[OpenMP] Use the OpenMPIRBuilder for `omp parallel`

This allows to use the OpenMPIRBuilder for parallel regions. Code was
extracted from D61953 and adapted to work with the new version (D70109).

All but one feature should be supported. An update of this patch will
provide test coverage and privatization other than shared.

Reviewed By: fghanim

Differential Revision: https://reviews.llvm.org/D70290

2 files changed, 142 insertions, 94 deletions

diff --git a/clang/test/OpenMP/cancel_codegen.cpp b/clang/test/OpenMP/cancel_codegen.cpp
index ee03edf7cd2..b2ef1d519c8 100644
--- a/clang/test/OpenMP/cancel_codegen.cpp
+++ b/clang/test/OpenMP/cancel_codegen.cpp
@@ -1,10 +1,10 @@
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - %s | FileCheck %s --check-prefixes=ALL,CHECK
 // RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -x c++ -std=c++11 -triple x86_64-apple-darwin13.4.0 -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -std=c++11 -include-pch %t -fsyntax-only -verify %s -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -std=c++11 -include-pch %t -fsyntax-only -verify %s -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - | FileCheck %s --check-prefixes=ALL,CHECK
 
-// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-enable-irbuilder -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -fopenmp-enable-irbuilder -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - %s | FileCheck %s --check-prefixes=ALL,IRBUILDER
 // RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-enable-irbuilder -x c++ -std=c++11 -triple x86_64-apple-darwin13.4.0 -emit-pch -o %t %s
-// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-enable-irbuilder -std=c++11 -include-pch %t -fsyntax-only -verify %s -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - | FileCheck %s
+// RUN: %clang_cc1 -fopenmp -fopenmp-version=45 -fopenmp-enable-irbuilder -std=c++11 -include-pch %t -fsyntax-only -verify %s -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - | FileCheck %s --check-prefixes=ALL,IRBUILDER
 
 // RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-version=45 -triple x86_64-apple-darwin13.4.0 -emit-llvm -o - %s | FileCheck --check-prefix SIMD-ONLY0 %s
 // RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=45 -x c++ -std=c++11 -triple x86_64-apple-darwin13.4.0 -emit-pch -o %t %s
@@ -16,7 +16,7 @@
 
