From: Alexey Bataev <a.bataev@hotmail.com>
Date: Wed, 24 Oct 2018 19:06:37 +0000 (+0000)
Subject: Do not always request an implicit taskgroup region inside the kmpc_taskloop function
X-Git-Tag: llvmorg-8.0.0-rc1~5888
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=ac6e4de714e1086d4bcd57e4118311e83a1e1c11;p=platform%2Fupstream%2Fllvm.git

Do not always request an implicit taskgroup region inside the kmpc_taskloop function

Summary:
For the following code:
```
    int i;
    #pragma omp taskloop
    for (i = 0; i < 100; ++i)
    {}

    #pragma omp taskloop nogroup
    for (i = 0; i < 100; ++i)
    {}
```

Clang emits the following LLVM IR:

```
 ...
  call void @__kmpc_taskgroup(%struct.ident_t* @0, i32 %0)
  %2 = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 %0, i32 1, i64 80, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*))
  ...
  call void @__kmpc_taskloop(%struct.ident_t* @0, i32 %0, i8* %2, i32 1, i64* %8, i64* %9, i64 %13, i32 0, i32 0, i64 0, i8* null)
  call void @__kmpc_end_taskgroup(%struct.ident_t* @0, i32 %0)

  ...
  %15 = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 %0, i32 1, i64 80, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.1*)* @.omp_task_entry..2 to i32 (i32, i8*)*))
  ...
  call void @__kmpc_taskloop(%struct.ident_t* @0, i32 %0, i8* %15, i32 1, i64* %21, i64* %22, i64 %26, i32 0, i32 0, i64 0, i8* null)

```

The first set of instructions corresponds to the first taskloop construct. It is important to note that the implicit taskgroup region associated with the taskloop construct has been materialized in our IR:  the `__kmpc_taskloop` occurs inside a taskgroup region. Note also that this taskgroup region does not exist in our second taskloop because we are using the `nogroup` clause.

The issue here is the 4th argument of the kmpc_taskloop call, starting from the end,  is always a zero. Checking the LLVM OpenMP RT implementation, we see that this argument corresponds to the nogroup parameter:

```
void __kmpc_taskloop(ident_t *loc, int gtid, kmp_task_t *task, int if_val,
                     kmp_uint64 *lb, kmp_uint64 *ub, kmp_int64 st, int nogroup,
                     int sched, kmp_uint64 grainsize, void *task_dup);
```

So basically we always tell to the RT to do another taskgroup region. For the first taskloop, this means that we create two taskgroup regions. For the second example, it means that despite the fact we had a nogroup clause we are going to have a taskgroup region, so we unnecessary wait until all descendant tasks have been executed.

