diff --git a/openmp/libomptarget/include/device.h b/openmp/libomptarget/include/device.h
--- a/openmp/libomptarget/include/device.h
+++ b/openmp/libomptarget/include/device.h
@@ -435,6 +435,12 @@
   /// OFFLOAD_SUCCESS/OFFLOAD_FAIL when succeeds/fails.
   int32_t synchronize(AsyncInfoTy &AsyncInfo);
 
+  /// Query for device/queue/event based completion on \p AsyncInfo in a
+  /// non-blocking manner and return OFFLOAD_SUCCESS/OFFLOAD_FAIL when
+  /// succeeds/fails. Must be called multiple times until AsyncInfo is
+  /// completed and AsyncInfo.isDone() returns true.
+  int32_t queryAsync(AsyncInfoTy &AsyncInfo);
+
   /// Calls the corresponding print in the \p RTLDEVID
   /// device RTL to obtain the information of the specific device.
   bool printDeviceInfo(int32_t RTLDevID);
diff --git a/openmp/libomptarget/include/omptarget.h b/openmp/libomptarget/include/omptarget.h
--- a/openmp/libomptarget/include/omptarget.h
+++ b/openmp/libomptarget/include/omptarget.h
@@ -15,11 +15,15 @@
 #define _OMPTARGET_H_
 
 #include <deque>
+#include <functional>
 #include <stddef.h>
 #include <stdint.h>
+#include <type_traits>
 
 #include <SourceInfo.h>
 
+#include "llvm/ADT/SmallVector.h"
+
 #define OFFLOAD_SUCCESS (0)
 #define OFFLOAD_FAIL (~0)
 
@@ -185,10 +189,21 @@
   /// as long as this AsyncInfoTy object.
   std::deque<void *> BufferLocations;
 
+  /// Post-processing operations executed after a successful synchronization.
+  /// \note the post-processing function should return OFFLOAD_SUCCESS or
+  /// OFFLOAD_FAIL appropriately.
+  using PostProcFuncTy = std::function<int()>;
+  llvm::SmallVector<PostProcFuncTy> PostProcessingFunctions;
+
   __tgt_async_info AsyncInfo;
   DeviceTy &Device;
 
 public:
+  enum class SyncType {
+    BLOCKING,
+    NON_BLOCKING
+  };
+
   AsyncInfoTy(DeviceTy &Device) : Device(Device) {}
   ~AsyncInfoTy() { synchronize(); }
 
@@ -199,11 +214,30 @@
   /// Synchronize all pending actions.
   ///
   /// \returns OFFLOAD_FAIL or OFFLOAD_SUCCESS appropriately.
-  int synchronize();
+  int synchronize(SyncType SyncType = SyncType::BLOCKING);
 
   /// Return a void* reference with a lifetime that is at least as long as this
   /// AsyncInfoTy object. The location can be used as intermediate buffer.
   void *&getVoidPtrLocation();
+
+  /// Check if all asynchronous operations are completed.
+  ///
+  /// \returns true if there is no pending asynchronous operations, false
+  /// otherwise.
+  bool isDone();
+
+  /// Add a new post-processing function to be executed after synchronization.
+  ///
+  /// \param[in] Function is a templated function (e.g., function pointers,
+  /// lambdas, std::function) that can be convertible to a PostProcFuncTy (i.e.,
+  /// it must have int() as its function signature).
+  template<typename FuncTy>
+  void addPostProcessingFunction(FuncTy &&Function) {
+    static_assert(std::is_convertible_v<FuncTy, PostProcFuncTy>,
+                  "Invalid post-processing function type. Please check "
+                  "function signature!");
+    PostProcessingFunctions.emplace_back(Function);
+  }
 };
 
 /// This struct is a record of non-contiguous information
diff --git a/openmp/libomptarget/include/omptargetplugin.h b/openmp/libomptarget/include/omptargetplugin.h
--- a/openmp/libomptarget/include/omptargetplugin.h
+++ b/openmp/libomptarget/include/omptargetplugin.h
@@ -155,6 +155,16 @@
 // error code.
 int32_t __tgt_rtl_synchronize(int32_t ID, __tgt_async_info *AsyncInfo);
 
+// Queries for the completion of asynchronous operations. Instead of blocking
+// the calling thread as __tgt_rtl_synchronize, the progress of the operations
+// stored in AsyncInfo->Queue is queried in a non-blocking manner, partially
+// advancing their execution. If all operations are completed, AsyncInfo->Queue
+// is set to nullptr. If there are still pending operations, AsyncInfo->Queue is
+// kept as a valid queue. In any case of success (i.e., successful query
+// with/without completing all operations), return zero. Otherwise, return an
+// error code.
+int32_t __tgt_rtl_query_async(int32_t ID, __tgt_async_info *AsyncInfo);
+
 // Set plugin's internal information flag externally.
 void __tgt_rtl_set_info_flag(uint32_t);
 
diff --git a/openmp/libomptarget/include/rtl.h b/openmp/libomptarget/include/rtl.h
--- a/openmp/libomptarget/include/rtl.h
+++ b/openmp/libomptarget/include/rtl.h
@@ -58,6 +58,7 @@
                                             __tgt_async_info *);
   typedef int64_t(init_requires_ty)(int64_t);
   typedef int32_t(synchronize_ty)(int32_t, __tgt_async_info *);
+  typedef int32_t(query_async_ty)(int32_t, __tgt_async_info *);
   typedef int32_t (*register_lib_ty)(__tgt_bin_desc *);
   typedef int32_t(supports_empty_images_ty)();
   typedef void(print_device_info_ty)(int32_t);
@@ -108,6 +109,7 @@
   run_team_region_async_ty *run_team_region_async = nullptr;
   init_requires_ty *init_requires = nullptr;
   synchronize_ty *synchronize = nullptr;
+  query_async_ty *query_async = nullptr;
   register_lib_ty register_lib = nullptr;
   register_lib_ty unregister_lib = nullptr;
   supports_empty_images_ty *supports_empty_images = nullptr;
diff --git a/openmp/libomptarget/plugins/cuda/dynamic_cuda/cuda.h b/openmp/libomptarget/plugins/cuda/dynamic_cuda/cuda.h
--- a/openmp/libomptarget/plugins/cuda/dynamic_cuda/cuda.h
+++ b/openmp/libomptarget/plugins/cuda/dynamic_cuda/cuda.h
@@ -29,6 +29,7 @@
   CUDA_ERROR_INVALID_VALUE = 1,
   CUDA_ERROR_NO_DEVICE = 100,
   CUDA_ERROR_INVALID_HANDLE = 400,
+  CUDA_ERROR_NOT_READY = 600,
 } CUresult;
 