 float flag;
 int main (int argc, char **argv) {
-// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num(
+// ALL: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num(
 #pragma omp parallel
 {
 #pragma omp cancel parallel if(flag)
@@ -24,15 +24,15 @@ int main (int argc, char **argv) {
 #pragma omp barrier
   argv[0][0] += argc;
 }
-// CHECK: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
+// ALL: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
 #pragma omp sections
 {
 #pragma omp cancel sections
 }
-// CHECK: call void @__kmpc_for_static_init_4(
-// CHECK: call i32 @__kmpc_cancel(
-// CHECK: call void @__kmpc_for_static_fini(
-// CHECK: call void @__kmpc_barrier(%struct.ident_t*
+// ALL: call void @__kmpc_for_static_init_4(
+// ALL: call i32 @__kmpc_cancel(
+// ALL: call void @__kmpc_for_static_fini(
+// ALL: call void @__kmpc_barrier(%struct.ident_t*
 #pragma omp sections
 {
 #pragma omp cancel sections
@@ -41,53 +41,53 @@ int main (int argc, char **argv) {
 #pragma omp cancel sections
   }
 }
-// CHECK: call void @__kmpc_for_static_init_4(
-// CHECK: [[RES:%.+]] = call i32 @__kmpc_cancel(%struct.ident_t* {{[^,]+}}, i32 [[GTID]], i32 3)
-// CHECK: [[CMP:%.+]] = icmp ne i32 [[RES]], 0
-// CHECK: br i1 [[CMP]], label %[[EXIT:[^,].+]], label %[[CONTINUE:.+]]
-// CHECK: [[EXIT]]
-// CHECK: br label
-// CHECK: [[CONTINUE]]
-// CHECK: br label
-// CHECK: [[RES:%.+]] = call i32 @__kmpc_cancel(%struct.ident_t* {{[^,]+}}, i32 [[GTID]], i32 3)
-// CHECK: [[CMP:%.+]] = icmp ne i32 [[RES]], 0
-// CHECK: br i1 [[CMP]], label %[[EXIT:[^,].+]], label %[[CONTINUE:.+]]
-// CHECK: [[EXIT]]
-// CHECK: br label
-// CHECK: [[CONTINUE]]
-// CHECK: br label
-// CHECK: call void @__kmpc_for_static_fini(
+// ALL: call void @__kmpc_for_static_init_4(
+// ALL: [[RES:%.+]] = call i32 @__kmpc_cancel(%struct.ident_t* {{[^,]+}}, i32 [[GTID]], i32 3)
+// ALL: [[CMP:%.+]] = icmp ne i32 [[RES]], 0
+// ALL: br i1 [[CMP]], label %[[EXIT:[^,].+]], label %[[CONTINUE:.+]]
+// ALL: [[EXIT]]
+// ALL: br label
+// ALL: [[CONTINUE]]
+// ALL: br label
+// ALL: [[RES:%.+]] = call i32 @__kmpc_cancel(%struct.ident_t* {{[^,]+}}, i32 [[GTID]], i32 3)
+// ALL: [[CMP:%.+]] = icmp ne i32 [[RES]], 0
+// ALL: br i1 [[CMP]], label %[[EXIT:[^,].+]], label %[[CONTINUE:.+]]
+// ALL: [[EXIT]]
+// ALL: br label
+// ALL: [[CONTINUE]]
+// ALL: br label
+// ALL: call void @__kmpc_for_static_fini(
 #pragma omp for
 for (int i = 0; i < argc; ++i) {
 #pragma omp cancel for if(cancel: flag)
 }
-// CHECK: call void @__kmpc_for_static_init_4(
-// CHECK: [[FLAG:%.+]] = load float, float* @{{.+}},
-// CHECK: [[BOOL:%.+]] = fcmp une float [[FLAG]], 0.000000e+00
-// CHECK: br i1 [[BOOL]], label %[[THEN:[^,]+]], label %[[ELSE:[^,]+]]
-// CHECK: [[THEN]]
-// CHECK: [[RES:%.+]] = call i32 @__kmpc_cancel(%struct.ident_t* {{[^,]+}}, i32 [[GTID]], i32 2)
-// CHECK: [[CMP:%.+]] = icmp ne i32 [[RES]], 0
-// CHECK: br i1 [[CMP]], label %[[EXIT:[^,].+]], label %[[CONTINUE:.+]]
-// CHECK: [[EXIT]]
-// CHECK: br label
-// CHECK: [[CONTINUE]]
-// CHECK: br label
-// CHECK: [[ELSE]]
-// CHECK: br label
-// CHECK: call void @__kmpc_for_static_fini(
-// CHECK: call void @__kmpc_barrier(%struct.ident_t*
+// ALL: call void @__kmpc_for_static_init_4(
+// ALL: [[FLAG:%.+]] = load float, float* @{{.+}},
+// ALL: [[BOOL:%.+]] = fcmp une float [[FLAG]], 0.000000e+00
+// ALL: br i1 [[BOOL]], label %[[THEN:[^,]+]], label %[[ELSE:[^,]+]]
+// ALL: [[THEN]]
+// ALL: [[RES:%.+]] = call i32 @__kmpc_cancel(%struct.ident_t* {{[^,]+}}, i32 [[GTID]], i32 2)
+// ALL: [[CMP:%.+]] = icmp ne i32 [[RES]], 0
+// ALL: br i1 [[CMP]], label %[[EXIT:[^,].+]], label %[[CONTINUE:.+]]
+// ALL: [[EXIT]]
+// ALL: br label
+// ALL: [[CONTINUE]]
+// ALL: br label
+// ALL: [[ELSE]]
+// ALL: br label
+// ALL: call void @__kmpc_for_static_fini(
+// ALL: call void @__kmpc_barrier(%struct.ident_t*
 #pragma omp task
 {
 #pragma omp cancel taskgroup
 }
-// CHECK: call i8* @__kmpc_omp_task_alloc(
-// CHECK: call i32 @__kmpc_omp_task(
+// ALL: call i8* @__kmpc_omp_task_alloc(
+// ALL: call i32 @__kmpc_omp_task(
 #pragma omp parallel sections
 {
 #pragma omp cancel sections
 }
-// CHECK: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
+// ALL: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
 #pragma omp parallel sections
 {
 #pragma omp cancel sections
@@ -96,14 +96,14 @@ for (int i = 0; i < argc; ++i) {
 #pragma omp cancel sections
   }
 }
-// CHECK: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
+// ALL: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
 int r = 0;
 #pragma omp parallel for reduction(+: r)
 for (int i = 0; i < argc; ++i) {
 #pragma omp cancel for
   r += i;
 }
-// CHECK: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
+// ALL: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(
   return argc;
 }
 
