] = getelementptr i8, i8* [[ARRAYIDX2]], i64 [[TMP11]]
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY19:%.*]] = icmp eq i8* [[ARRAYIDX2]], [[TMP91]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY19]], label [[OMP_ARRAYCPY_DONE32:%.*]], label [[OMP_ARRAYCPY_BODY20:%.*]]
// CHECK2: omp.arraycpy.body20:
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST21:%.*]] = phi i8* [ [[VLA]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT30:%.*]], [[ATOMIC_EXIT:%.*]] ]
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST22:%.*]] = phi i8* [ [[ARRAYIDX2]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT29:%.*]], [[ATOMIC_EXIT]] ]
// CHECK2-NEXT: [[TMP92:%.*]] = load i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST21]], align 1
// CHECK2-NEXT: [[CONV23:%.*]] = sext i8 [[TMP92]] to i32
// CHECK2-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST22]] monotonic, align 1
// CHECK2-NEXT: br label [[ATOMIC_CONT:%.*]]
// CHECK2: atomic_cont:
// CHECK2-NEXT: [[TMP93:%.*]] = phi i8 [ [[ATOMIC_LOAD]], [[OMP_ARRAYCPY_BODY20]] ], [ [[TMP98:%.*]], [[ATOMIC_CONT]] ]
// CHECK2-NEXT: store i8 [[TMP93]], i8* [[_TMP24]], align 1
// CHECK2-NEXT: [[TMP94:%.*]] = load i8, i8* [[_TMP24]], align 1
// CHECK2-NEXT: [[CONV25:%.*]] = sext i8 [[TMP94]] to i32
// CHECK2-NEXT: [[TMP95:%.*]] = load i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST21]], align 1
// CHECK2-NEXT: [[CONV26:%.*]] = sext i8 [[TMP95]] to i32
// CHECK2-NEXT: [[ADD27:%.*]] = add nsw i32 [[CONV25]], [[CONV26]]
// CHECK2-NEXT: [[CONV28:%.*]] = trunc i32 [[ADD27]] to i8
// CHECK2-NEXT: store i8 [[CONV28]], i8* [[ATOMIC_TEMP]], align 1
// CHECK2-NEXT: [[TMP96:%.*]] = load i8, i8* [[ATOMIC_TEMP]], align 1
// CHECK2-NEXT: [[TMP97:%.*]] = cmpxchg i8* [[OMP_ARRAYCPY_DESTELEMENTPAST22]], i8 [[TMP93]], i8 [[TMP96]] monotonic monotonic, align 1
// CHECK2-NEXT: [[TMP98]] = extractvalue { i8, i1 } [[TMP97]], 0
// CHECK2-NEXT: [[TMP99:%.*]] = extractvalue { i8, i1 } [[TMP97]], 1
// CHECK2-NEXT: br i1 [[TMP99]], label [[ATOMIC_EXIT]], label [[ATOMIC_CONT]]
// CHECK2: atomic_exit:
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT29]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST22]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT30]] = getelementptr i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST21]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE31:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT29]], [[TMP91]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE31]], label [[OMP_ARRAYCPY_DONE32]], label [[OMP_ARRAYCPY_BODY20]]
// CHECK2: omp.arraycpy.done32:
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK2: .omp.reduction.default:
// CHECK2-NEXT: [[TMP100:%.*]] = load i8*, i8** [[SAVED_STACK]], align 8
// CHECK2-NEXT: call void @llvm.stackrestore(i8* [[TMP100]])
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.red_init.
// CHECK2-SAME: (i8* noalias [[TMP0:%.*]], i8* noalias [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to i32*
// CHECK2-NEXT: store i32 0, i32* [[TMP3]], align 8
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.red_comb.