 typedef enum CUstream_flags_enum {
@@ -241,6 +242,7 @@
 CUresult cuStreamCreate(CUstream *, unsigned);
 CUresult cuStreamDestroy(CUstream);
 CUresult cuStreamSynchronize(CUstream);
+CUresult cuStreamQuery(CUstream);
 CUresult cuCtxSetCurrent(CUcontext);
 CUresult cuDevicePrimaryCtxRelease(CUdevice);
 CUresult cuDevicePrimaryCtxGetState(CUdevice, unsigned *, int *);
diff --git a/openmp/libomptarget/plugins/cuda/dynamic_cuda/cuda.cpp b/openmp/libomptarget/plugins/cuda/dynamic_cuda/cuda.cpp
--- a/openmp/libomptarget/plugins/cuda/dynamic_cuda/cuda.cpp
+++ b/openmp/libomptarget/plugins/cuda/dynamic_cuda/cuda.cpp
@@ -57,6 +57,7 @@
 DLWRAP(cuStreamCreate, 2);
 DLWRAP(cuStreamDestroy, 1);
 DLWRAP(cuStreamSynchronize, 1);
+DLWRAP(cuStreamQuery, 1);
 DLWRAP(cuCtxSetCurrent, 1);
 DLWRAP(cuDevicePrimaryCtxRelease, 1);
 DLWRAP(cuDevicePrimaryCtxGetState, 3);
diff --git a/openmp/libomptarget/plugins/cuda/src/rtl.cpp b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
--- a/openmp/libomptarget/plugins/cuda/src/rtl.cpp
+++ b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
@@ -1263,6 +1263,31 @@
     return (Err == CUDA_SUCCESS) ? OFFLOAD_SUCCESS : OFFLOAD_FAIL;
   }
 
+  int queryAsync(const int DeviceId, __tgt_async_info *AsyncInfo) const {
+    CUstream Stream = reinterpret_cast<CUstream>(AsyncInfo->Queue);
+    CUresult Err = cuStreamQuery(Stream);
+
+    if (Err == CUDA_ERROR_NOT_READY) {
+      // Not ready streams must be considered as successful operations.
+      Err = CUDA_SUCCESS;
+    } else {
+      // Once the stream is synchronized or an error occurs, return it to the
+      // stream pool and reset AsyncInfo. This is to make sure the
+      // synchronization only works for its own tasks.
+      StreamPool[DeviceId]->release(
+          reinterpret_cast<CUstream>(AsyncInfo->Queue));
+      AsyncInfo->Queue = nullptr;
+    }
+
+    if (Err != CUDA_SUCCESS) {
+      DP("Error when querying for stream progress. stream = " DPxMOD
+         ", async info ptr = " DPxMOD "\n",
+         DPxPTR(Stream), DPxPTR(AsyncInfo));
+      CUDA_ERR_STRING(Err);
+    }
+    return (Err == CUDA_SUCCESS) ? OFFLOAD_SUCCESS : OFFLOAD_FAIL;
+  }
+
   void printDeviceInfo(int32_t DeviceId) {
     char TmpChar[1000];
     std::string TmpStr;
@@ -1776,6 +1801,15 @@
   return DeviceRTL.synchronize(DeviceId, AsyncInfoPtr);
 }
 
+int32_t __tgt_rtl_query_async(int32_t DeviceId,
+                              __tgt_async_info *AsyncInfoPtr) {
+  assert(DeviceRTL.isValidDeviceId(DeviceId) && "device_id is invalid");
+  assert(AsyncInfoPtr && "async_info_ptr is nullptr");
+  assert(AsyncInfoPtr->Queue && "async_info_ptr->Queue is nullptr");
+  // NOTE: We don't need to set context for stream query.
+  return DeviceRTL.queryAsync(DeviceId, AsyncInfoPtr);
+}
+
 void __tgt_rtl_set_info_flag(uint32_t NewInfoLevel) {
   std::atomic<uint32_t> &InfoLevel = getInfoLevelInternal();
   InfoLevel.store(NewInfoLevel);
diff --git a/openmp/libomptarget/plugins/exports b/openmp/libomptarget/plugins/exports
--- a/openmp/libomptarget/plugins/exports
+++ b/openmp/libomptarget/plugins/exports
@@ -23,6 +23,7 @@
     __tgt_rtl_run_target_region;
     __tgt_rtl_run_target_region_async;
     __tgt_rtl_synchronize;
+    __tgt_rtl_query_async;
     __tgt_rtl_register_lib;
     __tgt_rtl_unregister_lib;
     __tgt_rtl_supports_empty_images;
diff --git a/openmp/libomptarget/src/device.cpp b/openmp/libomptarget/src/device.cpp
--- a/openmp/libomptarget/src/device.cpp
+++ b/openmp/libomptarget/src/device.cpp
@@ -628,6 +628,13 @@
   return OFFLOAD_SUCCESS;
 }
 
+int32_t DeviceTy::queryAsync(AsyncInfoTy &AsyncInfo) {
+  if (RTL->query_async)
+    return RTL->query_async(RTLDeviceID, AsyncInfo);
+
+  return synchronize(AsyncInfo);
+}
+
 int32_t DeviceTy::createEvent(void **Event) {
   if (RTL->create_event)
     return RTL->create_event(RTLDeviceID, Event);
diff --git a/openmp/libomptarget/src/interface.cpp b/openmp/libomptarget/src/interface.cpp
--- a/openmp/libomptarget/src/interface.cpp
+++ b/openmp/libomptarget/src/interface.cpp
@@ -61,6 +61,39 @@
   }
 }
 
+static inline void targetDataMapper(
+    ident_t *Loc, DeviceTy &Device, int64_t DeviceId, int32_t ArgNum,
+    void **ArgsBase, void **Args, int64_t *ArgSizes, int64_t *ArgTypes,
+    map_var_info_t *ArgNames, void **ArgMappers, AsyncInfoTy &AsyncInfo,
+    TargetDataFuncPtrTy TargetDataFunction, const char *RegionTypeMsg,
+    AsyncInfoTy::SyncType SyncType = AsyncInfoTy::SyncType::BLOCKING,
+    bool Dispatch = true, bool FromMapper = false) {
+  TIMESCOPE_WITH_IDENT(Loc);
+
+  if (getInfoLevel() & OMP_INFOTYPE_KERNEL_ARGS)
+    printKernelArguments(Loc, DeviceId, ArgNum, ArgSizes, ArgTypes, ArgNames,
+                         RegionTypeMsg);
+#ifdef OMPTARGET_DEBUG
+  for (int I = 0; I < ArgNum; ++I) {
+    DP("Entry %2d: Base=" DPxMOD ", Begin=" DPxMOD ", Size=%" PRId64
+       ", Type=0x%" PRIx64 ", Name=%s\n",
+       I, DPxPTR(ArgsBase[I]), DPxPTR(Args[I]), ArgSizes[I], ArgTypes[I],
+       (ArgNames) ? getNameFromMapping(ArgNames[I]).c_str() : "unknown");
+  }
+#endif
+
+  int Rc = OFFLOAD_SUCCESS;
+  if (Dispatch)
+    Rc = TargetDataFunction(Loc, Device, ArgNum, ArgsBase, Args, ArgSizes,
+                            ArgTypes, ArgNames, ArgMappers, AsyncInfo,
+                            FromMapper);
+
+  if (Rc == OFFLOAD_SUCCESS)
+    Rc = AsyncInfo.synchronize(SyncType);
+
+  handleTargetOutcome(Rc == OFFLOAD_SUCCESS, Loc);
+}
+
 /// creates host-to-target data mapping, stores it in the
 /// libomptarget.so internal structure (an entry in a stack of data maps)
 /// and passes the data to the device.
@@ -71,8 +104,10 @@
                                            map_var_info_t *ArgNames,
                                            void **ArgMappers) {
   TIMESCOPE_WITH_IDENT(Loc);
+
   DP("Entering data begin region for device %" PRId64 " with %d mappings\n",
      DeviceId, ArgNum);
+
   if (checkDeviceAndCtors(DeviceId, Loc)) {
     DP("Not offloading to device %" PRId64 "\n", DeviceId);
     return;
@@ -80,24 +115,10 @@
 
