Index: lib/CodeGen/CGOpenMPRuntime.cpp
===================================================================
--- lib/CodeGen/CGOpenMPRuntime.cpp
+++ lib/CodeGen/CGOpenMPRuntime.cpp
@@ -475,6 +475,12 @@
   OMP_REQ_DYNAMIC_ALLOCATORS      = 0x010,
   LLVM_MARK_AS_BITMASK_ENUM(/*LargestValue=*/OMP_REQ_DYNAMIC_ALLOCATORS)
 };
+
+enum OpenMPOffloadingReservedDeviceIDs {
+  /// Device ID if the device was not defined, runtime should get it
+  /// from environment variables in the spec.
+  OMP_DEVICEID_UNDEF = -1,
+};
 } // anonymous namespace
 
 /// Describes ident structure that describes a source location.
@@ -604,6 +610,11 @@
   // kmp_int32 flags, size_t sizeof_kmp_task_t, size_t sizeof_shareds,
   // kmp_routine_entry_t *task_entry);
   OMPRTL__kmpc_omp_task_alloc,
+  // Call to kmp_task_t * __kmpc_omp_target_task_alloc(ident_t *,
+  // kmp_int32 gtid, kmp_int32 flags, size_t sizeof_kmp_task_t,
+  // size_t sizeof_shareds, kmp_routine_entry_t *task_entry,
+  // kmp_int64 device_id);
+  OMPRTL__kmpc_omp_target_task_alloc,
   // Call to kmp_int32 __kmpc_omp_task(ident_t *, kmp_int32 gtid, kmp_task_t *
   // new_task);
   OMPRTL__kmpc_omp_task,
@@ -1912,6 +1923,21 @@
     RTLFn = CGM.CreateRuntimeFunction(FnTy, /*Name=*/"__kmpc_omp_task_alloc");
     break;
   }
+  case OMPRTL__kmpc_omp_target_task_alloc: {
+    // Build kmp_task_t *__kmpc_omp_target_task_alloc(ident_t *, kmp_int32 gtid,
+    // kmp_int32 flags, size_t sizeof_kmp_task_t, size_t sizeof_shareds,
+    // kmp_routine_entry_t *task_entry, kmp_int64 device_id);
+    assert(KmpRoutineEntryPtrTy != nullptr &&
+           "Type kmp_routine_entry_t must be created.");
+    llvm::Type *TypeParams[] = {getIdentTyPointerTy(), CGM.Int32Ty, CGM.Int32Ty,
+                                CGM.SizeTy, CGM.SizeTy, KmpRoutineEntryPtrTy,
+                                CGM.Int64Ty};
+    // Return void * and then cast to particular kmp_task_t type.
+    auto *FnTy =
+        llvm::FunctionType::get(CGM.VoidPtrTy, TypeParams, /*isVarArg=*/false);
+    RTLFn = CGM.CreateRuntimeFunction(FnTy, /*Name=*/"__kmpc_omp_target_task_alloc");
+    break;
+  }
   case OMPRTL__kmpc_omp_task: {
     // Build kmp_int32 __kmpc_omp_task(ident_t *, kmp_int32 gtid, kmp_task_t
     // *new_task);
@@ -5074,13 +5100,30 @@
           : CGF.Builder.getInt32(Data.Final.getInt() ? FinalFlag : 0);
   TaskFlags = CGF.Builder.CreateOr(TaskFlags, CGF.Builder.getInt32(Flags));
   llvm::Value *SharedsSize = CGM.getSize(C.getTypeSizeInChars(SharedsTy));
-  llvm::Value *AllocArgs[] = {emitUpdateLocation(CGF, Loc),
-                              getThreadID(CGF, Loc), TaskFlags,
-                              KmpTaskTWithPrivatesTySize, SharedsSize,
-                              CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
-                                  TaskEntry, KmpRoutineEntryPtrTy)};
-  llvm::Value *NewTask = CGF.EmitRuntimeCall(
+  SmallVector<llvm::Value *, 8> AllocArgs = {emitUpdateLocation(CGF, Loc),
+      getThreadID(CGF, Loc), TaskFlags, KmpTaskTWithPrivatesTySize,
+      SharedsSize, CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
+          TaskEntry, KmpRoutineEntryPtrTy)};
+  llvm::Value *NewTask;
+  if (D.hasClausesOfKind<OMPNowaitClause>()) {
+    // Check if we have any device clause associated with the directive.
+    const Expr *Device = nullptr;
+    if (auto *C = D.getSingleClause<OMPDeviceClause>())
+      Device = C->getDevice();
+    // Emit device ID if any otherwise use default value.
