shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/clang/test/OpenMP/parallel_codegen.cpp
Tom Eccles f7daa9d302
[mlir][OpenMP] fix crash outlining infinite loop (#129872) 
Previously an extra block was created by splitting the previous exit
block. This produced incorrect results when the outlined region
statically never terminated because then there wouldn't be a valid exit
block for the outlined region, this caused this newly added block to
have an incoming edge from outside of the outlining region, which caused
outlining to fail.

So far as I can tell this extra block no longer serves any purpose. The
comment says it is supposed to collate multiple control flow edges into
one place, but the code as it is now does not achieve this. In fact, as
can be seen from the changes to lit tests, this block was not actually
outlined in the end. This is because there are actually two code
extractors: one in the callback for creating a parallel op which is used
to find what the input/output variables are (which does have this block
added to it), and another one which actually does the outlining (which
this block was not added to).

Tested with the gfortran and fujitsu test suites.

Fixes #112884
2025-03-07 11:02:52 +00:00

989 lines
66 KiB
C++
Raw Blame History

// 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 -Wno-vla -fopenmp -x c++ -emit-llvm %s -triple x86_64-unknown-linux -fexceptions -fcxx-exceptions -o - | FileCheck %s --check-prefix=CHECK1
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -debug-info-kind=limited -std=c++11 -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK2
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp -fopenmp-enable-irbuilder -DIRBUILDER -x c++ -emit-llvm %s -triple x86_64-unknown-linux -fexceptions -fcxx-exceptions -o - | FileCheck %s --check-prefix=CHECK3
// RUN: %clang_cc1 -fopenmp -fopenmp-enable-irbuilder -DIRBUILDER -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-enable-irbuilder -DIRBUILDER -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -debug-info-kind=limited -gno-column-info -std=c++11 -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK4
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -x c++ -emit-llvm %s -triple x86_64-unknown-linux -fexceptions -fcxx-exceptions -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -debug-info-kind=limited -std=c++11 -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -verify -Wno-vla -fopenmp-simd -fopenmp-enable-irbuilder -x c++ -emit-llvm %s -triple x86_64-unknown-linux -fexceptions -fcxx-exceptions -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-enable-irbuilder -x c++ -std=c++11 -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-enable-irbuilder -x c++ -triple x86_64-unknown-unknown -fexceptions -fcxx-exceptions -debug-info-kind=limited -std=c++11 -include-pch %t -verify -Wno-vla %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
template <class T>
void foo(T argc) {}
template <typename T>
int tmain(T argc) {
typedef double (*chunk_t)[argc[0][0]];
#pragma omp parallel
{
foo(argc);
chunk_t var;(void)var[0][0];
}
return 0;
}
int global;
int main (int argc, char **argv) {
int a[argc];
#pragma omp parallel shared(global, a) default(none)
foo(a[1]), a[1] = global;
#ifndef IRBUILDER
// TODO: Support for privates in IRBuilder.
#pragma omp parallel private(global, a) default(none)
#pragma omp parallel shared(global, a) default(none)
foo(a[1]), a[1] = global;
// FIXME: IRBuilder crashes in void llvm::OpenMPIRBuilder::finalize()
// Assertion `Extractor.isEligible() && "Expected OpenMP outlining to be possible!"' failed.
#pragma omp parallel shared(global, a) default(none)
#pragma omp parallel shared(global, a) default(none)
foo(a[1]), a[1] = global;
#endif // IRBUILDER
return tmain(argv);
}
// Note that OpenMPIRBuilder puts the trailing arguments in a different order:
// arguments that are wrapped into additional pointers precede the other
// arguments. This is expected and not problematic because both the call and the
// function are generated from the same place, and the function is internal.
#endif
// CHECK1-LABEL: define {{[^@]+}}@main
// CHECK1-SAME: (i32 noundef [[ARGC:%.*]], ptr noundef [[ARGV:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[ARGC_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[ARGV_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[SAVED_STACK:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK1-NEXT: store i32 0, ptr [[RETVAL]], align 4
// CHECK1-NEXT: store i32 [[ARGC]], ptr [[ARGC_ADDR]], align 4
// CHECK1-NEXT: store ptr [[ARGV]], ptr [[ARGV_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARGC_ADDR]], align 4
// CHECK1-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
// CHECK1-NEXT: [[TMP2:%.*]] = call ptr @llvm.stacksave.p0()
// CHECK1-NEXT: store ptr [[TMP2]], ptr [[SAVED_STACK]], align 8
// CHECK1-NEXT: [[VLA:%.*]] = alloca i32, i64 [[TMP1]], align 16
// CHECK1-NEXT: store i64 [[TMP1]], ptr [[__VLA_EXPR0]], align 8
// CHECK1-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1:[0-9]+]], i32 2, ptr @main.omp_outlined, i64 [[TMP1]], ptr [[VLA]])
// CHECK1-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 1, ptr @main.omp_outlined.1, i64 [[TMP1]])
// CHECK1-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 2, ptr @main.omp_outlined.2, i64 [[TMP1]], ptr [[VLA]])
// CHECK1-NEXT: [[TMP3:%.*]] = load ptr, ptr [[ARGV_ADDR]], align 8
// CHECK1-NEXT: [[CALL:%.*]] = call noundef i32 @_Z5tmainIPPcEiT_(ptr noundef [[TMP3]])
// CHECK1-NEXT: store i32 [[CALL]], ptr [[RETVAL]], align 4
// CHECK1-NEXT: [[TMP4:%.*]] = load ptr, ptr [[SAVED_STACK]], align 8
// CHECK1-NEXT: call void @llvm.stackrestore.p0(ptr [[TMP4]])
// CHECK1-NEXT: [[TMP5:%.*]] = load i32, ptr [[RETVAL]], align 4
// CHECK1-NEXT: ret i32 [[TMP5]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@main.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2:[0-9]+]] personality ptr @__gxx_personality_v0 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1
// CHECK1-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK1-NEXT: invoke void @_Z3fooIiEvT_(i32 noundef [[TMP2]])
// CHECK1-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]]
// CHECK1: invoke.cont:
// CHECK1-NEXT: [[TMP3:%.*]] = load i32, ptr @global, align 4
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1
// CHECK1-NEXT: store i32 [[TMP3]], ptr [[ARRAYIDX1]], align 4
// CHECK1-NEXT: ret void
// CHECK1: terminate.lpad:
// CHECK1-NEXT: [[TMP4:%.*]] = landingpad { ptr, i32 }