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to i32*
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to i32*
// CHECK2-NEXT: [[TMP6:%.*]] = load i32, i32* [[TMP3]], align 8
// CHECK2-NEXT: [[TMP7:%.*]] = load i32, i32* [[TMP5]], align 8
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP6]], [[TMP7]]
// CHECK2-NEXT: store i32 [[ADD]], i32* [[TMP3]], align 8
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.red_init..1
// CHECK2-SAME: (i8* noalias [[TMP0:%.*]], i8* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK2-NEXT: [[TMP3:%.*]] = load i64, i64* @{{reduction_size[.].+[.]}}, align 8
// CHECK2-NEXT: [[TMP4:%.*]] = getelementptr i8, i8* [[TMP2]], i64 [[TMP3]]
// CHECK2-NEXT: [[OMP_ARRAYINIT_ISEMPTY:%.*]] = icmp eq i8* [[TMP2]], [[TMP4]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYINIT_ISEMPTY]], label [[OMP_ARRAYINIT_DONE:%.*]], label [[OMP_ARRAYINIT_BODY:%.*]]
// CHECK2: omp.arrayinit.body:
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i8* [ [[TMP2]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYINIT_BODY]] ]
// CHECK2-NEXT: store i8 0, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP4]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYINIT_DONE]], label [[OMP_ARRAYINIT_BODY]]
// CHECK2: omp.arrayinit.done:
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.red_comb..2
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load i64, i64* @{{reduction_size[.].+[.]}}, align 8
// CHECK2-NEXT: [[TMP3:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr i8, i8* [[TMP3]], i64 [[TMP2]]
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i8* [[TMP3]], [[TMP5]]
// 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 i8* [ [[TMP4]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i8* [ [[TMP3]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK2-NEXT: [[TMP6:%.*]] = load i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK2-NEXT: [[CONV:%.*]] = sext i8 [[TMP6]] to i32
// CHECK2-NEXT: [[TMP7:%.*]] = load i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 1
// CHECK2-NEXT: [[CONV2:%.*]] = sext i8 [[TMP7]] to i32
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[CONV]], [[CONV2]]
// CHECK2-NEXT: [[CONV3:%.*]] = trunc i32 [[ADD]] to i8
// CHECK2-NEXT: store i8 [[CONV3]], i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP5]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE4]], label [[OMP_ARRAYCPY_BODY]]
// CHECK2: omp.arraycpy.done4:
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_privates_map.
// CHECK2-SAME: (%struct..kmp_privates.t* noalias [[TMP0:%.*]], i8*** noalias [[TMP1:%.*]]) #[[ATTR6:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t*, align 8
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8***, align 8
// CHECK2-NEXT: store %struct..kmp_privates.t* [[TMP0]], %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK2-NEXT: store i8*** [[TMP1]], i8**** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct..kmp_privates.t*, %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK2-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP2]], i32 0, i32 0
// CHECK2-NEXT: [[TMP4:%.*]] = load i8***, i8**** [[DOTADDR1]], align 8
// CHECK2-NEXT: store i8** [[TMP3]], i8*** [[TMP4]], align 8
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_task_entry.
// CHECK2-SAME: (i32 [[TMP0:%.*]], %struct.kmp_task_t_with_privates* noalias [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK2-NEXT: [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon*, align 8
// CHECK2-NEXT: [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i8**, align 8
// CHECK2-NEXT: [[TMP_I:%.*]] = alloca i8**, align 8
// CHECK2-NEXT: [[TMP4_I:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates*, align 8
// CHECK2-NEXT: store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK2-NEXT: store %struct.kmp_task_t_with_privates* [[TMP1]], %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK2-NEXT: [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates*, %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP3]], i32 0, i32 0
// CHECK2-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon*
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES]], %struct.kmp_task_t_with_privates* [[TMP3]], i32 0, i32 1
// CHECK2-NEXT: [[TMP10:%.*]] = bitcast %struct..kmp_privates.t* [[TMP9]] to i8*