   DeviceTy &Device = *PM->Devices[DeviceId];
 
-  if (getInfoLevel() & OMP_INFOTYPE_KERNEL_ARGS)
-    printKernelArguments(Loc, DeviceId, ArgNum, ArgSizes, ArgTypes, ArgNames,
-                         "Entering OpenMP data region");
-#ifdef OMPTARGET_DEBUG
-  for (int I = 0; I < ArgNum; ++I) {
-    DP("Entry %2d: Base=" DPxMOD ", Begin=" DPxMOD ", Size=%" PRId64
-       ", Type=0x%" PRIx64 ", Name=%s\n",
-       I, DPxPTR(ArgsBase[I]), DPxPTR(Args[I]), ArgSizes[I], ArgTypes[I],
-       (ArgNames) ? getNameFromMapping(ArgNames[I]).c_str() : "unknown");
-  }
-#endif
-
   AsyncInfoTy AsyncInfo(Device);
-  int Rc = targetDataBegin(Loc, Device, ArgNum, ArgsBase, Args, ArgSizes,
-                           ArgTypes, ArgNames, ArgMappers, AsyncInfo);
-  if (Rc == OFFLOAD_SUCCESS)
-    Rc = AsyncInfo.synchronize();
-  handleTargetOutcome(Rc == OFFLOAD_SUCCESS, Loc);
+  targetDataMapper(Loc, Device, DeviceId, ArgNum, ArgsBase, Args, ArgSizes,
+                   ArgTypes, ArgNames, ArgMappers, AsyncInfo, targetDataBegin,
+                   "Entering OpenMP data region");
 }
 
 EXTERN void __tgt_target_data_begin_nowait_mapper(
@@ -107,8 +128,21 @@
     void *NoAliasDepList) {
   TIMESCOPE_WITH_IDENT(Loc);
 
-  __tgt_target_data_begin_mapper(Loc, DeviceId, ArgNum, ArgsBase, Args,
-                                 ArgSizes, ArgTypes, ArgNames, ArgMappers);
+  DP("Entering data begin region for device %" PRId64 " with %d mappings\n",
+     DeviceId, ArgNum);
+
+  if (checkDeviceAndCtors(DeviceId, Loc)) {
+    DP("Not offloading to device %" PRId64 "\n", DeviceId);
+    return;
+  }
+
+  DeviceTy &Device = *PM->Devices[DeviceId];
+
+  TaskAsyncInfoTy AsyncInfo(Device);
+  targetDataMapper(Loc, Device, DeviceId, ArgNum, ArgsBase, Args, ArgSizes,
+                   ArgTypes, ArgNames, ArgMappers, *AsyncInfo, targetDataBegin,
+                   "Entering OpenMP data region", AsyncInfo.getSyncType(),
+                   AsyncInfo.shouldDispatch());
 }
 
 /// passes data from the target, releases target memory and destroys
@@ -121,7 +155,10 @@
                                          map_var_info_t *ArgNames,
                                          void **ArgMappers) {
   TIMESCOPE_WITH_IDENT(Loc);
-  DP("Entering data end region with %d mappings\n", ArgNum);
+
+  DP("Entering data end region for device %" PRId64 " with %d mappings\n",
+     DeviceId, ArgNum);
+
   if (checkDeviceAndCtors(DeviceId, Loc)) {
     DP("Not offloading to device %" PRId64 "\n", DeviceId);
     return;
@@ -129,24 +166,10 @@
 
   DeviceTy &Device = *PM->Devices[DeviceId];
 
-  if (getInfoLevel() & OMP_INFOTYPE_KERNEL_ARGS)
-    printKernelArguments(Loc, DeviceId, ArgNum, ArgSizes, ArgTypes, ArgNames,
-                         "Exiting OpenMP data region");
-#ifdef OMPTARGET_DEBUG
-  for (int I = 0; I < ArgNum; ++I) {
-    DP("Entry %2d: Base=" DPxMOD ", Begin=" DPxMOD ", Size=%" PRId64
-       ", Type=0x%" PRIx64 ", Name=%s\n",
-       I, DPxPTR(ArgsBase[I]), DPxPTR(Args[I]), ArgSizes[I], ArgTypes[I],
-       (ArgNames) ? getNameFromMapping(ArgNames[I]).c_str() : "unknown");
-  }
-#endif
-
   AsyncInfoTy AsyncInfo(Device);
-  int Rc = targetDataEnd(Loc, Device, ArgNum, ArgsBase, Args, ArgSizes,
-                         ArgTypes, ArgNames, ArgMappers, AsyncInfo);
-  if (Rc == OFFLOAD_SUCCESS)
-    Rc = AsyncInfo.synchronize();
-  handleTargetOutcome(Rc == OFFLOAD_SUCCESS, Loc);
+  targetDataMapper(Loc, Device, DeviceId, ArgNum, ArgsBase, Args, ArgSizes,
+                   ArgTypes, ArgNames, ArgMappers, AsyncInfo, targetDataEnd,
+                   "Exiting OpenMP data region");
 }
 
 EXTERN void __tgt_target_data_end_nowait_mapper(
@@ -156,8 +179,21 @@
     void *NoAliasDepList) {
   TIMESCOPE_WITH_IDENT(Loc);
 
-  __tgt_target_data_end_mapper(Loc, DeviceId, ArgNum, ArgsBase, Args, ArgSizes,
-                               ArgTypes, ArgNames, ArgMappers);
+  DP("Entering data end region for device %" PRId64 " with %d mappings\n",
+     DeviceId, ArgNum);
+
+  if (checkDeviceAndCtors(DeviceId, Loc)) {
+    DP("Not offloading to device %" PRId64 "\n", DeviceId);
+    return;
+  }
+
+  DeviceTy &Device = *PM->Devices[DeviceId];
+
+  TaskAsyncInfoTy AsyncInfo(Device);
+  targetDataMapper(Loc, Device, DeviceId, ArgNum, ArgsBase, Args, ArgSizes,
+                   ArgTypes, ArgNames, ArgMappers, *AsyncInfo, targetDataEnd,
+                   "Exiting OpenMP data region", AsyncInfo.getSyncType(),
+                   AsyncInfo.shouldDispatch());
 }
 
