[OPENMP] Outlined function for parallel and other regions with list of captured variables.
Currently all variables used in OpenMP regions are captured into a record and passed to outlined functions in this record. It may result in some poor performance because of too complex analysis later in optimization passes. Patch makes to emit outlined functions for parallel-based regions with a list of captured variables. It reduces code for 2*n GEPs, stores and loads at least.
Codegen for task-based regions remains unchanged because runtime requires that all captured variables are passed in captured record.
llvm-svn: 247251
diff --git a/clang/test/OpenMP/parallel_if_codegen.cpp b/clang/test/OpenMP/parallel_if_codegen.cpp
index e711b5d..9ecf572 100644
--- a/clang/test/OpenMP/parallel_if_codegen.cpp
+++ b/clang/test/OpenMP/parallel_if_codegen.cpp
@@ -16,14 +16,14 @@
// CHECK-LABEL: define {{.*}}void @{{.+}}gtid_test
void gtid_test() {
-// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 1, {{.+}}* [[GTID_TEST_REGION1:@.+]] to void
+// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 0, {{.+}}* [[GTID_TEST_REGION1:@.+]] to void
#pragma omp parallel
#pragma omp parallel if (parallel: false)
gtid_test();
// CHECK: ret void
}
-// CHECK: define internal {{.*}}void [[GTID_TEST_REGION1]](i{{.+}}* [[GTID_PARAM:%.+]], i
+// CHECK: define internal {{.*}}void [[GTID_TEST_REGION1]](i{{.+}}* noalias [[GTID_PARAM:%.+]], i32* noalias
// CHECK: store i{{[0-9]+}}* [[GTID_PARAM]], i{{[0-9]+}}** [[GTID_ADDR_REF:%.+]],
// CHECK: [[GTID_ADDR:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[GTID_ADDR_REF]]
// CHECK: [[GTID:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[GTID_ADDR]]
@@ -51,7 +51,7 @@
// CHECK-LABEL: define {{.*}}i{{[0-9]+}} @main()
int main() {
// CHECK: [[GTID:%.+]] = call {{.*}}i32 @__kmpc_global_thread_num(
-// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 1, void {{.+}}* [[CAP_FN4:@.+]] to void
+// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 0, void {{.+}}* [[CAP_FN4:@.+]] to void
#pragma omp parallel if (true)
fn4();
// CHECK: call {{.*}}void @__kmpc_serialized_parallel(%{{.+}}* @{{.+}}, i32 [[GTID]])
@@ -63,7 +63,7 @@
// CHECK: br i1 %{{.+}}, label %[[OMP_THEN:.+]], label %[[OMP_ELSE:.+]]
// CHECK: [[OMP_THEN]]
-// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 1, void {{.+}}* [[CAP_FN6:@.+]] to void
+// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 0, void {{.+}}* [[CAP_FN6:@.+]] to void
// CHECK: br label %[[OMP_END:.+]]
// CHECK: [[OMP_ELSE]]
// CHECK: call {{.*}}void @__kmpc_serialized_parallel(%{{.+}}* @{{.+}}, i32 [[GTID]])
@@ -92,14 +92,14 @@
// CHECK-LABEL: define {{.+}} @{{.+}}tmain
// CHECK: [[GTID:%.+]] = call {{.*}}i32 @__kmpc_global_thread_num(
-// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 1, void {{.+}}* [[CAP_FN1:@.+]] to void
+// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 0, void {{.+}}* [[CAP_FN1:@.+]] to void
// CHECK: call {{.*}}void @__kmpc_serialized_parallel(%{{.+}}* @{{.+}}, i32 [[GTID]])
// CHECK: store i32 [[GTID]], i32* [[GTID_ADDR:%.+]],
// CHECK: call void [[CAP_FN2:@.+]](i32* [[GTID_ADDR]],
// CHECK: call {{.*}}void @__kmpc_end_serialized_parallel(%{{.+}}* @{{.+}}, i32 [[GTID]])
// CHECK: br i1 %{{.+}}, label %[[OMP_THEN:.+]], label %[[OMP_ELSE:.+]]
// CHECK: [[OMP_THEN]]
-// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 1, void {{.+}}* [[CAP_FN3:@.+]] to void
+// CHECK: call {{.*}}void {{.+}} @__kmpc_fork_call(%{{.+}}* @{{.+}}, i{{.+}} 0, void {{.+}}* [[CAP_FN3:@.+]] to void
// CHECK: br label %[[OMP_END:.+]]
// CHECK: [[OMP_ELSE]]
// CHECK: call {{.*}}void @__kmpc_serialized_parallel(%{{.+}}* @{{.+}}, i32 [[GTID]])