Index: openmp/libomptarget/include/omptarget.h
===================================================================
--- openmp/libomptarget/include/omptarget.h
+++ openmp/libomptarget/include/omptarget.h
@@ -170,6 +170,11 @@
     int64_t device_id, int32_t arg_num, void **args_base, void **args,
     int64_t *arg_sizes, int64_t *arg_types, void **arg_mappers, int32_t depNum,
     void *depList, int32_t noAliasDepNum, void *noAliasDepList);
+__tgt_async_info *__tgt_target_data_begin_mapper_issue(
+    int64_t device_id, int32_t arg_num, void **args_base, void **args,
+    int64_t *arg_sizes, int64_t *arg_types, void **arg_mappers);
+void __tgt_target_data_begin_mapper_wait(int32_t device_id,
+                                         __tgt_async_info *handle);
 
 // passes data from the target, release target memory and destroys the
 // host-target mapping (top entry from the stack of data maps) created by
Index: openmp/libomptarget/src/interface.cpp
===================================================================
--- openmp/libomptarget/src/interface.cpp
+++ openmp/libomptarget/src/interface.cpp
@@ -111,10 +111,34 @@
 EXTERN void __tgt_target_data_begin_mapper(int64_t device_id, int32_t arg_num,
     void **args_base, void **args, int64_t *arg_sizes, int64_t *arg_types,
     void **arg_mappers) {
-  if (IsOffloadDisabled()) return;
+
+  __tgt_async_info *Handle =
+      __tgt_target_data_begin_mapper_issue(device_id,arg_num, args_base, args,
+                                           arg_sizes, arg_types, arg_mappers);
+  __tgt_target_data_begin_mapper_wait(device_id, Handle);
+}
+
+EXTERN void __tgt_target_data_begin_nowait_mapper(int64_t device_id,
+    int32_t arg_num, void **args_base, void **args, int64_t *arg_sizes,
+    int64_t *arg_types, void **arg_mappers, int32_t depNum, void *depList,
+    int32_t noAliasDepNum, void *noAliasDepList) {
+  if (depNum + noAliasDepNum > 0)
+    __kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
+
+  __tgt_target_data_begin_mapper(device_id, arg_num, args_base, args,
+      arg_sizes, arg_types, arg_mappers);
+}
+
+EXTERN __tgt_async_info *__tgt_target_data_begin_mapper_issue(
+    int64_t device_id, int32_t arg_num, void **args_base, void **args,
+    int64_t *arg_sizes, int64_t *arg_types, void **arg_mappers) {
+
+  __tgt_async_info *Handle =
+      (__tgt_async_info *) malloc(sizeof(__tgt_async_info));
+  if (IsOffloadDisabled()) return Handle;
 
   DP("Entering data begin region for device %" PRId64 " with %d mappings\n",
-      device_id, arg_num);
+     device_id, arg_num);
 
   // No devices available?
   if (device_id == OFFLOAD_DEVICE_DEFAULT) {
@@ -125,7 +149,7 @@
   if (CheckDeviceAndCtors(device_id) != OFFLOAD_SUCCESS) {
     DP("Failed to get device %" PRId64 " ready\n", device_id);
     HandleTargetOutcome(false);
-    return;
+    return Handle;
   }
 
   DeviceTy &Device = Devices[device_id];
@@ -133,25 +157,32 @@
 #ifdef OMPTARGET_DEBUG
   for (int i = 0; i < arg_num; ++i) {
     DP("Entry %2d: Base=" DPxMOD ", Begin=" DPxMOD ", Size=%" PRId64
-       ", Type=0x%" PRIx64 "\n",
+           ", Type=0x%" PRIx64 "\n",
        i, DPxPTR(args_base[i]), DPxPTR(args[i]), arg_sizes[i], arg_types[i]);
   }
 #endif
 
   int rc = targetDataBegin(Device, arg_num, args_base, args, arg_sizes,
-                           arg_types, arg_mappers, nullptr);
+                           arg_types, arg_mappers, Handle);
   HandleTargetOutcome(rc == OFFLOAD_SUCCESS);
+
+  return Handle;
 }
 
-EXTERN void __tgt_target_data_begin_nowait_mapper(int64_t device_id,
-    int32_t arg_num, void **args_base, void **args, int64_t *arg_sizes,
-    int64_t *arg_types, void **arg_mappers, int32_t depNum, void *depList,
-    int32_t noAliasDepNum, void *noAliasDepList) {
-  if (depNum + noAliasDepNum > 0)
-    __kmpc_omp_taskwait(NULL, __kmpc_global_thread_num(NULL));
+EXTERN void __tgt_target_data_begin_mapper_wait(int32_t device_id,
+                                                __tgt_async_info *handle) {
+  if (!handle || !handle->Queue) {
+    DP("No handle to wait on!");
+    HandleTargetOutcome(false);
+    return;
+  }
 
-  __tgt_target_data_begin_mapper(device_id, arg_num, args_base, args,
-      arg_sizes, arg_types, arg_mappers);
+  // No devices available?
+  if (device_id == OFFLOAD_DEVICE_DEFAULT)
+    device_id = omp_get_default_device();
+
+  DeviceTy &Device = Devices[device_id];
+  Device.synchronize(handle);
 }
 
 /// passes data from the target, releases target memory and destroys