 EXTERN void __tgt_target_data_update_mapper(ident_t *Loc, int64_t DeviceId,
@@ -167,23 +203,21 @@
                                             map_var_info_t *ArgNames,
                                             void **ArgMappers) {
   TIMESCOPE_WITH_IDENT(Loc);
-  DP("Entering data update with %d mappings\n", ArgNum);
+
+  DP("Entering data update region for device %" PRId64 " with %d mappings\n",
+     DeviceId, ArgNum);
+
   if (checkDeviceAndCtors(DeviceId, Loc)) {
     DP("Not offloading to device %" PRId64 "\n", DeviceId);
     return;
   }
 
-  if (getInfoLevel() & OMP_INFOTYPE_KERNEL_ARGS)
-    printKernelArguments(Loc, DeviceId, ArgNum, ArgSizes, ArgTypes, ArgNames,
-                         "Updating OpenMP data");
-
   DeviceTy &Device = *PM->Devices[DeviceId];
+
   AsyncInfoTy AsyncInfo(Device);
-  int Rc = targetDataUpdate(Loc, Device, ArgNum, ArgsBase, Args, ArgSizes,
-                            ArgTypes, ArgNames, ArgMappers, AsyncInfo);
-  if (Rc == OFFLOAD_SUCCESS)
-    Rc = AsyncInfo.synchronize();
-  handleTargetOutcome(Rc == OFFLOAD_SUCCESS, Loc);
+  targetDataMapper(Loc, Device, DeviceId, ArgNum, ArgsBase, Args, ArgSizes,
+                   ArgTypes, ArgNames, ArgMappers, AsyncInfo, targetDataUpdate,
+                   "Updating OpenMP data");
 }
 
 EXTERN void __tgt_target_data_update_nowait_mapper(
@@ -193,35 +227,34 @@
     void *NoAliasDepList) {
   TIMESCOPE_WITH_IDENT(Loc);
 
-  __tgt_target_data_update_mapper(Loc, DeviceId, ArgNum, ArgsBase, Args,
-                                  ArgSizes, ArgTypes, ArgNames, ArgMappers);
+  DP("Entering data update region for device %" PRId64 " with %d mappings\n",
+     DeviceId, ArgNum);
+
+  if (checkDeviceAndCtors(DeviceId, Loc)) {
+    DP("Not offloading to device %" PRId64 "\n", DeviceId);
+    return;
+  }
+
+  DeviceTy &Device = *PM->Devices[DeviceId];
+
+  TaskAsyncInfoTy AsyncInfo(Device);
+  targetDataMapper(Loc, Device, DeviceId, ArgNum, ArgsBase, Args, ArgSizes,
+                   ArgTypes, ArgNames, ArgMappers, *AsyncInfo, targetDataUpdate,
+                   "Updating OpenMP data", AsyncInfo.getSyncType(),
+                   AsyncInfo.shouldDispatch());
 }
 
-/// Implements a kernel entry that executes the target region on the specified
-/// device.
-///
-/// \param Loc Source location associated with this target region.
-/// \param DeviceId The device to execute this region, -1 indicated the default.
-/// \param NumTeams Number of teams to launch the region with, -1 indicates a
-///                 non-teams region and 0 indicates it was unspecified.
-/// \param ThreadLimit Limit to the number of threads to use in the kernel
-///                    launch, 0 indicates it was unspecified.
-/// \param HostPtr  The pointer to the host function registered with the kernel.
-/// \param Args     All arguments to this kernel launch (see struct definition).
-EXTERN int __tgt_target_kernel(ident_t *Loc, int64_t DeviceId, int32_t NumTeams,
-                               int32_t ThreadLimit, void *HostPtr,
-                               __tgt_kernel_arguments *Args) {
+static inline int
+targetKernel(ident_t *Loc, DeviceTy &Device, int64_t DeviceId, int32_t NumTeams,
+             int32_t ThreadLimit, void *HostPtr, __tgt_kernel_arguments *Args,
+             AsyncInfoTy &AsyncInfo,
+             AsyncInfoTy::SyncType SyncType = AsyncInfoTy::SyncType::BLOCKING,
+             bool Dispatch = true) {
   TIMESCOPE_WITH_IDENT(Loc);
-  DP("Entering target region with entry point " DPxMOD " and device Id %" PRId64
-     "\n",
-     DPxPTR(HostPtr), DeviceId);
+
   if (Args->Version != 1) {
     DP("Unexpected ABI version: %d\n", Args->Version);
   }
-  if (checkDeviceAndCtors(DeviceId, Loc)) {
-    DP("Not offloading to device %" PRId64 "\n", DeviceId);
-    return OMP_TGT_FAIL;
-  }
 
   if (getInfoLevel() & OMP_INFOTYPE_KERNEL_ARGS)
     printKernelArguments(Loc, DeviceId, Args->NumArgs, Args->ArgSizes,
@@ -242,27 +275,75 @@
   if (!IsTeams)
     NumTeams = 0;
 
-  DeviceTy &Device = *PM->Devices[DeviceId];
-  AsyncInfoTy AsyncInfo(Device);
-  int Rc = target(Loc, Device, HostPtr, Args->NumArgs, Args->ArgBasePtrs,
-                  Args->ArgPtrs, Args->ArgSizes, Args->ArgTypes, Args->ArgNames,
-                  Args->ArgMappers, NumTeams, ThreadLimit, Args->Tripcount,
-                  IsTeams, AsyncInfo);
+  int Rc = OFFLOAD_SUCCESS;
+  if (AsyncInfo.isDone())
+    Rc = target(Loc, Device, HostPtr, Args->NumArgs, Args->ArgBasePtrs,
+                Args->ArgPtrs, Args->ArgSizes, Args->ArgTypes, Args->ArgNames,
+                Args->ArgMappers, NumTeams, ThreadLimit, Args->Tripcount,
+                IsTeams, AsyncInfo);
+
   if (Rc == OFFLOAD_SUCCESS)
-    Rc = AsyncInfo.synchronize();
+    Rc = AsyncInfo.synchronize(SyncType);
+
   handleTargetOutcome(Rc == OFFLOAD_SUCCESS, Loc);
   assert(Rc == OFFLOAD_SUCCESS && "__tgt_target_kernel unexpected failure!");
+
   return OMP_TGT_SUCCESS;
 }
 