// CHECK1-NEXT: catch ptr null
// CHECK1-NEXT: [[TMP5:%.*]] = extractvalue { ptr, i32 } [[TMP4]], 0
// CHECK1-NEXT: call void @__clang_call_terminate(ptr [[TMP5]]) #[[ATTR6:[0-9]+]]
// CHECK1-NEXT: unreachable
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z3fooIiEvT_
// CHECK1-SAME: (i32 noundef [[ARGC:%.*]]) #[[ATTR3:[0-9]+]] comdat {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[ARGC_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT: store i32 [[ARGC]], ptr [[ARGC_ADDR]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@__clang_call_terminate
// CHECK1-SAME: (ptr noundef [[TMP0:%.*]]) #[[ATTR4:[0-9]+]] comdat {
// CHECK1-NEXT: [[TMP2:%.*]] = call ptr @__cxa_begin_catch(ptr [[TMP0]]) #[[ATTR5:[0-9]+]]
// CHECK1-NEXT: call void @_ZSt9terminatev() #[[ATTR6]]
// CHECK1-NEXT: unreachable
//
//
// CHECK1-LABEL: define {{[^@]+}}@main.omp_outlined.1
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]]) #[[ATTR2]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[GLOBAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[SAVED_STACK:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK1-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = call ptr @llvm.stacksave.p0()
// CHECK1-NEXT: store ptr [[TMP1]], ptr [[SAVED_STACK]], align 8
// CHECK1-NEXT: [[VLA1:%.*]] = alloca i32, i64 [[TMP0]], align 16
// CHECK1-NEXT: store i64 [[TMP0]], ptr [[__VLA_EXPR0]], align 8
// CHECK1-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 3, ptr @main.omp_outlined.1.omp_outlined, i64 [[TMP0]], ptr [[VLA1]], ptr [[GLOBAL]])
// CHECK1-NEXT: [[TMP2:%.*]] = load ptr, ptr [[SAVED_STACK]], align 8
// CHECK1-NEXT: call void @llvm.stackrestore.p0(ptr [[TMP2]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@main.omp_outlined.1.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[GLOBAL:%.*]]) #[[ATTR2]] personality ptr @__gxx_personality_v0 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[GLOBAL_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT: store ptr [[GLOBAL]], ptr [[GLOBAL_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load ptr, ptr [[GLOBAL_ADDR]], align 8
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1
// CHECK1-NEXT: [[TMP3:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK1-NEXT: invoke void @_Z3fooIiEvT_(i32 noundef [[TMP3]])
// CHECK1-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]]
// CHECK1: invoke.cont:
// CHECK1-NEXT: [[TMP4:%.*]] = load i32, ptr [[TMP2]], align 4
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1
// CHECK1-NEXT: store i32 [[TMP4]], ptr [[ARRAYIDX1]], align 4
// CHECK1-NEXT: ret void
// CHECK1: terminate.lpad:
// CHECK1-NEXT: [[TMP5:%.*]] = landingpad { ptr, i32 }
// CHECK1-NEXT: catch ptr null
// CHECK1-NEXT: [[TMP6:%.*]] = extractvalue { ptr, i32 } [[TMP5]], 0
// CHECK1-NEXT: call void @__clang_call_terminate(ptr [[TMP6]]) #[[ATTR6]]
// CHECK1-NEXT: unreachable
//
//
// CHECK1-LABEL: define {{[^@]+}}@main.omp_outlined.2
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8
// CHECK1-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 2, ptr @main.omp_outlined.2.omp_outlined, i64 [[TMP0]], ptr [[TMP1]])
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@main.omp_outlined.2.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2]] personality ptr @__gxx_personality_v0 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1
// CHECK1-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK1-NEXT: invoke void @_Z3fooIiEvT_(i32 noundef [[TMP2]])
// CHECK1-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]]
// CHECK1: invoke.cont:
// CHECK1-NEXT: [[TMP3:%.*]] = load i32, ptr @global, align 4
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1
// CHECK1-NEXT: store i32 [[TMP3]], ptr [[ARRAYIDX1]], align 4
// CHECK1-NEXT: ret void
// CHECK1: terminate.lpad:
// CHECK1-NEXT: [[TMP4:%.*]] = landingpad { ptr, i32 }
// CHECK1-NEXT: catch ptr null
// CHECK1-NEXT: [[TMP5:%.*]] = extractvalue { ptr, i32 } [[TMP4]], 0
// CHECK1-NEXT: call void @__clang_call_terminate(ptr [[TMP5]]) #[[ATTR6]]
// CHECK1-NEXT: unreachable
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_
// CHECK1-SAME: (ptr noundef [[ARGC:%.*]]) #[[ATTR3]] comdat {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ARGC_ADDR]], align 8
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds ptr, ptr [[TMP0]], i64 0
// CHECK1-NEXT: [[TMP1:%.*]] = load ptr, ptr [[ARRAYIDX]], align 8
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i64 0
// CHECK1-NEXT: [[TMP2:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
// CHECK1-NEXT: [[TMP3:%.*]] = zext i8 [[TMP2]] to i64
// CHECK1-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 2, ptr @_Z5tmainIPPcEiT_.omp_outlined, ptr [[ARGC_ADDR]], i64 [[TMP3]])
// CHECK1-NEXT: ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_.omp_outlined
// CHECK1-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], ptr noundef nonnull align 8 dereferenceable(8) [[ARGC:%.*]], i64 noundef [[VLA:%.*]]) #[[ATTR2]] personality ptr @__gxx_personality_v0 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[VAR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK1-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ARGC_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TMP0]], align 8
// CHECK1-NEXT: invoke void @_Z3fooIPPcEvT_(ptr noundef [[TMP2]])
// CHECK1-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]]
// CHECK1: invoke.cont:
// CHECK1-NEXT: [[TMP3:%.*]] = load ptr, ptr [[VAR]], align 8
// CHECK1-NEXT: [[TMP4:%.*]] = mul nsw i64 0, [[TMP1]]
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, ptr [[TMP3]], i64 [[TMP4]]
// CHECK1-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds double, ptr [[ARRAYIDX]], i64 0
// CHECK1-NEXT: ret void
// CHECK1: terminate.lpad:
// CHECK1-NEXT: [[TMP5:%.*]] = landingpad { ptr, i32 }
// CHECK1-NEXT: catch ptr null
// CHECK1-NEXT: [[TMP6:%.*]] = extractvalue { ptr, i32 } [[TMP5]], 0
// CHECK1-NEXT: call void @__clang_call_terminate(ptr [[TMP6]]) #[[ATTR6]]
// CHECK1-NEXT: unreachable
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z3fooIPPcEvT_
// CHECK1-SAME: (ptr noundef [[ARGC:%.*]]) #[[ATTR3]] comdat {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK1-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK1-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@main
// CHECK2-SAME: (i32 noundef [[ARGC:%.*]], ptr noundef [[ARGV:%.*]]) #[[ATTR0:[0-9]+]] !dbg [[DBG11:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[ARGC_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[ARGV_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[SAVED_STACK:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK2-NEXT: store i32 0, ptr [[RETVAL]], align 4