+    llvm::Value *DeviceID;
+    if (Device)
+      DeviceID = CGF.Builder.CreateIntCast(CGF.EmitScalarExpr(Device),
+                                           CGF.Int64Ty, /*isSigned=*/true);
+    else
+      DeviceID = CGF.Builder.getInt64(OMP_DEVICEID_UNDEF);
+    AllocArgs.push_back(DeviceID);
+    NewTask = CGF.EmitRuntimeCall(
+      createRuntimeFunction(OMPRTL__kmpc_omp_target_task_alloc), AllocArgs);
+  } else {
+    NewTask = CGF.EmitRuntimeCall(
       createRuntimeFunction(OMPRTL__kmpc_omp_task_alloc), AllocArgs);
+  }
   llvm::Value *NewTaskNewTaskTTy =
       CGF.Builder.CreatePointerBitCastOrAddrSpaceCast(
           NewTask, KmpTaskTWithPrivatesPtrTy);
@@ -8350,12 +8393,6 @@
     CurMapTypes.back() |= OMP_MAP_IMPLICIT;
   }
 };
-
-enum OpenMPOffloadingReservedDeviceIDs {
-  /// Device ID if the device was not defined, runtime should get it
-  /// from environment variables in the spec.
-  OMP_DEVICEID_UNDEF = -1,
-};
 } // anonymous namespace
 
 /// Emit the arrays used to pass the captures and map information to the
Index: test/OpenMP/target_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_depend_codegen.cpp
+++ test/OpenMP/target_depend_codegen.cpp
@@ -133,7 +133,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1_:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
@@ -149,7 +149,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1__:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
Index: test/OpenMP/target_enter_data_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_enter_data_depend_codegen.cpp
+++ test/OpenMP/target_enter_data_depend_codegen.cpp
@@ -63,7 +63,7 @@
   // CK1: [[CAP_DEVICE:%.+]] = getelementptr inbounds %struct.anon, %struct.anon* [[CAPTURES:%.+]], i32 0, i32 0
   // CK1: [[DEVICE:%.+]] = load i32, i32* %{{.+}}
   // CK1: store i32 [[DEVICE]], i32* [[CAP_DEVICE]],
-  // CK1: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* {{.+}}, i32 {{.+}}, i32 1, i[[sz]] [[sz]], i[[sz]] 4, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* [[TASK_ENTRY0:@.+]] to i32 (i32, i8*)*))
+  // CK1: [[RES:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* {{.+}}, i32 {{.+}}, i32 1, i[[sz]] [[sz]], i[[sz]] 4, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* [[TASK_ENTRY0:@.+]] to i32 (i32, i8*)*), i64
   // CK1: [[BC:%.+]] = bitcast i8* [[RES]] to %struct.kmp_task_t_with_privates*
   // CK1: [[TASK_T:%.+]] = getelementptr inbounds %struct.kmp_task_t_with_privates, %struct.kmp_task_t_with_privates* [[BC]], i32 0, i32 0
   // CK1: [[SHAREDS:%.+]] = getelementptr inbounds %struct.kmp_task_t, %struct.kmp_task_t* [[TASK_T]], i32 0, i32 0
Index: test/OpenMP/target_exit_data_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_exit_data_depend_codegen.cpp
+++ test/OpenMP/target_exit_data_depend_codegen.cpp
@@ -63,7 +63,7 @@
   // CK1: [[CAP_DEVICE:%.+]] = getelementptr inbounds %struct.anon, %struct.anon* [[CAPTURES:%.+]], i32 0, i32 0
   // CK1: [[DEVICE:%.+]] = load i32, i32* %{{.+}}
   // CK1: store i32 [[DEVICE]], i32* [[CAP_DEVICE]],
-  // CK1: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* {{.+}}, i32 {{.+}}, i32 1, i[[sz]] [[sz]], i[[sz]] 4, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* [[TASK_ENTRY0:@.+]] to i32 (i32, i8*)*))
+  // CK1: [[RES:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* {{.+}}, i32 {{.+}}, i32 1, i[[sz]] [[sz]], i[[sz]] 4, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* [[TASK_ENTRY0:@.+]] to i32 (i32, i8*)*), i64
   // CK1: [[BC:%.+]] = bitcast i8* [[RES]] to %struct.kmp_task_t_with_privates*
   // CK1: [[TASK_T:%.+]] = getelementptr inbounds %struct.kmp_task_t_with_privates, %struct.kmp_task_t_with_privates* [[BC]], i32 0, i32 0
   // CK1: [[SHAREDS:%.+]] = getelementptr inbounds %struct.kmp_task_t, %struct.kmp_task_t* [[TASK_T]], i32 0, i32 0
Index: test/OpenMP/target_parallel_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_parallel_depend_codegen.cpp
+++ test/OpenMP/target_parallel_depend_codegen.cpp
@@ -133,7 +133,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1_:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
@@ -149,7 +149,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1__:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
Index: test/OpenMP/target_parallel_for_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_parallel_for_depend_codegen.cpp
+++ test/OpenMP/target_parallel_for_depend_codegen.cpp
@@ -133,7 +133,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[IN]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[IN]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1_:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
@@ -149,7 +149,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[IN]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[IN]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1__:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
Index: test/OpenMP/target_parallel_for_simd_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_parallel_for_simd_depend_codegen.cpp
+++ test/OpenMP/target_parallel_for_simd_depend_codegen.cpp