+/// Implements a kernel entry that executes the target region on the specified
+/// device.
+///
+/// \param Loc Source location associated with this target region.
+/// \param DeviceId The device to execute this region, -1 indicated the default.
+/// \param NumTeams Number of teams to launch the region with, -1 indicates a
+///                 non-teams region and 0 indicates it was unspecified.
+/// \param ThreadLimit Limit to the number of threads to use in the kernel
+///                    launch, 0 indicates it was unspecified.
+/// \param HostPtr  The pointer to the host function registered with the kernel.
+/// \param Args     All arguments to this kernel launch (see struct definition).
+EXTERN int __tgt_target_kernel(ident_t *Loc, int64_t DeviceId, int32_t NumTeams,
+                               int32_t ThreadLimit, void *HostPtr,
+                               __tgt_kernel_arguments *Args) {
+  TIMESCOPE_WITH_IDENT(Loc);
+
+  DP("Entering target region with entry point " DPxMOD " and device Id %" PRId64
+     "\n",
+     DPxPTR(HostPtr), DeviceId);
+
+  if (checkDeviceAndCtors(DeviceId, Loc)) {
+    DP("Not offloading to device %" PRId64 "\n", DeviceId);
+    return OMP_TGT_FAIL;
+  }
+
+  DeviceTy &Device = *PM->Devices[DeviceId];
+
+  AsyncInfoTy AsyncInfo(Device);
+  return targetKernel(Loc, Device, DeviceId, NumTeams, ThreadLimit, HostPtr,
+                      Args, AsyncInfo);
+}
+
 EXTERN int __tgt_target_kernel_nowait(
     ident_t *Loc, int64_t DeviceId, int32_t NumTeams, int32_t ThreadLimit,
     void *HostPtr, __tgt_kernel_arguments *Args, int32_t DepNum, void *DepList,
     int32_t NoAliasDepNum, void *NoAliasDepList) {
   TIMESCOPE_WITH_IDENT(Loc);
 
-  return __tgt_target_kernel(Loc, DeviceId, NumTeams, ThreadLimit, HostPtr,
-                             Args);
+  DP("Entering target region with entry point " DPxMOD " and device Id %" PRId64
+     "\n",
+     DPxPTR(HostPtr), DeviceId);
+
+  if (checkDeviceAndCtors(DeviceId, Loc)) {
+    DP("Not offloading to device %" PRId64 "\n", DeviceId);
+    return OMP_TGT_FAIL;
+  }
+
+  DeviceTy &Device = *PM->Devices[DeviceId];
+
+  TaskAsyncInfoTy AsyncInfo(Device);
+  return targetKernel(Loc, Device, DeviceId, NumTeams, ThreadLimit, HostPtr,
+                      Args, *AsyncInfo, AsyncInfo.getSyncType(),
+                      AsyncInfo.shouldDispatch());
 }
 
 // Get the current number of components for a user-defined mapper.
diff --git a/openmp/libomptarget/src/omptarget.cpp b/openmp/libomptarget/src/omptarget.cpp
--- a/openmp/libomptarget/src/omptarget.cpp
+++ b/openmp/libomptarget/src/omptarget.cpp
@@ -22,15 +22,33 @@
 
 using llvm::SmallVector;
 
-int AsyncInfoTy::synchronize() {
+int AsyncInfoTy::synchronize(SyncType SyncType) {
   int Result = OFFLOAD_SUCCESS;
   if (AsyncInfo.Queue) {
-    // If we have a queue we need to synchronize it now.
-    Result = Device.synchronize(*this);
-    assert(AsyncInfo.Queue == nullptr &&
-           "The device plugin should have nulled the queue to indicate there "
-           "are no outstanding actions!");
+    switch (SyncType) {
+    case SyncType::BLOCKING:
+      // If we have a queue we need to synchronize it now.
+      Result = Device.synchronize(*this);
+      assert(AsyncInfo.Queue == nullptr &&
+             "The device plugin should have nulled the queue to indicate there "
+             "are no outstanding actions!");
+      break;
+    case SyncType::NON_BLOCKING:
+      Result = Device.queryAsync(*this);
+      break;
+    }
+  }
+
+  // Run any pending post-processing function registered on this async object.
+  if (Result == OFFLOAD_SUCCESS && isDone()) {
+    for (auto &PostProcFunc : PostProcessingFunctions) {
+      Result = PostProcFunc();
+      if (Result != OFFLOAD_SUCCESS)
+        break;
+    }
+    PostProcessingFunctions.clear();
   }
+
   return Result;
 }
 
@@ -39,6 +57,8 @@
   return BufferLocations.back();
 }
 
+bool AsyncInfoTy::isDone() { return AsyncInfo.Queue == nullptr; }
+
 /* All begin addresses for partially mapped structs must be 8-aligned in order
  * to ensure proper alignment of members. E.g.
  *
@@ -675,12 +695,89 @@
 
 } // namespace
 
+/// Applies the necessary post-processing procedures to entries listed in \p
+/// EntriesInfo after the execution of all device side operations from a target
+/// data end. This includes the update of pointers at the host and removal of
+/// device buffer when needed. It returns OFFLOAD_FAIL or OFFLOAD_SUCCESS
+/// according to the successfulness of the operations.
+static int
+postProcessingTargetDataEnd(DeviceTy *Device,
+                            SmallVector<PostProcessingInfo> EntriesInfo,
+                            void * FromMapperBase) {
+  int Ret = OFFLOAD_SUCCESS;
+
+  for (PostProcessingInfo &Info : EntriesInfo) {
+    // If we marked the entry to be deleted we need to verify no other
+    // thread reused it by now. If deletion is still supposed to happen by
+    // this thread LR will be set and exclusive access to the HDTT map
+    // will avoid another thread reusing the entry now. Note that we do
+    // not request (exclusive) access to the HDTT map if Info.DelEntry is
+    // not set.
+    LookupResult LR;
+    DeviceTy::HDTTMapAccessorTy HDTTMap =
+        Device->HostDataToTargetMap.getExclusiveAccessor(!Info.DelEntry);
+
+    if (Info.DelEntry) {
+      LR = Device->lookupMapping(HDTTMap, Info.HstPtrBegin, Info.DataSize);
+      if (LR.Entry->getTotalRefCount() != 0 ||
+          LR.Entry->getDeleteThreadId() != std::this_thread::get_id()) {
+        // The thread is not in charge of deletion anymore. Give up access
+        // to the HDTT map and unset the deletion flag.
+        HDTTMap.destroy();
+        Info.DelEntry = false;
+      }
+    }
+
+    // If we copied back to the host a struct/array containing pointers,
+    // we need to restore the original host pointer values from their
+    // shadow copies. If the struct is going to be deallocated, remove any
+    // remaining shadow pointer entries for this struct.
+    auto CB = [&](ShadowPtrListTy::iterator &Itr) {
+      // If we copied the struct to the host, we need to restore the
+      // pointer.
+      if (Info.ArgType & OMP_TGT_MAPTYPE_FROM) {
+        void **ShadowHstPtrAddr = (void **)Itr->first;
+        *ShadowHstPtrAddr = Itr->second.HstPtrVal;
+        DP("Restoring original host pointer value " DPxMOD " for host "
+           "pointer " DPxMOD "\n",
+           DPxPTR(Itr->second.HstPtrVal), DPxPTR(ShadowHstPtrAddr));
+      }
+      // If the struct is to be deallocated, remove the shadow entry.
+      if (Info.DelEntry) {
+        DP("Removing shadow pointer " DPxMOD "\n", DPxPTR((void **)Itr->first));
+        auto OldItr = Itr;
+        Itr++;
+        Device->ShadowPtrMap.erase(OldItr);
+      } else {
+        ++Itr;
+      }
+      return OFFLOAD_SUCCESS;
+    };
+    applyToShadowMapEntries(*Device, CB, Info.HstPtrBegin, Info.DataSize,
+                            Info.TPR);
+
+    // If we are deleting the entry the DataMapMtx is locked and we own
+    // the entry.
+    if (Info.DelEntry) {
+      if (!FromMapperBase || FromMapperBase != Info.HstPtrBegin)
+        Ret = Device->deallocTgtPtr(HDTTMap, LR, Info.DataSize);
+
+      if (Ret != OFFLOAD_SUCCESS) {
+        REPORT("Deallocating data from device failed.\n");
+        break;
+      }
+    }
+  }
+
+  return Ret;
+}
+
 /// Internal function to undo the mapping and retrieve the data from the device.
 int targetDataEnd(ident_t *Loc, DeviceTy &Device, int32_t ArgNum,
                   void **ArgBases, void **Args, int64_t *ArgSizes,
                   int64_t *ArgTypes, map_var_info_t *ArgNames,
                   void **ArgMappers, AsyncInfoTy &AsyncInfo, bool FromMapper) {
-  int Ret;
+  int Ret = OFFLOAD_SUCCESS;
   SmallVector<PostProcessingInfo> PostProcessingPtrs;
   void *FromMapperBase = nullptr;
   // process each input.
@@ -839,75 +936,13 @@
     }
   }
 