// CHECK2-NEXT: store i32 [[ARGC]], ptr [[ARGC_ADDR]], align 4
// CHECK2-NEXT: #dbg_declare(ptr [[ARGC_ADDR]], [[META18:![0-9]+]], !DIExpression(), [[META19:![0-9]+]])
// CHECK2-NEXT: store ptr [[ARGV]], ptr [[ARGV_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[ARGV_ADDR]], [[META20:![0-9]+]], !DIExpression(), [[META21:![0-9]+]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARGC_ADDR]], align 4, !dbg [[DBG22:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64, !dbg [[DBG23:![0-9]+]]
// CHECK2-NEXT: [[TMP2:%.*]] = call ptr @llvm.stacksave.p0(), !dbg [[DBG23]]
// CHECK2-NEXT: store ptr [[TMP2]], ptr [[SAVED_STACK]], align 8, !dbg [[DBG23]]
// CHECK2-NEXT: [[VLA:%.*]] = alloca i32, i64 [[TMP1]], align 16, !dbg [[DBG23]]
// CHECK2-NEXT: store i64 [[TMP1]], ptr [[__VLA_EXPR0]], align 8, !dbg [[DBG23]]
// CHECK2-NEXT: #dbg_declare(ptr [[__VLA_EXPR0]], [[META24:![0-9]+]], !DIExpression(), [[META26:![0-9]+]])
// CHECK2-NEXT: #dbg_declare(ptr [[VLA]], [[META27:![0-9]+]], !DIExpression(), [[META31:![0-9]+]])
// CHECK2-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1:[0-9]+]], i32 2, ptr @main.omp_outlined, i64 [[TMP1]], ptr [[VLA]]), !dbg [[DBG32:![0-9]+]]
// CHECK2-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB5:[0-9]+]], i32 1, ptr @main.omp_outlined.1, i64 [[TMP1]]), !dbg [[DBG33:![0-9]+]]
// CHECK2-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB9:[0-9]+]], i32 2, ptr @main.omp_outlined.3, i64 [[TMP1]], ptr [[VLA]]), !dbg [[DBG34:![0-9]+]]
// CHECK2-NEXT: [[TMP3:%.*]] = load ptr, ptr [[ARGV_ADDR]], align 8, !dbg [[DBG35:![0-9]+]]
// CHECK2-NEXT: [[CALL:%.*]] = call noundef i32 @_Z5tmainIPPcEiT_(ptr noundef [[TMP3]]), !dbg [[DBG36:![0-9]+]]
// CHECK2-NEXT: store i32 [[CALL]], ptr [[RETVAL]], align 4, !dbg [[DBG37:![0-9]+]]
// CHECK2-NEXT: [[TMP4:%.*]] = load ptr, ptr [[SAVED_STACK]], align 8, !dbg [[DBG38:![0-9]+]]
// CHECK2-NEXT: call void @llvm.stackrestore.p0(ptr [[TMP4]]), !dbg [[DBG38]]
// CHECK2-NEXT: [[TMP5:%.*]] = load i32, ptr [[RETVAL]], align 4, !dbg [[DBG38]]
// CHECK2-NEXT: ret i32 [[TMP5]], !dbg [[DBG38]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@main.omp_outlined_debug__
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2:[0-9]+]] personality ptr @__gxx_personality_v0 !dbg [[DBG39:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META47:![0-9]+]], !DIExpression(), [[META48:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META49:![0-9]+]], !DIExpression(), [[META48]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META50:![0-9]+]], !DIExpression(), [[META48]])
// CHECK2-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[A_ADDR]], [[META51:![0-9]+]], !DIExpression(), [[META52:![0-9]+]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG53:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG53]]
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1, !dbg [[DBG54:![0-9]+]]
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX]], align 4, !dbg [[DBG54]]
// CHECK2-NEXT: invoke void @_Z3fooIiEvT_(i32 noundef [[TMP2]])
// CHECK2-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]], !dbg [[DBG53]]
// CHECK2: invoke.cont:
// CHECK2-NEXT: [[TMP3:%.*]] = load i32, ptr @global, align 4, !dbg [[DBG55:![0-9]+]]
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1, !dbg [[DBG56:![0-9]+]]
// CHECK2-NEXT: store i32 [[TMP3]], ptr [[ARRAYIDX1]], align 4, !dbg [[DBG57:![0-9]+]]
// CHECK2-NEXT: ret void, !dbg [[DBG55]]
// CHECK2: terminate.lpad:
// CHECK2-NEXT: [[TMP4:%.*]] = landingpad { ptr, i32 }
// CHECK2-NEXT: catch ptr null, !dbg [[DBG53]]
// CHECK2-NEXT: [[TMP5:%.*]] = extractvalue { ptr, i32 } [[TMP4]], 0, !dbg [[DBG53]]
// CHECK2-NEXT: call void @__clang_call_terminate(ptr [[TMP5]]) #[[ATTR6:[0-9]+]], !dbg [[DBG53]]
// CHECK2-NEXT: unreachable, !dbg [[DBG53]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@main.omp_outlined
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2]] !dbg [[DBG58:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META59:![0-9]+]], !DIExpression(), [[META60:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META61:![0-9]+]], !DIExpression(), [[META60]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META62:![0-9]+]], !DIExpression(), [[META60]])
// CHECK2-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[A_ADDR]], [[META63:![0-9]+]], !DIExpression(), [[META60]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG64:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG64]]
// CHECK2-NEXT: [[TMP2:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8, !dbg [[DBG64]]
// CHECK2-NEXT: [[TMP3:%.*]] = load ptr, ptr [[DOTBOUND_TID__ADDR]], align 8, !dbg [[DBG64]]
// CHECK2-NEXT: [[TMP4:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG64]]
// CHECK2-NEXT: call void @main.omp_outlined_debug__(ptr [[TMP2]], ptr [[TMP3]], i64 [[TMP0]], ptr [[TMP4]]) #[[ATTR5:[0-9]+]], !dbg [[DBG64]]
// CHECK2-NEXT: ret void, !dbg [[DBG64]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z3fooIiEvT_
// CHECK2-SAME: (i32 noundef [[ARGC:%.*]]) #[[ATTR3:[0-9]+]] comdat !dbg [[DBG65:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[ARGC_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: store i32 [[ARGC]], ptr [[ARGC_ADDR]], align 4
// CHECK2-NEXT: #dbg_declare(ptr [[ARGC_ADDR]], [[META70:![0-9]+]], !DIExpression(), [[META71:![0-9]+]])
// CHECK2-NEXT: ret void, !dbg [[DBG72:![0-9]+]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@__clang_call_terminate
// CHECK2-SAME: (ptr noundef [[TMP0:%.*]]) #[[ATTR4:[0-9]+]] comdat {
// CHECK2-NEXT: [[TMP2:%.*]] = call ptr @__cxa_begin_catch(ptr [[TMP0]]) #[[ATTR5]]
// CHECK2-NEXT: call void @_ZSt9terminatev() #[[ATTR6]]
// CHECK2-NEXT: unreachable
//
//
// CHECK2-LABEL: define {{[^@]+}}@main.omp_outlined_debug__.2
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]]) #[[ATTR2]] !dbg [[DBG75:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[GLOBAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[SAVED_STACK:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META78:![0-9]+]], !DIExpression(), [[META79:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META80:![0-9]+]], !DIExpression(), [[META79]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META81:![0-9]+]], !DIExpression(), [[META79]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG82:![0-9]+]]