@@ -133,7 +133,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[IN]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[IN]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1_:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
@@ -149,7 +149,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[IN]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[IN]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1__:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
Index: test/OpenMP/target_simd_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_simd_depend_codegen.cpp
+++ test/OpenMP/target_simd_depend_codegen.cpp
@@ -133,7 +133,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1_:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
@@ -149,7 +149,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1__:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
Index: test/OpenMP/target_teams_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_teams_depend_codegen.cpp
+++ test/OpenMP/target_teams_depend_codegen.cpp
@@ -133,7 +133,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1_:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
@@ -149,7 +149,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* @0, i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1__:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
Index: test/OpenMP/target_teams_distribute_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_teams_distribute_depend_codegen.cpp
+++ test/OpenMP/target_teams_distribute_depend_codegen.cpp
@@ -133,7 +133,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1_:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
@@ -149,7 +149,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1__:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
Index: test/OpenMP/target_teams_distribute_parallel_for_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_teams_distribute_parallel_for_depend_codegen.cpp
+++ test/OpenMP/target_teams_distribute_parallel_for_depend_codegen.cpp
@@ -133,7 +133,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1_:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
@@ -149,7 +149,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1__:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
Index: test/OpenMP/target_teams_distribute_parallel_for_simd_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_teams_distribute_parallel_for_simd_depend_codegen.cpp
+++ test/OpenMP/target_teams_distribute_parallel_for_simd_depend_codegen.cpp
@@ -133,7 +133,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1_:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
@@ -149,7 +149,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1__:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
Index: test/OpenMP/target_teams_distribute_simd_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_teams_distribute_simd_depend_codegen.cpp
+++ test/OpenMP/target_teams_distribute_simd_depend_codegen.cpp
@@ -133,7 +133,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{104|52}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1_:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1_:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
@@ -149,7 +149,7 @@
   // CHECK:       [[DEV:%.+]] = load i32, i32* [[DEVICE_CAP]],
   // CHECK:       store i32 [[DEV]], i32* [[GEP]],
 
-  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*))
+  // CHECK:       [[TASK:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* [[ID]], i32 [[GTID]], i32 1, i[[SZ]] {{56|28}}, i[[SZ]] {{16|12}}, i32 (i32, i8*)* bitcast (i32 (i32, %{{.+}}*)* [[TASK_ENTRY1__:@.+]] to i32 (i32, i8*)*), i64
   // CHECK:       [[BC_TASK:%.+]] = bitcast i8* [[TASK]] to [[TASK_TY1__:%.+]]*
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 0
   // CHECK:       getelementptr inbounds [3 x %struct.kmp_depend_info], [3 x %struct.kmp_depend_info]* %{{.+}}, i[[SZ]] 0, i[[SZ]] 1
Index: test/OpenMP/target_update_depend_codegen.cpp
===================================================================
--- test/OpenMP/target_update_depend_codegen.cpp
+++ test/OpenMP/target_update_depend_codegen.cpp
@@ -63,7 +63,7 @@
   // CK1: [[CAP_DEVICE:%.+]] = getelementptr inbounds %struct.anon, %struct.anon* [[CAPTURES:%.+]], i32 0, i32 0
   // CK1: [[DEVICE:%.+]] = load i32, i32* %{{.+}}
   // CK1: store i32 [[DEVICE]], i32* [[CAP_DEVICE]],
-  // CK1: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* {{.+}}, i32 {{.+}}, i32 1, i[[sz]] [[sz]], i[[sz]] 4, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* [[TASK_ENTRY0:@.+]] to i32 (i32, i8*)*))
+  // CK1: [[RES:%.+]] = call i8* @__kmpc_omp_target_task_alloc(%struct.ident_t* {{.+}}, i32 {{.+}}, i32 1, i[[sz]] [[sz]], i[[sz]] 4, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* [[TASK_ENTRY0:@.+]] to i32 (i32, i8*)*), i64
   // CK1: [[BC:%.+]] = bitcast i8* [[RES]] to %struct.kmp_task_t_with_privates*
   // CK1: [[TASK_T:%.+]] = getelementptr inbounds %struct.kmp_task_t_with_privates, %struct.kmp_task_t_with_privates* [[BC]], i32 0, i32 0
   // CK1: [[SHAREDS:%.+]] = getelementptr inbounds %struct.kmp_task_t, %struct.kmp_task_t* [[TASK_T]], i32 0, i32 0