-  // TODO: We should not synchronize here but pass the AsyncInfo object to the
-  //       allocate/deallocate device APIs.
-  //
-  // We need to synchronize before deallocating data.
-  Ret = AsyncInfo.synchronize();
-  if (Ret != OFFLOAD_SUCCESS)
-    return OFFLOAD_FAIL;
-
-  // Deallocate target pointer
-  for (PostProcessingInfo &Info : PostProcessingPtrs) {
-    // If we marked the entry to be deleted we need to verify no other thread
-    // reused it by now. If deletion is still supposed to happen by this thread
-    // LR will be set and exclusive access to the HDTT map will avoid another
-    // thread reusing the entry now. Note that we do not request (exclusive)
-    // access to the HDTT map if Info.DelEntry is not set.
-    LookupResult LR;
-    DeviceTy::HDTTMapAccessorTy HDTTMap =
-        Device.HostDataToTargetMap.getExclusiveAccessor(!Info.DelEntry);
-
-    if (Info.DelEntry) {
-      LR = Device.lookupMapping(HDTTMap, Info.HstPtrBegin, Info.DataSize);
-      if (LR.Entry->getTotalRefCount() != 0 ||
-          LR.Entry->getDeleteThreadId() != std::this_thread::get_id()) {
-        // The thread is not in charge of deletion anymore. Give up access to
-        // the HDTT map and unset the deletion flag.
-        HDTTMap.destroy();
-        Info.DelEntry = false;
-      }
-    }
-
-    // If we copied back to the host a struct/array containing pointers, we
-    // need to restore the original host pointer values from their shadow
-    // copies. If the struct is going to be deallocated, remove any remaining
-    // shadow pointer entries for this struct.
-    auto CB = [&](ShadowPtrListTy::iterator &Itr) {
-      // If we copied the struct to the host, we need to restore the pointer.
-      if (Info.ArgType & OMP_TGT_MAPTYPE_FROM) {
-        void **ShadowHstPtrAddr = (void **)Itr->first;
-        *ShadowHstPtrAddr = Itr->second.HstPtrVal;
-        DP("Restoring original host pointer value " DPxMOD " for host "
-           "pointer " DPxMOD "\n",
-           DPxPTR(Itr->second.HstPtrVal), DPxPTR(ShadowHstPtrAddr));
-      }
-      // If the struct is to be deallocated, remove the shadow entry.
-      if (Info.DelEntry) {
-        DP("Removing shadow pointer " DPxMOD "\n", DPxPTR((void **)Itr->first));
-        auto OldItr = Itr;
-        Itr++;
-        Device.ShadowPtrMap.erase(OldItr);
-      } else {
-        ++Itr;
-      }
-      return OFFLOAD_SUCCESS;
-    };
-    applyToShadowMapEntries(Device, CB, Info.HstPtrBegin, Info.DataSize,
-                            Info.TPR);
-
-    // If we are deleting the entry the DataMapMtx is locked and we own the
-    // entry.
-    if (Info.DelEntry) {
-      if (!FromMapperBase || FromMapperBase != Info.HstPtrBegin)
-        Ret = Device.deallocTgtPtr(HDTTMap, LR, Info.DataSize);
-
-      if (Ret != OFFLOAD_SUCCESS) {
-        REPORT("Deallocating data from device failed.\n");
-        break;
-      }
-    }
-  }
+  // Add post-processing functions
+  AsyncInfo.addPostProcessingFunction(
+      [=, Device = &Device,
+       PostProcessingPtrs = std::move(PostProcessingPtrs)]() mutable -> int {
+        return postProcessingTargetDataEnd(Device, PostProcessingPtrs,
+                                           FromMapperBase);
+      });
 
   return Ret;
 }
@@ -947,20 +982,22 @@
       return OFFLOAD_FAIL;
     }
 
-    auto CB = [&](ShadowPtrListTy::iterator &Itr) {
-      void **ShadowHstPtrAddr = (void **)Itr->first;
-      // Wait for device-to-host memcopies for whole struct to complete,
-      // before restoring the correct host pointer.
-      if (AsyncInfo.synchronize() != OFFLOAD_SUCCESS)
-        return OFFLOAD_FAIL;
-      *ShadowHstPtrAddr = Itr->second.HstPtrVal;
-      DP("Restoring original host pointer value " DPxMOD
-         " for host pointer " DPxMOD "\n",
-         DPxPTR(Itr->second.HstPtrVal), DPxPTR(ShadowHstPtrAddr));
-      ++Itr;
+    // Wait for device-to-host memcopies for whole struct to complete,
+    // before restoring the correct host pointer.
+    AsyncInfo.addPostProcessingFunction([=, Device = &Device]() -> int {
+      auto CB = [&](ShadowPtrListTy::iterator &Itr) {
+        void **ShadowHstPtrAddr = (void **)Itr->first;
+        *ShadowHstPtrAddr = Itr->second.HstPtrVal;
+        DP("Restoring original host pointer value " DPxMOD
+           " for host pointer " DPxMOD "\n",
+           DPxPTR(Itr->second.HstPtrVal), DPxPTR(ShadowHstPtrAddr));
+        ++Itr;
+        return OFFLOAD_SUCCESS;
+      };
+      applyToShadowMapEntries(*Device, CB, HstPtrBegin, ArgSize, TPR);
+
       return OFFLOAD_SUCCESS;
-    };
-    applyToShadowMapEntries(Device, CB, HstPtrBegin, ArgSize, TPR);
+    });
   }
 
   if (ArgType & OMP_TGT_MAPTYPE_TO) {
@@ -1157,19 +1194,19 @@
   /// first-private arguments and transfer them all at once.
   struct FirstPrivateArgInfoTy {
     /// The index of the element in \p TgtArgs corresponding to the argument
-    const int Index;
+    int Index;
     /// Host pointer begin
-    const char *HstPtrBegin;
+    char *HstPtrBegin;
     /// Host pointer end
-    const char *HstPtrEnd;
+    char *HstPtrEnd;
     /// Aligned size
-    const int64_t AlignedSize;
+    int64_t AlignedSize;
     /// Host pointer name
-    const map_var_info_t HstPtrName = nullptr;
+    map_var_info_t HstPtrName = nullptr;
 