// CHECK2-NEXT: #dbg_declare(ptr [[GLOBAL]], [[META83:![0-9]+]], !DIExpression(), [[META79]])
// CHECK2-NEXT: [[TMP1:%.*]] = call ptr @llvm.stacksave.p0(), !dbg [[DBG82]]
// CHECK2-NEXT: store ptr [[TMP1]], ptr [[SAVED_STACK]], align 8, !dbg [[DBG82]]
// CHECK2-NEXT: [[VLA1:%.*]] = alloca i32, i64 [[TMP0]], align 16, !dbg [[DBG82]]
// CHECK2-NEXT: store i64 [[TMP0]], ptr [[__VLA_EXPR0]], align 8, !dbg [[DBG82]]
// CHECK2-NEXT: #dbg_declare(ptr [[__VLA_EXPR0]], [[META84:![0-9]+]], !DIExpression(), [[META79]])
// CHECK2-NEXT: #dbg_declare(ptr [[VLA1]], [[META85:![0-9]+]], !DIExpression(), [[META79]])
// CHECK2-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB3:[0-9]+]], i32 3, ptr @main.omp_outlined_debug__.2.omp_outlined, i64 [[TMP0]], ptr [[VLA1]], ptr [[GLOBAL]]), !dbg [[DBG82]]
// CHECK2-NEXT: [[TMP2:%.*]] = load ptr, ptr [[SAVED_STACK]], align 8, !dbg [[DBG86:![0-9]+]]
// CHECK2-NEXT: call void @llvm.stackrestore.p0(ptr [[TMP2]]), !dbg [[DBG86]]
// CHECK2-NEXT: ret void, !dbg [[DBG88:![0-9]+]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@main.omp_outlined.1
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]]) #[[ATTR2]] !dbg [[DBG89:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META90:![0-9]+]], !DIExpression(), [[META91:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META92:![0-9]+]], !DIExpression(), [[META91]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META93:![0-9]+]], !DIExpression(), [[META91]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG94:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8, !dbg [[DBG94]]
// CHECK2-NEXT: [[TMP2:%.*]] = load ptr, ptr [[DOTBOUND_TID__ADDR]], align 8, !dbg [[DBG94]]
// CHECK2-NEXT: call void @main.omp_outlined_debug__.2(ptr [[TMP1]], ptr [[TMP2]], i64 [[TMP0]]) #[[ATTR5]], !dbg [[DBG94]]
// CHECK2-NEXT: ret void, !dbg [[DBG94]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@main.omp_outlined_debug__.2.omp_outlined_debug__
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[GLOBAL:%.*]]) #[[ATTR2]] personality ptr @__gxx_personality_v0 !dbg [[DBG95:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[GLOBAL_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META98:![0-9]+]], !DIExpression(), [[META99:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META100:![0-9]+]], !DIExpression(), [[META99]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META101:![0-9]+]], !DIExpression(), [[META99]])
// CHECK2-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[A_ADDR]], [[META102:![0-9]+]], !DIExpression(), [[META103:![0-9]+]])
// CHECK2-NEXT: store ptr [[GLOBAL]], ptr [[GLOBAL_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[GLOBAL_ADDR]], [[META104:![0-9]+]], !DIExpression(), [[META105:![0-9]+]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG106:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG106]]
// CHECK2-NEXT: [[TMP2:%.*]] = load ptr, ptr [[GLOBAL_ADDR]], align 8, !dbg [[DBG106]]
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1, !dbg [[DBG107:![0-9]+]]
// CHECK2-NEXT: [[TMP3:%.*]] = load i32, ptr [[ARRAYIDX]], align 4, !dbg [[DBG107]]
// CHECK2-NEXT: invoke void @_Z3fooIiEvT_(i32 noundef [[TMP3]])
// CHECK2-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]], !dbg [[DBG106]]
// CHECK2: invoke.cont:
// CHECK2-NEXT: [[TMP4:%.*]] = load i32, ptr [[TMP2]], align 4, !dbg [[DBG108:![0-9]+]]
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1, !dbg [[DBG109:![0-9]+]]
// CHECK2-NEXT: store i32 [[TMP4]], ptr [[ARRAYIDX1]], align 4, !dbg [[DBG110:![0-9]+]]
// CHECK2-NEXT: ret void, !dbg [[DBG108]]
// CHECK2: terminate.lpad:
// CHECK2-NEXT: [[TMP5:%.*]] = landingpad { ptr, i32 }
// CHECK2-NEXT: catch ptr null, !dbg [[DBG106]]
// CHECK2-NEXT: [[TMP6:%.*]] = extractvalue { ptr, i32 } [[TMP5]], 0, !dbg [[DBG106]]
// CHECK2-NEXT: call void @__clang_call_terminate(ptr [[TMP6]]) #[[ATTR6]], !dbg [[DBG106]]
// CHECK2-NEXT: unreachable, !dbg [[DBG106]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@main.omp_outlined_debug__.2.omp_outlined
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[GLOBAL:%.*]]) #[[ATTR2]] !dbg [[DBG111:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[GLOBAL_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META112:![0-9]+]], !DIExpression(), [[META113:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META114:![0-9]+]], !DIExpression(), [[META113]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META115:![0-9]+]], !DIExpression(), [[META113]])
// CHECK2-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[A_ADDR]], [[META116:![0-9]+]], !DIExpression(), [[META113]])
// CHECK2-NEXT: store ptr [[GLOBAL]], ptr [[GLOBAL_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[GLOBAL_ADDR]], [[META117:![0-9]+]], !DIExpression(), [[META113]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG118:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG118]]
// CHECK2-NEXT: [[TMP2:%.*]] = load ptr, ptr [[GLOBAL_ADDR]], align 8, !dbg [[DBG118]]
// CHECK2-NEXT: [[TMP3:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8, !dbg [[DBG118]]
// CHECK2-NEXT: [[TMP4:%.*]] = load ptr, ptr [[DOTBOUND_TID__ADDR]], align 8, !dbg [[DBG118]]
// CHECK2-NEXT: [[TMP5:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG118]]
// CHECK2-NEXT: [[TMP6:%.*]] = load ptr, ptr [[GLOBAL_ADDR]], align 8, !dbg [[DBG118]]
// CHECK2-NEXT: call void @main.omp_outlined_debug__.2.omp_outlined_debug__(ptr [[TMP3]], ptr [[TMP4]], i64 [[TMP0]], ptr [[TMP5]], ptr [[TMP6]]) #[[ATTR5]], !dbg [[DBG118]]
// CHECK2-NEXT: ret void, !dbg [[DBG118]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@main.omp_outlined_debug__.4
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2]] !dbg [[DBG119:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META120:![0-9]+]], !DIExpression(), [[META121:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META122:![0-9]+]], !DIExpression(), [[META121]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META123:![0-9]+]], !DIExpression(), [[META121]])
// CHECK2-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[A_ADDR]], [[META124:![0-9]+]], !DIExpression(), [[META125:![0-9]+]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG126:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG126]]
// CHECK2-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB7:[0-9]+]], i32 2, ptr @main.omp_outlined_debug__.4.omp_outlined, i64 [[TMP0]], ptr [[TMP1]]), !dbg [[DBG126]]
// CHECK2-NEXT: ret void, !dbg [[DBG127:![0-9]+]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@main.omp_outlined.3
