// RUN: %clang_cc1 -verify -fopenmp -x c++ -emit-llvm %s -triple %itanium_abi_triple -fexceptions -fcxx-exceptions -o - | FileCheck %s
// 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 %s -emit-llvm -o - | FileCheck --check-prefix=CHECK-DEBUG %s
// expected-no-diagnostics
// REQUIRES: x86-registered-target
#ifndef HEADER
#define HEADER
// CHECK-DAG: %ident_t = type { i32, i32, i32, i32, i8* }
// CHECK-DAG: [[STR:@.+]] = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00"
// CHECK-DAG: [[DEF_LOC_2:@.+]] = private unnamed_addr constant %ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
// CHECK-DEBUG-DAG: %ident_t = type { i32, i32, i32, i32, i8* }
// CHECK-DEBUG-DAG: [[STR:@.+]] = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00"
// CHECK-DEBUG-DAG: [[DEF_LOC_2:@.+]] = private unnamed_addr constant %ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
// CHECK-DEBUG-DAG: [[LOC1:@.+]] = private unnamed_addr constant [{{.+}} x i8] c";{{.*}}parallel_codegen.cpp;main;[[@LINE+14]];9;;\00"
// CHECK-DEBUG-DAG: [[LOC2:@.+]] = private unnamed_addr constant [{{.+}} x i8] c";{{.*}}parallel_codegen.cpp;tmain;[[@LINE+7]];9;;\00"

template <class T>
void foo(T argc) {}

template <typename T>
int tmain(T argc) {
#pragma omp parallel
  foo(argc);
  return 0;
}

int main (int argc, char **argv) {
#pragma omp parallel
  foo(argc);
  return tmain(argv);
}

// CHECK-LABEL: define {{[a-z\_\b]*[ ]?i32}} @main({{i32[ ]?[a-z]*}} %argc, i8** %argv)
// CHECK: store i32 %argc, i32* [[ARGC_ADDR:%.+]],
// CHECK:  call {{.*}}void (%ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%ident_t* [[DEF_LOC_2]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i32* [[ARGC_ADDR]])
// CHECK-NEXT:  [[ARGV:%.+]] = load i8**, i8*** {{%[a-z0-9.]+}}
// CHECK-NEXT:  [[RET:%.+]] = call {{[a-z\_\b]*[ ]?i32}} [[TMAIN:@.+tmain.+]](i8** [[ARGV]])
// CHECK-NEXT:  ret i32 [[RET]]
// CHECK-NEXT:  }
// CHECK-DEBUG-LABEL: define i32 @main(i32 %argc, i8** %argv)
// CHECK-DEBUG:       [[LOC_2_ADDR:%.+]] = alloca %ident_t
// CHECK-DEBUG:       [[KMPC_LOC_VOIDPTR:%.+]] = bitcast %ident_t* [[LOC_2_ADDR]] to i8*
// CHECK-DEBUG-NEXT:  [[KMPC_DEFAULT_LOC_VOIDPTR:%.+]] = bitcast %ident_t* [[DEF_LOC_2]] to i8*
// CHECK-DEBUG-NEXT:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[KMPC_LOC_VOIDPTR]], i8* [[KMPC_DEFAULT_LOC_VOIDPTR]], i64 24, i32 8, i1 false)
// CHECK-DEBUG:       store i32 %argc, i32* [[ARGC_ADDR:%.+]],
// CHECK-DEBUG:       [[KMPC_LOC_PSOURCE_REF:%.+]] = getelementptr inbounds %ident_t, %ident_t* [[LOC_2_ADDR]], i32 0, i32 4
// CHECK-DEBUG-NEXT:  store i8* getelementptr inbounds ([{{.+}} x i8], [{{.+}} x i8]* [[LOC1]], i32 0, i32 0), i8** [[KMPC_LOC_PSOURCE_REF]]
// CHECK-DEBUG:  call {{.*}}void (%ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%ident_t* [[LOC_2_ADDR]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i32* [[ARGC_ADDR]])
// CHECK-DEBUG-NEXT:  [[ARGV:%.+]] = load i8**, i8*** {{%[a-z0-9.]+}}
// CHECK-DEBUG-NEXT:  [[RET:%.+]] = call i32 [[TMAIN:@.+tmain.+]](i8** [[ARGV]])
// CHECK-DEBUG-NEXT:  ret i32 [[RET]]
// CHECK-DEBUG-NEXT:  }

// CHECK:       define internal {{.*}}void [[OMP_OUTLINED]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i32* dereferenceable(4) [[ARGC_ADDR:%[^)]+]])
// CHECK-SAME:       #[[FN_ATTRS:[0-9]+]]
// CHECK:       store i32* [[ARGC_ADDR]], i32** [[ARGC_PTR_ADDR:%.+]],
// CHECK:       [[ARGC_REF:%.+]] = load i32*, i32** [[ARGC_PTR_ADDR]]
// CHECK-NEXT:  [[ARGC:%.+]] = load i32, i32* [[ARGC_REF]]
// CHECK-NEXT:  invoke {{.*}}void [[FOO:@.+foo.+]](i32{{[ ]?[a-z]*}} [[ARGC]])
// CHECK:       ret void
// CHECK:       call {{.*}}void @{{.+terminate.*|abort}}(
// CHECK-NEXT:  unreachable
// CHECK-NEXT:  }
// CHECK-DEBUG:       define internal void [[OMP_OUTLINED]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i32* dereferenceable(4) [[ARGC_ADDR:%[^)]+]])
// CHECK-DEBUG-SAME:  #[[FN_ATTRS:[0-9]+]]
// CHECK-DEBUG:       store i32* [[ARGC_ADDR]], i32** [[ARGC_PTR_ADDR:%.+]],
// CHECK-DEBUG:  [[ARGC_REF:%.+]] = load i32*, i32** [[ARGC_PTR_ADDR]]
// CHECK-DEBUG-NEXT:  [[ARGC:%.+]] = load i32, i32* [[ARGC_REF]]
// CHECK-DEBUG-NEXT:  invoke void [[FOO:@.+foo.+]](i32 [[ARGC]])
// CHECK-DEBUG:       ret void
// CHECK-DEBUG:       call void @{{.+terminate.*|abort}}(
// CHECK-DEBUG-NEXT:  unreachable
// CHECK-DEBUG-NEXT:  }