-    FirstPrivateArgInfoTy(int Index, const void *HstPtr, int64_t Size,
+    FirstPrivateArgInfoTy(int Index, void *HstPtr, int64_t Size,
                           const map_var_info_t HstPtrName = nullptr)
-        : Index(Index), HstPtrBegin(reinterpret_cast<const char *>(HstPtr)),
+        : Index(Index), HstPtrBegin(reinterpret_cast<char *>(HstPtr)),
           HstPtrEnd(HstPtrBegin + Size), AlignedSize(Size + Size % Alignment),
           HstPtrName(HstPtrName) {}
   };
@@ -1471,12 +1508,17 @@
     return OFFLOAD_FAIL;
   }
 
-  // Free target memory for private arguments
-  Ret = PrivateArgumentManager.free();
-  if (Ret != OFFLOAD_SUCCESS) {
-    REPORT("Failed to deallocate target memory for private args\n");
-    return OFFLOAD_FAIL;
-  }
+  // Free target memory for private arguments after synchronization.
+  AsyncInfo.addPostProcessingFunction(
+      [PrivateArgumentManager =
+           std::move(PrivateArgumentManager)]() mutable -> int {
+        int Ret = PrivateArgumentManager.free();
+        if (Ret != OFFLOAD_SUCCESS) {
+          REPORT("Failed to deallocate target memory for private args\n");
+          return OFFLOAD_FAIL;
+        }
+        return Ret;
+      });
 
   return OFFLOAD_SUCCESS;
 }
@@ -1530,7 +1572,7 @@
 
   PrivateArgumentManagerTy PrivateArgumentManager(Device, AsyncInfo);
 
-  int Ret;
+  int Ret = OFFLOAD_SUCCESS;
   if (ArgNum) {
     // Process data, such as data mapping, before launching the kernel
     Ret = processDataBefore(Loc, DeviceId, HostPtr, ArgNum, ArgBases, Args,
diff --git a/openmp/libomptarget/src/private.h b/openmp/libomptarget/src/private.h
--- a/openmp/libomptarget/src/private.h
+++ b/openmp/libomptarget/src/private.h
@@ -115,6 +115,10 @@
                           kmp_depend_info_t *dep_list, kmp_int32 ndeps_noalias,
                           kmp_depend_info_t *noalias_dep_list)
     __attribute__((weak));
+void *__kmpc_omp_get_target_async_handle(kmp_int32 gtid) __attribute__((weak));
+void __kmpc_omp_set_target_async_handle(kmp_int32 gtid, void *handle)
+    __attribute__((weak));
+bool __kmpc_omp_has_task_team(kmp_int32 gtid) __attribute__((weak));
 #ifdef __cplusplus
 }
 #endif
@@ -187,6 +191,55 @@
   }
 }
 
+class TaskAsyncInfoTy {
+  const int ExecThreadID = -1;
+  AsyncInfoTy::SyncType SyncType = AsyncInfoTy::SyncType::BLOCKING;
+  AsyncInfoTy *AsyncInfo = nullptr;
+  bool IsNew = false;
+
+public:
+  TaskAsyncInfoTy(DeviceTy &Device)
+      : ExecThreadID(__kmpc_global_thread_num(NULL)) {
+    // Acquire the AsyncInfo stored in async handle of the current task being
+    // executed. If no valid async handle is present, a new AsyncInfo is
+    // allocated and stored in the current task.
+    AsyncInfo = (AsyncInfoTy *)__kmpc_omp_get_target_async_handle(ExecThreadID);
+
+    if (!AsyncInfo) {
+      AsyncInfo = new AsyncInfoTy(Device);
+      __kmpc_omp_set_target_async_handle(ExecThreadID, (void *)AsyncInfo);
+      IsNew = true;
+    }
+
+    // Define the synchronization type based on the current task context. Only
+    // tasks with an assigned task team can be re-enqueue and thus can use the
+    // non-blocking synchronization scheme.
+    if (__kmpc_omp_has_task_team(ExecThreadID))
+      SyncType = AsyncInfoTy::SyncType::NON_BLOCKING;
+  }
+
+  /// Delete AsyncInfo if it is completed and remove it from the current task
+  /// async handle.
+  ~TaskAsyncInfoTy() {
+    if (!AsyncInfo || !AsyncInfo->isDone())
+      return;
+
+    delete AsyncInfo;
+    __kmpc_omp_set_target_async_handle(ExecThreadID, NULL);
+  }
+
+  AsyncInfoTy &operator*() { return *AsyncInfo; }
+
+  AsyncInfoTy::SyncType getSyncType() { return SyncType; }
+
+  /// Return if the device side operations should be dispatched or not. When the
+  /// async info attached to the task struct was just created, the target region
+  /// operations must be dispatched and accumulated on the internal AsyncInfo.
+  /// Otherwise, the operations were already dispatched before and only
+  /// synchronization is needed.
+  bool shouldDispatch() { return !IsNew; }
+};
+
 #ifdef OMPTARGET_PROFILE_ENABLED
 #include "llvm/Support/TimeProfiler.h"
 #define TIMESCOPE() llvm::TimeTraceScope TimeScope(__FUNCTION__)
diff --git a/openmp/libomptarget/src/rtl.cpp b/openmp/libomptarget/src/rtl.cpp
--- a/openmp/libomptarget/src/rtl.cpp
+++ b/openmp/libomptarget/src/rtl.cpp
@@ -212,6 +212,8 @@
     *((void **)&R.run_team_region_async) =
         dlsym(DynlibHandle, "__tgt_rtl_run_target_team_region_async");
     *((void **)&R.synchronize) = dlsym(DynlibHandle, "__tgt_rtl_synchronize");
+    *((void **)&R.query_async) =
+        dlsym(DynlibHandle, "__tgt_rtl_query_async");
     *((void **)&R.data_exchange) =
         dlsym(DynlibHandle, "__tgt_rtl_data_exchange");
     *((void **)&R.data_exchange_async) =
diff --git a/openmp/runtime/src/kmp.h b/openmp/runtime/src/kmp.h
--- a/openmp/runtime/src/kmp.h
+++ b/openmp/runtime/src/kmp.h
@@ -2475,6 +2475,10 @@
 
 } kmp_tasking_flags_t;
 