@@ -173,4 +173,29 @@ for (int i = 0; i < argc; ++i) {
 // CHECK: call void @__kmpc_for_static_fini(
 // CHECK: ret void
 
+// IRBUILDER: define internal void @main
+
+// IRBUILDER: [[RETURN:omp.par.exit[^:]*]]
+// IRBUILDER-NEXT: ret void
+// IRBUILDER: [[FLAG:%.+]] = load float, float* @{{.+}},
+
+// IRBUILDER: [[BOOL:%.+]] = fcmp une float [[FLAG]], 0.000000e+00
+// IRBUILDER: br i1 [[BOOL]], label %[[THEN:[^,]+]], label %[[ELSE:[^,]+]]
+// IRBUILDER: [[ELSE]]
+// IRBUILDER-NEXT:   br label %[[ELSE2:.*]]
+// IRBUILDER: [[ELSE2]]
+// The barrier directive should now call __kmpc_cancel_barrier
+// IRBUILDER: call i32 @__kmpc_cancel_barrier(%struct.ident_t*
+// IRBUILDER: br label
+// IRBUILDER: [[THEN]]
+// IRBUILDER: [[RES:%.+]] = call i32 @__kmpc_cancel(%struct.ident_t* {{[^,]+}}, i32 {{[^,]+}}, i32 1)
+// IRBUILDER: [[CMP:%.+]] = icmp eq i32 [[RES]], 0
+// IRBUILDER: br i1 [[CMP]], label %[[CONTINUE:[^,].+]], label %[[EXIT:.+]]
+// IRBUILDER: [[EXIT]]
+// IRBUILDER: br label %[[EXIT2:.+]]
+// IRBUILDER: [[EXIT2]]
+// IRBUILDER: br label %[[RETURN]]
+// IRBUILDER: [[CONTINUE]]
+// IRBUILDER: br label %[[ELSE:.+]]
+
 #endif
diff --git a/clang/test/OpenMP/parallel_codegen.cpp b/clang/test/OpenMP/parallel_codegen.cpp
index 498a0590b51..55246bfac46 100644
--- a/clang/test/OpenMP/parallel_codegen.cpp
+++ b/clang/test/OpenMP/parallel_codegen.cpp
@@ -1,22 +1,31 @@
-// RUN: %clang_cc1 -verify -fopenmp -x c++ -emit-llvm %s -triple %itanium_abi_triple -fexceptions -fcxx-exceptions -o - | FileCheck %s
+// RUN: %clang_cc1 -verify -fopenmp -x c++ -emit-llvm %s -triple %itanium_abi_triple -fexceptions -fcxx-exceptions -o - | FileCheck %s --check-prefixes=ALL,CHECK
 // 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
+// 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-prefixes=ALL-DEBUG,CHECK-DEBUG %s
+// RUN: %clang_cc1 -verify -fopenmp -fopenmp-enable-irbuilder -x c++ -emit-llvm %s -triple %itanium_abi_triple -fexceptions -fcxx-exceptions -o - | FileCheck %s --check-prefixes=ALL,IRBUILDER
+// RUN: %clang_cc1 -fopenmp -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 -fopenmp-enable-irbuilder -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-prefixes=ALL-DEBUG,IRBUILDER-DEBUG %s
 
 // RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -emit-llvm %s -triple %itanium_abi_triple -fexceptions -fcxx-exceptions -o - | FileCheck --check-prefix SIMD-ONLY0 %s
 // 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 %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
+// RUN: %clang_cc1 -verify -fopenmp-simd -fopenmp-enable-irbuilder -x c++ -emit-llvm %s -triple %itanium_abi_triple -fexceptions -fcxx-exceptions -o - | FileCheck --check-prefix SIMD-ONLY0 %s
+// 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 %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
 // SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
 // expected-no-diagnostics
 #ifndef HEADER
 #define HEADER
-// CHECK-DAG: %struct.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 global %struct.ident_t { i32 0, i32 2, i32 0, i32 0, i8* getelementptr inbounds ([23 x i8], [23 x i8]* [[STR]], i32 0, i32 0) }
+// ALL-DAG: %struct.ident_t = type { i32, i32, i32, i32, i8* }
+// ALL-DAG: [[STR:@.+]] = private unnamed_addr constant [23 x i8] c";unknown;unknown;0;0;;\00"
+// ALL-DAG: [[DEF_LOC_2:@.+]] = private unnamed_addr global %struct.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: %struct.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 global %struct.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+19]];1;;\00"
-// CHECK-DEBUG-DAG: [[LOC2:@.+]] = private unnamed_addr constant [{{.+}} x i8] c";{{.*}}parallel_codegen.cpp;tmain;[[@LINE+8]];1;;\00"
+// CHECK-DEBUG-DAG: [[LOC1:@.+]] = private unnamed_addr constant [{{.+}} x i8] c";{{.*}}parallel_codegen.cpp;main;[[@LINE+22]];1;;\00"
+// CHECK-DEBUG-DAG: [[LOC2:@.+]] = private unnamed_addr constant [{{.+}} x i8] c";{{.*}}parallel_codegen.cpp;tmain;[[@LINE+11]];1;;\00"
+// IRBUILDER-DEBUG-DAG: %struct.ident_t = type { i32, i32, i32, i32, i8* }
+// IRBUILDER-DEBUG-DAG: [[LOC1:@.+]] = private unnamed_addr constant [{{.+}} x i8] c";{{.*}}parallel_codegen.cpp;main;[[@LINE+19]];0;;\00"
+// IRBUILDER-DEBUG-DAG: [[LOC2:@.+]] = private unnamed_addr constant [{{.+}} x i8] c";{{.*}}parallel_codegen.cpp;tmain<char **>;[[@LINE+8]];0;;\00"
 
 template <class T>
 void foo(T argc) {}
@@ -39,65 +48,74 @@ int main (int argc, char **argv) {
   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: [[VLA:%.+]] = alloca i32, i{{[0-9]+}} [[VLA_SIZE:%[^,]+]],
+// ALL-LABEL: define {{[a-z\_\b]*[ ]?i32}} @main({{i32[ ]?[a-z]*}} %argc, i8** %argv)
+// ALL: store i32 %argc, i32* [[ARGC_ADDR:%.+]],
+// ALL: [[VLA:%.+]] = alloca i32, i{{[0-9]+}} [[VLA_SIZE:%[^,]+]],
 // CHECK:  call {{.*}}void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* [[DEF_LOC_2]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i{{[0-9]+}}, i32*)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i{{[0-9]+}} [[VLA_SIZE]], i32* [[VLA]])
-// CHECK-NEXT:  [[ARGV:%.+]] = load i8**, i8*** {{%[a-z0-9.]+}}
-// CHECK-NEXT:  [[RET:%.+]] = call {{[a-z\_\b]*[ ]?i32}} [[TMAIN:@.+tmain.+]](i8** [[ARGV]])
-// CHECK:       ret i32
-// CHECK-NEXT:  }
-// CHECK-DEBUG-LABEL: define i32 @main(i32 %argc, i8** %argv)
+// IRBUILDER:   call {{.*}}void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* [[DEF_LOC_2]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i32* [[VLA]])
+// ALL:  [[ARGV:%.+]] = load i8**, i8*** {{%[a-z0-9.]+}}
+// ALL-NEXT:  [[RET:%.+]] = call {{[a-z\_\b]*[ ]?i32}} [[TMAIN:@.+tmain.+]](i8** [[ARGV]])
+// ALL:       ret i32
+// ALL-NEXT:  }
+// ALL-DEBUG-LABEL: define i32 @main(i32 %argc, i8** %argv)
 // CHECK-DEBUG:       [[LOC_2_ADDR:%.+]] = alloca %struct.ident_t
 // CHECK-DEBUG:       [[KMPC_LOC_VOIDPTR:%.+]] = bitcast %struct.ident_t* [[LOC_2_ADDR]] to i8*
 // CHECK-DEBUG-NEXT:  [[KMPC_DEFAULT_LOC_VOIDPTR:%.+]] = bitcast %struct.ident_t* [[DEF_LOC_2]] to i8*
 // CHECK-DEBUG-NEXT:   call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[KMPC_LOC_VOIDPTR]], i8* align 8 [[KMPC_DEFAULT_LOC_VOIDPTR]], i64 24, i1 false)
-// CHECK-DEBUG:       store i32 %argc, i32* [[ARGC_ADDR:%.+]],
-// CHECK-DEBUG:       [[VLA:%.+]] = alloca i32, i64 [[VLA_SIZE:%[^,]+]],
+// ALL-DEBUG:       store i32 %argc, i32* [[ARGC_ADDR:%.+]],
+// ALL-DEBUG:       [[VLA:%.+]] = alloca i32, i64 [[VLA_SIZE:%[^,]+]],
 // CHECK-DEBUG:       [[KMPC_LOC_PSOURCE_REF:%.+]] = getelementptr inbounds %struct.ident_t, %struct.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 (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* [[LOC_2_ADDR]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i64, i32*)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i64 [[VLA_SIZE]], i32* [[VLA]])
-// CHECK-DEBUG-NEXT:  [[ARGV:%.+]] = load i8**, i8*** {{%[a-z0-9.]+}}
-// CHECK-DEBUG-NEXT:  [[RET:%.+]] = call i32 [[TMAIN:@.+tmain.+]](i8** [[ARGV]])
-// CHECK-DEBUG:       ret i32
-// CHECK-DEBUG-NEXT:  }
+// IRBUILDER-DEBUG:       call {{.*}}void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @{{.*}}, i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i32* [[VLA]])
+// ALL-DEBUG:        [[ARGV:%.+]] = load i8**, i8*** {{%[a-z0-9.]+}}
+// ALL-DEBUG:        [[RET:%.+]] = call i32 [[TMAIN:@.+tmain.+]](i8** [[ARGV]])
+// ALL-DEBUG:        ret i32
+// ALL-DEBUG-NEXT:  }
 