// CHECK-DAG: define linkonce_odr {{.*}}void [[FOO]]({{i32[ ]?[a-z]*}} %argc)
// CHECK-DAG: declare {{.*}}void @__kmpc_fork_call(%ident_t*, i32, void (i32*, i32*, ...)*, ...)
// CHECK-DEBUG-DAG: define linkonce_odr void [[FOO]](i32 %argc)
// CHECK-DEBUG-DAG: declare void @__kmpc_fork_call(%ident_t*, i32, void (i32*, i32*, ...)*, ...)

// CHECK:       define linkonce_odr {{[a-z\_\b]*[ ]?i32}} [[TMAIN]](i8** %argc)
// CHECK:       store i8** %argc, i8*** [[ARGC_ADDR:%.+]],
// CHECK-NEXT:  call {{.*}}void (%ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%ident_t* [[DEF_LOC_2]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i8***)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i8*** [[ARGC_ADDR]])
// CHECK-NEXT:  ret i32 0
// CHECK-NEXT:  }
// CHECK-DEBUG:       define linkonce_odr i32 [[TMAIN]](i8** %argc)
// CHECK-DEBUG-DAG:   [[LOC_2_ADDR:%.+]] = alloca %ident_t
// CHECK-DEBUG:       [[KMPC_LOC_VOIDPTR:%.+]] = bitcast %ident_t* [[LOC_2_ADDR]] to i8*
// CHECK-DEBUG-NEXT:  [[KMPC_DEFAULT_LOC_VOIDPTR:%.+]] = bitcast %ident_t* [[DEF_LOC_2]] to i8*
// CHECK-DEBUG-NEXT:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[KMPC_LOC_VOIDPTR]], i8* [[KMPC_DEFAULT_LOC_VOIDPTR]], i64 24, i32 8, i1 false)
// CHECK-DEBUG-NEXT:  store i8** %argc, i8*** [[ARGC_ADDR:%.+]],
// CHECK-DEBUG:  [[KMPC_LOC_PSOURCE_REF:%.+]] = getelementptr inbounds %ident_t, %ident_t* [[LOC_2_ADDR]], i32 0, i32 4
// CHECK-DEBUG-NEXT:  store i8* getelementptr inbounds ([{{.+}} x i8], [{{.+}} x i8]* [[LOC2]], i32 0, i32 0), i8** [[KMPC_LOC_PSOURCE_REF]]
// CHECK-DEBUG-NEXT:  call void (%ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%ident_t* [[LOC_2_ADDR]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i8***)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i8*** [[ARGC_ADDR]])
// CHECK-DEBUG-NEXT:  ret i32 0
// CHECK-DEBUG-NEXT:  }

// CHECK:       define internal {{.*}}void [[OMP_OUTLINED]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i8*** dereferenceable({{4|8}}) %argc)
// CHECK:       store i8*** %argc, i8**** [[ARGC_PTR_ADDR:%.+]],
// CHECK:       [[ARGC_REF:%.+]] = load i8***, i8**** [[ARGC_PTR_ADDR]]
// CHECK-NEXT:  [[ARGC:%.+]] = load i8**, i8*** [[ARGC_REF]]
// CHECK-NEXT:  invoke {{.*}}void [[FOO1:@.+foo.+]](i8** [[ARGC]])
// CHECK:       ret void
// CHECK:       call {{.*}}void @{{.+terminate.*|abort}}(
// CHECK-NEXT:  unreachable
// CHECK-NEXT:  }
// CHECK-DEBUG:       define internal void [[OMP_OUTLINED]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i8*** dereferenceable({{4|8}}) %argc)
// CHECK-DEBUG:       store i8*** %argc, i8**** [[ARGC_PTR_ADDR:%.+]],
// CHECK-DEBUG:       [[ARGC_REF:%.+]] = load i8***, i8**** [[ARGC_PTR_ADDR]]
// CHECK-DEBUG-NEXT:  [[ARGC:%.+]] = load i8**, i8*** [[ARGC_REF]]
// CHECK-DEBUG-NEXT:  invoke void [[FOO1:@.+foo.+]](i8** [[ARGC]])
// CHECK-DEBUG:       ret void
// CHECK-DEBUG:       call void @{{.+terminate.*|abort}}(
// CHECK-DEBUG-NEXT:  unreachable
// CHECK-DEBUG-NEXT:  }

// CHECK: define linkonce_odr {{.*}}void [[FOO1]](i8** %argc)
// CHECK-DEBUG: define linkonce_odr void [[FOO1]](i8** %argc)

// CHECK: attributes #[[FN_ATTRS]] = {{.+}} nounwind
// CHECK-DEBUG: attributes #[[FN_ATTRS]] = {{.+}} nounwind

#endif