+typedef struct kmp_target_data {
+  void *async_handle; // libomptarget async handle for task completion query
+} kmp_target_data_t;
+
 struct kmp_taskdata { /* aligned during dynamic allocation       */
   kmp_int32 td_task_id; /* id, assigned by debugger                */
   kmp_tasking_flags_t td_flags; /* task flags                              */
@@ -2517,6 +2521,7 @@
 #if OMPT_SUPPORT
   ompt_task_info_t ompt_task_info;
 #endif
+  kmp_target_data_t td_target_data;
 }; // struct kmp_taskdata
 
 // Make sure padding above worked
@@ -4011,6 +4016,11 @@
 KMP_EXPORT void __kmp_set_teams_thread_limit(int limit);
 KMP_EXPORT int __kmp_get_teams_thread_limit(void);
 
+/* Interface target task integration */
+KMP_EXPORT void *__kmpc_omp_get_target_async_handle(kmp_int32 gtid);
+KMP_EXPORT void __kmpc_omp_set_target_async_handle(kmp_int32 gtid, void *handle);
+KMP_EXPORT bool __kmpc_omp_has_task_team(kmp_int32 gtid);
+
 /* Lock interface routines (fast versions with gtid passed in) */
 KMP_EXPORT void __kmpc_init_lock(ident_t *loc, kmp_int32 gtid,
                                  void **user_lock);
diff --git a/openmp/runtime/src/kmp_tasking.cpp b/openmp/runtime/src/kmp_tasking.cpp
--- a/openmp/runtime/src/kmp_tasking.cpp
+++ b/openmp/runtime/src/kmp_tasking.cpp
@@ -1063,7 +1063,7 @@
   KMP_DEBUG_ASSERT(taskdata->td_flags.started == 1);
   KMP_DEBUG_ASSERT(taskdata->td_flags.freed == 0);
 
-  bool detach = false;
+  bool completed = true;
   if (UNLIKELY(taskdata->td_flags.detachable == TASK_DETACHABLE)) {
     if (taskdata->td_allow_completion_event.type ==
         KMP_EVENT_ALLOW_COMPLETION) {
@@ -1087,13 +1087,24 @@
         // __kmp_fulfill_event might free taskdata at any time from now
 
         taskdata->td_flags.proxy = TASK_PROXY; // proxify!
-        detach = true;
+        completed = false;
       }
       __kmp_release_tas_lock(&taskdata->td_allow_completion_event.lock, gtid);
     }
   }
 
-  if (!detach) {
+  // Tasks with valid target async handles must be re-enqueued.
+  if (taskdata->td_target_data.async_handle != NULL) {
+    // Note: no need to translate gtid to its shadow. If the current thread is a
+    // hidden helper one, then the gtid is already correct. Otherwise, hidden
+    // helper threads are disabled, and gtid refers to a OpenMP thread.
+    __kmpc_give_task(task, __kmp_tid_from_gtid(gtid));
+    if (KMP_HIDDEN_HELPER_THREAD(gtid))
+      __kmp_hidden_helper_worker_thread_signal();
+    completed = false;
+  }
+
+  if (completed) {
     taskdata->td_flags.complete = 1; // mark the task as completed
 
 #if OMPT_SUPPORT
@@ -1125,6 +1136,13 @@
     // function
     KMP_DEBUG_ASSERT(taskdata->td_flags.executing == 1);
     taskdata->td_flags.executing = 0; // suspend the finishing task
+
+    // Decrement the counter of hidden helper tasks to be executed.
+    if (taskdata->td_flags.hidden_helper) {
+      // Hidden helper tasks can only be executed by hidden helper threads.
+      KMP_ASSERT(KMP_HIDDEN_HELPER_THREAD(gtid));
+      KMP_ATOMIC_DEC(&__kmp_unexecuted_hidden_helper_tasks);
+    }
   }
 
   KA_TRACE(
@@ -1136,7 +1154,7 @@
   // johnmc: if an asynchronous inquiry peers into the runtime system
   // it doesn't see the freed task as the current task.
   thread->th.th_current_task = resumed_task;
-  if (!detach)
+  if (completed)
     __kmp_free_task_and_ancestors(gtid, taskdata, thread);
 
   // TODO: GEH - make sure root team implicit task is initialized properly.
@@ -1532,6 +1550,7 @@
       parent_task->td_taskgroup; // task inherits taskgroup from the parent task
   taskdata->td_dephash = NULL;
   taskdata->td_depnode = NULL;
+  taskdata->td_target_data.async_handle = NULL;
   if (flags->tiedness == TASK_UNTIED)
     taskdata->td_last_tied = NULL; // will be set when the task is scheduled
   else
@@ -1674,13 +1693,6 @@
   }
 #endif
 
-  // Decreament the counter of hidden helper tasks to be executed
-  if (taskdata->td_flags.hidden_helper) {
-    // Hidden helper tasks can only be executed by hidden helper threads
-    KMP_ASSERT(KMP_HIDDEN_HELPER_THREAD(gtid));
-    KMP_ATOMIC_DEC(&__kmp_unexecuted_hidden_helper_tasks);
-  }
-
   // Proxy tasks are not handled by the runtime
   if (taskdata->td_flags.proxy != TASK_PROXY) {
     __kmp_task_start(gtid, task, current_task); // OMPT only if not discarded
@@ -5131,3 +5143,58 @@
                  modifier, task_dup);
   KA_TRACE(20, ("__kmpc_taskloop_5(exit): T#%d\n", gtid));
 }
+
+/*!
+@ingroup TASKING
+@param gtid Global Thread ID of current thread
+@return Returns a opaque pointer to the thread's current task. If no task is
+present, returns NULL.
+
+Acqurires the target async handle from the current task.
+*/
+void *__kmpc_omp_get_target_async_handle(kmp_int32 gtid) {
+  void *handle = NULL;
+  kmp_info_t *thread = __kmp_thread_from_gtid(gtid);
+  kmp_taskdata_t *taskdata = thread->th.th_current_task;
+
+  if (taskdata) {
+    handle = taskdata->td_target_data.async_handle;
+  }
+
+  return handle;
+}
+
+/*!
+@ingroup TASKING
+@param gtid Global Thread ID of current thread
+@param handle New async handle address
+
+Sets the target async handle for the current task.
+*/
+void __kmpc_omp_set_target_async_handle(kmp_int32 gtid, void *handle) {
+  kmp_info_t *thread = __kmp_thread_from_gtid(gtid);
+  kmp_taskdata_t *taskdata = thread->th.th_current_task;
+
+  if (taskdata) {
+    taskdata->td_target_data.async_handle = handle;
+  }
+}
+
+/*!
+@ingroup TASKING
+@param gtid Global Thread ID of current thread
+@return Returns true if the current thread of the given thread has a task team
+allocated to it.
+
+Checks if the current thread has a task team.
+*/
+KMP_EXPORT bool __kmpc_omp_has_task_team(kmp_int32 gtid) {
+  kmp_info_t *thread = __kmp_thread_from_gtid(gtid);
+  kmp_taskdata_t *taskdata = thread->th.th_current_task;
+
+  if (taskdata) {
+    return taskdata->td_task_team != NULL;
+  }
+
+  return FALSE;
+}