-// CHECK:       define internal {{.*}}void [[OMP_OUTLINED]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i{{[0-9]+}}{{.*}} [[VLA_SIZE:%.+]], i32* {{.+}} [[VLA_ADDR:%[^)]+]])
-// CHECK-SAME:       #[[FN_ATTRS:[0-9]+]]
+// CHECK:           define internal {{.*}}void [[OMP_OUTLINED]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i{{[0-9]+}}{{.*}} [[VLA_SIZE:%.+]], i32* {{.+}} [[VLA_ADDR:%[^)]+]])
+// CHECK-SAME:      #[[FN_ATTRS:[0-9]+]]
+// IRBUILDER:       define internal {{.*}}void [[OMP_OUTLINED]](i32* noalias %{{.*}}, i32* noalias %{{.*}}, i32* [[VLA_REF:%[^)]+]])
+// IRBUILDER-SAME:  #[[FN_ATTRS:[0-9]+]]
 // CHECK:       store i32* [[VLA_ADDR]], i32** [[VLA_PTR_ADDR:%.+]],
 // CHECK:       [[VLA_REF:%.+]] = load i32*, i32** [[VLA_PTR_ADDR]]
-// CHECK:       [[VLA_ELEM_REF:%.+]] = getelementptr inbounds i32, i32* [[VLA_REF]], i{{[0-9]+}} 1
-// CHECK-NEXT:  [[VLA_ELEM:%.+]] = load i32, i32* [[VLA_ELEM_REF]]
+// ALL:       [[VLA_ELEM_REF:%.+]] = getelementptr inbounds i32, i32* [[VLA_REF]], i{{[0-9]+}} 1
+// ALL-NEXT:  [[VLA_ELEM:%.+]] = load i32, i32* [[VLA_ELEM_REF]]
 // CHECK-NEXT:  invoke {{.*}}void [[FOO:@.+foo.+]](i32{{[ ]?[a-z]*}} [[VLA_ELEM]])
+// IRBUILDER: call {{.*}}void [[FOO:@.+foo.+]](i32{{[ ]?[a-z]*}} [[VLA_ELEM]])
 // CHECK:       ret void
 // CHECK:       call {{.*}}void @{{.+terminate.*|abort}}(
 // CHECK-NEXT:  unreachable
 // CHECK-NEXT:  }
-// CHECK-DEBUG:       define internal void [[OMP_OUTLINED_DEBUG:@.+]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i64 [[VLA_SIZE:%.+]], i32* {{.+}} [[VLA_ADDR:%[^)]+]])
-// CHECK-DEBUG-SAME:  #[[FN_ATTRS:[0-9]+]]
+// CHECK-DEBUG:           define internal void [[OMP_OUTLINED_DEBUG:@.+]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i64 [[VLA_SIZE:%.+]], i32* {{.+}} [[VLA_ADDR:%[^)]+]])
+// CHECK-DEBUG-SAME:      #[[FN_ATTRS:[0-9]+]]
+// IRBUILDER-DEBUG:       define internal void [[OMP_OUTLINED_DEBUG:@.+]](i32* noalias %{{.*}}, i32* noalias %{{.*}}, i32* [[VLA_REF:%[^)]+]])
+// IRBUILDER-DEBUG-SAME:  #[[FN_ATTRS:[0-9]+]]
 // CHECK-DEBUG:       store i32* [[VLA_ADDR]], i32** [[VLA_PTR_ADDR:%.+]],
 // CHECK-DEBUG:       [[VLA_REF:%.+]] = load i32*, i32** [[VLA_PTR_ADDR]]
-// CHECK-DEBUG:       [[VLA_ELEM_REF:%.+]] = getelementptr inbounds i32, i32* [[VLA_REF]], i64 1
-// CHECK-DEBUG-NEXT:  [[VLA_ELEM:%.+]] = load i32, i32* [[VLA_ELEM_REF]]
+// ALL-DEBUG:       [[VLA_ELEM_REF:%.+]] = getelementptr inbounds i32, i32* [[VLA_REF]], i64 1
+// ALL-DEBUG-NEXT:  [[VLA_ELEM:%.+]] = load i32, i32* [[VLA_ELEM_REF]]
 // CHECK-DEBUG-NEXT:  invoke void [[FOO:@.+foo.+]](i32 [[VLA_ELEM]])
+// IRBUILDER-DEBUG-NEXT:  call void [[FOO:@.+foo.+]](i32 [[VLA_ELEM]])
 // 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 !callback ![[cbid:[0-9]+]] {{.*}}void @__kmpc_fork_call(%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...)
-// CHECK-DEBUG-DAG: define linkonce_odr void [[FOO]](i32 %argc)
-// CHECK-DEBUG-DAG: declare !callback ![[cbid:[0-9]+]] void @__kmpc_fork_call(%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...)
+// ALL-DAG: define linkonce_odr {{.*}}void [[FOO]]({{i32[ ]?[a-z]*}} %argc)
+// ALL-DAG: declare !callback ![[cbid:[0-9]+]] {{.*}}void @__kmpc_fork_call(%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...)
+// ALL-DEBUG-DAG: define linkonce_odr void [[FOO]](i32 %argc)
+// ALL-DEBUG-DAG: declare !callback ![[cbid:[0-9]+]] void @__kmpc_fork_call(%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...)
 // CHECK-DEBUG-DAG:       define internal void [[OMP_OUTLINED]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i64 [[VLA_SIZE:%.+]], i32* {{.+}} [[VLA_ADDR:%[^)]+]])
 // CHECK-DEBUG-DAG:       call void [[OMP_OUTLINED_DEBUG]]
 