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2]] !dbg [[DBG128:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META129:![0-9]+]], !DIExpression(), [[META130:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META131:![0-9]+]], !DIExpression(), [[META130]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META132:![0-9]+]], !DIExpression(), [[META130]])
// CHECK2-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[A_ADDR]], [[META133:![0-9]+]], !DIExpression(), [[META130]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG134:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG134]]
// CHECK2-NEXT: [[TMP2:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8, !dbg [[DBG134]]
// CHECK2-NEXT: [[TMP3:%.*]] = load ptr, ptr [[DOTBOUND_TID__ADDR]], align 8, !dbg [[DBG134]]
// CHECK2-NEXT: [[TMP4:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG134]]
// CHECK2-NEXT: call void @main.omp_outlined_debug__.4(ptr [[TMP2]], ptr [[TMP3]], i64 [[TMP0]], ptr [[TMP4]]) #[[ATTR5]], !dbg [[DBG134]]
// CHECK2-NEXT: ret void, !dbg [[DBG134]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@main.omp_outlined_debug__.4.omp_outlined_debug__
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2]] personality ptr @__gxx_personality_v0 !dbg [[DBG135:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META136:![0-9]+]], !DIExpression(), [[META137:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META138:![0-9]+]], !DIExpression(), [[META137]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META139:![0-9]+]], !DIExpression(), [[META137]])
// CHECK2-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[A_ADDR]], [[META140:![0-9]+]], !DIExpression(), [[META141:![0-9]+]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG142:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG142]]
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1, !dbg [[DBG143:![0-9]+]]
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX]], align 4, !dbg [[DBG143]]
// CHECK2-NEXT: invoke void @_Z3fooIiEvT_(i32 noundef [[TMP2]])
// CHECK2-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]], !dbg [[DBG142]]
// CHECK2: invoke.cont:
// CHECK2-NEXT: [[TMP3:%.*]] = load i32, ptr @global, align 4, !dbg [[DBG144:![0-9]+]]
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i64 1, !dbg [[DBG145:![0-9]+]]
// CHECK2-NEXT: store i32 [[TMP3]], ptr [[ARRAYIDX1]], align 4, !dbg [[DBG146:![0-9]+]]
// CHECK2-NEXT: ret void, !dbg [[DBG144]]
// CHECK2: terminate.lpad:
// CHECK2-NEXT: [[TMP4:%.*]] = landingpad { ptr, i32 }
// CHECK2-NEXT: catch ptr null, !dbg [[DBG142]]
// CHECK2-NEXT: [[TMP5:%.*]] = extractvalue { ptr, i32 } [[TMP4]], 0, !dbg [[DBG142]]
// CHECK2-NEXT: call void @__clang_call_terminate(ptr [[TMP5]]) #[[ATTR6]], !dbg [[DBG142]]
// CHECK2-NEXT: unreachable, !dbg [[DBG142]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@main.omp_outlined_debug__.4.omp_outlined
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], i64 noundef [[VLA:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2]] !dbg [[DBG147:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META148:![0-9]+]], !DIExpression(), [[META149:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META150:![0-9]+]], !DIExpression(), [[META149]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META151:![0-9]+]], !DIExpression(), [[META149]])
// CHECK2-NEXT: store ptr [[A]], ptr [[A_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[A_ADDR]], [[META152:![0-9]+]], !DIExpression(), [[META149]])
// CHECK2-NEXT: [[TMP0:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG153:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG153]]
// CHECK2-NEXT: [[TMP2:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8, !dbg [[DBG153]]
// CHECK2-NEXT: [[TMP3:%.*]] = load ptr, ptr [[DOTBOUND_TID__ADDR]], align 8, !dbg [[DBG153]]
// CHECK2-NEXT: [[TMP4:%.*]] = load ptr, ptr [[A_ADDR]], align 8, !dbg [[DBG153]]
// CHECK2-NEXT: call void @main.omp_outlined_debug__.4.omp_outlined_debug__(ptr [[TMP2]], ptr [[TMP3]], i64 [[TMP0]], ptr [[TMP4]]) #[[ATTR5]], !dbg [[DBG153]]
// CHECK2-NEXT: ret void, !dbg [[DBG153]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_
// CHECK2-SAME: (ptr noundef [[ARGC:%.*]]) #[[ATTR3]] comdat !dbg [[DBG154:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[ARGC_ADDR]], [[META159:![0-9]+]], !DIExpression(), [[META160:![0-9]+]])
// CHECK2-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ARGC_ADDR]], align 8, !dbg [[DBG161:![0-9]+]]
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds ptr, ptr [[TMP0]], i64 0, !dbg [[DBG161]]
// CHECK2-NEXT: [[TMP1:%.*]] = load ptr, ptr [[ARRAYIDX]], align 8, !dbg [[DBG161]]
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i64 0, !dbg [[DBG161]]
// CHECK2-NEXT: [[TMP2:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1, !dbg [[DBG161]]
// CHECK2-NEXT: [[TMP3:%.*]] = zext i8 [[TMP2]] to i64, !dbg [[DBG162:![0-9]+]]
// CHECK2-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB11:[0-9]+]], i32 2, ptr @_Z5tmainIPPcEiT_.omp_outlined, ptr [[ARGC_ADDR]], i64 [[TMP3]]), !dbg [[DBG163:![0-9]+]]
// CHECK2-NEXT: ret i32 0, !dbg [[DBG164:![0-9]+]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_.omp_outlined_debug__
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], ptr noundef nonnull align 8 dereferenceable(8) [[ARGC:%.*]], i64 noundef [[VLA:%.*]]) #[[ATTR2]] personality ptr @__gxx_personality_v0 !dbg [[DBG165:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: [[VAR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META169:![0-9]+]], !DIExpression(), [[META170:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META171:![0-9]+]], !DIExpression(), [[META170]])
// CHECK2-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[ARGC_ADDR]], [[META172:![0-9]+]], !DIExpression(), [[META173:![0-9]+]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META174:![0-9]+]], !DIExpression(), [[META170]])
// CHECK2-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ARGC_ADDR]], align 8, !dbg [[DBG175:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG175]]
// CHECK2-NEXT: [[TMP2:%.*]] = load ptr, ptr [[TMP0]], align 8, !dbg [[DBG176:![0-9]+]]
// CHECK2-NEXT: invoke void @_Z3fooIPPcEvT_(ptr noundef [[TMP2]])
// CHECK2-NEXT: to label [[INVOKE_CONT:%.*]] unwind label [[TERMINATE_LPAD:%.*]], !dbg [[DBG178:![0-9]+]]
// CHECK2: invoke.cont:
// CHECK2-NEXT: #dbg_declare(ptr [[VAR]], [[META179:![0-9]+]], !DIExpression(), [[META186:![0-9]+]])
// CHECK2-NEXT: [[TMP3:%.*]] = load ptr, ptr [[VAR]], align 8, !dbg [[DBG187:![0-9]+]]