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates* [[TMP3]] to i8*
[OpenMP] Add Module metadata for OpenMP compilation This patch adds a module level metadata flag indicating that the module was compiled with the `-fopenmp` flag. This will make it easier for passes like OpenMPOpt to determine if it should be run. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D102361
2021-06-25 02:39:12 +08:00
// CHECK2-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META3:![0-9]+]])
// CHECK2-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META6:![0-9]+]])
// CHECK2-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META8:![0-9]+]])
// CHECK2-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META10:![0-9]+]])
// CHECK2-NEXT: store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !12
// CHECK2-NEXT: store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT: store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT: store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t*, i8***)* @.omp_task_privates_map. to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT: store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT: store %struct.anon* [[TMP8]], %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT: [[TMP12:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT: [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !12
// CHECK2-NEXT: [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !12
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i8***)*
// CHECK2-NEXT: call void [[TMP15]](i8* [[TMP14]], i8*** [[DOTFIRSTPRIV_PTR_ADDR_I]]) #[[ATTR5]]
[OpenMP] Add Module metadata for OpenMP compilation This patch adds a module level metadata flag indicating that the module was compiled with the `-fopenmp` flag. This will make it easier for passes like OpenMPOpt to determine if it should be run. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D102361
2021-06-25 02:39:12 +08:00
// CHECK2-NEXT: [[TMP16:%.*]] = load i8**, i8*** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !12
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TMP17:%.*]] = getelementptr inbounds [[STRUCT_ANON:%.*]], %struct.anon* [[TMP12]], i32 0, i32 1
// CHECK2-NEXT: [[TMP18:%.*]] = load i32*, i32** [[TMP17]], align 8
// CHECK2-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP16]], align 8
[OpenMP] Add Module metadata for OpenMP compilation This patch adds a module level metadata flag indicating that the module was compiled with the `-fopenmp` flag. This will make it easier for passes like OpenMPOpt to determine if it should be run. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D102361
2021-06-25 02:39:12 +08:00
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !12
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TMP21:%.*]] = bitcast i32* [[TMP18]] to i8*
// CHECK2-NEXT: [[TMP22:%.*]] = call i8* @__kmpc_task_reduction_get_th_data(i32 [[TMP20]], i8* [[TMP19]], i8* [[TMP21]]) #[[ATTR5]]
// CHECK2-NEXT: [[CONV_I:%.*]] = bitcast i8* [[TMP22]] to i32*
// CHECK2-NEXT: [[TMP23:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP12]], i32 0, i32 2
// CHECK2-NEXT: [[TMP24:%.*]] = load i8**, i8*** [[TMP23]], align 8
// CHECK2-NEXT: [[TMP25:%.*]] = load i8*, i8** [[TMP24]], align 8
// CHECK2-NEXT: [[TMP26:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP12]], i32 0, i32 1
// CHECK2-NEXT: [[TMP27:%.*]] = load i32*, i32** [[TMP26]], align 8
// CHECK2-NEXT: [[TMP28:%.*]] = load i32, i32* [[TMP27]], align 4
// CHECK2-NEXT: [[TMP29:%.*]] = sext i32 [[TMP28]] to i64
// CHECK2-NEXT: [[LB_ADD_LEN_I:%.*]] = add nsw i64 -1, [[TMP29]]
// CHECK2-NEXT: [[TMP30:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP12]], i32 0, i32 2
// CHECK2-NEXT: [[TMP31:%.*]] = load i8**, i8*** [[TMP30]], align 8
// CHECK2-NEXT: [[ARRAYIDX2_I:%.*]] = getelementptr inbounds i8*, i8** [[TMP31]], i64 9
// CHECK2-NEXT: [[TMP32:%.*]] = load i8*, i8** [[ARRAYIDX2_I]], align 8
// CHECK2-NEXT: [[ARRAYIDX3_I:%.*]] = getelementptr inbounds i8, i8* [[TMP32]], i64 [[LB_ADD_LEN_I]]
// CHECK2-NEXT: [[TMP33:%.*]] = ptrtoint i8* [[ARRAYIDX3_I]] to i64
// CHECK2-NEXT: [[TMP34:%.*]] = ptrtoint i8* [[TMP25]] to i64
// CHECK2-NEXT: [[TMP35:%.*]] = sub i64 [[TMP33]], [[TMP34]]
// CHECK2-NEXT: [[TMP36:%.*]] = sdiv exact i64 [[TMP35]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK2-NEXT: [[TMP37:%.*]] = add nuw i64 [[TMP36]], 1