-// CHECK:       define linkonce_odr {{[a-z\_\b]*[ ]?i32}} [[TMAIN]](i8** %argc)
-// CHECK:       store i8** %argc, i8*** [[ARGC_ADDR:%.+]],
+// ALL:       define linkonce_odr {{[a-z\_\b]*[ ]?i32}} [[TMAIN]](i8** %argc)
+// ALL:       store i8** %argc, i8*** [[ARGC_ADDR:%.+]],
 // CHECK:       call {{.*}}void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* [[DEF_LOC_2]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i8***, i{{64|32}})* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i8*** [[ARGC_ADDR]], i{{64|32}} %{{.+}})
-// CHECK-NEXT:  ret i32 0
-// CHECK-NEXT:  }
-// CHECK-DEBUG:       define linkonce_odr i32 [[TMAIN]](i8** %argc)
+// IRBUILDER:   call {{.*}}void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* [[DEF_LOC_2]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i8***, i64)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i8*** [[ARGC_ADDR]], i64 %{{.+}})
+// ALL:  ret i32 0
+// ALL-NEXT:  }
+// ALL-DEBUG:       define linkonce_odr i32 [[TMAIN]](i8** %argc)
 // CHECK-DEBUG-DAG:   [[LOC_2_ADDR:%.+]] = alloca %struct.ident_t
 // CHECK-DEBUG:       [[KMPC_LOC_VOIDPTR:%.+]] = bitcast %struct.ident_t* [[LOC_2_ADDR]] to i8*
 // CHECK-DEBUG-NEXT:  [[KMPC_DEFAULT_LOC_VOIDPTR:%.+]] = bitcast %struct.ident_t* [[DEF_LOC_2]] to i8*
@@ -106,35 +124,40 @@ int main (int argc, char **argv) {
 // CHECK-DEBUG:  [[KMPC_LOC_PSOURCE_REF:%.+]] = getelementptr inbounds %struct.ident_t, %struct.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 (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* [[LOC_2_ADDR]], i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i8***, i64)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i8*** [[ARGC_ADDR]], i64 %{{.+}})
-// CHECK-DEBUG-NEXT:  ret i32 0
-// CHECK-DEBUG-NEXT:  }
+// IRBUILDER-DEBUG:  call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @{{.*}}, i32 2, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i8***, i64)* [[OMP_OUTLINED:@.+]] to void (i32*, i32*, ...)*), i8*** [[ARGC_ADDR]], i64 %{{.+}})
+// ALL-DEBUG:  ret i32 0
+// ALL-DEBUG-NEXT:  }
 