Reviewers: ABataev

Reviewed By: ABataev

Subscribers: rogfer01, cfe-commits

Differential Revision: https://reviews.llvm.org/D53636

llvm-svn: 345180
---

diff --git a/clang/lib/CodeGen/CGOpenMPRuntime.cpp b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
index c00f66d..cd3bc3a 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntime.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
@@ -5246,8 +5246,8 @@ void CGOpenMPRuntime::emitTaskLoopCall(CodeGenFunction &CGF, SourceLocation Loc,
       LBLVal.getPointer(),
       UBLVal.getPointer(),
       CGF.EmitLoadOfScalar(StLVal, Loc),
-      llvm::ConstantInt::getNullValue(
-          CGF.IntTy), // Always 0 because taskgroup emitted by the compiler
+      llvm::ConstantInt::getSigned(
+              CGF.IntTy, 1), // Always 1 because taskgroup emitted by the compiler
       llvm::ConstantInt::getSigned(
           CGF.IntTy, Data.Schedule.getPointer()
                          ? Data.Schedule.getInt() ? NumTasks : Grainsize
diff --git a/clang/test/OpenMP/taskloop_codegen.cpp b/clang/test/OpenMP/taskloop_codegen.cpp
index 82b8e1b..26033e7 100644
--- a/clang/test/OpenMP/taskloop_codegen.cpp
+++ b/clang/test/OpenMP/taskloop_codegen.cpp
@@ -28,7 +28,7 @@ int main(int argc, char **argv) {
 // CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 7
 // CHECK: store i64 1, i64* [[ST]],
 // CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
-// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 0, i64 0, i8* null)
+// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 1, i32 0, i64 0, i8* null)
 // CHECK: call void @__kmpc_end_taskgroup(%struct.ident_t* [[DEFLOC]], i32 [[GTID]])
 #pragma omp taskloop priority(argc)
   for (int i = 0; i < 10; ++i)
@@ -44,7 +44,7 @@ int main(int argc, char **argv) {
 // CHECK: store i64 1, i64* [[ST]],
 // CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
 // CHECK: [[GRAINSIZE:%.+]] = zext i32 %{{.+}} to i64
-// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 1, i64 [[GRAINSIZE]], i8* null)
+// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 1, i32 1, i64 [[GRAINSIZE]], i8* null)
 #pragma omp taskloop nogroup grainsize(argc)
   for (int i = 0; i < 10; ++i)
     ;
@@ -61,7 +61,7 @@ int main(int argc, char **argv) {
 // CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 7
 // CHECK: store i64 1, i64* [[ST]],
 // CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
-// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 [[IF_INT]], i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 2, i64 4, i8* null)
+// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 [[IF_INT]], i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 1, i32 2, i64 4, i8* null)
 // CHECK: call void @__kmpc_end_taskgroup(%struct.ident_t* [[DEFLOC]], i32 [[GTID]])
   int i;
 #pragma omp taskloop if(argc) shared(argc, argv) collapse(2) num_tasks(4)
@@ -164,7 +164,7 @@ struct S {
 // CHECK: store i64 1, i64* [[ST]],
 // CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
 // CHECK: [[NUM_TASKS:%.+]] = zext i32 %{{.+}} to i64
-// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 2, i64 [[NUM_TASKS]], i8* null)
+// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 1, i32 2, i64 [[NUM_TASKS]], i8* null)
 #pragma omp taskloop shared(c) num_tasks(a)
     for (a = 0; a < c; ++a)
       ;
diff --git a/clang/test/OpenMP/taskloop_firstprivate_codegen.cpp b/clang/test/OpenMP/taskloop_firstprivate_codegen.cpp
index d617835..8f3b246 100644
--- a/clang/test/OpenMP/taskloop_firstprivate_codegen.cpp
+++ b/clang/test/OpenMP/taskloop_firstprivate_codegen.cpp
@@ -77,7 +77,7 @@ int main() {
 // LAMBDA: [[SIVAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[SIVAR_ADDR_REF]]
 // LAMBDA: store i{{[0-9]+}} [[SIVAR_VAL]], i{{[0-9]+}}* [[SIVAR_PRIVATE_ADDR]]
 
-// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* null)
+// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
 // LAMBDA: ret
 #pragma omp taskloop firstprivate(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -120,7 +120,7 @@ int main() {
   // BLOCKS: [[SIVAR_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
   // BLOCKS: [[SIVAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[SIVAR_ADDR_REF]]
   // BLOCKS: store i{{[0-9]+}} [[SIVAR_VAL]], i{{[0-9]+}}* [[SIVAR_PRIVATE_ADDR]]
-  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* null)
+  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
   // BLOCKS: ret
 #pragma omp taskloop firstprivate(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -253,7 +253,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_MAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
 
 // CHECK: = call i{{.+}} [[TMAIN_INT:@.+]]()
 
@@ -416,7 +416,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_TMAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
 
 // No destructors must be called for private copies of s_arr and var.
 // CHECK-NOT: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
diff --git a/clang/test/OpenMP/taskloop_lastprivate_codegen.cpp b/clang/test/OpenMP/taskloop_lastprivate_codegen.cpp
index a6f7abc..fa1549d 100644
--- a/clang/test/OpenMP/taskloop_lastprivate_codegen.cpp
+++ b/clang/test/OpenMP/taskloop_lastprivate_codegen.cpp
@@ -68,7 +68,7 @@ int main() {
   // LAMBDA: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%{{[^ ]+}} @{{[^,]+}}, i32 %{{[^,]+}}, i32 1, i64 96, i64 16, i32 (i32, i8*)* bitcast (i32 (i32, %{{[^*]+}}*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
 // LAMBDA: [[PRIVATES:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
 
-// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY:%[^*]+]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
+// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY:%[^*]+]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
 // LAMBDA: ret
 #pragma omp taskloop lastprivate(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -108,7 +108,7 @@ int main() {
   // BLOCKS: define{{.*}} internal{{.*}} void {{.+}}(i8*
   // BLOCKS: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%{{[^ ]+}} @{{[^,]+}}, i32 %{{[^,]+}}, i32 1, i64 96, i64 16, i32 (i32, i8*)* bitcast (i32 (i32, %{{[^*]+}}*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
   // BLOCKS: [[PRIVATES:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
-  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY:%[^*]+]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
+  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY:%[^*]+]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
   // BLOCKS: ret
 #pragma omp taskloop lastprivate(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -226,7 +226,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_MAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
 
 // CHECK: = call i{{.+}} [[TMAIN_INT:@.+]]()
 
@@ -400,7 +400,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_TMAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
 
 // No destructors must be called for private copies of s_arr and var.
 // CHECK-NOT: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
diff --git a/clang/test/OpenMP/taskloop_private_codegen.cpp b/clang/test/OpenMP/taskloop_private_codegen.cpp
index 21ffcba..8e2c13c 100644
--- a/clang/test/OpenMP/taskloop_private_codegen.cpp
+++ b/clang/test/OpenMP/taskloop_private_codegen.cpp
@@ -65,7 +65,7 @@ int main() {
   // LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
   // LAMBDA: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%{{[^ ]+}} @{{[^,]+}}, i32 %{{[^,]+}}, i32 1, i64 96, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %{{[^*]+}}*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
 // LAMBDA: [[PRIVATES:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
-// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* null)
+// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
 // LAMBDA: ret
 #pragma omp taskloop private(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -101,7 +101,7 @@ int main() {
   // BLOCKS: define{{.*}} internal{{.*}} void {{.+}}(i8*
   // BLOCKS: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%{{[^ ]+}} @{{[^,]+}}, i32 %{{[^,]+}}, i32 1, i64 96, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %{{[^*]+}}*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
   // BLOCKS: [[PRIVATES:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
-  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* null)
+  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
   // BLOCKS: ret
 #pragma omp taskloop private(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -193,7 +193,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_MAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
 // CHECK: call i32 @__kmpc_omp_task([[LOC]], i32 [[GTID]], i8*
 
 // CHECK: = call i{{.+}} [[TMAIN_INT:@.+]]()
@@ -324,7 +324,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_TMAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
 
 // No destructors must be called for private copies of s_arr and var.
 // CHECK-NOT: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
diff --git a/clang/test/OpenMP/taskloop_reduction_codegen.cpp b/clang/test/OpenMP/taskloop_reduction_codegen.cpp
index 3a3434a..a9f79a5 100644
--- a/clang/test/OpenMP/taskloop_reduction_codegen.cpp
+++ b/clang/test/OpenMP/taskloop_reduction_codegen.cpp
@@ -148,7 +148,7 @@ sum = 0.0;
 // CHECK:    [[SUB12:%.*]] = sub nsw i32 [[DIV]], 1
 // CHECK:    store i32 [[SUB12]], i32* [[DOTCAPTURE_EXPR_9]],
 // CHECK:    [[TMP65:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* %{{.+}}, i32 [[TMP0]], i32 1, i64 888, i64 72, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @[[TASK:.+]] to i32 (i32, i8*)*))
-// CHECK:    call void @__kmpc_taskloop(%struct.ident_t* %{{.+}}, i32 [[TMP0]], i8* [[TMP65]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* null)
+// CHECK:    call void @__kmpc_taskloop(%struct.ident_t* %{{.+}}, i32 [[TMP0]], i8* [[TMP65]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
 // CHECK:    call void @__kmpc_end_taskgroup(%struct.ident_t*
 