// CHECK2-NEXT: [[TMP4:%.*]] = mul nsw i64 0, [[TMP1]], !dbg [[DBG187]]
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, ptr [[TMP3]], i64 [[TMP4]], !dbg [[DBG187]]
// CHECK2-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds double, ptr [[ARRAYIDX]], i64 0, !dbg [[DBG187]]
// CHECK2-NEXT: ret void, !dbg [[DBG188:![0-9]+]]
// CHECK2: terminate.lpad:
// CHECK2-NEXT: [[TMP5:%.*]] = landingpad { ptr, i32 }
// CHECK2-NEXT: catch ptr null, !dbg [[DBG178]]
// CHECK2-NEXT: [[TMP6:%.*]] = extractvalue { ptr, i32 } [[TMP5]], 0, !dbg [[DBG178]]
// CHECK2-NEXT: call void @__clang_call_terminate(ptr [[TMP6]]) #[[ATTR6]], !dbg [[DBG178]]
// CHECK2-NEXT: unreachable, !dbg [[DBG178]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_.omp_outlined
// CHECK2-SAME: (ptr noalias noundef [[DOTGLOBAL_TID_:%.*]], ptr noalias noundef [[DOTBOUND_TID_:%.*]], ptr noundef nonnull align 8 dereferenceable(8) [[ARGC:%.*]], i64 noundef [[VLA:%.*]]) #[[ATTR2]] !dbg [[DBG189:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: [[VLA_ADDR:%.*]] = alloca i64, align 8
// CHECK2-NEXT: store ptr [[DOTGLOBAL_TID_]], ptr [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTGLOBAL_TID__ADDR]], [[META190:![0-9]+]], !DIExpression(), [[META191:![0-9]+]])
// CHECK2-NEXT: store ptr [[DOTBOUND_TID_]], ptr [[DOTBOUND_TID__ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[DOTBOUND_TID__ADDR]], [[META192:![0-9]+]], !DIExpression(), [[META191]])
// CHECK2-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[ARGC_ADDR]], [[META193:![0-9]+]], !DIExpression(), [[META191]])
// CHECK2-NEXT: store i64 [[VLA]], ptr [[VLA_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[VLA_ADDR]], [[META194:![0-9]+]], !DIExpression(), [[META191]])
// CHECK2-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ARGC_ADDR]], align 8, !dbg [[DBG195:![0-9]+]]
// CHECK2-NEXT: [[TMP1:%.*]] = load i64, ptr [[VLA_ADDR]], align 8, !dbg [[DBG195]]
// CHECK2-NEXT: [[TMP2:%.*]] = load ptr, ptr [[DOTGLOBAL_TID__ADDR]], align 8, !dbg [[DBG195]]
// CHECK2-NEXT: [[TMP3:%.*]] = load ptr, ptr [[DOTBOUND_TID__ADDR]], align 8, !dbg [[DBG195]]
// CHECK2-NEXT: [[TMP4:%.*]] = load ptr, ptr [[ARGC_ADDR]], align 8, !dbg [[DBG195]]
// CHECK2-NEXT: call void @_Z5tmainIPPcEiT_.omp_outlined_debug__(ptr [[TMP2]], ptr [[TMP3]], ptr [[TMP4]], i64 [[TMP1]]) #[[ATTR5]], !dbg [[DBG195]]
// CHECK2-NEXT: ret void, !dbg [[DBG195]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z3fooIPPcEvT_
// CHECK2-SAME: (ptr noundef [[ARGC:%.*]]) #[[ATTR3]] comdat !dbg [[DBG196:![0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK2-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK2-NEXT: #dbg_declare(ptr [[ARGC_ADDR]], [[META199:![0-9]+]], !DIExpression(), [[META200:![0-9]+]])
// CHECK2-NEXT: ret void, !dbg [[DBG201:![0-9]+]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@main
// CHECK3-SAME: (i32 noundef [[ARGC:%.*]], ptr noundef [[ARGV:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[STRUCTARG:%.*]] = alloca { ptr }, align 8
// CHECK3-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[ARGC_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[ARGV_ADDR:%.*]] = alloca ptr, align 8
// CHECK3-NEXT: [[SAVED_STACK:%.*]] = alloca ptr, align 8
// CHECK3-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK3-NEXT: store i32 0, ptr [[RETVAL]], align 4
// CHECK3-NEXT: store i32 [[ARGC]], ptr [[ARGC_ADDR]], align 4
// CHECK3-NEXT: store ptr [[ARGV]], ptr [[ARGV_ADDR]], align 8
// CHECK3-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARGC_ADDR]], align 4
// CHECK3-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64
// CHECK3-NEXT: [[TMP2:%.*]] = call ptr @llvm.stacksave.p0()
// CHECK3-NEXT: store ptr [[TMP2]], ptr [[SAVED_STACK]], align 8
// CHECK3-NEXT: [[VLA:%.*]] = alloca i32, i64 [[TMP1]], align 16
// CHECK3-NEXT: store i64 [[TMP1]], ptr [[__VLA_EXPR0]], align 8
// CHECK3-NEXT: [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]])
// CHECK3-NEXT: br label [[OMP_PARALLEL:%.*]]
// CHECK3: omp_parallel:
// CHECK3-NEXT: [[GEP_VLA:%.*]] = getelementptr { ptr }, ptr [[STRUCTARG]], i32 0, i32 0
// CHECK3-NEXT: store ptr [[VLA]], ptr [[GEP_VLA]], align 8
// CHECK3-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 1, ptr @main..omp_par, ptr [[STRUCTARG]])
// CHECK3-NEXT: br label [[OMP_PAR_OUTLINED_EXIT:%.*]]
// CHECK3: omp.par.exit:
// CHECK3-NEXT: [[TMP3:%.*]] = load ptr, ptr [[ARGV_ADDR]], align 8
// CHECK3-NEXT: [[CALL:%.*]] = call noundef i32 @_Z5tmainIPPcEiT_(ptr noundef [[TMP3]])
// CHECK3-NEXT: store i32 [[CALL]], ptr [[RETVAL]], align 4
// CHECK3-NEXT: [[TMP4:%.*]] = load ptr, ptr [[SAVED_STACK]], align 8
// CHECK3-NEXT: call void @llvm.stackrestore.p0(ptr [[TMP4]])
// CHECK3-NEXT: [[TMP5:%.*]] = load i32, ptr [[RETVAL]], align 4
// CHECK3-NEXT: ret i32 [[TMP5]]
//
//
// CHECK3-LABEL: define {{[^@]+}}@main..omp_par
// CHECK3-SAME: (ptr noalias [[TID_ADDR:%.*]], ptr noalias [[ZERO_ADDR:%.*]], ptr [[TMP0:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK3-NEXT: omp.par.entry:
// CHECK3-NEXT: [[GEP_VLA:%.*]] = getelementptr { ptr }, ptr [[TMP0]], i32 0, i32 0
// CHECK3-NEXT: [[LOADGEP_VLA:%.*]] = load ptr, ptr [[GEP_VLA]], align 8
// CHECK3-NEXT: [[TID_ADDR_LOCAL:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load i32, ptr [[TID_ADDR]], align 4
// CHECK3-NEXT: store i32 [[TMP1]], ptr [[TID_ADDR_LOCAL]], align 4
// CHECK3-NEXT: [[TID:%.*]] = load i32, ptr [[TID_ADDR_LOCAL]], align 4
// CHECK3-NEXT: br label [[OMP_PAR_REGION:%.*]]
// CHECK3: omp.par.region:
// CHECK3-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[LOADGEP_VLA]], i64 1
// CHECK3-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
// CHECK3-NEXT: call void @_Z3fooIiEvT_(i32 noundef [[TMP2]])
// CHECK3-NEXT: [[TMP3:%.*]] = load i32, ptr @global, align 4
// CHECK3-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[LOADGEP_VLA]], i64 1
// CHECK3-NEXT: store i32 [[TMP3]], ptr [[ARRAYIDX1]], align 4
// CHECK3-NEXT: br label [[OMP_PAR_REGION_PARALLEL_AFTER:%.*]]
// CHECK3: omp.par.region.parallel.after:
// CHECK3-NEXT: br label [[OMP_PAR_PRE_FINALIZE:%.*]]
// CHECK3: omp.par.pre_finalize:
// CHECK3-NEXT: br label [[OMP_PAR_OUTLINED_EXIT_EXITSTUB:%.*]]
// CHECK3: omp.par.exit.exitStub:
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z3fooIiEvT_
// CHECK3-SAME: (i32 noundef [[ARGC:%.*]]) #[[ATTR4:[0-9]+]] comdat {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[ARGC_ADDR:%.*]] = alloca i32, align 4
// CHECK3-NEXT: store i32 [[ARGC]], ptr [[ARGC_ADDR]], align 4