 // CHECK:       define internal {{.*}}void [[OMP_OUTLINED]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i8*** dereferenceable({{4|8}}) %argc, i{{64|32}}{{.*}} %{{.+}})
+// IRBUILDER:   define internal {{.*}}void [[OMP_OUTLINED]](i32* noalias %{{.*}}, i32* noalias %{{.*}}, i8*** [[ARGC_REF:%.*]], i{{64|32}}{{.*}} %{{.+}})
 // CHECK:       store i8*** %argc, i8**** [[ARGC_PTR_ADDR:%.+]],
 // CHECK:       [[ARGC_REF:%.+]] = load i8***, i8**** [[ARGC_PTR_ADDR]]
-// CHECK:       [[ARGC:%.+]] = load i8**, i8*** [[ARGC_REF]]
+// ALL:         [[ARGC:%.+]] = load i8**, i8*** [[ARGC_REF]]
 // CHECK-NEXT:  invoke {{.*}}void [[FOO1:@.+foo.+]](i8** [[ARGC]])
+// IRBUILDER-NEXT: call {{.*}}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_DEBUG:@.+]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i8*** dereferenceable({{4|8}}) %argc, i64 %{{.+}})
+// IRBUILDER-DEBUG:   define internal void [[OMP_OUTLINED_DEBUG:@.+]](i32* noalias %{{.*}}, i32* noalias %{{.*}}, i8*** [[ARGC_REF:%.*]], i64 %{{.+}})
 // CHECK-DEBUG:       store i8*** %argc, i8**** [[ARGC_PTR_ADDR:%.+]],
 // CHECK-DEBUG:       [[ARGC_REF:%.+]] = load i8***, i8**** [[ARGC_PTR_ADDR]]
-// CHECK-DEBUG:       [[ARGC:%.+]] = load i8**, i8*** [[ARGC_REF]]
+// ALL-DEBUG:         [[ARGC:%.+]] = load i8**, i8*** [[ARGC_REF]]
 // CHECK-DEBUG-NEXT:  invoke void [[FOO1:@.+foo.+]](i8** [[ARGC]])
+// IRBUILDER-DEBUG-NEXT:  call 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)
+// ALL: define linkonce_odr {{.*}}void [[FOO1]](i8** %argc)
 // CHECK-DEBUG-DAG: define linkonce_odr void [[FOO1]](i8** %argc)
 // CHECK-DEBUG-DAG: define internal void [[OMP_OUTLINED]](i32* noalias %.global_tid., i32* noalias %.bound_tid., i8*** dereferenceable({{4|8}}) %argc, i64 %{{.+}})
 // CHECK-DEBUG-DAG: call void [[OMP_OUTLINED_DEBUG]]({{[^)]+}}){{[^,]*}}, !dbg
 
-// CHECK: attributes #[[FN_ATTRS]] = {{.+}} nounwind
-// CHECK-DEBUG: attributes #[[FN_ATTRS]] = {{.+}} nounwind
-// CHECK: ![[cbid]] = !{![[cbidb:[0-9]+]]}
-// CHECK: ![[cbidb]] = !{i64 2, i64 -1, i64 -1, i1 true}
+// ALL: attributes #[[FN_ATTRS]] = {{.+}} nounwind
+// ALL-DEBUG: attributes #[[FN_ATTRS]] = {{.+}} nounwind
+// ALL: ![[cbid]] = !{![[cbidb:[0-9]+]]}
+// ALL: ![[cbidb]] = !{i64 2, i64 -1, i64 -1, i1 true}
 #endif