// CHECK2-NEXT: [[TMP38:%.*]] = mul nuw i64 [[TMP37]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK2-NEXT: store i64 [[TMP37]], i64* @{{reduction_size[.].+[.]}}, align 8
// CHECK2-NEXT: [[TMP39:%.*]] = load i8*, i8** [[TMP16]], align 8
// CHECK2-NEXT: [[TMP40:%.*]] = call i8* @__kmpc_task_reduction_get_th_data(i32 [[TMP20]], i8* [[TMP39]], i8* [[TMP25]]) #[[ATTR5]]
// CHECK2-NEXT: [[TMP41:%.*]] = getelementptr inbounds [[STRUCT_ANON]], %struct.anon* [[TMP12]], i32 0, i32 2
// CHECK2-NEXT: [[TMP42:%.*]] = load i8**, i8*** [[TMP41]], align 8
// CHECK2-NEXT: [[TMP43:%.*]] = load i8*, i8** [[TMP42]], align 8
// CHECK2-NEXT: [[TMP44:%.*]] = ptrtoint i8* [[TMP43]] to i64
// CHECK2-NEXT: [[TMP45:%.*]] = ptrtoint i8* [[TMP25]] to i64
// CHECK2-NEXT: [[TMP46:%.*]] = sub i64 [[TMP44]], [[TMP45]]
// CHECK2-NEXT: [[TMP47:%.*]] = sdiv exact i64 [[TMP46]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CHECK2-NEXT: [[TMP48:%.*]] = getelementptr i8, i8* [[TMP40]], i64 [[TMP47]]
[OpenMP] Add Module metadata for OpenMP compilation This patch adds a module level metadata flag indicating that the module was compiled with the `-fopenmp` flag. This will make it easier for passes like OpenMPOpt to determine if it should be run. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D102361
2021-06-25 02:39:12 +08:00
// CHECK2-NEXT: store i8** [[TMP4_I]], i8*** [[TMP_I]], align 8, !noalias !12
// CHECK2-NEXT: store i8* [[TMP48]], i8** [[TMP4_I]], align 8, !noalias !12
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
// CHECK2-SAME: (i8* [[TMP0:%.*]], i8* [[TMP1:%.*]]) #[[ATTR3]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [3 x i8*]*
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [3 x i8*]*
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP5]], i64 0, i64 0
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 0
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP5]], i64 0, i64 1
// CHECK2-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
// CHECK2-NEXT: [[TMP14:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 1
// CHECK2-NEXT: [[TMP15:%.*]] = load i8*, i8** [[TMP14]], align 8
// CHECK2-NEXT: [[TMP16:%.*]] = getelementptr inbounds [3 x i8*], [3 x i8*]* [[TMP3]], i64 0, i64 2
// CHECK2-NEXT: [[TMP17:%.*]] = load i8*, i8** [[TMP16]], align 8
// CHECK2-NEXT: [[TMP18:%.*]] = ptrtoint i8* [[TMP17]] to i64
// CHECK2-NEXT: [[TMP19:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK2-NEXT: [[TMP20:%.*]] = load i32, i32* [[TMP8]], align 4
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP19]], [[TMP20]]
// CHECK2-NEXT: store i32 [[ADD]], i32* [[TMP11]], align 4
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr i8, i8* [[TMP15]], i64 [[TMP18]]
// CHECK2-NEXT: [[OMP_ARRAYCPY_ISEMPTY:%.*]] = icmp eq i8* [[TMP15]], [[TMP21]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_ISEMPTY]], label [[OMP_ARRAYCPY_DONE5:%.*]], label [[OMP_ARRAYCPY_BODY:%.*]]
// CHECK2: omp.arraycpy.body:
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRCELEMENTPAST:%.*]] = phi i8* [ [[TMP13]], [[ENTRY:%.*]] ], [ [[OMP_ARRAYCPY_SRC_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK2-NEXT: [[OMP_ARRAYCPY_DESTELEMENTPAST:%.*]] = phi i8* [ [[TMP15]], [[ENTRY]] ], [ [[OMP_ARRAYCPY_DEST_ELEMENT:%.*]], [[OMP_ARRAYCPY_BODY]] ]
// CHECK2-NEXT: [[TMP22:%.*]] = load i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK2-NEXT: [[CONV:%.*]] = sext i8 [[TMP22]] to i32
// CHECK2-NEXT: [[TMP23:%.*]] = load i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], align 1
// CHECK2-NEXT: [[CONV2:%.*]] = sext i8 [[TMP23]] to i32
// CHECK2-NEXT: [[ADD3:%.*]] = add nsw i32 [[CONV]], [[CONV2]]
// CHECK2-NEXT: [[CONV4:%.*]] = trunc i32 [[ADD3]] to i8
// CHECK2-NEXT: store i8 [[CONV4]], i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], align 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DEST_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_DESTELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_SRC_ELEMENT]] = getelementptr i8, i8* [[OMP_ARRAYCPY_SRCELEMENTPAST]], i32 1
// CHECK2-NEXT: [[OMP_ARRAYCPY_DONE:%.*]] = icmp eq i8* [[OMP_ARRAYCPY_DEST_ELEMENT]], [[TMP21]]
// CHECK2-NEXT: br i1 [[OMP_ARRAYCPY_DONE]], label [[OMP_ARRAYCPY_DONE5]], label [[OMP_ARRAYCPY_BODY]]
// CHECK2: omp.arraycpy.done5:
// CHECK2-NEXT: ret void
//