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_
// CHECK3-SAME: (ptr noundef [[ARGC:%.*]]) #[[ATTR5:[0-9]+]] comdat {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[STRUCTARG:%.*]] = alloca { ptr, ptr }, align 8
// CHECK3-NEXT: [[DOTRELOADED:%.*]] = alloca i64, align 8
// CHECK3-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK3-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK3-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ARGC_ADDR]], align 8
// CHECK3-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds ptr, ptr [[TMP0]], i64 0
// CHECK3-NEXT: [[TMP1:%.*]] = load ptr, ptr [[ARRAYIDX]], align 8
// CHECK3-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i64 0
// CHECK3-NEXT: [[TMP2:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1
// CHECK3-NEXT: [[TMP3:%.*]] = zext i8 [[TMP2]] to i64
// CHECK3-NEXT: [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1]])
// CHECK3-NEXT: store i64 [[TMP3]], ptr [[DOTRELOADED]], align 8
// CHECK3-NEXT: br label [[OMP_PARALLEL:%.*]]
// CHECK3: omp_parallel:
// CHECK3-NEXT: [[GEP__RELOADED:%.*]] = getelementptr { ptr, ptr }, ptr [[STRUCTARG]], i32 0, i32 0
// CHECK3-NEXT: store ptr [[DOTRELOADED]], ptr [[GEP__RELOADED]], align 8
// CHECK3-NEXT: [[GEP_ARGC_ADDR:%.*]] = getelementptr { ptr, ptr }, ptr [[STRUCTARG]], i32 0, i32 1
// CHECK3-NEXT: store ptr [[ARGC_ADDR]], ptr [[GEP_ARGC_ADDR]], align 8
// CHECK3-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 1, ptr @_Z5tmainIPPcEiT_..omp_par, ptr [[STRUCTARG]])
// CHECK3-NEXT: br label [[OMP_PAR_OUTLINED_EXIT:%.*]]
// CHECK3: omp.par.exit:
// CHECK3-NEXT: ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_..omp_par
// CHECK3-SAME: (ptr noalias [[TID_ADDR:%.*]], ptr noalias [[ZERO_ADDR:%.*]], ptr [[TMP0:%.*]]) #[[ATTR6:[0-9]+]] {
// CHECK3-NEXT: omp.par.entry:
// CHECK3-NEXT: [[GEP__RELOADED:%.*]] = getelementptr { ptr, ptr }, ptr [[TMP0]], i32 0, i32 0
// CHECK3-NEXT: [[LOADGEP__RELOADED:%.*]] = load ptr, ptr [[GEP__RELOADED]], align 8
// CHECK3-NEXT: [[GEP_ARGC_ADDR:%.*]] = getelementptr { ptr, ptr }, ptr [[TMP0]], i32 0, i32 1
// CHECK3-NEXT: [[LOADGEP_ARGC_ADDR:%.*]] = load ptr, ptr [[GEP_ARGC_ADDR]], align 8
// CHECK3-NEXT: [[TID_ADDR_LOCAL:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[TMP1:%.*]] = load i32, ptr [[TID_ADDR]], align 4
// CHECK3-NEXT: store i32 [[TMP1]], ptr [[TID_ADDR_LOCAL]], align 4
// CHECK3-NEXT: [[TID:%.*]] = load i32, ptr [[TID_ADDR_LOCAL]], align 4
// CHECK3-NEXT: [[VAR:%.*]] = alloca ptr, align 8
// CHECK3-NEXT: [[TMP2:%.*]] = load i64, ptr [[LOADGEP__RELOADED]], align 8
// CHECK3-NEXT: br label [[OMP_PAR_REGION:%.*]]
// CHECK3: omp.par.region:
// CHECK3-NEXT: [[TMP3:%.*]] = load ptr, ptr [[LOADGEP_ARGC_ADDR]], align 8
// CHECK3-NEXT: call void @_Z3fooIPPcEvT_(ptr noundef [[TMP3]])
// CHECK3-NEXT: [[TMP4:%.*]] = load ptr, ptr [[VAR]], align 8
// CHECK3-NEXT: [[TMP5:%.*]] = mul nsw i64 0, [[TMP2]]
// CHECK3-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds double, ptr [[TMP4]], i64 [[TMP5]]
// CHECK3-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds double, ptr [[ARRAYIDX2]], i64 0
// CHECK3-NEXT: br label [[OMP_PAR_REGION_PARALLEL_AFTER:%.*]]
// CHECK3: omp.par.region.parallel.after:
// CHECK3-NEXT: br label [[OMP_PAR_PRE_FINALIZE:%.*]]
// CHECK3: omp.par.pre_finalize:
// CHECK3-NEXT: br label [[OMP_PAR_OUTLINED_EXIT_EXITSTUB:%.*]]
// CHECK3: omp.par.exit.exitStub:
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z3fooIPPcEvT_
// CHECK3-SAME: (ptr noundef [[ARGC:%.*]]) #[[ATTR4]] comdat {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK3-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK3-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@main
// CHECK4-SAME: (i32 noundef [[ARGC:%.*]], ptr noundef [[ARGV:%.*]]) #[[ATTR0:[0-9]+]] !dbg [[DBG11:![0-9]+]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[STRUCTARG:%.*]] = alloca { ptr }, align 8
// CHECK4-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[ARGC_ADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[ARGV_ADDR:%.*]] = alloca ptr, align 8
// CHECK4-NEXT: [[SAVED_STACK:%.*]] = alloca ptr, align 8
// CHECK4-NEXT: [[__VLA_EXPR0:%.*]] = alloca i64, align 8
// CHECK4-NEXT: store i32 0, ptr [[RETVAL]], align 4
// CHECK4-NEXT: store i32 [[ARGC]], ptr [[ARGC_ADDR]], align 4
// CHECK4-NEXT: #dbg_declare(ptr [[ARGC_ADDR]], [[META18:![0-9]+]], !DIExpression(), [[META19:![0-9]+]])
// CHECK4-NEXT: store ptr [[ARGV]], ptr [[ARGV_ADDR]], align 8
// CHECK4-NEXT: #dbg_declare(ptr [[ARGV_ADDR]], [[META20:![0-9]+]], !DIExpression(), [[META19]])
// CHECK4-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARGC_ADDR]], align 4, !dbg [[DBG21:![0-9]+]]
// CHECK4-NEXT: [[TMP1:%.*]] = zext i32 [[TMP0]] to i64, !dbg [[DBG21]]
// CHECK4-NEXT: [[TMP2:%.*]] = call ptr @llvm.stacksave.p0(), !dbg [[DBG21]]
// CHECK4-NEXT: store ptr [[TMP2]], ptr [[SAVED_STACK]], align 8, !dbg [[DBG21]]
// CHECK4-NEXT: [[VLA:%.*]] = alloca i32, i64 [[TMP1]], align 16, !dbg [[DBG21]]
// CHECK4-NEXT: store i64 [[TMP1]], ptr [[__VLA_EXPR0]], align 8, !dbg [[DBG21]]
// CHECK4-NEXT: #dbg_declare(ptr [[__VLA_EXPR0]], [[META22:![0-9]+]], !DIExpression(), [[META24:![0-9]+]])
// CHECK4-NEXT: #dbg_declare(ptr [[VLA]], [[META25:![0-9]+]], !DIExpression(), [[DBG21]])
// CHECK4-NEXT: [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB1:[0-9]+]]), !dbg [[DBG29:![0-9]+]]
// CHECK4-NEXT: br label [[OMP_PARALLEL:%.*]]
// CHECK4: omp_parallel:
// CHECK4-NEXT: [[GEP_VLA:%.*]] = getelementptr { ptr }, ptr [[STRUCTARG]], i32 0, i32 0
// CHECK4-NEXT: store ptr [[VLA]], ptr [[GEP_VLA]], align 8
// CHECK4-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB1]], i32 1, ptr @main..omp_par, ptr [[STRUCTARG]]), !dbg [[DBG30:![0-9]+]]
// CHECK4-NEXT: br label [[OMP_PAR_OUTLINED_EXIT:%.*]]
// CHECK4: omp.par.exit:
// CHECK4-NEXT: [[TMP3:%.*]] = load ptr, ptr [[ARGV_ADDR]], align 8, !dbg [[DBG31:![0-9]+]]
// CHECK4-NEXT: [[CALL:%.*]] = call noundef i32 @_Z5tmainIPPcEiT_(ptr noundef [[TMP3]]), !dbg [[DBG31]]
// CHECK4-NEXT: store i32 [[CALL]], ptr [[RETVAL]], align 4, !dbg [[DBG31]]
// CHECK4-NEXT: [[TMP4:%.*]] = load ptr, ptr [[SAVED_STACK]], align 8, !dbg [[DBG32:![0-9]+]]
// CHECK4-NEXT: call void @llvm.stackrestore.p0(ptr [[TMP4]]), !dbg [[DBG32]]
// CHECK4-NEXT: [[TMP5:%.*]] = load i32, ptr [[RETVAL]], align 4, !dbg [[DBG32]]
// CHECK4-NEXT: ret i32 [[TMP5]], !dbg [[DBG32]]
//
//
// CHECK4-LABEL: define {{[^@]+}}@main..omp_par