 // CHECK:    ret i32
diff --git a/clang/test/OpenMP/taskloop_simd_codegen.cpp b/clang/test/OpenMP/taskloop_simd_codegen.cpp
index d3efec5..4da4eb8 100644
--- a/clang/test/OpenMP/taskloop_simd_codegen.cpp
+++ b/clang/test/OpenMP/taskloop_simd_codegen.cpp
@@ -24,7 +24,7 @@ int main(int argc, char **argv) {
 // CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 7
 // CHECK: store i64 1, i64* [[ST]],
 // CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
-// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 0, i64 0, i8* null)
+// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 1, i32 0, i64 0, i8* null)
 // CHECK: call void @__kmpc_end_taskgroup(%struct.ident_t* [[DEFLOC]], i32 [[GTID]])
 #pragma omp taskloop simd priority(argc)
   for (int i = 0; i < 10; ++i)
@@ -40,7 +40,7 @@ int main(int argc, char **argv) {
 // CHECK: store i64 1, i64* [[ST]],
 // CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
 // CHECK: [[GRAINSIZE:%.+]] = zext i32 %{{.+}} to i64
-// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 1, i64 [[GRAINSIZE]], i8* null)
+// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 1, i32 1, i64 [[GRAINSIZE]], i8* null)
 #pragma omp taskloop simd nogroup grainsize(argc) simdlen(4)
   for (int i = 0; i < 10; ++i)
     ;
@@ -57,7 +57,7 @@ int main(int argc, char **argv) {
 // CHECK: [[ST:%.+]] = getelementptr inbounds [[TD_TY]], [[TD_TY]]* [[TASK_DATA]], i32 0, i32 7
 // CHECK: store i64 1, i64* [[ST]],
 // CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
-// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 [[IF_INT]], i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 2, i64 4, i8* null)
+// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 [[IF_INT]], i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 1, i32 2, i64 4, i8* null)
 // CHECK: call void @__kmpc_end_taskgroup(%struct.ident_t* [[DEFLOC]], i32 [[GTID]])
   int i;
 #pragma omp taskloop simd if(argc) shared(argc, argv) collapse(2) num_tasks(4) safelen(32)
@@ -162,7 +162,7 @@ struct S {
 // CHECK: store i64 1, i64* [[ST]],
 // CHECK: [[ST_VAL:%.+]] = load i64, i64* [[ST]],
 // CHECK: [[NUM_TASKS:%.+]] = zext i32 %{{.+}} to i64
-// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 0, i32 2, i64 [[NUM_TASKS]], i8* null)
+// CHECK: call void @__kmpc_taskloop(%struct.ident_t* [[DEFLOC]], i32 [[GTID]], i8* [[TASKV]], i32 1, i64* [[DOWN]], i64* [[UP]], i64 [[ST_VAL]], i32 1, i32 2, i64 [[NUM_TASKS]], i8* null)
 #pragma omp taskloop simd shared(c) num_tasks(a) simdlen(8) safelen(64)
     for (a = 0; a < c; ++a)
       ;
diff --git a/clang/test/OpenMP/taskloop_simd_firstprivate_codegen.cpp b/clang/test/OpenMP/taskloop_simd_firstprivate_codegen.cpp
index 4f406b2..b7e8ba9 100644
--- a/clang/test/OpenMP/taskloop_simd_firstprivate_codegen.cpp
+++ b/clang/test/OpenMP/taskloop_simd_firstprivate_codegen.cpp
@@ -77,7 +77,7 @@ int main() {
 // LAMBDA: [[SIVAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[SIVAR_ADDR_REF]]
 // LAMBDA: store i{{[0-9]+}} [[SIVAR_VAL]], i{{[0-9]+}}* [[SIVAR_PRIVATE_ADDR]]
 
-// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* null)
+// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
 // LAMBDA: ret
 #pragma omp taskloop simd firstprivate(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -120,7 +120,7 @@ int main() {
   // BLOCKS: [[SIVAR_ADDR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
   // BLOCKS: [[SIVAR_VAL:%.+]] = load i{{[0-9]+}}, i{{[0-9]+}}* [[SIVAR_ADDR_REF]]
   // BLOCKS: store i{{[0-9]+}} [[SIVAR_VAL]], i{{[0-9]+}}* [[SIVAR_PRIVATE_ADDR]]
-  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* null)
+  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
   // BLOCKS: ret
 #pragma omp taskloop simd firstprivate(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -253,7 +253,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_MAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
 
 // CHECK: = call i{{.+}} [[TMAIN_INT:@.+]]()
 
@@ -416,7 +416,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_TMAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
 
 // No destructors must be called for private copies of s_arr and var.
 // CHECK-NOT: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
diff --git a/clang/test/OpenMP/taskloop_simd_lastprivate_codegen.cpp b/clang/test/OpenMP/taskloop_simd_lastprivate_codegen.cpp
index be48446..750bf97 100644
--- a/clang/test/OpenMP/taskloop_simd_lastprivate_codegen.cpp
+++ b/clang/test/OpenMP/taskloop_simd_lastprivate_codegen.cpp
@@ -68,7 +68,7 @@ int main() {
   // LAMBDA: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%{{[^ ]+}} @{{[^,]+}}, i32 %{{[^,]+}}, i32 1, i64 96, i64 16, i32 (i32, i8*)* bitcast (i32 (i32, %{{[^*]+}}*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
 // LAMBDA: [[PRIVATES:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
 
-// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY:%[^*]+]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
+// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY:%[^*]+]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
 // LAMBDA: ret
 #pragma omp taskloop simd lastprivate(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -108,7 +108,7 @@ int main() {
   // BLOCKS: define{{.*}} internal{{.*}} void {{.+}}(i8*
   // BLOCKS: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%{{[^ ]+}} @{{[^,]+}}, i32 %{{[^,]+}}, i32 1, i64 96, i64 16, i32 (i32, i8*)* bitcast (i32 (i32, %{{[^*]+}}*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
   // BLOCKS: [[PRIVATES:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
-  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY:%[^*]+]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
+  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY:%[^*]+]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
   // BLOCKS: ret
 #pragma omp taskloop simd lastprivate(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -226,7 +226,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_MAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
 
 // CHECK: = call i{{.+}} [[TMAIN_INT:@.+]]()
 
@@ -400,7 +400,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_TMAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
 
 // No destructors must be called for private copies of s_arr and var.
 // CHECK-NOT: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
diff --git a/clang/test/OpenMP/taskloop_simd_private_codegen.cpp b/clang/test/OpenMP/taskloop_simd_private_codegen.cpp
index fd0820a..c6e1df9 100644
--- a/clang/test/OpenMP/taskloop_simd_private_codegen.cpp
+++ b/clang/test/OpenMP/taskloop_simd_private_codegen.cpp
@@ -65,7 +65,7 @@ int main() {
   // LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
   // LAMBDA: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%{{[^ ]+}} @{{[^,]+}}, i32 %{{[^,]+}}, i32 1, i64 96, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %{{[^*]+}}*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
 // LAMBDA: [[PRIVATES:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
-// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* null)
+// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
 // LAMBDA: ret
 #pragma omp taskloop simd private(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -101,7 +101,7 @@ int main() {
   // BLOCKS: define{{.*}} internal{{.*}} void {{.+}}(i8*
   // BLOCKS: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%{{[^ ]+}} @{{[^,]+}}, i32 %{{[^,]+}}, i32 1, i64 96, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %{{[^*]+}}*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
   // BLOCKS: [[PRIVATES:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
-  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* null)
+  // BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
   // BLOCKS: ret
 #pragma omp taskloop simd private(g, sivar)
   for (int i = 0; i < 10; ++i) {
@@ -193,7 +193,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_MAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
 // CHECK: call i32 @__kmpc_omp_task([[LOC]], i32 [[GTID]], i8*
 
 // CHECK: = call i{{.+}} [[TMAIN_INT:@.+]]()
@@ -324,7 +324,7 @@ int main() {
 // CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_TMAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
 
 // Start task.
-// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
+// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
 
 // No destructors must be called for private copies of s_arr and var.
 // CHECK-NOT: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
diff --git a/clang/test/OpenMP/taskloop_simd_reduction_codegen.cpp b/clang/test/OpenMP/taskloop_simd_reduction_codegen.cpp
index d2c4b8b..37a60c8 100644
--- a/clang/test/OpenMP/taskloop_simd_reduction_codegen.cpp
+++ b/clang/test/OpenMP/taskloop_simd_reduction_codegen.cpp
@@ -148,7 +148,7 @@ sum = 0.0;
 // CHECK:    [[SUB12:%.*]] = sub nsw i32 [[DIV]], 1
 // CHECK:    store i32 [[SUB12]], i32* [[DOTCAPTURE_EXPR_9]],
 // CHECK:    [[TMP65:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* %{{.+}}, i32 [[TMP0]], i32 1, i64 888, i64 72, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @{{.+}} to i32 (i32, i8*)*))
-// CHECK:    call void @__kmpc_taskloop(%struct.ident_t* %{{.+}}, i32 [[TMP0]], i8* [[TMP65]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 0, i32 0, i64 0, i8* null)
+// CHECK:    call void @__kmpc_taskloop(%struct.ident_t* %{{.+}}, i32 [[TMP0]], i8* [[TMP65]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
 // CHECK:    call void @__kmpc_end_taskgroup(%struct.ident_t*
 
 // CHECK:    ret i32