// CHECK4-SAME: (ptr noalias [[TID_ADDR:%.*]], ptr noalias [[ZERO_ADDR:%.*]], ptr [[TMP0:%.*]]) #[[ATTR1:[0-9]+]] !dbg [[DBG33:![0-9]+]] {
// CHECK4-NEXT: omp.par.entry:
// CHECK4-NEXT: [[GEP_VLA:%.*]] = getelementptr { ptr }, ptr [[TMP0]], i32 0, i32 0
// CHECK4-NEXT: [[LOADGEP_VLA:%.*]] = load ptr, ptr [[GEP_VLA]], align 8
// CHECK4-NEXT: [[TID_ADDR_LOCAL:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[TMP1:%.*]] = load i32, ptr [[TID_ADDR]], align 4
// CHECK4-NEXT: store i32 [[TMP1]], ptr [[TID_ADDR_LOCAL]], align 4
// CHECK4-NEXT: [[TID:%.*]] = load i32, ptr [[TID_ADDR_LOCAL]], align 4
// CHECK4-NEXT: br label [[OMP_PAR_REGION:%.*]]
// CHECK4: omp.par.region:
// CHECK4-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[LOADGEP_VLA]], i64 1, !dbg [[DBG35:![0-9]+]]
// CHECK4-NEXT: [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX]], align 4, !dbg [[DBG35]]
// CHECK4-NEXT: call void @_Z3fooIiEvT_(i32 noundef [[TMP2]]), !dbg [[DBG35]]
// CHECK4-NEXT: [[TMP3:%.*]] = load i32, ptr @global, align 4, !dbg [[DBG35]]
// CHECK4-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[LOADGEP_VLA]], i64 1, !dbg [[DBG35]]
// CHECK4-NEXT: store i32 [[TMP3]], ptr [[ARRAYIDX1]], align 4, !dbg [[DBG35]]
// CHECK4-NEXT: br label [[OMP_PAR_REGION_PARALLEL_AFTER:%.*]], !dbg [[DBG35]]
// CHECK4: omp.par.region.parallel.after:
// CHECK4-NEXT: br label [[OMP_PAR_PRE_FINALIZE:%.*]]
// CHECK4: omp.par.pre_finalize:
// CHECK4-NEXT: br label [[OMP_PAR_OUTLINED_EXIT_EXITSTUB:%.*]], !dbg [[DBG35]]
// CHECK4: omp.par.exit.exitStub:
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_Z3fooIiEvT_
// CHECK4-SAME: (i32 noundef [[ARGC:%.*]]) #[[ATTR4:[0-9]+]] comdat !dbg [[DBG36:![0-9]+]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[ARGC_ADDR:%.*]] = alloca i32, align 4
// CHECK4-NEXT: store i32 [[ARGC]], ptr [[ARGC_ADDR]], align 4
// CHECK4-NEXT: #dbg_declare(ptr [[ARGC_ADDR]], [[META41:![0-9]+]], !DIExpression(), [[META42:![0-9]+]])
// CHECK4-NEXT: ret void, !dbg [[META42]]
//
//
// CHECK4-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_
// CHECK4-SAME: (ptr noundef [[ARGC:%.*]]) #[[ATTR5:[0-9]+]] comdat !dbg [[DBG43:![0-9]+]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[STRUCTARG:%.*]] = alloca { ptr, ptr }, align 8
// CHECK4-NEXT: [[DOTRELOADED:%.*]] = alloca i64, align 8
// CHECK4-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK4-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK4-NEXT: #dbg_declare(ptr [[ARGC_ADDR]], [[META48:![0-9]+]], !DIExpression(), [[META49:![0-9]+]])
// CHECK4-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ARGC_ADDR]], align 8, !dbg [[DBG50:![0-9]+]]
// CHECK4-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds ptr, ptr [[TMP0]], i64 0, !dbg [[DBG50]]
// CHECK4-NEXT: [[TMP1:%.*]] = load ptr, ptr [[ARRAYIDX]], align 8, !dbg [[DBG50]]
// CHECK4-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, ptr [[TMP1]], i64 0, !dbg [[DBG50]]
// CHECK4-NEXT: [[TMP2:%.*]] = load i8, ptr [[ARRAYIDX1]], align 1, !dbg [[DBG50]]
// CHECK4-NEXT: [[TMP3:%.*]] = zext i8 [[TMP2]] to i64, !dbg [[DBG50]]
// CHECK4-NEXT: [[OMP_GLOBAL_THREAD_NUM:%.*]] = call i32 @__kmpc_global_thread_num(ptr @[[GLOB3:[0-9]+]]), !dbg [[DBG51:![0-9]+]]
// CHECK4-NEXT: store i64 [[TMP3]], ptr [[DOTRELOADED]], align 8
// CHECK4-NEXT: br label [[OMP_PARALLEL:%.*]]
// CHECK4: omp_parallel:
// CHECK4-NEXT: [[GEP__RELOADED:%.*]] = getelementptr { ptr, ptr }, ptr [[STRUCTARG]], i32 0, i32 0
// CHECK4-NEXT: store ptr [[DOTRELOADED]], ptr [[GEP__RELOADED]], align 8
// CHECK4-NEXT: [[GEP_ARGC_ADDR:%.*]] = getelementptr { ptr, ptr }, ptr [[STRUCTARG]], i32 0, i32 1
// CHECK4-NEXT: store ptr [[ARGC_ADDR]], ptr [[GEP_ARGC_ADDR]], align 8
// CHECK4-NEXT: call void (ptr, i32, ptr, ...) @__kmpc_fork_call(ptr @[[GLOB3]], i32 1, ptr @_Z5tmainIPPcEiT_..omp_par, ptr [[STRUCTARG]]), !dbg [[DBG52:![0-9]+]]
// CHECK4-NEXT: br label [[OMP_PAR_OUTLINED_EXIT:%.*]]
// CHECK4: omp.par.exit:
// CHECK4-NEXT: ret i32 0, !dbg [[DBG54:![0-9]+]]
//
//
// CHECK4-LABEL: define {{[^@]+}}@_Z5tmainIPPcEiT_..omp_par
// CHECK4-SAME: (ptr noalias [[TID_ADDR:%.*]], ptr noalias [[ZERO_ADDR:%.*]], ptr [[TMP0:%.*]]) #[[ATTR6:[0-9]+]] !dbg [[DBG55:![0-9]+]] {
// CHECK4-NEXT: omp.par.entry:
// CHECK4-NEXT: [[GEP__RELOADED:%.*]] = getelementptr { ptr, ptr }, ptr [[TMP0]], i32 0, i32 0
// CHECK4-NEXT: [[LOADGEP__RELOADED:%.*]] = load ptr, ptr [[GEP__RELOADED]], align 8
// CHECK4-NEXT: [[GEP_ARGC_ADDR:%.*]] = getelementptr { ptr, ptr }, ptr [[TMP0]], i32 0, i32 1
// CHECK4-NEXT: [[LOADGEP_ARGC_ADDR:%.*]] = load ptr, ptr [[GEP_ARGC_ADDR]], align 8
// CHECK4-NEXT: [[TID_ADDR_LOCAL:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[TMP1:%.*]] = load i32, ptr [[TID_ADDR]], align 4
// CHECK4-NEXT: store i32 [[TMP1]], ptr [[TID_ADDR_LOCAL]], align 4
// CHECK4-NEXT: [[TID:%.*]] = load i32, ptr [[TID_ADDR_LOCAL]], align 4
// CHECK4-NEXT: [[VAR:%.*]] = alloca ptr, align 8
// CHECK4-NEXT: [[TMP2:%.*]] = load i64, ptr [[LOADGEP__RELOADED]], align 8
// CHECK4-NEXT: br label [[OMP_PAR_REGION:%.*]]
// CHECK4: omp.par.region:
// CHECK4-NEXT: [[TMP3:%.*]] = load ptr, ptr [[LOADGEP_ARGC_ADDR]], align 8, !dbg [[DBG56:![0-9]+]]
// CHECK4-NEXT: call void @_Z3fooIPPcEvT_(ptr noundef [[TMP3]]), !dbg [[DBG56]]
// CHECK4-NEXT: #dbg_declare(ptr [[VAR]], [[META58:![0-9]+]], !DIExpression(), [[META65:![0-9]+]])
// CHECK4-NEXT: [[TMP4:%.*]] = load ptr, ptr [[VAR]], align 8, !dbg [[META65]]
// CHECK4-NEXT: [[TMP5:%.*]] = mul nsw i64 0, [[TMP2]], !dbg [[META65]]
// CHECK4-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds double, ptr [[TMP4]], i64 [[TMP5]], !dbg [[META65]]
// CHECK4-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds double, ptr [[ARRAYIDX2]], i64 0, !dbg [[META65]]
// CHECK4-NEXT: br label [[OMP_PAR_REGION_PARALLEL_AFTER:%.*]], !dbg [[DBG66:![0-9]+]]
// CHECK4: omp.par.region.parallel.after:
// CHECK4-NEXT: br label [[OMP_PAR_PRE_FINALIZE:%.*]]
// CHECK4: omp.par.pre_finalize:
// CHECK4-NEXT: br label [[OMP_PAR_OUTLINED_EXIT_EXITSTUB:%.*]], !dbg [[DBG66]]
// CHECK4: omp.par.exit.exitStub:
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_Z3fooIPPcEvT_
// CHECK4-SAME: (ptr noundef [[ARGC:%.*]]) #[[ATTR4]] comdat !dbg [[DBG69:![0-9]+]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[ARGC_ADDR:%.*]] = alloca ptr, align 8
// CHECK4-NEXT: store ptr [[ARGC]], ptr [[ARGC_ADDR]], align 8
// CHECK4-NEXT: #dbg_declare(ptr [[ARGC_ADDR]], [[META72:![0-9]+]], !DIExpression(), [[META73:![0-9]+]])
// CHECK4-NEXT: ret void, !dbg [[META73]]
//
Reference in New Issue View Git Blame Copy Permalink